System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing content of a web site using a generation AI to identify areas in need of modification; means for generating a proposed modification based on the analysis of the generation AI; means for generating a hypothetical renewal web site image based on the proposed modification; means for presenting the hypothetical renewal web site image to a user and collecting feedback; and means for generating a final report based on the feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, many website operators are unable to efficiently respond to advances in information gathering and analysis technology using generative AI. Furthermore, while websites are required to achieve high scores in third-party evaluations (e.g., ESG evaluations), current technology requires frequent manual updates, placing a significant burden on operators. Furthermore, the web industry faces challenges such as a labor shortage and long working hours, making it urgent to find effective solutions to these problems. [Means for solving the problem]

[0005] This invention provides a system for automatically analyzing, evaluating, and optimizing website content using generative AI. Specifically, the system includes a means for analyzing website content using generative AI and identifying areas requiring modification, a means for generating modification proposals based on the analysis results of the generative AI, a means for creating a virtual redesigned website image based on the modification proposals, a means for presenting the virtual redesigned website image to users and collecting feedback, and a means for generating a final report based on the feedback. This system enables website operators to efficiently optimize their websites in response to generative AI and improve the quality of their information dissemination.

[0006] "Generative AI" is an artificial intelligence technology that analyzes and evaluates website content and automatically generates optimization and improvement proposals based on the results.

[0007] A "website" is a group of HTML pages that are published on the Internet and contain documents and media for providing information.

[0008] "Analysis" is the process of evaluating each element of a website, such as text, images, and structure, to identify areas for improvement.

[0009] "Improvement proposals" are specific suggestions for improving a website based on the analysis results of the generative AI.

[0010] The "virtual renewal website image" is an image showing the structure of a virtual website that reflects the proposed renovations.

[0011] "Feedback" refers to opinions and comments on the virtual renewal proposal provided by the user.

[0012] The "Final Report" is a report summarizing the results of the generative AI's analysis, proposed improvements, a virtual image of the renewed website, and feedback from users. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

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

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

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

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0034] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. The main functions and examples are described below.

[0035] 1. Information gathering stage

[0036] 1. User requirements:

[0037] The user enters the URL of the website they want to analyze.

[0038] 2. Get data from the server:

[0039] The server sends an HTTP request based on the URL provided by the user to retrieve the HTML content of the web page.

[0040] The server saves the retrieved HTML content in the database.

[0041] 2. Content analysis stage

[0042] 1. Load the generative AI model:

[0043] The server loads the generative AI model used for analysis.

[0044] 2. Content Analysis:

[0045] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0046] Based on the analysis results, the quality of the website is scored.

[0047] 3. Identifying points to be improved

[0048] 1. Obtaining analysis results:

[0049] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[0050] 2. Generate renovation proposals:

[0051] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[0052] 4. Generation of virtual renewal proposals

[0053] 1. Create a virtual site based on the proposed renovation:

[0054] The server creates a virtual renewal website image with the proposed modifications applied.

[0055] The server prepares data for providing a virtual renewal website image to the user.

[0056] 5. User Acknowledgment and Feedback

[0057] 1. Confirmation of virtual renewal proposal:

[0058] The user checks the provided virtual renewal website image.

[0059] 2. Providing Feedback:

[0060] Users provide feedback on the virtual renewal proposal.

[0061] 6. Generate the final report

[0062] 1. Incorporating feedback:

[0063] The server will incorporate user feedback and adjust the final revision proposal.

[0064] 2. Generate and provide reports:

[0065] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[0066] The server provides the final report to the user.

[0067] Specific examples

[0068] Example 1: Information gathering and analysis

[0069] 1. User Action:

[0070] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0071] 2. Server operation:

[0072] The server retrieves the HTML content from the specified URL and stores it in the database.

[0073] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[0074] The server performs scoring based on the analysis results and lists points that need to be improved.

[0075] Example 2: Generation of renovation proposals and virtual renovation

[0076] 1. Server operation:

[0077] The server generates specific repair plans based on the analysis results.

[0078] The server creates a virtual renewal website image and presents it to the user.

[0079] 2. User Action:

[0080] The user checks the virtual renewal website image and provides feedback as needed.

[0081] Example 3: Generating a Final Report

[0082] 1. Server operation:

[0083] The server will incorporate user feedback and adjust the final revision proposal.

[0084] The server generates the final report and provides it to the user.

[0085] This allows website operators to efficiently optimize their websites to accommodate generative AI.

[0086] The processing flow will be explained below.

[0087] Step 1:

[0088] The user enters the URL of the website to be analyzed into the terminal.

[0089] Step 2:

[0090] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[0091] Step 3:

[0092] The server saves the retrieved HTML content in the database.

[0093] Step 4:

[0094] The server loads the generative AI model.

[0095] Step 5:

[0096] The server retrieves the collected HTML content from the database and prepares it for analysis.

[0097] Step 6:

[0098] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[0099] Step 7:

[0100] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[0101] Step 8:

[0102] Specific improvement proposals are listed based on the analysis results generated by the server.

[0103] Step 9:

[0104] The server creates a virtual renewal website image based on the proposed modifications.

[0105] Step 10:

[0106] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[0107] Step 11:

[0108] The user checks the virtual renewal website image and provides feedback from the terminal as needed.

[0109] Step 12:

[0110] The server receives user feedback and adjusts the final revision proposal to reflect the feedback.

[0111] Step 13:

[0112] The server generates the final report and provides it to the user.

[0113] Example 1

[0114] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0115] The traditional website optimization process was time-consuming and costly, requiring a lot of manual work. Furthermore, identifying areas for improvement and proposing specific proposals required a high level of specialized knowledge. This made it difficult for small and medium-sized businesses and individuals to efficiently improve their websites.

[0116] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0117] In this invention, the server includes means for inputting a website URL provided by a user, means for acquiring HTML content from the URL and saving it in a database, means for loading a generative AI model, means for analyzing the HTML content using the generative AI model, means for calculating a website quality score based on the analysis results and listing areas requiring improvement, means for generating an improvement plan based on the analysis results, means for creating a virtual renewed website image based on the improvement plan, means for presenting the virtual renewed website image to a user and collecting feedback, and means for generating a final report based on the feedback. This significantly reduces time and cost, and enables even users without specialized knowledge to efficiently improve their websites.

[0118] The "means for inputting the URL of the website provided by the user" is a method by which the user inputs the URL of the website to be analyzed into the interface.

[0119] "Means for obtaining HTML content from the URL and storing it in a database" refers to a method for obtaining HTML content from an input URL via an HTTP request and storing the data in a database.

[0120] A "means for loading a generative AI model" is a method for loading a specified generative AI model (e.g., GPT-3, BERT, etc.) into memory.

[0121] The "means for analyzing HTML content using the generative AI model" is a method for analyzing text, images, and structure within the retrieved HTML content using the loaded generative AI model.

[0122] "Means for calculating a quality score for a website based on the analysis results and listing areas that require improvement" refers to a method of calculating a score for each element of a website based on the analysis results provided by a generative AI model and listing specific areas that require improvement.

[0123] The "means for generating a modification plan based on the analysis results" is a method for generating a specific improvement plan based on the analysis results.

[0124] The "means for creating a virtual renewal website image based on the proposed modification" is a method for creating a virtual website that reflects the created modification plan.

[0125] The "means for presenting the virtual renewal website image to users and collecting feedback" refers to a method for providing users with a preview of the virtual renewal website and collecting their opinions and improvements as feedback.

[0126] The "means for generating a final report based on the feedback" refers to a method for generating a report that reflects feedback from the user and summarizes the final modification plan and its results.

[0127] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. Specifically, the system involves a server-based process of processing various data, presenting modification proposals to users, and creating a virtual renewal website. A detailed explanation is provided below.

[0128] Hardware and software used

[0129] Hardware

[0130] Server: A server with high-performance computing resources is required, with enough processing power to load the generative AI model and perform the analytical processing.

[0131] software

[0132] Generative AI model: The AI ​​model used for analysis, such as GPT-3 or BERT.

[0133] Database: A database for storing HTML content and analysis results. Typically, an SQL database is used.

[0134] HTTP request library: A library used to retrieve HTML content from a website, for example, the Python Requests library.

[0135] Specific explanation of program processing

[0136] 1. User requirements

[0137] The user enters the URL of the website they want to analyze into a dedicated web interface and sends it to the server.

[0138] 2. Obtaining data from the server

[0139] The server sends an HTTP GET request to the entered URL to retrieve the HTML content.

[0140] The acquired HTML content is stored in the server's database.

[0141] 3. Loading the generative AI model

[0142] The server reads the name of the generative AI model to use from the configuration file and loads it. For example, if you want to use the GPT-3 model, you load the model using the API key.

[0143] 4. Content Analysis

[0144] The server retrieves the collected HTML content from the database.

[0145] The server feeds the HTML data into a generative AI model, which analyzes the text, images, and structure.

[0146] 5. Calculating quality scores and identifying areas for improvement

[0147] Based on the analysis results of the generative AI model, a quality score is calculated for each element of the website.

[0148] List areas where the server needs repair.

[0149] 6. Generation of renovation proposals

[0150] The server generates specific repair plans based on the analysis results.

[0151] To present the proposed modifications to the user, they are compiled in a list format.

[0152] 7. Generation of Virtual Renewal Plans

[0153] The server creates a virtual renewal website image to which the generated modification plan has been applied.

[0154] A preview link of the virtual renewal website is generated and provided to the user.

[0155] 8. User Acknowledgment and Feedback

[0156] The user reviews the provided virtual relaunch website image and provides feedback.

[0157] The user fills in the feedback form with any necessary improvements or comments and submits it.

[0158] 9. Generate the final report

[0159] The server will incorporate user feedback and adjust the final revision proposal.

[0160] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[0161] Generate the final report in PDF or HTML format and provide it to the user via email or download link.

[0162] Specific examples of behavior and prompts for the generative AI model

[0163] Example 1: Information gathering and analysis

[0164] User action: The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0165] Server operation: The server retrieves HTML content from the specified URL and stores it in a database. The server uses a generative AI model to analyze the text, images, and structure of the retrieved content. The server scores the content based on the analysis results and lists points to be improved.

[0166] Prompt Sentence Examples

[0167] "Get the HTML content of the specified website https: / / example.com"

[0168] "Analyze the retrieved content and evaluate the quality of the website."

[0169] "Generate renovation proposals and create virtual renovation sites."

[0170] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0171] Step 1:

[0172] User requirements

[0173] Input: The user enters the URL of the website they want to analyze into a dedicated web interface and submits it.

[0174] Specific behavior: A user enters a URL (e.g., https: / / example.com) into an input form on a web browser and clicks the submit button.

[0175] Output: The entered URL is sent to the server.

[0176] Step 2:

[0177] Server Data Acquisition

[0178] Input: A URL provided by the user.

[0179] Specific operation: The server sends an HTTP GET request to the entered URL and retrieves the HTML content.

[0180] Output: The retrieved HTML content is saved in the server database.

[0181] Step 3:

[0182] Loading a generative AI model

[0183] Input: The name of the generative AI model to use from the server's config file.

[0184] Specific operation: The server reads the configuration file and loads the specified generative AI model (e.g., GPT-3).

[0185] Output: The generative AI model is loaded into memory and ready for analysis.

[0186] Step 4:

[0187] Content Analysis

[0188] Input: HTML content stored in the server's database.

[0189] What it does: The server retrieves HTML content from the database and feeds it into the generative AI model for analysis.

[0190] Output: The analytical results obtained from the generative AI model are obtained.

[0191] Step 5:

[0192] Calculating quality scores and identifying areas to improve

[0193] Input: Analysis results obtained from a generative AI model.

[0194] What it does: Based on the analysis results, the server calculates a quality score for each element of the website and lists areas that need improvement.

[0195] Output: Quality score and list of areas that need improvement.

[0196] Step 6:

[0197] Generate renovation proposals

[0198] Input: A list of areas that need renovation.

[0199] Specific operation: The server uses the generative AI model again based on the analysis results to generate specific repair proposals.

[0200] Output: Get a list of proposed modifications.

[0201] Step 7:

[0202] Generation of virtual renewal proposals

[0203] Input: Generated renovation proposal.

[0204] Specific operation: The server applies the proposed modifications and creates a virtual redesigned website image.

[0205] Output: Preview link of the virtual renewal website.

[0206] Step 8:

[0207] User Acknowledgment and Feedback

[0208] Input: Preview link for your virtual relaunch website.

[0209] What happens: The user clicks on the provided preview link to see the virtual renewal site.

[0210] Output: User feedback.

[0211] Step 9:

[0212] Generate the final report

[0213] Input: User feedback.

[0214] What happens: The server incorporates the feedback, adjusts the final revision proposal, and generates the final report.

[0215] Output: The final report is generated in PDF and HTML format and provided to the user.

[0216] (Application example 1)

[0217] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] Improving user experience and conversion rates are key challenges for modern online shopping websites. However, for many online shopping websites, regularly reviewing and revising the entire site is time-consuming and inefficient. It is also difficult to effectively utilize user feedback to optimize the site. For these reasons, there is a need for a more efficient and automated way to optimize websites and improve user experience.

[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0220] In this invention, the server includes: means for analyzing website content using a generation AI and identifying areas requiring improvement; means for generating an improvement plan based on the analysis results by the generation AI; means for creating a virtual renewal website image based on the improvement plan; means for presenting the virtual renewal website image to users and collecting feedback; means for generating a final report based on the feedback; means for collecting website content and saving it in a database; means for analyzing text, structure, and images using the generation AI and performing scoring; means for creating an improvement plan for the online shopping website based on the reviews and feedback analyzed using the generation AI; means for presenting the improvement plan to users and providing a virtual renewal site where the improvement content can be previewed; and means for generating a final improvement report based on user feedback on the virtual renewal site. This makes the online shopping website improvement process more efficient and improves the user experience.

[0221] "Generative AI" is a technology that uses artificial intelligence to generate data and automatically perform tasks such as analysis and evaluation.

[0222] A "website" is a collection of information published on the Internet and written in a markup language such as HTML.

[0223] "Content analysis" is the process of analyzing and evaluating the information within a website, including text, images, structure, etc.

[0224] "Areas in need of improvement" refers to parts of the website that require improvement.

[0225] A "renovation proposal" is a plan that proposes specific corrections or changes to the identified areas for improvement.

[0226] "Virtual renewal website" refers to a virtual web page to which the proposed modifications have been applied.

[0227] "Feedback" refers to opinions and evaluations provided by users, and is information that can be used to improve the system.

[0228] "Final report" refers to the final report that incorporates the feedback.

[0229] "Data collection" refers to the acquisition and storage of website content on a server.

[0230] A "database" is a system for systematically storing and managing collected data.

[0231] "Scoring" is the process of quantifying and evaluating a website's quality and areas for improvement based on the analysis results.

[0232] "Review" refers to comments and ratings that record users' experiences and opinions.

[0233] An "online shopping site" is a website that sells products and services over the Internet.

[0234] "Preview" is a feature that allows users to virtually check improvement proposals before they are actually implemented.

[0235] "Improvement Report" refers to the detailed analysis report that is finally generated based on improvement suggestions and feedback.

[0236] The system for implementing the present invention includes a server, a user terminal, and a generative AI model. The specific operation of this system is described below.

[0237] System Overview

[0238] 1. Get data from the server:

[0239] The user enters the URL of the shopping site they want to analyze. The server sends an HTTP request, retrieves the HTML content from the specified URL, and stores it in a database. For example, if a user enters the URL "https: / / example-shop.com," the server will collect the HTML content of that website.

[0240] 2. Load the generative AI model:

[0241] The server loads and uses a generative AI model (e.g., GPT-3.5-turbo) for analysis, which uses advanced natural language processing to provide a detailed analysis of the website content.

[0242] 3. Content Analysis:

[0243] The server passes the HTML content retrieved from the database to the generative AI model for analysis. The analysis is performed on each element, such as text, images, and structure, to identify its quality and areas for improvement. The analysis results are then scored to quantify the evaluation.

[0244] 4. Review and Feedback Analysis:

[0245] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, which identifies specific areas for improvement based on user experience.

[0246] 5. Generation of renovation proposals and presentation of virtual renewal proposals:

[0247] Based on the analysis results of the generative AI model, the server generates a proposed redesign. Based on this proposed redesign, a virtual redesigned website image is created and presented to the user. At this stage, the user can confirm the proposed redesign and preview the virtual redesigned website.

[0248] 6. Collect user feedback and generate final report:

[0249] The server receives feedback from users about the virtual renewal proposal. The server reflects this feedback and generates a final improvement report. The final report includes the revision proposal, a virtual renewal website image, and user feedback.

[0250] Hardware and software used

[0251] 1. Hardware:

[0252] Server: Collects, analyzes, and manages databases of HTML content.

[0253] User device (smartphone): Enter the URL, provide feedback, and preview the virtual renewal proposal.

[0254] 2. Software:

[0255] requests: A Python library for retrieving HTML content from websites.

[0256] BeautifulSoup: A Python library for parsing HTML content.

[0257] transformers: Libraries for content analysis using generative AI models (e.g., GPT-3.5-turbo).

[0258] Specific examples

[0259] If a user types "https: / / example-shop.com", the server collects the HTML content from this URL and stores it in a database. It then uses a generative AI model to analyze the website's text, images, and structure. It then inputs the following prompt to the generative AI model:

[0260] This is the HTML content from https: / / example-shop.com. Please analyze its text, images, and structure to find areas for improvement and suggest potential enhancements.

[0261] Based on the analysis results, the generative AI model will suggest improvements such as, "The product descriptions lack detailed information. Adding more information about each product will help attract customers' interest. Consider using high-quality images in the product gallery." This will streamline the work of improving online shopping sites and improve the user experience.

[0262] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0263] Step 1:

[0264] Entering URLs and collecting data

[0265] The user enters the URL of their shopping site. The server sends an HTTP request to the entered URL and retrieves the website's HTML content. Specifically, it uses Python's requests library to retrieve HTML data from the specified URL and saves this data in a database.

[0266] Input: The URL entered by the user

[0267] Output: Retrieved HTML content (stored in database)

[0268] Step 2:

[0269] Loading a generative AI model

[0270] The server loads the generative AI model (e.g., GPT-3.5-turbo) and prepares it for analysis. The server loads the model using the transformers library.

[0271] Input: File path of the generated AI model

[0272] Output: The loaded generative AI model

[0273] Step 3:

[0274] Parsing HTML content

[0275] The server retrieves HTML content from the database and passes it to the generative AI model for analysis. BeautifulSoup is used to parse the HTML content and extract the text, images, and structure contained within it. This data is then input into the generative AI model to obtain the analysis results.

[0276] Input: HTML content stored in the database

[0277] Output: Analysis results from the generative AI model

[0278] Step 4:

[0279] Review and feedback analysis

[0280] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, thereby extracting specific points for improvement based on the user experience.

[0281] Input: User reviews and feedback

[0282] Output: Analysis results and points for improvement by the generative AI model

[0283] Step 5:

[0284] Generate renovation proposals

[0285] Based on the analysis results, the server generates specific improvement proposals, using a generative AI model to review each analysis data and propose ways to improve the relevant areas.

[0286] Input: Analysis results from generative AI model

[0287] Output: Specific renovation proposal

[0288] Step 6:

[0289] Virtual renewal website generation

[0290] Based on the proposed modifications obtained in the previous step, the server creates a virtual renewal website that allows users to preview how the site will look with the proposed modifications.

[0291] Input: Specific renovation plan

[0292] Output: Virtual renewal website image

[0293] Step 7:

[0294] User preview and feedback gathering

[0295] The user terminal displays the virtual renewal website image, allowing the user to check its contents and provide feedback.

[0296] Input: Virtual renewal website image

[0297] Output: User feedback

[0298] Step 8:

[0299] Generate the final report

[0300] After collecting user feedback, the server uses this information to generate a final report, which includes proposed improvements, virtual redesigned website images, and user feedback.

[0301] Input: User feedback

[0302] Output: Final report

[0303] Through these steps, the online shopping site renovation process will be made more efficient and the user experience will be improved.

[0304] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0305] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine.

[0306] 1. Information gathering stage

[0307] 1. User requirements:

[0308] The user enters the URL of the website they want to analyze into the device.

[0309] 2. Get data from the server:

[0310] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website.

[0311] The server saves the retrieved HTML content in the database.

[0312] 2. Content analysis stage

[0313] 1. Load the generative AI model:

[0314] The server loads the generative AI model used for analysis.

[0315] 2. Content Analysis:

[0316] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0317] The server scores the quality of the website based on the analysis results.

[0318] 3. Identifying points to be improved

[0319] 1. Obtaining analysis results:

[0320] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[0321] 2. Generate renovation proposals:

[0322] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[0323] 4. Generation of virtual renewal proposals

[0324] 1. Create a virtual site based on the proposed renovation:

[0325] The server creates a virtual renewal website image with the proposed modifications applied.

[0326] The server prepares data for providing a virtual renewal website image to the user.

[0327] 5. User Acknowledgment and Feedback

[0328] 1. Confirmation of virtual renewal proposal:

[0329] The user checks the provided virtual renewal website image.

[0330] At this time, the server uses an emotion engine to analyze the user's facial expressions and tone of voice, and recognize the user's emotions.

[0331] 2. Providing Feedback:

[0332] Users provide feedback on the virtual renewal proposal.

[0333] The server also takes into consideration the emotional data collected using an emotion engine and reflects it in the feedback content.

[0334] 6. Generate the final report

[0335] 1. Incorporating feedback:

[0336] The server receives user feedback and adjusts the final revision proposal based on the feedback.

[0337] At this stage, emotional data is analyzed by the emotion engine to improve the quality of feedback.

[0338] 2. Generate and provide reports:

[0339] The server generates a final report containing the final redesign proposal, virtual redesigned website images, and user feedback and sentiment data.

[0340] The server provides the final report to the user.

[0341] Specific examples

[0342] Example 1: Information gathering and analysis

[0343] 1. User Action:

[0344] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0345] 2. Server operation:

[0346] The server retrieves the HTML content from the specified URL and stores it in the database.

[0347] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[0348] The server performs scoring based on the analysis results and lists points that need to be improved.

[0349] Example 2: Generation of renovation proposals and virtual renovation

[0350] 1. Server operation:

[0351] The server generates specific repair plans based on the analysis results.

[0352] The server creates a virtual renewal website image and presents it to the user.

[0353] When a user views the virtual renewal website image, the emotion engine recognizes the user's emotion.

[0354] 2. User Action:

[0355] The user checks the virtual renewal website image and provides feedback as needed.

[0356] Example 3: Generating a Final Report

[0357] 1. Server operation:

[0358] The server receives user feedback and emotional data and adjusts the final revision proposal.

[0359] The server generates the final report and provides it to the user.

[0360] By combining it with an emotion engine that recognizes user emotions, website operators can obtain specific data to improve user satisfaction and efficiently achieve optimization compatible with generative AI.

[0361] The processing flow will be explained below.

[0362] Step 1:

[0363] The user enters the URL of the website to be analyzed into the terminal.

[0364] Step 2:

[0365] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[0366] Step 3:

[0367] The server saves the retrieved HTML content in the database.

[0368] Step 4:

[0369] The server loads the generative AI model.

[0370] Step 5:

[0371] The server retrieves the collected HTML content from the database and prepares it for analysis.

[0372] Step 6:

[0373] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[0374] Step 7:

[0375] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[0376] Step 8:

[0377] Specific improvement proposals are listed based on the analysis results generated by the server.

[0378] Step 9:

[0379] The server creates a virtual renewal website image based on the proposed modifications.

[0380] Step 10:

[0381] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[0382] Step 11:

[0383] When the user checks the virtual renewal website image, the server uses an emotion engine to recognize the user's emotion.

[0384] Step 12:

[0385] The user provides feedback on the virtual renewal proposal from the terminal.

[0386] Step 13:

[0387] The server receives user feedback and emotional data and adjusts the final revision proposal.

[0388] Step 14:

[0389] The server generates the final report and provides it to the user.

[0390] Example 2

[0391] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0392] Conventional website analysis systems focused on evaluating content quality and generating improvement proposals, but did not adequately address the collection of feedback and the creation of final reports that took user emotions into account. This made it difficult to obtain specific insights for improving user experience and satisfaction. Furthermore, when creating and evaluating virtual renewal images of proposed improvements, there was a lack of a way to reflect user emotions in real time.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0394] In this invention, the server includes means for analyzing the content of the website using a generation AI and identifying areas that need modification, means for generating a modification plan based on the analysis results by the generation AI, means for creating a virtual renewed website image based on the modification plan, means for analyzing user emotions using an emotion engine, means for improving feedback based on user emotion data, and means for generating a final report, thereby enabling website optimization that takes user emotions into consideration in real time.

[0395] "Generative AI" is an algorithm that uses artificial intelligence technology to generate new information and patterns from data.

[0396] A "website" is a collection of pages that provide information or content on the Internet.

[0397] An "emotion engine" is a technology that analyzes user emotions and collects and utilizes that data.

[0398] "Analysis" is the process of breaking down data or information into smaller pieces to understand its structure and content.

[0399] "Proposal for Improvement" means a proposed plan or method for improving an existing system or structure.

[0400] A "virtual renewal website image" is a visual model of a virtual website created based on the proposed renovation plan.

[0401] "Feedback" refers to opinions and evaluations from users regarding proposed improvements.

[0402] The "Final Report" is a report summarizing the results, recommendations, and feedback of the renovation process.

[0403] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0404] "Scoring" is the process of assigning a score to evaluate the quality and performance of an object based on the analysis results.

[0405] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine. It mainly involves servers, terminals, and users.

[0406] First, the user inputs the URL of the website they want to analyze into their device. Next, the server sends an HTTP request to the specified URL and retrieves the website's HTML content. The server uses the Python requests library to do this. The retrieved HTML content is then stored in a database such as MySQL or MongoDB.

[0407] Next, the server loads the generative AI model to be used for analysis. For generative AI models, advanced natural language processing models such as GPT-3 and BERT are used. The weight and configuration files for the model are loaded, and the server is ready for analysis.

[0408] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc. Natural language processing technology is used for text analysis, and deep learning models are used for image analysis. Based on the analysis results, the quality of the website is scored. Evaluation criteria include page loading speed, content relevance, and user experience.

[0409] Next, the server uses the results of the AI's analysis to create a list of areas of the website that need improvement. This list includes specific points of concern and suggestions for improvement. Suggested improvements include, for example, optimizing image size and revising content.

[0410] The server creates an image of a virtual redesigned website with the proposed modifications applied. It uses HTML, CSS, JavaScript, etc. to build the virtual website and prepares the data to be presented to the user. The user can then view this image of the virtual redesigned website through their browser.

[0411] The server's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. The system uses facial and voice recognition technology to capture the user's emotions. The user provides feedback on the virtual renewal proposal.

[0412] After the user provides their feedback, the server adjusts the final revision proposal based on the feedback. At this stage, the emotion engine analyzes the emotion data to improve the accuracy of the feedback. A final report is generated containing the final revision proposal, an image of the virtual redesigned website, the feedback, and the emotion data, and is sent to the user via email.

[0413] Specific examples

[0414] Example 1: Data acquisition and analysis

[0415] User Action:

[0416] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0417] Server behavior:

[0418] The server uses Python's requests library to retrieve HTML content from the specified URL and saves it in a MySQL database. It then uses a generative AI model (e.g., GPT-3) to analyze the text, images, and structure of the retrieved content. It then scores the content based on the analysis results and lists points to improve.

[0419] Example 2: Renovation proposal generation and virtual renovation

[0420] Server behavior:

[0421] The server generates specific renovation proposals based on the analysis results, creates an image of a virtual renewal website using HTML and CSS, and presents it to the user.

[0422] User Action:

[0423] When a user browses the virtual renewal website and provides feedback, the emotion engine recognizes the user's facial expressions and collects emotional data.

[0424] Example 3: Final report generation

[0425] Server behavior:

[0426] The server receives user feedback and sentiment data, adjusts the final revision proposal, and generates a final report to provide to the user.

[0427] Prompt Sentence Examples

[0428] "Analyze the website at the following URL and generate improvement recommendations: https: / / example.com"

[0429] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0430] Program processing flow

[0431] Step 1:

[0432] User requirements

[0433] The user inputs the URL of the website they want to analyze into the device, which then sends this URL data to the server.

[0434] Enter: Website URL

[0435] Output: Sends URL data to the server

[0436] Step 2:

[0437] Data Acquisition

[0438] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website. The server uses the Python requests library and saves the retrieved HTML content in a database (e.g., MySQL, MongoDB).

[0439] Input: URL data

[0440] Output: HTML content, saved to database

[0441] Specific behavior:

[0442] The server retrieves the HTML using requests.get(URL) and saves it in the database.

[0443] Step 3:

[0444] Loading a Model

[0445] The server loads the generative AI model to be used for analysis. We use natural language processing models such as GPT-3 and BERT as generative AI models. We also load the model weight and configuration files.

[0446] Input: None (preparatory operation in previous stage)

[0447] Output: Model instantiation

[0448] Specific behavior:

[0449] The server loads the model using a library such as from transformers import GPT3.

[0450] Step 4:

[0451] Content Analysis

[0452] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0453] Input: HTML content (retrieved from database)

[0454] Output: Text, image and structure analysis data

[0455] Specific behavior:

[0456] The server inputs HTML data into the model and performs text analysis (natural language processing) and image analysis (deep learning model).

[0457] Step 5:

[0458] Scoring

[0459] The server then scores the website's quality based on the analysis, including criteria such as page load speed, content relevance, and user experience.

[0460] Input: Analysis data

[0461] Output: Scoring results

[0462] Specific behavior:

[0463] Points are assigned according to the evaluation criteria and an overall score is calculated.

[0464] Step 6:

[0465] Identifying points to be repaired

[0466] The server generates a list of areas of the website that need improvement based on the results of the AI ​​analysis, and outputs specific points of emphasis and suggestions for improvement.

[0467] Input: Scoring results, analysis data

[0468] Output: List of modification points

[0469] Specific behavior:

[0470] We will make a list of areas that need improvement and propose specific improvement plans.

[0471] Step 7:

[0472] Generate renovation proposals

[0473] The server generates specific improvement proposals for the listed improvement points, such as "optimizing image size" and "reviewing content."

[0474] Input: List of renovation points

[0475] Output: Revision proposal

[0476] Specific behavior:

[0477] Generate and list specific improvement methods.

[0478] Step 8:

[0479] Generate a virtual renewal site

[0480] The server creates an image of a virtual redesigned website with the proposed modifications applied. The virtual website is built using HTML, CSS, JavaScript, etc.

[0481] Input: Renovation proposal

[0482] Output: Image of the virtual renewal site

[0483] Specific behavior:

[0484] Build the website's HTML and styles based on the proposed changes.

[0485] Step 9:

[0486] User Verification

[0487] The user checks the image of the virtual renewal website provided through a browser.

[0488] Input: Image of the virtual renewal site

[0489] Output: User feedback

[0490] Specific behavior:

[0491] A user reviews a website in a browser and provides feedback.

[0492] Step 10:

[0493] Emotion analysis

[0494] The server's emotion engine analyzes the user's facial expressions and tone of voice, using facial and voice recognition technology.

[0495] Input: User feedback, real-time video / audio data

[0496] Output: Emotion data

[0497] Specific behavior:

[0498] It analyzes the user's facial expressions and tone of voice in real time to collect emotional data.

[0499] Step 11:

[0500] Feedback collection

[0501] Users provide feedback on virtual renewal proposals. By taking emotion data into account, more accurate feedback can be obtained.

[0502] Input: User feedback, emotion data

[0503] Output: Improved feedback

[0504] Specific behavior:

[0505] Emotional data is reflected in the feedback to improve accuracy.

[0506] Step 12:

[0507] Final revision proposal and report generation

[0508] The server receives the feedback and emotion data from the users, adjusts the final renovation proposal, and generates a final report including the final renovation proposal, an image of the virtual renewal website, the feedback, and the emotion data, and provides it to the user.

[0509] Input: Improved feedback, emotional data

[0510] Output: Final report

[0511] Specific behavior:

[0512] A final list of renovation proposals will be compiled and a final report will be generated in PDF format, including the virtual renewal site and feedback.

[0513] (Application example 2)

[0514] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0515] In modern content delivery services, personalized recommendations that take into account not only the content viewed but also the user's real-time emotional state are required to improve the user experience. However, conventional systems have difficulty accurately grasping the user's emotions and suggesting optimal content. Furthermore, in the process of analyzing websites and proposing improvements, it is difficult to collect accurate feedback, which can result in a decrease in user satisfaction.

[0516] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the content of a website using a generation AI and identifying areas requiring modification, means for generating a modification proposal based on the analysis results by the generation AI, means for creating a virtual renewal website image based on the modification proposal, means for presenting the virtual renewal website image to a user and collecting feedback, means for generating a final report based on the feedback, means for analyzing the user's emotional state using an emotion engine when collecting feedback, and means for making personalized recommendations based on the emotional state. This enables personalized content recommendations that take into account the user's real-time emotional state and highly accurate feedback collection in the website analysis and modification process.

[0517] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze content such as text and images.

[0518] An "emotion engine" is software that analyzes a user's facial expressions, voice, etc., and recognizes and evaluates their emotional state.

[0519] "Website content" refers to the digital information contained on a web page, such as text, images, video, and link structure.

[0520] "Improvement Proposal" means a proposal that identifies areas of the Website or Content that need improvement and presents how to correct or improve them.

[0521] "Virtual Renewal Website Image" means an image or prototype of an improved website that is virtually created based on the proposed renovation.

[0522] "Feedback" refers to the evaluation or opinion provided by the user after checking the virtual renewal website image.

[0523] "Final Report" is a document detailing website or content optimization recommendations that take into account user feedback and emotional state.

[0524] "Personalized recommendations" are the act of suggesting appropriate content based on the attributes, behavioral history, and emotional state of individual users.

[0525] This invention is a system that utilizes generative AI and an emotion engine to improve the user experience in content distribution services. A specific implementation method of this system is described below.

[0526] First, when a user views content, the server retrieves the URL associated with the content and sends an HTTP request to retrieve the HTML content. In this process, the hardware used is the server, and the software required is a library to process the HTTP request. The retrieved HTML content is then stored in a database.

[0527] Next, the server loads a generative AI model and analyzes the content. For example, the "transformers" library is used as the generative AI model. At this stage, the server analyzes the acquired text, images, structural information, etc., and performs a quality score on the content. The analysis results are stored in a database and are used in a later step to generate improvement proposals.

[0528] After the analysis, the server executes a procedure to generate a modification plan based on the analysis results of the generative AI. The generated modification plan is visualized as a virtual renewal website image. The virtual renewal website image is presented to the user, who then confirms it. The software used here is an image processing library, and the user interface is a web browser.

[0529] When a user views the virtual renewal website image, the server uses an emotion engine to analyze the user's emotional state in real time. The emotion engine uses the "DeepFace" library to capture and analyze the user's facial expressions and voice. Personalized content recommendations are made based on the user's emotional state.

[0530] Finally, the server generates a final report that takes into account user feedback and sentiment data, including a virtual website redesign image, proposed improvements, and user feedback, leading to efficient website and content optimization and improved user satisfaction.

[0531] For example, if the emotion engine determines that the user is feeling stressed, a prompt can be used to recommend relaxing music or videos. For example, the prompt could be, "Please analyze the main topics and emotions of this web page" or "Please recommend content that will help the user relax."

[0532] As described above, the system of the present invention integrates generative AI and an emotion engine to provide personalized recommendations based on the user's emotional state, thereby significantly improving the user experience in content distribution services.

[0533] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0534] Step 1:

[0535] The user enters the URL of the website they wish to view on their device. The device then sends this URL to the server. The server receives the URL and sends an HTTP request to retrieve the HTML content of the website. The input data is the URL entered by the user, and the output data is the retrieved HTML content. This process uses the HTTP request library to download the website content.

[0536] Step 2:

[0537] The server saves the acquired HTML content in a database. The input data is the acquired HTML content, and the output data is the content saved in the database. The saving process is performed using a database operation library.

[0538] Step 3:

[0539] The server loads the generative AI model and retrieves HTML content from the database. The input data is the HTML content stored in the database, and the output data is the analysis results. The generative AI model uses the "transformers" library to analyze the retrieved text, images, and structural information. Specific operations include text tokenization and structural analysis.

[0540] Step 4:

[0541] The server scores the quality of the website based on the analysis results. The input data is the analysis results of the generative AI model, and the output data is a quality score. Scoring includes multiple indicators such as text readability and image optimization.

[0542] Step 5:

[0543] The server generates a repair plan based on the scoring results. The input data is the quality score, and the output data is the repair plan. Using a generative AI model, it identifies areas that need repair and uses prompts to suggest how to improve them.

[0544] Step 6:

[0545] The server creates a virtual renewal website image based on the proposed modifications. The input data is the modification proposal, and the output data is the virtual renewal website image. Here, an image processing library is used to visually represent the proposed modifications.

[0546] Step 7:

[0547] The server presents the virtual renewal website image to the user, and the user checks the virtual renewal website image and provides feedback, where the input data is the virtual renewal website image and the output data is the user's feedback.

[0548] Step 8:

[0549] When collecting feedback, the server uses an emotion engine to analyze the user's emotional state. The input data is the user's facial expressions and voice, and the output data is emotion data. Specifically, the server uses the "DeepFace" library to perform facial and voice analysis.

[0550] Step 9:

[0551] The server makes personalized content recommendations based on emotional data. The input data is emotional data, and the output data is recommended content. Using a generative AI model, it suggests songs and videos that correspond to the user's emotional state.

[0552] Step 10:

[0553] The server generates a final report by taking into account the user's feedback and emotion data. The input data is the user's feedback and emotion data, and the output data is the final report. The final report includes a virtual renewal website image, a modification proposal, and the user's feedback.

[0554] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0555] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0556] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0557] [Second embodiment]

[0558] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0559] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0560] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0561] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0562] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0563] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0564] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0565] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0566] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0567] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0568] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0569] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0570] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. The main functions and examples are described below.

[0571] 1. Information gathering stage

[0572] 1. User requirements:

[0573] The user enters the URL of the website they want to analyze.

[0574] 2. Get data from the server:

[0575] The server sends an HTTP request based on the URL provided by the user to retrieve the HTML content of the web page.

[0576] The server saves the retrieved HTML content in the database.

[0577] 2. Content analysis stage

[0578] 1. Load the generative AI model:

[0579] The server loads the generative AI model used for analysis.

[0580] 2. Content Analysis:

[0581] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0582] Based on the analysis results, the quality of the website is scored.

[0583] 3. Identifying points to be improved

[0584] 1. Obtaining analysis results:

[0585] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[0586] 2. Generate renovation proposals:

[0587] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[0588] 4. Generation of virtual renewal proposals

[0589] 1. Create a virtual site based on the proposed renovation:

[0590] The server creates a virtual renewal website image with the proposed modifications applied.

[0591] The server prepares data for providing a virtual renewal website image to the user.

[0592] 5. User Acknowledgment and Feedback

[0593] 1. Confirmation of virtual renewal proposal:

[0594] The user checks the provided virtual renewal website image.

[0595] 2. Providing Feedback:

[0596] Users provide feedback on the virtual renewal proposal.

[0597] 6. Generate the final report

[0598] 1. Incorporating feedback:

[0599] The server will incorporate user feedback and adjust the final revision proposal.

[0600] 2. Generate and provide reports:

[0601] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[0602] The server provides the final report to the user.

[0603] Specific examples

[0604] Example 1: Information gathering and analysis

[0605] 1. User Action:

[0606] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0607] 2. Server operation:

[0608] The server retrieves the HTML content from the specified URL and stores it in the database.

[0609] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[0610] The server performs scoring based on the analysis results and lists points that need to be improved.

[0611] Example 2: Generation of renovation proposals and virtual renovation

[0612] 1. Server operation:

[0613] The server generates specific repair plans based on the analysis results.

[0614] The server creates a virtual renewal website image and presents it to the user.

[0615] 2. User Action:

[0616] The user checks the virtual renewal website image and provides feedback as needed.

[0617] Example 3: Generating a Final Report

[0618] 1. Server operation:

[0619] The server will incorporate user feedback and adjust the final revision proposal.

[0620] The server generates the final report and provides it to the user.

[0621] This allows website operators to efficiently optimize their websites to accommodate generative AI.

[0622] The processing flow will be explained below.

[0623] Step 1:

[0624] The user enters the URL of the website to be analyzed into the terminal.

[0625] Step 2:

[0626] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[0627] Step 3:

[0628] The server saves the retrieved HTML content in the database.

[0629] Step 4:

[0630] The server loads the generative AI model.

[0631] Step 5:

[0632] The server retrieves the collected HTML content from the database and prepares it for analysis.

[0633] Step 6:

[0634] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[0635] Step 7:

[0636] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[0637] Step 8:

[0638] Specific improvement proposals are listed based on the analysis results generated by the server.

[0639] Step 9:

[0640] The server creates a virtual renewal website image based on the proposed modifications.

[0641] Step 10:

[0642] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[0643] Step 11:

[0644] The user checks the virtual renewal website image and provides feedback from the terminal as needed.

[0645] Step 12:

[0646] The server receives user feedback and adjusts the final revision proposal to reflect the feedback.

[0647] Step 13:

[0648] The server generates the final report and provides it to the user.

[0649] Example 1

[0650] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0651] The traditional website optimization process was time-consuming and costly, requiring a lot of manual work. Furthermore, identifying areas for improvement and proposing specific proposals required a high level of specialized knowledge. This made it difficult for small and medium-sized businesses and individuals to efficiently improve their websites.

[0652] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0653] In this invention, the server includes means for inputting a website URL provided by a user, means for acquiring HTML content from the URL and saving it in a database, means for loading a generative AI model, means for analyzing the HTML content using the generative AI model, means for calculating a website quality score based on the analysis results and listing areas requiring improvement, means for generating an improvement plan based on the analysis results, means for creating a virtual renewed website image based on the improvement plan, means for presenting the virtual renewed website image to a user and collecting feedback, and means for generating a final report based on the feedback. This significantly reduces time and cost, and enables even users without specialized knowledge to efficiently improve their websites.

[0654] The "means for inputting the URL of the website provided by the user" is a method by which the user inputs the URL of the website to be analyzed into the interface.

[0655] "Means for obtaining HTML content from the URL and storing it in a database" refers to a method for obtaining HTML content from an input URL via an HTTP request and storing the data in a database.

[0656] A "means for loading a generative AI model" is a method for loading a specified generative AI model (e.g., GPT-3, BERT, etc.) into memory.

[0657] The "means for analyzing HTML content using the generative AI model" is a method for analyzing text, images, and structure within the retrieved HTML content using the loaded generative AI model.

[0658] "Means for calculating a quality score for a website based on the analysis results and listing areas that require improvement" refers to a method of calculating a score for each element of a website based on the analysis results provided by a generative AI model and listing specific areas that require improvement.

[0659] The "means for generating a modification plan based on the analysis results" is a method for generating a specific improvement plan based on the analysis results.

[0660] The "means for creating a virtual renewal website image based on the proposed modification" is a method for creating a virtual website that reflects the created modification plan.

[0661] The "means for presenting the virtual renewal website image to users and collecting feedback" refers to a method for providing users with a preview of the virtual renewal website and collecting their opinions and improvements as feedback.

[0662] The "means for generating a final report based on the feedback" refers to a method for generating a report that reflects feedback from the user and summarizes the final modification plan and its results.

[0663] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. Specifically, the system involves a server-based process of processing various data, presenting modification proposals to users, and creating a virtual renewal website. A detailed explanation is provided below.

[0664] Hardware and software used

[0665] Hardware

[0666] Server: A server with high-performance computing resources is required, with enough processing power to load the generative AI model and perform the analytical processing.

[0667] software

[0668] Generative AI model: The AI ​​model used for analysis, such as GPT-3 or BERT.

[0669] Database: A database for storing HTML content and analysis results. Typically, an SQL database is used.

[0670] HTTP request library: A library used to retrieve HTML content from a website, for example, the Python Requests library.

[0671] Specific explanation of program processing

[0672] 1. User requirements

[0673] The user enters the URL of the website they want to analyze into a dedicated web interface and sends it to the server.

[0674] 2. Obtaining data from the server

[0675] The server sends an HTTP GET request to the entered URL to retrieve the HTML content.

[0676] The acquired HTML content is stored in the server's database.

[0677] 3. Loading the generative AI model

[0678] The server reads the name of the generative AI model to use from the configuration file and loads it. For example, if you want to use the GPT-3 model, you load the model using the API key.

[0679] 4. Content Analysis

[0680] The server retrieves the collected HTML content from the database.

[0681] The server feeds the HTML data into a generative AI model, which analyzes the text, images, and structure.

[0682] 5. Calculating quality scores and identifying areas for improvement

[0683] Based on the analysis results of the generative AI model, a quality score is calculated for each element of the website.

[0684] List areas where the server needs repair.

[0685] 6. Generation of renovation proposals

[0686] The server generates specific repair plans based on the analysis results.

[0687] To present the proposed modifications to the user, they are compiled in a list format.

[0688] 7. Generation of Virtual Renewal Plans

[0689] The server creates a virtual renewal website image to which the generated modification plan has been applied.

[0690] A preview link of the virtual renewal website is generated and provided to the user.

[0691] 8. User Acknowledgment and Feedback

[0692] The user reviews the provided virtual relaunch website image and provides feedback.

[0693] The user fills in the feedback form with any necessary improvements or comments and submits it.

[0694] 9. Generate the final report

[0695] The server will incorporate user feedback and adjust the final revision proposal.

[0696] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[0697] Generate the final report in PDF or HTML format and provide it to the user via email or download link.

[0698] Specific examples of behavior and prompts for the generative AI model

[0699] Example 1: Information gathering and analysis

[0700] User action: The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0701] Server operation: The server retrieves HTML content from the specified URL and stores it in a database. The server uses a generative AI model to analyze the text, images, and structure of the retrieved content. The server scores the content based on the analysis results and lists points to be improved.

[0702] Prompt Sentence Examples

[0703] "Get the HTML content of the specified website https: / / example.com"

[0704] "Analyze the retrieved content and evaluate the quality of the website."

[0705] "Generate renovation proposals and create virtual renovation sites."

[0706] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0707] Step 1:

[0708] User requirements

[0709] Input: The user enters the URL of the website they want to analyze into a dedicated web interface and submits it.

[0710] Specific behavior: A user enters a URL (e.g., https: / / example.com) into an input form on a web browser and clicks the submit button.

[0711] Output: The entered URL is sent to the server.

[0712] Step 2:

[0713] Server Data Acquisition

[0714] Input: A URL provided by the user.

[0715] Specific operation: The server sends an HTTP GET request to the entered URL and retrieves the HTML content.

[0716] Output: The retrieved HTML content is saved in the server database.

[0717] Step 3:

[0718] Loading a generative AI model

[0719] Input: The name of the generative AI model to use from the server's config file.

[0720] Specific operation: The server reads the configuration file and loads the specified generative AI model (e.g., GPT-3).

[0721] Output: The generative AI model is loaded into memory and ready for analysis.

[0722] Step 4:

[0723] Content Analysis

[0724] Input: HTML content stored in the server's database.

[0725] What it does: The server retrieves HTML content from the database and feeds it into the generative AI model for analysis.

[0726] Output: The analytical results obtained from the generative AI model are obtained.

[0727] Step 5:

[0728] Calculating quality scores and identifying areas to improve

[0729] Input: Analysis results obtained from a generative AI model.

[0730] What it does: Based on the analysis results, the server calculates a quality score for each element of the website and lists areas that need improvement.

[0731] Output: Quality score and list of areas that need improvement.

[0732] Step 6:

[0733] Generate renovation proposals

[0734] Input: A list of areas that need renovation.

[0735] Specific operation: The server uses the generative AI model again based on the analysis results to generate specific repair proposals.

[0736] Output: Get a list of proposed modifications.

[0737] Step 7:

[0738] Generation of virtual renewal proposals

[0739] Input: Generated renovation proposal.

[0740] Specific operation: The server applies the proposed modifications and creates a virtual redesigned website image.

[0741] Output: Preview link of the virtual renewal website.

[0742] Step 8:

[0743] User Acknowledgment and Feedback

[0744] Input: Preview link for your virtual relaunch website.

[0745] What happens: The user clicks on the provided preview link to see the virtual renewal site.

[0746] Output: User feedback.

[0747] Step 9:

[0748] Generate the final report

[0749] Input: User feedback.

[0750] What happens: The server incorporates the feedback, adjusts the final revision proposal, and generates the final report.

[0751] Output: The final report is generated in PDF and HTML format and provided to the user.

[0752] (Application example 1)

[0753] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0754] Improving user experience and conversion rates are key challenges for modern online shopping websites. However, for many online shopping websites, regularly reviewing and revising the entire site is time-consuming and inefficient. It is also difficult to effectively utilize user feedback to optimize the site. For these reasons, there is a need for a more efficient and automated way to optimize websites and improve user experience.

[0755] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0756] In this invention, the server includes: means for analyzing website content using a generation AI and identifying areas requiring improvement; means for generating an improvement plan based on the analysis results by the generation AI; means for creating a virtual renewal website image based on the improvement plan; means for presenting the virtual renewal website image to users and collecting feedback; means for generating a final report based on the feedback; means for collecting website content and saving it in a database; means for analyzing text, structure, and images using the generation AI and performing scoring; means for creating an improvement plan for the online shopping website based on the reviews and feedback analyzed using the generation AI; means for presenting the improvement plan to users and providing a virtual renewal site where the improvement content can be previewed; and means for generating a final improvement report based on user feedback on the virtual renewal site. This makes the online shopping website improvement process more efficient and improves the user experience.

[0757] "Generative AI" is a technology that uses artificial intelligence to generate data and automatically perform tasks such as analysis and evaluation.

[0758] A "website" is a collection of information published on the Internet and written in a markup language such as HTML.

[0759] "Content analysis" is the process of analyzing and evaluating the information within a website, including text, images, structure, etc.

[0760] "Areas in need of improvement" refers to parts of the website that require improvement.

[0761] A "renovation proposal" is a plan that proposes specific corrections or changes to the identified areas for improvement.

[0762] "Virtual renewal website" refers to a virtual web page to which the proposed modifications have been applied.

[0763] "Feedback" refers to opinions and evaluations provided by users, and is information that can be used to improve the system.

[0764] "Final report" refers to the final report that incorporates the feedback.

[0765] "Data collection" refers to the acquisition and storage of website content on a server.

[0766] A "database" is a system for systematically storing and managing collected data.

[0767] "Scoring" is the process of quantifying and evaluating a website's quality and areas for improvement based on the analysis results.

[0768] "Review" refers to comments and ratings that record users' experiences and opinions.

[0769] An "online shopping site" is a website that sells products and services over the Internet.

[0770] "Preview" is a feature that allows users to virtually check improvement proposals before they are actually implemented.

[0771] "Improvement Report" refers to the detailed analysis report that is finally generated based on improvement suggestions and feedback.

[0772] The system for implementing the present invention includes a server, a user terminal, and a generative AI model. The specific operation of this system is described below.

[0773] System Overview

[0774] 1. Get data from the server:

[0775] The user enters the URL of the shopping site they want to analyze. The server sends an HTTP request, retrieves the HTML content from the specified URL, and stores it in a database. For example, if a user enters the URL "https: / / example-shop.com," the server will collect the HTML content of that website.

[0776] 2. Load the generative AI model:

[0777] The server loads and uses a generative AI model (e.g., GPT-3.5-turbo) for analysis, which uses advanced natural language processing to provide a detailed analysis of the website content.

[0778] 3. Content Analysis:

[0779] The server passes the HTML content retrieved from the database to the generative AI model for analysis. The analysis is performed on each element, such as text, images, and structure, to identify its quality and areas for improvement. The analysis results are then scored to quantify the evaluation.

[0780] 4. Review and Feedback Analysis:

[0781] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, which identifies specific areas for improvement based on user experience.

[0782] 5. Generation of renovation proposals and presentation of virtual renewal proposals:

[0783] Based on the analysis results of the generative AI model, the server generates a proposed redesign. Based on this proposed redesign, a virtual redesigned website image is created and presented to the user. At this stage, the user can confirm the proposed redesign and preview the virtual redesigned website.

[0784] 6. Collect user feedback and generate final report:

[0785] The server receives feedback from users about the virtual renewal proposal. The server reflects this feedback and generates a final improvement report. The final report includes the revision proposal, a virtual renewal website image, and user feedback.

[0786] Hardware and software used

[0787] 1. Hardware:

[0788] Server: Collects, analyzes, and manages databases of HTML content.

[0789] User device (smartphone): Enter the URL, provide feedback, and preview the virtual renewal proposal.

[0790] 2. Software:

[0791] requests: A Python library for retrieving HTML content from websites.

[0792] BeautifulSoup: A Python library for parsing HTML content.

[0793] transformers: Libraries for content analysis using generative AI models (e.g., GPT-3.5-turbo).

[0794] Specific examples

[0795] If a user types "https: / / example-shop.com", the server collects the HTML content from this URL and stores it in a database. It then uses a generative AI model to analyze the website's text, images, and structure. It then inputs the following prompt to the generative AI model:

[0796] This is the HTML content from https: / / example-shop.com. Please analyze its text, images, and structure to find areas for improvement and suggest potential enhancements.

[0797] Based on the analysis results, the generative AI model will suggest improvements such as, "The product descriptions lack detailed information. Adding more information about each product will help attract customers' interest. Consider using high-quality images in the product gallery." This will streamline the work of improving online shopping sites and improve the user experience.

[0798] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0799] Step 1:

[0800] Entering URLs and collecting data

[0801] The user enters the URL of their shopping site. The server sends an HTTP request to the entered URL and retrieves the website's HTML content. Specifically, it uses Python's requests library to retrieve HTML data from the specified URL and saves this data in a database.

[0802] Input: The URL entered by the user

[0803] Output: Retrieved HTML content (stored in database)

[0804] Step 2:

[0805] Loading a generative AI model

[0806] The server loads the generative AI model (e.g., GPT-3.5-turbo) and prepares it for analysis. The server loads the model using the transformers library.

[0807] Input: File path of the generated AI model

[0808] Output: The loaded generative AI model

[0809] Step 3:

[0810] Parsing HTML content

[0811] The server retrieves HTML content from the database and passes it to the generative AI model for analysis. BeautifulSoup is used to parse the HTML content and extract the text, images, and structure contained within it. This data is then input into the generative AI model to obtain the analysis results.

[0812] Input: HTML content stored in the database

[0813] Output: Analysis results from the generative AI model

[0814] Step 4:

[0815] Review and feedback analysis

[0816] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, thereby extracting specific points for improvement based on the user experience.

[0817] Input: User reviews and feedback

[0818] Output: Analysis results and points for improvement by the generative AI model

[0819] Step 5:

[0820] Generate renovation proposals

[0821] Based on the analysis results, the server generates specific improvement proposals, using a generative AI model to review each analysis data and propose ways to improve the relevant areas.

[0822] Input: Analysis results from generative AI model

[0823] Output: Specific renovation proposal

[0824] Step 6:

[0825] Virtual renewal website generation

[0826] Based on the proposed modifications obtained in the previous step, the server creates a virtual renewal website that allows users to preview how the site will look with the proposed modifications.

[0827] Input: Specific renovation plan

[0828] Output: Virtual renewal website image

[0829] Step 7:

[0830] User preview and feedback gathering

[0831] The user terminal displays the virtual renewal website image, allowing the user to check its contents and provide feedback.

[0832] Input: Virtual renewal website image

[0833] Output: User feedback

[0834] Step 8:

[0835] Generate the final report

[0836] After collecting user feedback, the server uses this information to generate a final report, which includes proposed improvements, virtual redesigned website images, and user feedback.

[0837] Input: User feedback

[0838] Output: Final report

[0839] Through these steps, the online shopping site renovation process will be made more efficient and the user experience will be improved.

[0840] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0841] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine.

[0842] 1. Information gathering stage

[0843] 1. User requirements:

[0844] The user enters the URL of the website they want to analyze into the device.

[0845] 2. Get data from the server:

[0846] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website.

[0847] The server saves the retrieved HTML content in the database.

[0848] 2. Content analysis stage

[0849] 1. Load the generative AI model:

[0850] The server loads the generative AI model used for analysis.

[0851] 2. Content Analysis:

[0852] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0853] The server scores the quality of the website based on the analysis results.

[0854] 3. Identifying points to be improved

[0855] 1. Obtaining analysis results:

[0856] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[0857] 2. Generate renovation proposals:

[0858] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[0859] 4. Generation of virtual renewal proposals

[0860] 1. Create a virtual site based on the proposed renovation:

[0861] The server creates a virtual renewal website image with the proposed modifications applied.

[0862] The server prepares data for providing a virtual renewal website image to the user.

[0863] 5. User Acknowledgment and Feedback

[0864] 1. Confirmation of virtual renewal proposal:

[0865] The user checks the provided virtual renewal website image.

[0866] At this time, the server uses an emotion engine to analyze the user's facial expressions and tone of voice, and recognize the user's emotions.

[0867] 2. Providing Feedback:

[0868] Users provide feedback on the virtual renewal proposal.

[0869] The server also takes into consideration the emotional data collected using an emotion engine and reflects it in the feedback content.

[0870] 6. Generate the final report

[0871] 1. Incorporating feedback:

[0872] The server receives user feedback and adjusts the final revision proposal based on the feedback.

[0873] At this stage, emotional data is analyzed by the emotion engine to improve the quality of feedback.

[0874] 2. Generate and provide reports:

[0875] The server generates a final report containing the final redesign proposal, virtual redesigned website images, and user feedback and sentiment data.

[0876] The server provides the final report to the user.

[0877] Specific examples

[0878] Example 1: Information gathering and analysis

[0879] 1. User Action:

[0880] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0881] 2. Server operation:

[0882] The server retrieves the HTML content from the specified URL and stores it in the database.

[0883] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[0884] The server performs scoring based on the analysis results and lists points that need to be improved.

[0885] Example 2: Generation of renovation proposals and virtual renovation

[0886] 1. Server operation:

[0887] The server generates specific repair plans based on the analysis results.

[0888] The server creates a virtual renewal website image and presents it to the user.

[0889] When a user views the virtual renewal website image, the emotion engine recognizes the user's emotion.

[0890] 2. User Action:

[0891] The user checks the virtual renewal website image and provides feedback as needed.

[0892] Example 3: Generating a Final Report

[0893] 1. Server operation:

[0894] The server receives user feedback and emotional data and adjusts the final revision proposal.

[0895] The server generates the final report and provides it to the user.

[0896] By combining it with an emotion engine that recognizes user emotions, website operators can obtain specific data to improve user satisfaction and efficiently achieve optimization compatible with generative AI.

[0897] The processing flow will be explained below.

[0898] Step 1:

[0899] The user enters the URL of the website to be analyzed into the terminal.

[0900] Step 2:

[0901] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[0902] Step 3:

[0903] The server saves the retrieved HTML content in the database.

[0904] Step 4:

[0905] The server loads the generative AI model.

[0906] Step 5:

[0907] The server retrieves the collected HTML content from the database and prepares it for analysis.

[0908] Step 6:

[0909] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[0910] Step 7:

[0911] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[0912] Step 8:

[0913] Specific improvement proposals are listed based on the analysis results generated by the server.

[0914] Step 9:

[0915] The server creates a virtual renewal website image based on the proposed modifications.

[0916] Step 10:

[0917] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[0918] Step 11:

[0919] When the user checks the virtual renewal website image, the server uses an emotion engine to recognize the user's emotion.

[0920] Step 12:

[0921] The user provides feedback on the virtual renewal proposal from the terminal.

[0922] Step 13:

[0923] The server receives user feedback and emotional data and adjusts the final revision proposal.

[0924] Step 14:

[0925] The server generates the final report and provides it to the user.

[0926] Example 2

[0927] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0928] Conventional website analysis systems focused on evaluating content quality and generating improvement proposals, but did not adequately address the collection of feedback and the creation of final reports that took user emotions into account. This made it difficult to obtain specific insights for improving user experience and satisfaction. Furthermore, when creating and evaluating virtual renewal images of proposed improvements, there was a lack of a way to reflect user emotions in real time.

[0929] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0930] In this invention, the server includes means for analyzing the content of the website using a generation AI and identifying areas that need modification, means for generating a modification plan based on the analysis results by the generation AI, means for creating a virtual renewed website image based on the modification plan, means for analyzing user emotions using an emotion engine, means for improving feedback based on user emotion data, and means for generating a final report, thereby enabling website optimization that takes user emotions into consideration in real time.

[0931] "Generative AI" is an algorithm that uses artificial intelligence technology to generate new information and patterns from data.

[0932] A "website" is a collection of pages that provide information or content on the Internet.

[0933] An "emotion engine" is a technology that analyzes user emotions and collects and utilizes that data.

[0934] "Analysis" is the process of breaking down data or information into smaller pieces to understand its structure and content.

[0935] "Proposal for Improvement" means a proposed plan or method for improving an existing system or structure.

[0936] A "virtual renewal website image" is a visual model of a virtual website created based on the proposed renovation plan.

[0937] "Feedback" refers to opinions and evaluations from users regarding proposed improvements.

[0938] The "Final Report" is a report summarizing the results, recommendations, and feedback of the renovation process.

[0939] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[0940] "Scoring" is the process of assigning a score to evaluate the quality and performance of an object based on the analysis results.

[0941] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine. It mainly involves servers, terminals, and users.

[0942] First, the user inputs the URL of the website they want to analyze into their device. Next, the server sends an HTTP request to the specified URL and retrieves the website's HTML content. The server uses the Python requests library to do this. The retrieved HTML content is then stored in a database such as MySQL or MongoDB.

[0943] Next, the server loads the generative AI model to be used for analysis. For generative AI models, advanced natural language processing models such as GPT-3 and BERT are used. The weight and configuration files for the model are loaded, and the server is ready for analysis.

[0944] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc. Natural language processing technology is used for text analysis, and deep learning models are used for image analysis. Based on the analysis results, the quality of the website is scored. Evaluation criteria include page loading speed, content relevance, and user experience.

[0945] Next, the server uses the results of the AI's analysis to create a list of areas of the website that need improvement. This list includes specific points of concern and suggestions for improvement. Suggested improvements include, for example, optimizing image size and revising content.

[0946] The server creates an image of a virtual redesigned website with the proposed modifications applied. It uses HTML, CSS, JavaScript, etc. to build the virtual website and prepares the data to be presented to the user. The user can then view this image of the virtual redesigned website through their browser.

[0947] The server's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. The system uses facial and voice recognition technology to capture the user's emotions. The user provides feedback on the virtual renewal proposal.

[0948] After the user provides their feedback, the server adjusts the final revision proposal based on the feedback. At this stage, the emotion engine analyzes the emotion data to improve the accuracy of the feedback. A final report is generated containing the final revision proposal, an image of the virtual redesigned website, the feedback, and the emotion data, and is sent to the user via email.

[0949] Specific examples

[0950] Example 1: Data acquisition and analysis

[0951] User Action:

[0952] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[0953] Server behavior:

[0954] The server uses Python's requests library to retrieve HTML content from the specified URL and saves it in a MySQL database. It then uses a generative AI model (e.g., GPT-3) to analyze the text, images, and structure of the retrieved content. It then scores the content based on the analysis results and lists points to improve.

[0955] Example 2: Renovation proposal generation and virtual renovation

[0956] Server behavior:

[0957] The server generates specific renovation proposals based on the analysis results, creates an image of a virtual renewal website using HTML and CSS, and presents it to the user.

[0958] User Action:

[0959] When a user browses the virtual renewal website and provides feedback, the emotion engine recognizes the user's facial expressions and collects emotional data.

[0960] Example 3: Final report generation

[0961] Server behavior:

[0962] The server receives user feedback and sentiment data, adjusts the final revision proposal, and generates a final report to provide to the user.

[0963] Prompt Sentence Examples

[0964] "Analyze the website at the following URL and generate improvement recommendations: https: / / example.com"

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Program processing flow

[0967] Step 1:

[0968] User requirements

[0969] The user inputs the URL of the website they want to analyze into the device, which then sends this URL data to the server.

[0970] Enter: Website URL

[0971] Output: Sends URL data to the server

[0972] Step 2:

[0973] Data Acquisition

[0974] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website. The server uses the Python requests library and saves the retrieved HTML content in a database (e.g., MySQL, MongoDB).

[0975] Input: URL data

[0976] Output: HTML content, saved to database

[0977] Specific behavior:

[0978] The server retrieves the HTML using requests.get(URL) and saves it in the database.

[0979] Step 3:

[0980] Loading a Model

[0981] The server loads the generative AI model to be used for analysis. We use natural language processing models such as GPT-3 and BERT as generative AI models. We also load the model weight and configuration files.

[0982] Input: None (preparatory operation in previous stage)

[0983] Output: Model instantiation

[0984] Specific behavior:

[0985] The server loads the model using a library such as from transformers import GPT3.

[0986] Step 4:

[0987] Content Analysis

[0988] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[0989] Input: HTML content (retrieved from database)

[0990] Output: Text, image and structure analysis data

[0991] Specific behavior:

[0992] The server inputs HTML data into the model and performs text analysis (natural language processing) and image analysis (deep learning model).

[0993] Step 5:

[0994] Scoring

[0995] The server then scores the website's quality based on the analysis, including criteria such as page load speed, content relevance, and user experience.

[0996] Input: Analysis data

[0997] Output: Scoring results

[0998] Specific behavior:

[0999] Points are assigned according to the evaluation criteria and an overall score is calculated.

[1000] Step 6:

[1001] Identifying points to be repaired

[1002] The server generates a list of areas of the website that need improvement based on the results of the AI ​​analysis, and outputs specific points of emphasis and suggestions for improvement.

[1003] Input: Scoring results, analysis data

[1004] Output: List of modification points

[1005] Specific behavior:

[1006] We will make a list of areas that need improvement and propose specific improvement plans.

[1007] Step 7:

[1008] Generate renovation proposals

[1009] The server generates specific improvement proposals for the listed improvement points, such as "optimizing image size" and "reviewing content."

[1010] Input: List of renovation points

[1011] Output: Revision proposal

[1012] Specific behavior:

[1013] Generate and list specific improvement methods.

[1014] Step 8:

[1015] Generate a virtual renewal site

[1016] The server creates an image of a virtual redesigned website with the proposed modifications applied. The virtual website is built using HTML, CSS, JavaScript, etc.

[1017] Input: Renovation proposal

[1018] Output: Image of the virtual renewal site

[1019] Specific behavior:

[1020] Build the website's HTML and styles based on the proposed changes.

[1021] Step 9:

[1022] User Verification

[1023] The user checks the image of the virtual renewal website provided through a browser.

[1024] Input: Image of the virtual renewal site

[1025] Output: User feedback

[1026] Specific behavior:

[1027] A user reviews a website in a browser and provides feedback.

[1028] Step 10:

[1029] Emotion analysis

[1030] The server's emotion engine analyzes the user's facial expressions and tone of voice, using facial and voice recognition technology.

[1031] Input: User feedback, real-time video / audio data

[1032] Output: Emotion data

[1033] Specific behavior:

[1034] It analyzes the user's facial expressions and tone of voice in real time to collect emotional data.

[1035] Step 11:

[1036] Feedback collection

[1037] Users provide feedback on virtual renewal proposals. By taking emotion data into account, more accurate feedback can be obtained.

[1038] Input: User feedback, emotion data

[1039] Output: Improved feedback

[1040] Specific behavior:

[1041] Emotional data is reflected in the feedback to improve accuracy.

[1042] Step 12:

[1043] Final revision proposal and report generation

[1044] The server receives the feedback and emotion data from the users, adjusts the final renovation proposal, and generates a final report including the final renovation proposal, an image of the virtual renewal website, the feedback, and the emotion data, and provides it to the user.

[1045] Input: Improved feedback, emotional data

[1046] Output: Final report

[1047] Specific behavior:

[1048] A final list of renovation proposals will be compiled and a final report will be generated in PDF format, including the virtual renewal site and feedback.

[1049] (Application example 2)

[1050] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1051] In modern content delivery services, personalized recommendations that take into account not only the content viewed but also the user's real-time emotional state are required to improve the user experience. However, conventional systems have difficulty accurately grasping the user's emotions and suggesting optimal content. Furthermore, in the process of analyzing websites and proposing improvements, it is difficult to collect accurate feedback, which can result in a decrease in user satisfaction.

[1052] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the content of a website using a generation AI and identifying areas requiring modification, means for generating a modification proposal based on the analysis results by the generation AI, means for creating a virtual renewal website image based on the modification proposal, means for presenting the virtual renewal website image to a user and collecting feedback, means for generating a final report based on the feedback, means for analyzing the user's emotional state using an emotion engine when collecting feedback, and means for making personalized recommendations based on the emotional state. This enables personalized content recommendations that take into account the user's real-time emotional state and highly accurate feedback collection in the website analysis and modification process.

[1053] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze content such as text and images.

[1054] An "emotion engine" is software that analyzes a user's facial expressions, voice, etc., and recognizes and evaluates their emotional state.

[1055] "Website content" refers to the digital information contained on a web page, such as text, images, video, and link structure.

[1056] "Improvement Proposal" means a proposal that identifies areas of the Website or Content that need improvement and presents how to correct or improve them.

[1057] "Virtual Renewal Website Image" means an image or prototype of an improved website that is virtually created based on the proposed renovation.

[1058] "Feedback" refers to the evaluation or opinion provided by the user after checking the virtual renewal website image.

[1059] "Final Report" is a document detailing website or content optimization recommendations that take into account user feedback and emotional state.

[1060] "Personalized recommendations" are the act of suggesting appropriate content based on the attributes, behavioral history, and emotional state of individual users.

[1061] This invention is a system that utilizes generative AI and an emotion engine to improve the user experience in content distribution services. A specific implementation method of this system is described below.

[1062] First, when a user views content, the server retrieves the URL associated with the content and sends an HTTP request to retrieve the HTML content. In this process, the hardware used is the server, and the software required is a library to process the HTTP request. The retrieved HTML content is then stored in a database.

[1063] Next, the server loads a generative AI model and analyzes the content. For example, the "transformers" library is used as the generative AI model. At this stage, the server analyzes the acquired text, images, structural information, etc., and performs a quality score on the content. The analysis results are stored in a database and are used in a later step to generate improvement proposals.

[1064] After the analysis, the server executes a procedure to generate a modification plan based on the analysis results of the generative AI. The generated modification plan is visualized as a virtual renewal website image. The virtual renewal website image is presented to the user, who then confirms it. The software used here is an image processing library, and the user interface is a web browser.

[1065] When a user views the virtual renewal website image, the server uses an emotion engine to analyze the user's emotional state in real time. The emotion engine uses the "DeepFace" library to capture and analyze the user's facial expressions and voice. Personalized content recommendations are made based on the user's emotional state.

[1066] Finally, the server generates a final report that takes into account user feedback and sentiment data, including a virtual website redesign image, proposed improvements, and user feedback, leading to efficient website and content optimization and improved user satisfaction.

[1067] For example, if the emotion engine determines that the user is feeling stressed, a prompt can be used to recommend relaxing music or videos. For example, the prompt could be, "Please analyze the main topics and emotions of this web page" or "Please recommend content that will help the user relax."

[1068] As described above, the system of the present invention integrates generative AI and an emotion engine to provide personalized recommendations based on the user's emotional state, thereby significantly improving the user experience in content distribution services.

[1069] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1070] Step 1:

[1071] The user enters the URL of the website they wish to view on their device. The device then sends this URL to the server. The server receives the URL and sends an HTTP request to retrieve the HTML content of the website. The input data is the URL entered by the user, and the output data is the retrieved HTML content. This process uses the HTTP request library to download the website content.

[1072] Step 2:

[1073] The server saves the acquired HTML content in a database. The input data is the acquired HTML content, and the output data is the content saved in the database. The saving process is performed using a database operation library.

[1074] Step 3:

[1075] The server loads the generative AI model and retrieves HTML content from the database. The input data is the HTML content stored in the database, and the output data is the analysis results. The generative AI model uses the "transformers" library to analyze the retrieved text, images, and structural information. Specific operations include text tokenization and structural analysis.

[1076] Step 4:

[1077] The server scores the quality of the website based on the analysis results. The input data is the analysis results of the generative AI model, and the output data is a quality score. Scoring includes multiple indicators such as text readability and image optimization.

[1078] Step 5:

[1079] The server generates a repair plan based on the scoring results. The input data is the quality score, and the output data is the repair plan. Using a generative AI model, it identifies areas that need repair and uses prompts to suggest how to improve them.

[1080] Step 6:

[1081] The server creates a virtual renewal website image based on the proposed modifications. The input data is the modification proposal, and the output data is the virtual renewal website image. Here, an image processing library is used to visually represent the proposed modifications.

[1082] Step 7:

[1083] The server presents the virtual renewal website image to the user, and the user checks the virtual renewal website image and provides feedback, where the input data is the virtual renewal website image and the output data is the user's feedback.

[1084] Step 8:

[1085] When collecting feedback, the server uses an emotion engine to analyze the user's emotional state. The input data is the user's facial expressions and voice, and the output data is emotion data. Specifically, the server uses the "DeepFace" library to perform facial and voice analysis.

[1086] Step 9:

[1087] The server makes personalized content recommendations based on emotional data. The input data is emotional data, and the output data is recommended content. Using a generative AI model, it suggests songs and videos that correspond to the user's emotional state.

[1088] Step 10:

[1089] The server generates a final report by taking into account the user's feedback and emotion data. The input data is the user's feedback and emotion data, and the output data is the final report. The final report includes a virtual renewal website image, a modification proposal, and the user's feedback.

[1090] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1091] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1092] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1093] [Third embodiment]

[1094] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1095] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1096] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1097] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1098] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1099] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1100] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1101] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1102] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1103] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1104] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1105] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1106] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. The main functions and examples are described below.

[1107] 1. Information gathering stage

[1108] 1. User requirements:

[1109] The user enters the URL of the website they want to analyze.

[1110] 2. Get data from the server:

[1111] The server sends an HTTP request based on the URL provided by the user to retrieve the HTML content of the web page.

[1112] The server saves the retrieved HTML content in the database.

[1113] 2. Content analysis stage

[1114] 1. Load the generative AI model:

[1115] The server loads the generative AI model used for analysis.

[1116] 2. Content Analysis:

[1117] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[1118] Based on the analysis results, the quality of the website is scored.

[1119] 3. Identifying points to be improved

[1120] 1. Obtaining analysis results:

[1121] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[1122] 2. Generate renovation proposals:

[1123] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[1124] 4. Generation of virtual renewal proposals

[1125] 1. Create a virtual site based on the proposed renovation:

[1126] The server creates a virtual renewal website image with the proposed modifications applied.

[1127] The server prepares data for providing a virtual renewal website image to the user.

[1128] 5. User Acknowledgment and Feedback

[1129] 1. Confirmation of virtual renewal proposal:

[1130] The user checks the provided virtual renewal website image.

[1131] 2. Providing Feedback:

[1132] Users provide feedback on the virtual renewal proposal.

[1133] 6. Generate the final report

[1134] 1. Incorporating feedback:

[1135] The server will incorporate user feedback and adjust the final revision proposal.

[1136] 2. Generate and provide reports:

[1137] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[1138] The server provides the final report to the user.

[1139] Specific examples

[1140] Example 1: Information gathering and analysis

[1141] 1. User Action:

[1142] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1143] 2. Server operation:

[1144] The server retrieves the HTML content from the specified URL and stores it in the database.

[1145] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[1146] The server performs scoring based on the analysis results and lists points that need to be improved.

[1147] Example 2: Generation of renovation proposals and virtual renovation

[1148] 1. Server operation:

[1149] The server generates specific repair plans based on the analysis results.

[1150] The server creates a virtual renewal website image and presents it to the user.

[1151] 2. User Action:

[1152] The user checks the virtual renewal website image and provides feedback as needed.

[1153] Example 3: Generating a Final Report

[1154] 1. Server operation:

[1155] The server will incorporate user feedback and adjust the final revision proposal.

[1156] The server generates the final report and provides it to the user.

[1157] This allows website operators to efficiently optimize their websites to accommodate generative AI.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] The user enters the URL of the website to be analyzed into the terminal.

[1161] Step 2:

[1162] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[1163] Step 3:

[1164] The server saves the retrieved HTML content in the database.

[1165] Step 4:

[1166] The server loads the generative AI model.

[1167] Step 5:

[1168] The server retrieves the collected HTML content from the database and prepares it for analysis.

[1169] Step 6:

[1170] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[1171] Step 7:

[1172] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[1173] Step 8:

[1174] Specific improvement proposals are listed based on the analysis results generated by the server.

[1175] Step 9:

[1176] The server creates a virtual renewal website image based on the proposed modifications.

[1177] Step 10:

[1178] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[1179] Step 11:

[1180] The user checks the virtual renewal website image and provides feedback from the terminal as needed.

[1181] Step 12:

[1182] The server receives user feedback and adjusts the final revision proposal to reflect the feedback.

[1183] Step 13:

[1184] The server generates the final report and provides it to the user.

[1185] Example 1

[1186] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1187] The traditional website optimization process was time-consuming and costly, requiring a lot of manual work. Furthermore, identifying areas for improvement and proposing specific proposals required a high level of specialized knowledge. This made it difficult for small and medium-sized businesses and individuals to efficiently improve their websites.

[1188] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1189] In this invention, the server includes means for inputting a website URL provided by a user, means for acquiring HTML content from the URL and saving it in a database, means for loading a generative AI model, means for analyzing the HTML content using the generative AI model, means for calculating a website quality score based on the analysis results and listing areas requiring improvement, means for generating an improvement plan based on the analysis results, means for creating a virtual renewed website image based on the improvement plan, means for presenting the virtual renewed website image to a user and collecting feedback, and means for generating a final report based on the feedback. This significantly reduces time and cost, and enables even users without specialized knowledge to efficiently improve their websites.

[1190] The "means for inputting the URL of the website provided by the user" is a method by which the user inputs the URL of the website to be analyzed into the interface.

[1191] "Means for obtaining HTML content from the URL and storing it in a database" refers to a method for obtaining HTML content from an input URL via an HTTP request and storing the data in a database.

[1192] A "means for loading a generative AI model" is a method for loading a specified generative AI model (e.g., GPT-3, BERT, etc.) into memory.

[1193] The "means for analyzing HTML content using the generative AI model" is a method for analyzing text, images, and structure within the retrieved HTML content using the loaded generative AI model.

[1194] "Means for calculating a quality score for a website based on the analysis results and listing areas that require improvement" refers to a method of calculating a score for each element of a website based on the analysis results provided by a generative AI model and listing specific areas that require improvement.

[1195] The "means for generating a modification plan based on the analysis results" is a method for generating a specific improvement plan based on the analysis results.

[1196] The "means for creating a virtual renewal website image based on the proposed modification" is a method for creating a virtual website that reflects the created modification plan.

[1197] The "means for presenting the virtual renewal website image to users and collecting feedback" refers to a method for providing users with a preview of the virtual renewal website and collecting their opinions and improvements as feedback.

[1198] The "means for generating a final report based on the feedback" refers to a method for generating a report that reflects feedback from the user and summarizes the final modification plan and its results.

[1199] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. Specifically, the system involves a server-based process of processing various data, presenting modification proposals to users, and creating a virtual renewal website. A detailed explanation is provided below.

[1200] Hardware and software used

[1201] Hardware

[1202] Server: A server with high-performance computing resources is required, with enough processing power to load the generative AI model and perform the analytical processing.

[1203] software

[1204] Generative AI model: The AI ​​model used for analysis, such as GPT-3 or BERT.

[1205] Database: A database for storing HTML content and analysis results. Typically, an SQL database is used.

[1206] HTTP request library: A library used to retrieve HTML content from a website, for example, the Python Requests library.

[1207] Specific explanation of program processing

[1208] 1. User requirements

[1209] The user enters the URL of the website they want to analyze into a dedicated web interface and sends it to the server.

[1210] 2. Obtaining data from the server

[1211] The server sends an HTTP GET request to the entered URL to retrieve the HTML content.

[1212] The acquired HTML content is stored in the server's database.

[1213] 3. Loading the generative AI model

[1214] The server reads the name of the generative AI model to use from the configuration file and loads it. For example, if you want to use the GPT-3 model, you load the model using the API key.

[1215] 4. Content Analysis

[1216] The server retrieves the collected HTML content from the database.

[1217] The server feeds the HTML data into a generative AI model, which analyzes the text, images, and structure.

[1218] 5. Calculating quality scores and identifying areas for improvement

[1219] Based on the analysis results of the generative AI model, a quality score is calculated for each element of the website.

[1220] List areas where the server needs repair.

[1221] 6. Generation of renovation proposals

[1222] The server generates specific repair plans based on the analysis results.

[1223] To present the proposed modifications to the user, they are compiled in a list format.

[1224] 7. Generation of Virtual Renewal Plans

[1225] The server creates a virtual renewal website image to which the generated modification plan has been applied.

[1226] A preview link of the virtual renewal website is generated and provided to the user.

[1227] 8. User Acknowledgment and Feedback

[1228] The user reviews the provided virtual relaunch website image and provides feedback.

[1229] The user fills in the feedback form with any necessary improvements or comments and submits it.

[1230] 9. Generate the final report

[1231] The server will incorporate user feedback and adjust the final revision proposal.

[1232] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[1233] Generate the final report in PDF or HTML format and provide it to the user via email or download link.

[1234] Specific examples of behavior and prompts for the generative AI model

[1235] Example 1: Information gathering and analysis

[1236] User action: The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1237] Server operation: The server retrieves HTML content from the specified URL and stores it in a database. The server uses a generative AI model to analyze the text, images, and structure of the retrieved content. The server scores the content based on the analysis results and lists points to be improved.

[1238] Prompt Sentence Examples

[1239] "Get the HTML content of the specified website https: / / example.com"

[1240] "Analyze the retrieved content and evaluate the quality of the website."

[1241] "Generate renovation proposals and create virtual renovation sites."

[1242] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1243] Step 1:

[1244] User requirements

[1245] Input: The user enters the URL of the website they want to analyze into a dedicated web interface and submits it.

[1246] Specific behavior: A user enters a URL (e.g., https: / / example.com) into an input form on a web browser and clicks the submit button.

[1247] Output: The entered URL is sent to the server.

[1248] Step 2:

[1249] Server Data Acquisition

[1250] Input: A URL provided by the user.

[1251] Specific operation: The server sends an HTTP GET request to the entered URL and retrieves the HTML content.

[1252] Output: The retrieved HTML content is saved in the server database.

[1253] Step 3:

[1254] Loading a generative AI model

[1255] Input: The name of the generative AI model to use from the server's config file.

[1256] Specific operation: The server reads the configuration file and loads the specified generative AI model (e.g., GPT-3).

[1257] Output: The generative AI model is loaded into memory and ready for analysis.

[1258] Step 4:

[1259] Content Analysis

[1260] Input: HTML content stored in the server's database.

[1261] What it does: The server retrieves HTML content from the database and feeds it into the generative AI model for analysis.

[1262] Output: The analytical results obtained from the generative AI model are obtained.

[1263] Step 5:

[1264] Calculating quality scores and identifying areas to improve

[1265] Input: Analysis results obtained from a generative AI model.

[1266] What it does: Based on the analysis results, the server calculates a quality score for each element of the website and lists areas that need improvement.

[1267] Output: Quality score and list of areas that need improvement.

[1268] Step 6:

[1269] Generate renovation proposals

[1270] Input: A list of areas that need renovation.

[1271] Specific operation: The server uses the generative AI model again based on the analysis results to generate specific repair proposals.

[1272] Output: Get a list of proposed modifications.

[1273] Step 7:

[1274] Generation of virtual renewal proposals

[1275] Input: Generated renovation proposal.

[1276] Specific operation: The server applies the proposed modifications and creates a virtual redesigned website image.

[1277] Output: Preview link of the virtual renewal website.

[1278] Step 8:

[1279] User Acknowledgment and Feedback

[1280] Input: Preview link for your virtual relaunch website.

[1281] What happens: The user clicks on the provided preview link to see the virtual renewal site.

[1282] Output: User feedback.

[1283] Step 9:

[1284] Generate the final report

[1285] Input: User feedback.

[1286] What happens: The server incorporates the feedback, adjusts the final revision proposal, and generates the final report.

[1287] Output: The final report is generated in PDF and HTML format and provided to the user.

[1288] (Application example 1)

[1289] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1290] Improving user experience and conversion rates are key challenges for modern online shopping websites. However, for many online shopping websites, regularly reviewing and revising the entire site is time-consuming and inefficient. It is also difficult to effectively utilize user feedback to optimize the site. For these reasons, there is a need for a more efficient and automated way to optimize websites and improve user experience.

[1291] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1292] In this invention, the server includes: means for analyzing website content using a generation AI and identifying areas requiring improvement; means for generating an improvement plan based on the analysis results by the generation AI; means for creating a virtual renewal website image based on the improvement plan; means for presenting the virtual renewal website image to users and collecting feedback; means for generating a final report based on the feedback; means for collecting website content and saving it in a database; means for analyzing text, structure, and images using the generation AI and performing scoring; means for creating an improvement plan for the online shopping website based on the reviews and feedback analyzed using the generation AI; means for presenting the improvement plan to users and providing a virtual renewal site where the improvement content can be previewed; and means for generating a final improvement report based on user feedback on the virtual renewal site. This makes the online shopping website improvement process more efficient and improves the user experience.

[1293] "Generative AI" is a technology that uses artificial intelligence to generate data and automatically perform tasks such as analysis and evaluation.

[1294] A "website" is a collection of information published on the Internet and written in a markup language such as HTML.

[1295] "Content analysis" is the process of analyzing and evaluating the information within a website, including text, images, structure, etc.

[1296] "Areas in need of improvement" refers to parts of the website that require improvement.

[1297] A "renovation proposal" is a plan that proposes specific corrections or changes to the identified areas for improvement.

[1298] "Virtual renewal website" refers to a virtual web page to which the proposed modifications have been applied.

[1299] "Feedback" refers to opinions and evaluations provided by users, and is information that can be used to improve the system.

[1300] "Final report" refers to the final report that incorporates the feedback.

[1301] "Data collection" refers to the acquisition and storage of website content on a server.

[1302] A "database" is a system for systematically storing and managing collected data.

[1303] "Scoring" is the process of quantifying and evaluating a website's quality and areas for improvement based on the analysis results.

[1304] "Review" refers to comments and ratings that record users' experiences and opinions.

[1305] An "online shopping site" is a website that sells products and services over the Internet.

[1306] "Preview" is a feature that allows users to virtually check improvement proposals before they are actually implemented.

[1307] "Improvement Report" refers to the detailed analysis report that is finally generated based on improvement suggestions and feedback.

[1308] The system for implementing the present invention includes a server, a user terminal, and a generative AI model. The specific operation of this system is described below.

[1309] System Overview

[1310] 1. Get data from the server:

[1311] The user enters the URL of the shopping site they want to analyze. The server sends an HTTP request, retrieves the HTML content from the specified URL, and stores it in a database. For example, if a user enters the URL "https: / / example-shop.com," the server will collect the HTML content of that website.

[1312] 2. Load the generative AI model:

[1313] The server loads and uses a generative AI model (e.g., GPT-3.5-turbo) for analysis, which uses advanced natural language processing to provide a detailed analysis of the website content.

[1314] 3. Content Analysis:

[1315] The server passes the HTML content retrieved from the database to the generative AI model for analysis. The analysis is performed on each element, such as text, images, and structure, to identify its quality and areas for improvement. The analysis results are then scored to quantify the evaluation.

[1316] 4. Review and Feedback Analysis:

[1317] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, which identifies specific areas for improvement based on user experience.

[1318] 5. Generation of renovation proposals and presentation of virtual renewal proposals:

[1319] Based on the analysis results of the generative AI model, the server generates a proposed redesign. Based on this proposed redesign, a virtual redesigned website image is created and presented to the user. At this stage, the user can confirm the proposed redesign and preview the virtual redesigned website.

[1320] 6. Collect user feedback and generate final report:

[1321] The server receives feedback from users about the virtual renewal proposal. The server reflects this feedback and generates a final improvement report. The final report includes the revision proposal, a virtual renewal website image, and user feedback.

[1322] Hardware and software used

[1323] 1. Hardware:

[1324] Server: Collects, analyzes, and manages databases of HTML content.

[1325] User device (smartphone): Enter the URL, provide feedback, and preview the virtual renewal proposal.

[1326] 2. Software:

[1327] requests: A Python library for retrieving HTML content from websites.

[1328] BeautifulSoup: A Python library for parsing HTML content.

[1329] transformers: Libraries for content analysis using generative AI models (e.g., GPT-3.5-turbo).

[1330] Specific examples

[1331] If a user types "https: / / example-shop.com", the server collects the HTML content from this URL and stores it in a database. It then uses a generative AI model to analyze the website's text, images, and structure. It then inputs the following prompt to the generative AI model:

[1332] This is the HTML content from https: / / example-shop.com. Please analyze its text, images, and structure to find areas for improvement and suggest potential enhancements.

[1333] Based on the analysis results, the generative AI model will suggest improvements such as, "The product descriptions lack detailed information. Adding more information about each product will help attract customers' interest. Consider using high-quality images in the product gallery." This will streamline the work of improving online shopping sites and improve the user experience.

[1334] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1335] Step 1:

[1336] Entering URLs and collecting data

[1337] The user enters the URL of their shopping site. The server sends an HTTP request to the entered URL and retrieves the website's HTML content. Specifically, it uses Python's requests library to retrieve HTML data from the specified URL and saves this data in a database.

[1338] Input: The URL entered by the user

[1339] Output: Retrieved HTML content (stored in database)

[1340] Step 2:

[1341] Loading a generative AI model

[1342] The server loads the generative AI model (e.g., GPT-3.5-turbo) and prepares it for analysis. The server loads the model using the transformers library.

[1343] Input: File path of the generated AI model

[1344] Output: The loaded generative AI model

[1345] Step 3:

[1346] Parsing HTML content

[1347] The server retrieves HTML content from the database and passes it to the generative AI model for analysis. BeautifulSoup is used to parse the HTML content and extract the text, images, and structure contained within it. This data is then input into the generative AI model to obtain the analysis results.

[1348] Input: HTML content stored in the database

[1349] Output: Analysis results from the generative AI model

[1350] Step 4:

[1351] Review and feedback analysis

[1352] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, thereby extracting specific points for improvement based on the user experience.

[1353] Input: User reviews and feedback

[1354] Output: Analysis results and points for improvement by the generative AI model

[1355] Step 5:

[1356] Generate renovation proposals

[1357] Based on the analysis results, the server generates specific improvement proposals, using a generative AI model to review each analysis data and propose ways to improve the relevant areas.

[1358] Input: Analysis results from generative AI model

[1359] Output: Specific renovation proposal

[1360] Step 6:

[1361] Virtual renewal website generation

[1362] Based on the proposed modifications obtained in the previous step, the server creates a virtual renewal website that allows users to preview how the site will look with the proposed modifications.

[1363] Input: Specific renovation plan

[1364] Output: Virtual renewal website image

[1365] Step 7:

[1366] User preview and feedback gathering

[1367] The user terminal displays the virtual renewal website image, allowing the user to check its contents and provide feedback.

[1368] Input: Virtual renewal website image

[1369] Output: User feedback

[1370] Step 8:

[1371] Generate the final report

[1372] After collecting user feedback, the server uses this information to generate a final report, which includes proposed improvements, virtual redesigned website images, and user feedback.

[1373] Input: User feedback

[1374] Output: Final report

[1375] Through these steps, the online shopping site renovation process will be made more efficient and the user experience will be improved.

[1376] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1377] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine.

[1378] 1. Information gathering stage

[1379] 1. User requirements:

[1380] The user enters the URL of the website they want to analyze into the device.

[1381] 2. Get data from the server:

[1382] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website.

[1383] The server saves the retrieved HTML content in the database.

[1384] 2. Content analysis stage

[1385] 1. Load the generative AI model:

[1386] The server loads the generative AI model used for analysis.

[1387] 2. Content Analysis:

[1388] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[1389] The server scores the quality of the website based on the analysis results.

[1390] 3. Identifying points to be improved

[1391] 1. Obtaining analysis results:

[1392] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[1393] 2. Generate renovation proposals:

[1394] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[1395] 4. Generation of virtual renewal proposals

[1396] 1. Create a virtual site based on the proposed renovation:

[1397] The server creates a virtual renewal website image with the proposed modifications applied.

[1398] The server prepares data for providing a virtual renewal website image to the user.

[1399] 5. User Acknowledgment and Feedback

[1400] 1. Confirmation of virtual renewal proposal:

[1401] The user checks the provided virtual renewal website image.

[1402] At this time, the server uses an emotion engine to analyze the user's facial expressions and tone of voice, and recognize the user's emotions.

[1403] 2. Providing Feedback:

[1404] Users provide feedback on the virtual renewal proposal.

[1405] The server also takes into consideration the emotional data collected using an emotion engine and reflects it in the feedback content.

[1406] 6. Generate the final report

[1407] 1. Incorporating feedback:

[1408] The server receives user feedback and adjusts the final revision proposal based on the feedback.

[1409] At this stage, emotional data is analyzed by the emotion engine to improve the quality of feedback.

[1410] 2. Generate and provide reports:

[1411] The server generates a final report containing the final redesign proposal, virtual redesigned website images, and user feedback and sentiment data.

[1412] The server provides the final report to the user.

[1413] Specific examples

[1414] Example 1: Information gathering and analysis

[1415] 1. User Action:

[1416] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1417] 2. Server operation:

[1418] The server retrieves the HTML content from the specified URL and stores it in the database.

[1419] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[1420] The server performs scoring based on the analysis results and lists points that need to be improved.

[1421] Example 2: Generation of renovation proposals and virtual renovation

[1422] 1. Server operation:

[1423] The server generates specific repair plans based on the analysis results.

[1424] The server creates a virtual renewal website image and presents it to the user.

[1425] When a user views the virtual renewal website image, the emotion engine recognizes the user's emotion.

[1426] 2. User Action:

[1427] The user checks the virtual renewal website image and provides feedback as needed.

[1428] Example 3: Generating a Final Report

[1429] 1. Server operation:

[1430] The server receives user feedback and emotional data and adjusts the final revision proposal.

[1431] The server generates the final report and provides it to the user.

[1432] By combining it with an emotion engine that recognizes user emotions, website operators can obtain specific data to improve user satisfaction and efficiently achieve optimization compatible with generative AI.

[1433] The processing flow will be explained below.

[1434] Step 1:

[1435] The user enters the URL of the website to be analyzed into the terminal.

[1436] Step 2:

[1437] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[1438] Step 3:

[1439] The server saves the retrieved HTML content in the database.

[1440] Step 4:

[1441] The server loads the generative AI model.

[1442] Step 5:

[1443] The server retrieves the collected HTML content from the database and prepares it for analysis.

[1444] Step 6:

[1445] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[1446] Step 7:

[1447] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[1448] Step 8:

[1449] Specific improvement proposals are listed based on the analysis results generated by the server.

[1450] Step 9:

[1451] The server creates a virtual renewal website image based on the proposed modifications.

[1452] Step 10:

[1453] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[1454] Step 11:

[1455] When the user checks the virtual renewal website image, the server uses an emotion engine to recognize the user's emotion.

[1456] Step 12:

[1457] The user provides feedback on the virtual renewal proposal from the terminal.

[1458] Step 13:

[1459] The server receives user feedback and emotional data and adjusts the final revision proposal.

[1460] Step 14:

[1461] The server generates the final report and provides it to the user.

[1462] Example 2

[1463] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1464] Conventional website analysis systems focused on evaluating content quality and generating improvement proposals, but did not adequately address the collection of feedback and the creation of final reports that took user emotions into account. This made it difficult to obtain specific insights for improving user experience and satisfaction. Furthermore, when creating and evaluating virtual renewal images of proposed improvements, there was a lack of a way to reflect user emotions in real time.

[1465] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1466] In this invention, the server includes means for analyzing the content of the website using a generation AI and identifying areas that need modification, means for generating a modification plan based on the analysis results by the generation AI, means for creating a virtual renewed website image based on the modification plan, means for analyzing user emotions using an emotion engine, means for improving feedback based on user emotion data, and means for generating a final report, thereby enabling website optimization that takes user emotions into consideration in real time.

[1467] "Generative AI" is an algorithm that uses artificial intelligence technology to generate new information and patterns from data.

[1468] A "website" is a collection of pages that provide information or content on the Internet.

[1469] An "emotion engine" is a technology that analyzes user emotions and collects and utilizes that data.

[1470] "Analysis" is the process of breaking down data or information into smaller pieces to understand its structure and content.

[1471] "Proposal for Improvement" means a proposed plan or method for improving an existing system or structure.

[1472] A "virtual renewal website image" is a visual model of a virtual website created based on the proposed renovation plan.

[1473] "Feedback" refers to opinions and evaluations from users regarding proposed improvements.

[1474] The "Final Report" is a report summarizing the results, recommendations, and feedback of the renovation process.

[1475] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[1476] "Scoring" is the process of assigning a score to evaluate the quality and performance of an object based on the analysis results.

[1477] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine. It mainly involves servers, terminals, and users.

[1478] First, the user inputs the URL of the website they want to analyze into their device. Next, the server sends an HTTP request to the specified URL and retrieves the website's HTML content. The server uses the Python requests library to do this. The retrieved HTML content is then stored in a database such as MySQL or MongoDB.

[1479] Next, the server loads the generative AI model to be used for analysis. For generative AI models, advanced natural language processing models such as GPT-3 and BERT are used. The weight and configuration files for the model are loaded, and the server is ready for analysis.

[1480] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc. Natural language processing technology is used for text analysis, and deep learning models are used for image analysis. Based on the analysis results, the quality of the website is scored. Evaluation criteria include page loading speed, content relevance, and user experience.

[1481] Next, the server uses the results of the AI's analysis to create a list of areas of the website that need improvement. This list includes specific points of concern and suggestions for improvement. Suggested improvements include, for example, optimizing image size and revising content.

[1482] The server creates an image of a virtual redesigned website with the proposed modifications applied. It uses HTML, CSS, JavaScript, etc. to build the virtual website and prepares the data to be presented to the user. The user can then view this image of the virtual redesigned website through their browser.

[1483] The server's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. The system uses facial and voice recognition technology to capture the user's emotions. The user provides feedback on the virtual renewal proposal.

[1484] After the user provides their feedback, the server adjusts the final revision proposal based on the feedback. At this stage, the emotion engine analyzes the emotion data to improve the accuracy of the feedback. A final report is generated containing the final revision proposal, an image of the virtual redesigned website, the feedback, and the emotion data, and is sent to the user via email.

[1485] Specific examples

[1486] Example 1: Data acquisition and analysis

[1487] User Action:

[1488] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1489] Server behavior:

[1490] The server uses Python's requests library to retrieve HTML content from the specified URL and saves it in a MySQL database. It then uses a generative AI model (e.g., GPT-3) to analyze the text, images, and structure of the retrieved content. It then scores the content based on the analysis results and lists points to improve.

[1491] Example 2: Renovation proposal generation and virtual renovation

[1492] Server behavior:

[1493] The server generates specific renovation proposals based on the analysis results, creates an image of a virtual renewal website using HTML and CSS, and presents it to the user.

[1494] User Action:

[1495] When a user browses the virtual renewal website and provides feedback, the emotion engine recognizes the user's facial expressions and collects emotional data.

[1496] Example 3: Final report generation

[1497] Server behavior:

[1498] The server receives user feedback and sentiment data, adjusts the final revision proposal, and generates a final report to provide to the user.

[1499] Prompt Sentence Examples

[1500] "Analyze the website at the following URL and generate improvement recommendations: https: / / example.com"

[1501] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1502] Program processing flow

[1503] Step 1:

[1504] User requirements

[1505] The user inputs the URL of the website they want to analyze into the device, which then sends this URL data to the server.

[1506] Enter: Website URL

[1507] Output: Sends URL data to the server

[1508] Step 2:

[1509] Data Acquisition

[1510] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website. The server uses the Python requests library and saves the retrieved HTML content in a database (e.g., MySQL, MongoDB).

[1511] Input: URL data

[1512] Output: HTML content, saved to database

[1513] Specific behavior:

[1514] The server retrieves the HTML using requests.get(URL) and saves it in the database.

[1515] Step 3:

[1516] Loading a Model

[1517] The server loads the generative AI model to be used for analysis. We use natural language processing models such as GPT-3 and BERT as generative AI models. We also load the model weight and configuration files.

[1518] Input: None (preparatory operation in previous stage)

[1519] Output: Model instantiation

[1520] Specific behavior:

[1521] The server loads the model using a library such as from transformers import GPT3.

[1522] Step 4:

[1523] Content Analysis

[1524] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[1525] Input: HTML content (retrieved from database)

[1526] Output: Text, image and structure analysis data

[1527] Specific behavior:

[1528] The server inputs HTML data into the model and performs text analysis (natural language processing) and image analysis (deep learning model).

[1529] Step 5:

[1530] Scoring

[1531] The server then scores the website's quality based on the analysis, including criteria such as page load speed, content relevance, and user experience.

[1532] Input: Analysis data

[1533] Output: Scoring results

[1534] Specific behavior:

[1535] Points are assigned according to the evaluation criteria and an overall score is calculated.

[1536] Step 6:

[1537] Identifying points to be repaired

[1538] The server generates a list of areas of the website that need improvement based on the results of the AI ​​analysis, and outputs specific points of emphasis and suggestions for improvement.

[1539] Input: Scoring results, analysis data

[1540] Output: List of modification points

[1541] Specific behavior:

[1542] We will make a list of areas that need improvement and propose specific improvement plans.

[1543] Step 7:

[1544] Generate renovation proposals

[1545] The server generates specific improvement proposals for the listed improvement points, such as "optimizing image size" and "reviewing content."

[1546] Input: List of renovation points

[1547] Output: Revision proposal

[1548] Specific behavior:

[1549] Generate and list specific improvement methods.

[1550] Step 8:

[1551] Generate a virtual renewal site

[1552] The server creates an image of a virtual redesigned website with the proposed modifications applied. The virtual website is built using HTML, CSS, JavaScript, etc.

[1553] Input: Renovation proposal

[1554] Output: Image of the virtual renewal site

[1555] Specific behavior:

[1556] Build the website's HTML and styles based on the proposed changes.

[1557] Step 9:

[1558] User Verification

[1559] The user checks the image of the virtual renewal website provided through a browser.

[1560] Input: Image of the virtual renewal site

[1561] Output: User feedback

[1562] Specific behavior:

[1563] A user reviews a website in a browser and provides feedback.

[1564] Step 10:

[1565] Emotion analysis

[1566] The server's emotion engine analyzes the user's facial expressions and tone of voice, using facial and voice recognition technology.

[1567] Input: User feedback, real-time video / audio data

[1568] Output: Emotion data

[1569] Specific behavior:

[1570] It analyzes the user's facial expressions and tone of voice in real time to collect emotional data.

[1571] Step 11:

[1572] Feedback collection

[1573] Users provide feedback on virtual renewal proposals. By taking emotion data into account, more accurate feedback can be obtained.

[1574] Input: User feedback, emotion data

[1575] Output: Improved feedback

[1576] Specific behavior:

[1577] Emotional data is reflected in the feedback to improve accuracy.

[1578] Step 12:

[1579] Final revision proposal and report generation

[1580] The server receives the feedback and emotion data from the users, adjusts the final renovation proposal, and generates a final report including the final renovation proposal, an image of the virtual renewal website, the feedback, and the emotion data, and provides it to the user.

[1581] Input: Improved feedback, emotional data

[1582] Output: Final report

[1583] Specific behavior:

[1584] A final list of renovation proposals will be compiled and a final report will be generated in PDF format, including the virtual renewal site and feedback.

[1585] (Application example 2)

[1586] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1587] In modern content delivery services, personalized recommendations that take into account not only the content viewed but also the user's real-time emotional state are required to improve the user experience. However, conventional systems have difficulty accurately grasping the user's emotions and suggesting optimal content. Furthermore, in the process of analyzing websites and proposing improvements, it is difficult to collect accurate feedback, which can result in a decrease in user satisfaction.

[1588] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the content of a website using a generation AI and identifying areas requiring modification, means for generating a modification proposal based on the analysis results by the generation AI, means for creating a virtual renewal website image based on the modification proposal, means for presenting the virtual renewal website image to a user and collecting feedback, means for generating a final report based on the feedback, means for analyzing the user's emotional state using an emotion engine when collecting feedback, and means for making personalized recommendations based on the emotional state. This enables personalized content recommendations that take into account the user's real-time emotional state and highly accurate feedback collection in the website analysis and modification process.

[1589] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze content such as text and images.

[1590] An "emotion engine" is software that analyzes a user's facial expressions, voice, etc., and recognizes and evaluates their emotional state.

[1591] "Website content" refers to the digital information contained on a web page, such as text, images, video, and link structure.

[1592] "Improvement Proposal" means a proposal that identifies areas of the Website or Content that need improvement and presents how to correct or improve them.

[1593] "Virtual Renewal Website Image" means an image or prototype of an improved website that is virtually created based on the proposed renovation.

[1594] "Feedback" refers to the evaluation or opinion provided by the user after checking the virtual renewal website image.

[1595] "Final Report" is a document detailing website or content optimization recommendations that take into account user feedback and emotional state.

[1596] "Personalized recommendations" are the act of suggesting appropriate content based on the attributes, behavioral history, and emotional state of individual users.

[1597] This invention is a system that utilizes generative AI and an emotion engine to improve the user experience in content distribution services. A specific implementation method of this system is described below.

[1598] First, when a user views content, the server retrieves the URL associated with the content and sends an HTTP request to retrieve the HTML content. In this process, the hardware used is the server, and the software required is a library to process the HTTP request. The retrieved HTML content is then stored in a database.

[1599] Next, the server loads a generative AI model and analyzes the content. For example, the "transformers" library is used as the generative AI model. At this stage, the server analyzes the acquired text, images, structural information, etc., and performs a quality score on the content. The analysis results are stored in a database and are used in a later step to generate improvement proposals.

[1600] After the analysis, the server executes a procedure to generate a modification plan based on the analysis results of the generative AI. The generated modification plan is visualized as a virtual renewal website image. The virtual renewal website image is presented to the user, who then confirms it. The software used here is an image processing library, and the user interface is a web browser.

[1601] When a user views the virtual renewal website image, the server uses an emotion engine to analyze the user's emotional state in real time. The emotion engine uses the "DeepFace" library to capture and analyze the user's facial expressions and voice. Personalized content recommendations are made based on the user's emotional state.

[1602] Finally, the server generates a final report that takes into account user feedback and sentiment data, including a virtual website redesign image, proposed improvements, and user feedback, leading to efficient website and content optimization and improved user satisfaction.

[1603] For example, if the emotion engine determines that the user is feeling stressed, a prompt can be used to recommend relaxing music or videos. For example, the prompt could be, "Please analyze the main topics and emotions of this web page" or "Please recommend content that will help the user relax."

[1604] As described above, the system of the present invention integrates generative AI and an emotion engine to provide personalized recommendations based on the user's emotional state, thereby significantly improving the user experience in content distribution services.

[1605] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1606] Step 1:

[1607] The user enters the URL of the website they wish to view on their device. The device then sends this URL to the server. The server receives the URL and sends an HTTP request to retrieve the HTML content of the website. The input data is the URL entered by the user, and the output data is the retrieved HTML content. This process uses the HTTP request library to download the website content.

[1608] Step 2:

[1609] The server saves the acquired HTML content in a database. The input data is the acquired HTML content, and the output data is the content saved in the database. The saving process is performed using a database operation library.

[1610] Step 3:

[1611] The server loads the generative AI model and retrieves HTML content from the database. The input data is the HTML content stored in the database, and the output data is the analysis results. The generative AI model uses the "transformers" library to analyze the retrieved text, images, and structural information. Specific operations include text tokenization and structural analysis.

[1612] Step 4:

[1613] The server scores the quality of the website based on the analysis results. The input data is the analysis results of the generative AI model, and the output data is a quality score. Scoring includes multiple indicators such as text readability and image optimization.

[1614] Step 5:

[1615] The server generates a repair plan based on the scoring results. The input data is the quality score, and the output data is the repair plan. Using a generative AI model, it identifies areas that need repair and uses prompts to suggest how to improve them.

[1616] Step 6:

[1617] The server creates a virtual renewal website image based on the proposed modifications. The input data is the modification proposal, and the output data is the virtual renewal website image. Here, an image processing library is used to visually represent the proposed modifications.

[1618] Step 7:

[1619] The server presents the virtual renewal website image to the user, and the user checks the virtual renewal website image and provides feedback, where the input data is the virtual renewal website image and the output data is the user's feedback.

[1620] Step 8:

[1621] When collecting feedback, the server uses an emotion engine to analyze the user's emotional state. The input data is the user's facial expressions and voice, and the output data is emotion data. Specifically, the server uses the "DeepFace" library to perform facial and voice analysis.

[1622] Step 9:

[1623] The server makes personalized content recommendations based on emotional data. The input data is emotional data, and the output data is recommended content. Using a generative AI model, it suggests songs and videos that correspond to the user's emotional state.

[1624] Step 10:

[1625] The server generates a final report by taking into account the user's feedback and emotion data. The input data is the user's feedback and emotion data, and the output data is the final report. The final report includes a virtual renewal website image, a modification proposal, and the user's feedback.

[1626] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1627] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1628] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1629] [Fourth embodiment]

[1630] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1631] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1632] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1634] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1636] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1637] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1638] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1639] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1640] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1641] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1642] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1643] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. The main functions and examples are described below.

[1644] 1. Information gathering stage

[1645] 1. User requirements:

[1646] The user enters the URL of the website they want to analyze.

[1647] 2. Get data from the server:

[1648] The server sends an HTTP request based on the URL provided by the user to retrieve the HTML content of the web page.

[1649] The server saves the retrieved HTML content in the database.

[1650] 2. Content analysis stage

[1651] 1. Load the generative AI model:

[1652] The server loads the generative AI model used for analysis.

[1653] 2. Content Analysis:

[1654] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[1655] Based on the analysis results, the quality of the website is scored.

[1656] 3. Identifying points to be improved

[1657] 1. Obtaining analysis results:

[1658] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[1659] 2. Generate renovation proposals:

[1660] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[1661] 4. Generation of virtual renewal proposals

[1662] 1. Create a virtual site based on the proposed renovation:

[1663] The server creates a virtual renewal website image with the proposed modifications applied.

[1664] The server prepares data for providing a virtual renewal website image to the user.

[1665] 5. User Acknowledgment and Feedback

[1666] 1. Confirmation of virtual renewal proposal:

[1667] The user checks the provided virtual renewal website image.

[1668] 2. Providing Feedback:

[1669] Users provide feedback on the virtual renewal proposal.

[1670] 6. Generate the final report

[1671] 1. Incorporating feedback:

[1672] The server will incorporate user feedback and adjust the final revision proposal.

[1673] 2. Generate and provide reports:

[1674] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[1675] The server provides the final report to the user.

[1676] Specific examples

[1677] Example 1: Information gathering and analysis

[1678] 1. User Action:

[1679] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1680] 2. Server operation:

[1681] The server retrieves the HTML content from the specified URL and stores it in the database.

[1682] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[1683] The server performs scoring based on the analysis results and lists points that need to be improved.

[1684] Example 2: Generation of renovation proposals and virtual renovation

[1685] 1. Server operation:

[1686] The server generates specific repair plans based on the analysis results.

[1687] The server creates a virtual renewal website image and presents it to the user.

[1688] 2. User Action:

[1689] The user checks the virtual renewal website image and provides feedback as needed.

[1690] Example 3: Generating a Final Report

[1691] 1. Server operation:

[1692] The server will incorporate user feedback and adjust the final revision proposal.

[1693] The server generates the final report and provides it to the user.

[1694] This allows website operators to efficiently optimize their websites to accommodate generative AI.

[1695] The processing flow will be explained below.

[1696] Step 1:

[1697] The user enters the URL of the website to be analyzed into the terminal.

[1698] Step 2:

[1699] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[1700] Step 3:

[1701] The server saves the retrieved HTML content in the database.

[1702] Step 4:

[1703] The server loads the generative AI model.

[1704] Step 5:

[1705] The server retrieves the collected HTML content from the database and prepares it for analysis.

[1706] Step 6:

[1707] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[1708] Step 7:

[1709] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[1710] Step 8:

[1711] Specific improvement proposals are listed based on the analysis results generated by the server.

[1712] Step 9:

[1713] The server creates a virtual renewal website image based on the proposed modifications.

[1714] Step 10:

[1715] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[1716] Step 11:

[1717] The user checks the virtual renewal website image and provides feedback from the terminal as needed.

[1718] Step 12:

[1719] The server receives user feedback and adjusts the final revision proposal to reflect the feedback.

[1720] Step 13:

[1721] The server generates the final report and provides it to the user.

[1722] Example 1

[1723] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1724] The traditional website optimization process was time-consuming and costly, requiring a lot of manual work. Furthermore, identifying areas for improvement and proposing specific proposals required a high level of specialized knowledge. This made it difficult for small and medium-sized businesses and individuals to efficiently improve their websites.

[1725] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1726] In this invention, the server includes means for inputting a website URL provided by a user, means for acquiring HTML content from the URL and saving it in a database, means for loading a generative AI model, means for analyzing the HTML content using the generative AI model, means for calculating a website quality score based on the analysis results and listing areas requiring improvement, means for generating an improvement plan based on the analysis results, means for creating a virtual renewed website image based on the improvement plan, means for presenting the virtual renewed website image to a user and collecting feedback, and means for generating a final report based on the feedback. This significantly reduces time and cost, and enables even users without specialized knowledge to efficiently improve their websites.

[1727] The "means for inputting the URL of the website provided by the user" is a method by which the user inputs the URL of the website to be analyzed into the interface.

[1728] "Means for obtaining HTML content from the URL and storing it in a database" refers to a method for obtaining HTML content from an input URL via an HTTP request and storing the data in a database.

[1729] A "means for loading a generative AI model" is a method for loading a specified generative AI model (e.g., GPT-3, BERT, etc.) into memory.

[1730] The "means for analyzing HTML content using the generative AI model" is a method for analyzing text, images, and structure within the retrieved HTML content using the loaded generative AI model.

[1731] "Means for calculating a quality score for a website based on the analysis results and listing areas that require improvement" refers to a method of calculating a score for each element of a website based on the analysis results provided by a generative AI model and listing specific areas that require improvement.

[1732] The "means for generating a modification plan based on the analysis results" is a method for generating a specific improvement plan based on the analysis results.

[1733] The "means for creating a virtual renewal website image based on the proposed modification" is a method for creating a virtual website that reflects the created modification plan.

[1734] The "means for presenting the virtual renewal website image to users and collecting feedback" refers to a method for providing users with a preview of the virtual renewal website and collecting their opinions and improvements as feedback.

[1735] The "means for generating a final report based on the feedback" refers to a method for generating a report that reflects feedback from the user and summarizes the final modification plan and its results.

[1736] The system of this invention utilizes generative AI to automatically analyze, evaluate, and optimize website content. Specifically, the system involves a server-based process of processing various data, presenting modification proposals to users, and creating a virtual renewal website. A detailed explanation is provided below.

[1737] Hardware and software used

[1738] Hardware

[1739] Server: A server with high-performance computing resources is required, with enough processing power to load the generative AI model and perform the analytical processing.

[1740] software

[1741] Generative AI model: The AI ​​model used for analysis, such as GPT-3 or BERT.

[1742] Database: A database for storing HTML content and analysis results. Typically, an SQL database is used.

[1743] HTTP request library: A library used to retrieve HTML content from a website, for example, the Python Requests library.

[1744] Specific explanation of program processing

[1745] 1. User requirements

[1746] The user enters the URL of the website they want to analyze into a dedicated web interface and sends it to the server.

[1747] 2. Obtaining data from the server

[1748] The server sends an HTTP GET request to the entered URL to retrieve the HTML content.

[1749] The acquired HTML content is stored in the server's database.

[1750] 3. Loading the generative AI model

[1751] The server reads the name of the generative AI model to use from the configuration file and loads it. For example, if you want to use the GPT-3 model, you load the model using the API key.

[1752] 4. Content Analysis

[1753] The server retrieves the collected HTML content from the database.

[1754] The server feeds the HTML data into a generative AI model, which analyzes the text, images, and structure.

[1755] 5. Calculating quality scores and identifying areas for improvement

[1756] Based on the analysis results of the generative AI model, a quality score is calculated for each element of the website.

[1757] List areas where the server needs repair.

[1758] 6. Generation of renovation proposals

[1759] The server generates specific repair plans based on the analysis results.

[1760] To present the proposed modifications to the user, they are compiled in a list format.

[1761] 7. Generation of Virtual Renewal Plans

[1762] The server creates a virtual renewal website image to which the generated modification plan has been applied.

[1763] A preview link of the virtual renewal website is generated and provided to the user.

[1764] 8. User Acknowledgment and Feedback

[1765] The user reviews the provided virtual relaunch website image and provides feedback.

[1766] The user fills in the feedback form with any necessary improvements or comments and submits it.

[1767] 9. Generate the final report

[1768] The server will incorporate user feedback and adjust the final revision proposal.

[1769] The server generates a final report including the final redesign proposal, virtual redesigned website images, and user feedback.

[1770] Generate the final report in PDF or HTML format and provide it to the user via email or download link.

[1771] Specific examples of behavior and prompts for the generative AI model

[1772] Example 1: Information gathering and analysis

[1773] User action: The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1774] Server operation: The server retrieves HTML content from the specified URL and stores it in a database. The server uses a generative AI model to analyze the text, images, and structure of the retrieved content. The server scores the content based on the analysis results and lists points to be improved.

[1775] Prompt Sentence Examples

[1776] "Get the HTML content of the specified website https: / / example.com"

[1777] "Analyze the retrieved content and evaluate the quality of the website."

[1778] "Generate renovation proposals and create virtual renovation sites."

[1779] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1780] Step 1:

[1781] User requirements

[1782] Input: The user enters the URL of the website they want to analyze into a dedicated web interface and submits it.

[1783] Specific behavior: A user enters a URL (e.g., https: / / example.com) into an input form on a web browser and clicks the submit button.

[1784] Output: The entered URL is sent to the server.

[1785] Step 2:

[1786] Server Data Acquisition

[1787] Input: A URL provided by the user.

[1788] Specific operation: The server sends an HTTP GET request to the entered URL and retrieves the HTML content.

[1789] Output: The retrieved HTML content is saved in the server database.

[1790] Step 3:

[1791] Loading a generative AI model

[1792] Input: The name of the generative AI model to use from the server's config file.

[1793] Specific operation: The server reads the configuration file and loads the specified generative AI model (e.g., GPT-3).

[1794] Output: The generative AI model is loaded into memory and ready for analysis.

[1795] Step 4:

[1796] Content Analysis

[1797] Input: HTML content stored in the server's database.

[1798] What it does: The server retrieves HTML content from the database and feeds it into the generative AI model for analysis.

[1799] Output: The analytical results obtained from the generative AI model are obtained.

[1800] Step 5:

[1801] Calculating quality scores and identifying areas to improve

[1802] Input: Analysis results obtained from a generative AI model.

[1803] What it does: Based on the analysis results, the server calculates a quality score for each element of the website and lists areas that need improvement.

[1804] Output: Quality score and list of areas that need improvement.

[1805] Step 6:

[1806] Generate renovation proposals

[1807] Input: A list of areas that need renovation.

[1808] Specific operation: The server uses the generative AI model again based on the analysis results to generate specific repair proposals.

[1809] Output: Get a list of proposed modifications.

[1810] Step 7:

[1811] Generation of virtual renewal proposals

[1812] Input: Generated renovation proposal.

[1813] Specific operation: The server applies the proposed modifications and creates a virtual redesigned website image.

[1814] Output: Preview link of the virtual renewal website.

[1815] Step 8:

[1816] User Acknowledgment and Feedback

[1817] Input: Preview link for your virtual relaunch website.

[1818] What happens: The user clicks on the provided preview link to see the virtual renewal site.

[1819] Output: User feedback.

[1820] Step 9:

[1821] Generate the final report

[1822] Input: User feedback.

[1823] What happens: The server incorporates the feedback, adjusts the final revision proposal, and generates the final report.

[1824] Output: The final report is generated in PDF and HTML format and provided to the user.

[1825] (Application example 1)

[1826] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1827] Improving user experience and conversion rates are key challenges for modern online shopping websites. However, for many online shopping websites, regularly reviewing and revising the entire site is time-consuming and inefficient. It is also difficult to effectively utilize user feedback to optimize the site. For these reasons, there is a need for a more efficient and automated way to optimize websites and improve user experience.

[1828] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1829] In this invention, the server includes: means for analyzing website content using a generation AI and identifying areas requiring improvement; means for generating an improvement plan based on the analysis results by the generation AI; means for creating a virtual renewal website image based on the improvement plan; means for presenting the virtual renewal website image to users and collecting feedback; means for generating a final report based on the feedback; means for collecting website content and saving it in a database; means for analyzing text, structure, and images using the generation AI and performing scoring; means for creating an improvement plan for the online shopping website based on the reviews and feedback analyzed using the generation AI; means for presenting the improvement plan to users and providing a virtual renewal site where the improvement content can be previewed; and means for generating a final improvement report based on user feedback on the virtual renewal site. This makes the online shopping website improvement process more efficient and improves the user experience.

[1830] "Generative AI" is a technology that uses artificial intelligence to generate data and automatically perform tasks such as analysis and evaluation.

[1831] A "website" is a collection of information published on the Internet and written in a markup language such as HTML.

[1832] "Content analysis" is the process of analyzing and evaluating the information within a website, including text, images, structure, etc.

[1833] "Areas in need of improvement" refers to parts of the website that require improvement.

[1834] A "renovation proposal" is a plan that proposes specific corrections or changes to the identified areas for improvement.

[1835] "Virtual renewal website" refers to a virtual web page to which the proposed modifications have been applied.

[1836] "Feedback" refers to opinions and evaluations provided by users, and is information that can be used to improve the system.

[1837] "Final report" refers to the final report that incorporates the feedback.

[1838] "Data collection" refers to the acquisition and storage of website content on a server.

[1839] A "database" is a system for systematically storing and managing collected data.

[1840] "Scoring" is the process of quantifying and evaluating a website's quality and areas for improvement based on the analysis results.

[1841] "Review" refers to comments and ratings that record users' experiences and opinions.

[1842] An "online shopping site" is a website that sells products and services over the Internet.

[1843] "Preview" is a feature that allows users to virtually check improvement proposals before they are actually implemented.

[1844] "Improvement Report" refers to the detailed analysis report that is finally generated based on improvement suggestions and feedback.

[1845] The system for implementing the present invention includes a server, a user terminal, and a generative AI model. The specific operation of this system is described below.

[1846] System Overview

[1847] 1. Get data from the server:

[1848] The user enters the URL of the shopping site they want to analyze. The server sends an HTTP request, retrieves the HTML content from the specified URL, and stores it in a database. For example, if a user enters the URL "https: / / example-shop.com," the server will collect the HTML content of that website.

[1849] 2. Load the generative AI model:

[1850] The server loads and uses a generative AI model (e.g., GPT-3.5-turbo) for analysis, which uses advanced natural language processing to provide a detailed analysis of the website content.

[1851] 3. Content Analysis:

[1852] The server passes the HTML content retrieved from the database to the generative AI model for analysis. The analysis is performed on each element, such as text, images, and structure, to identify its quality and areas for improvement. The analysis results are then scored to quantify the evaluation.

[1853] 4. Review and Feedback Analysis:

[1854] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, which identifies specific areas for improvement based on user experience.

[1855] 5. Generation of renovation proposals and presentation of virtual renewal proposals:

[1856] Based on the analysis results of the generative AI model, the server generates a proposed redesign. Based on this proposed redesign, a virtual redesigned website image is created and presented to the user. At this stage, the user can confirm the proposed redesign and preview the virtual redesigned website.

[1857] 6. Collect user feedback and generate final report:

[1858] The server receives feedback from users about the virtual renewal proposal. The server reflects this feedback and generates a final improvement report. The final report includes the revision proposal, a virtual renewal website image, and user feedback.

[1859] Hardware and software used

[1860] 1. Hardware:

[1861] Server: Collects, analyzes, and manages databases of HTML content.

[1862] User device (smartphone): Enter the URL, provide feedback, and preview the virtual renewal proposal.

[1863] 2. Software:

[1864] requests: A Python library for retrieving HTML content from websites.

[1865] BeautifulSoup: A Python library for parsing HTML content.

[1866] transformers: Libraries for content analysis using generative AI models (e.g., GPT-3.5-turbo).

[1867] Specific examples

[1868] If a user types "https: / / example-shop.com", the server collects the HTML content from this URL and stores it in a database. It then uses a generative AI model to analyze the website's text, images, and structure. It then inputs the following prompt to the generative AI model:

[1869] This is the HTML content from https: / / example-shop.com. Please analyze its text, images, and structure to find areas for improvement and suggest potential enhancements.

[1870] Based on the analysis results, the generative AI model will suggest improvements such as, "The product descriptions lack detailed information. Adding more information about each product will help attract customers' interest. Consider using high-quality images in the product gallery." This will streamline the work of improving online shopping sites and improve the user experience.

[1871] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1872] Step 1:

[1873] Entering URLs and collecting data

[1874] The user enters the URL of their shopping site. The server sends an HTTP request to the entered URL and retrieves the website's HTML content. Specifically, it uses Python's requests library to retrieve HTML data from the specified URL and saves this data in a database.

[1875] Input: The URL entered by the user

[1876] Output: Retrieved HTML content (stored in database)

[1877] Step 2:

[1878] Loading a generative AI model

[1879] The server loads the generative AI model (e.g., GPT-3.5-turbo) and prepares it for analysis. The server loads the model using the transformers library.

[1880] Input: File path of the generated AI model

[1881] Output: The loaded generative AI model

[1882] Step 3:

[1883] Parsing HTML content

[1884] The server retrieves HTML content from the database and passes it to the generative AI model for analysis. BeautifulSoup is used to parse the HTML content and extract the text, images, and structure contained within it. This data is then input into the generative AI model to obtain the analysis results.

[1885] Input: HTML content stored in the database

[1886] Output: Analysis results from the generative AI model

[1887] Step 4:

[1888] Review and feedback analysis

[1889] The server also collects reviews and user feedback from online shopping sites and analyzes them with a generative AI model, thereby extracting specific points for improvement based on the user experience.

[1890] Input: User reviews and feedback

[1891] Output: Analysis results and points for improvement by the generative AI model

[1892] Step 5:

[1893] Generate renovation proposals

[1894] Based on the analysis results, the server generates specific improvement proposals, using a generative AI model to review each analysis data and propose ways to improve the relevant areas.

[1895] Input: Analysis results from generative AI model

[1896] Output: Specific renovation proposal

[1897] Step 6:

[1898] Virtual renewal website generation

[1899] Based on the proposed modifications obtained in the previous step, the server creates a virtual renewal website that allows users to preview how the site will look with the proposed modifications.

[1900] Input: Specific renovation plan

[1901] Output: Virtual renewal website image

[1902] Step 7:

[1903] User preview and feedback gathering

[1904] The user terminal displays the virtual renewal website image, allowing the user to check its contents and provide feedback.

[1905] Input: Virtual renewal website image

[1906] Output: User feedback

[1907] Step 8:

[1908] Generate the final report

[1909] After collecting user feedback, the server uses this information to generate a final report, which includes proposed improvements, virtual redesigned website images, and user feedback.

[1910] Input: User feedback

[1911] Output: Final report

[1912] Through these steps, the online shopping site renovation process will be made more efficient and the user experience will be improved.

[1913] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1914] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine.

[1915] 1. Information gathering stage

[1916] 1. User requirements:

[1917] The user enters the URL of the website they want to analyze into the device.

[1918] 2. Get data from the server:

[1919] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website.

[1920] The server saves the retrieved HTML content in the database.

[1921] 2. Content analysis stage

[1922] 1. Load the generative AI model:

[1923] The server loads the generative AI model used for analysis.

[1924] 2. Content Analysis:

[1925] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[1926] The server scores the quality of the website based on the analysis results.

[1927] 3. Identifying points to be improved

[1928] 1. Obtaining analysis results:

[1929] Based on the results of the server-generated AI analysis, the server creates a list of areas of the website that need improvement.

[1930] 2. Generate renovation proposals:

[1931] The server generates specific improvement proposals and lists them in a format that can be presented to the user.

[1932] 4. Generation of virtual renewal proposals

[1933] 1. Create a virtual site based on the proposed renovation:

[1934] The server creates a virtual renewal website image with the proposed modifications applied.

[1935] The server prepares data for providing a virtual renewal website image to the user.

[1936] 5. User Acknowledgment and Feedback

[1937] 1. Confirmation of virtual renewal proposal:

[1938] The user checks the provided virtual renewal website image.

[1939] At this time, the server uses an emotion engine to analyze the user's facial expressions and tone of voice, and recognize the user's emotions.

[1940] 2. Providing Feedback:

[1941] Users provide feedback on the virtual renewal proposal.

[1942] The server also takes into consideration the emotional data collected using an emotion engine and reflects it in the feedback content.

[1943] 6. Generate the final report

[1944] 1. Incorporating feedback:

[1945] The server receives user feedback and adjusts the final revision proposal based on the feedback.

[1946] At this stage, emotional data is analyzed by the emotion engine to improve the quality of feedback.

[1947] 2. Generate and provide reports:

[1948] The server generates a final report containing the final redesign proposal, virtual redesigned website images, and user feedback and sentiment data.

[1949] The server provides the final report to the user.

[1950] Specific examples

[1951] Example 1: Information gathering and analysis

[1952] 1. User Action:

[1953] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[1954] 2. Server operation:

[1955] The server retrieves the HTML content from the specified URL and stores it in the database.

[1956] The server uses generative AI models to analyze the text, images, and structure of the retrieved content.

[1957] The server performs scoring based on the analysis results and lists points that need to be improved.

[1958] Example 2: Generation of renovation proposals and virtual renovation

[1959] 1. Server operation:

[1960] The server generates specific repair plans based on the analysis results.

[1961] The server creates a virtual renewal website image and presents it to the user.

[1962] When a user views the virtual renewal website image, the emotion engine recognizes the user's emotion.

[1963] 2. User Action:

[1964] The user checks the virtual renewal website image and provides feedback as needed.

[1965] Example 3: Generating a Final Report

[1966] 1. Server operation:

[1967] The server receives user feedback and emotional data and adjusts the final revision proposal.

[1968] The server generates the final report and provides it to the user.

[1969] By combining it with an emotion engine that recognizes user emotions, website operators can obtain specific data to improve user satisfaction and efficiently achieve optimization compatible with generative AI.

[1970] The processing flow will be explained below.

[1971] Step 1:

[1972] The user enters the URL of the website to be analyzed into the terminal.

[1973] Step 2:

[1974] The server sends an HTTP request to the URL it received and retrieves the HTML content of the website.

[1975] Step 3:

[1976] The server saves the retrieved HTML content in the database.

[1977] Step 4:

[1978] The server loads the generative AI model.

[1979] Step 5:

[1980] The server retrieves the collected HTML content from the database and prepares it for analysis.

[1981] Step 6:

[1982] The server uses generative AI models to analyze the text, images, and structure of the HTML content.

[1983] Step 7:

[1984] Based on the analysis results, the server scores the quality of the website and identifies areas for improvement.

[1985] Step 8:

[1986] Specific improvement proposals are listed based on the analysis results generated by the server.

[1987] Step 9:

[1988] The server creates a virtual renewal website image based on the proposed modifications.

[1989] Step 10:

[1990] The server prepares the data in an appropriate format to provide the virtual renewal website image to the user.

[1991] Step 11:

[1992] When the user checks the virtual renewal website image, the server uses an emotion engine to recognize the user's emotion.

[1993] Step 12:

[1994] The user provides feedback on the virtual renewal proposal from the terminal.

[1995] Step 13:

[1996] The server receives user feedback and emotional data and adjusts the final revision proposal.

[1997] Step 14:

[1998] The server generates the final report and provides it to the user.

[1999] Example 2

[2000] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2001] Conventional website analysis systems focused on evaluating content quality and generating improvement proposals, but did not adequately address the collection of feedback and the creation of final reports that took user emotions into account. This made it difficult to obtain specific insights for improving user experience and satisfaction. Furthermore, when creating and evaluating virtual renewal images of proposed improvements, there was a lack of a way to reflect user emotions in real time.

[2002] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2003] In this invention, the server includes means for analyzing the content of the website using a generation AI and identifying areas that need modification, means for generating a modification plan based on the analysis results by the generation AI, means for creating a virtual renewed website image based on the modification plan, means for analyzing user emotions using an emotion engine, means for improving feedback based on user emotion data, and means for generating a final report, thereby enabling website optimization that takes user emotions into consideration in real time.

[2004] "Generative AI" is an algorithm that uses artificial intelligence technology to generate new information and patterns from data.

[2005] A "website" is a collection of pages that provide information or content on the Internet.

[2006] An "emotion engine" is a technology that analyzes user emotions and collects and utilizes that data.

[2007] "Analysis" is the process of breaking down data or information into smaller pieces to understand its structure and content.

[2008] "Proposal for Improvement" means a proposed plan or method for improving an existing system or structure.

[2009] A "virtual renewal website image" is a visual model of a virtual website created based on the proposed renovation plan.

[2010] "Feedback" refers to opinions and evaluations from users regarding proposed improvements.

[2011] The "Final Report" is a report summarizing the results, recommendations, and feedback of the renovation process.

[2012] A "database" is a system for efficiently storing, managing, and searching large amounts of data.

[2013] "Scoring" is the process of assigning a score to evaluate the quality and performance of an object based on the analysis results.

[2014] This invention is a system that automatically analyzes, evaluates, and optimizes website content using generative AI and an emotion engine. It mainly involves servers, terminals, and users.

[2015] First, the user inputs the URL of the website they want to analyze into their device. Next, the server sends an HTTP request to the specified URL and retrieves the website's HTML content. The server uses the Python requests library to do this. The retrieved HTML content is then stored in a database such as MySQL or MongoDB.

[2016] Next, the server loads the generative AI model to be used for analysis. For generative AI models, advanced natural language processing models such as GPT-3 and BERT are used. The weight and configuration files for the model are loaded, and the server is ready for analysis.

[2017] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc. Natural language processing technology is used for text analysis, and deep learning models are used for image analysis. Based on the analysis results, the quality of the website is scored. Evaluation criteria include page loading speed, content relevance, and user experience.

[2018] Next, the server uses the results of the AI's analysis to create a list of areas of the website that need improvement. This list includes specific points of concern and suggestions for improvement. Suggested improvements include, for example, optimizing image size and revising content.

[2019] The server creates an image of a virtual redesigned website with the proposed modifications applied. It uses HTML, CSS, JavaScript, etc. to build the virtual website and prepares the data to be presented to the user. The user can then view this image of the virtual redesigned website through their browser.

[2020] The server's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. The system uses facial and voice recognition technology to capture the user's emotions. The user provides feedback on the virtual renewal proposal.

[2021] After the user provides their feedback, the server adjusts the final revision proposal based on the feedback. At this stage, the emotion engine analyzes the emotion data to improve the accuracy of the feedback. A final report is generated containing the final revision proposal, an image of the virtual redesigned website, the feedback, and the emotion data, and is sent to the user via email.

[2022] Specific examples

[2023] Example 1: Data acquisition and analysis

[2024] User Action:

[2025] The user enters the website URL to be analyzed (e.g., https: / / example.com) into the system.

[2026] Server behavior:

[2027] The server uses Python's requests library to retrieve HTML content from the specified URL and saves it in a MySQL database. It then uses a generative AI model (e.g., GPT-3) to analyze the text, images, and structure of the retrieved content. It then scores the content based on the analysis results and lists points to improve.

[2028] Example 2: Renovation proposal generation and virtual renovation

[2029] Server behavior:

[2030] The server generates specific renovation proposals based on the analysis results, creates an image of a virtual renewal website using HTML and CSS, and presents it to the user.

[2031] User Action:

[2032] When a user browses the virtual renewal website and provides feedback, the emotion engine recognizes the user's facial expressions and collects emotional data.

[2033] Example 3: Final report generation

[2034] Server behavior:

[2035] The server receives user feedback and sentiment data, adjusts the final revision proposal, and generates a final report to provide to the user.

[2036] Prompt Sentence Examples

[2037] "Analyze the website at the following URL and generate improvement recommendations: https: / / example.com"

[2038] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2039] Program processing flow

[2040] Step 1:

[2041] User requirements

[2042] The user inputs the URL of the website they want to analyze into the device, which then sends this URL data to the server.

[2043] Enter: Website URL

[2044] Output: Sends URL data to the server

[2045] Step 2:

[2046] Data Acquisition

[2047] The server sends an HTTP request to the specified URL to retrieve the HTML content of the website. The server uses the Python requests library and saves the retrieved HTML content in a database (e.g., MySQL, MongoDB).

[2048] Input: URL data

[2049] Output: HTML content, saved to database

[2050] Specific behavior:

[2051] The server retrieves the HTML using requests.get(URL) and saves it in the database.

[2052] Step 3:

[2053] Loading a Model

[2054] The server loads the generative AI model to be used for analysis. We use natural language processing models such as GPT-3 and BERT as generative AI models. We also load the model weight and configuration files.

[2055] Input: None (preparatory operation in previous stage)

[2056] Output: Model instantiation

[2057] Specific behavior:

[2058] The server loads the model using a library such as from transformers import GPT3.

[2059] Step 4:

[2060] Content Analysis

[2061] The server retrieves the collected HTML content from the database and uses a generative AI model to analyze the text, images, structure, etc.

[2062] Input: HTML content (retrieved from database)

[2063] Output: Text, image and structure analysis data

[2064] Specific behavior:

[2065] The server inputs HTML data into the model and performs text analysis (natural language processing) and image analysis (deep learning model).

[2066] Step 5:

[2067] Scoring

[2068] The server then scores the website's quality based on the analysis, including criteria such as page load speed, content relevance, and user experience.

[2069] Input: Analysis data

[2070] Output: Scoring results

[2071] Specific behavior:

[2072] Points are assigned according to the evaluation criteria and an overall score is calculated.

[2073] Step 6:

[2074] Identifying points to be repaired

[2075] The server generates a list of areas of the website that need improvement based on the results of the AI ​​analysis, and outputs specific points of emphasis and suggestions for improvement.

[2076] Input: Scoring results, analysis data

[2077] Output: List of modification points

[2078] Specific behavior:

[2079] We will make a list of areas that need improvement and propose specific improvement plans.

[2080] Step 7:

[2081] Generate renovation proposals

[2082] The server generates specific improvement proposals for the listed improvement points, such as "optimizing image size" and "reviewing content."

[2083] Input: List of renovation points

[2084] Output: Revision proposal

[2085] Specific behavior:

[2086] Generate and list specific improvement methods.

[2087] Step 8:

[2088] Generate a virtual renewal site

[2089] The server creates an image of a virtual redesigned website with the proposed modifications applied. The virtual website is built using HTML, CSS, JavaScript, etc.

[2090] Input: Renovation proposal

[2091] Output: Image of the virtual renewal site

[2092] Specific behavior:

[2093] Build the website's HTML and styles based on the proposed changes.

[2094] Step 9:

[2095] User Verification

[2096] The user checks the image of the virtual renewal website provided through a browser.

[2097] Input: Image of the virtual renewal site

[2098] Output: User feedback

[2099] Specific behavior:

[2100] A user reviews a website in a browser and provides feedback.

[2101] Step 10:

[2102] Emotion analysis

[2103] The server's emotion engine analyzes the user's facial expressions and tone of voice, using facial and voice recognition technology.

[2104] Input: User feedback, real-time video / audio data

[2105] Output: Emotion data

[2106] Specific behavior:

[2107] It analyzes the user's facial expressions and tone of voice in real time to collect emotional data.

[2108] Step 11:

[2109] Feedback collection

[2110] Users provide feedback on virtual renewal proposals. By taking emotion data into account, more accurate feedback can be obtained.

[2111] Input: User feedback, emotion data

[2112] Output: Improved feedback

[2113] Specific behavior:

[2114] Emotional data is reflected in the feedback to improve accuracy.

[2115] Step 12:

[2116] Final revision proposal and report generation

[2117] The server receives the feedback and emotion data from the users, adjusts the final renovation proposal, and generates a final report including the final renovation proposal, an image of the virtual renewal website, the feedback, and the emotion data, and provides it to the user.

[2118] Input: Improved feedback, emotional data

[2119] Output: Final report

[2120] Specific behavior:

[2121] A final list of renovation proposals will be compiled and a final report will be generated in PDF format, including the virtual renewal site and feedback.

[2122] (Application example 2)

[2123] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2124] In modern content delivery services, personalized recommendations that take into account not only the content viewed but also the user's real-time emotional state are required to improve the user experience. However, conventional systems have difficulty accurately grasping the user's emotions and suggesting optimal content. Furthermore, in the process of analyzing websites and proposing improvements, it is difficult to collect accurate feedback, which can result in a decrease in user satisfaction.

[2125] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the content of a website using a generation AI and identifying areas requiring modification, means for generating a modification proposal based on the analysis results by the generation AI, means for creating a virtual renewal website image based on the modification proposal, means for presenting the virtual renewal website image to a user and collecting feedback, means for generating a final report based on the feedback, means for analyzing the user's emotional state using an emotion engine when collecting feedback, and means for making personalized recommendations based on the emotional state. This enables personalized content recommendations that take into account the user's real-time emotional state and highly accurate feedback collection in the website analysis and modification process.

[2126] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze content such as text and images.

[2127] An "emotion engine" is software that analyzes a user's facial expressions, voice, etc., and recognizes and evaluates their emotional state.

[2128] "Website content" refers to the digital information contained on a web page, such as text, images, video, and link structure.

[2129] "Improvement Proposal" means a proposal that identifies areas of the Website or Content that need improvement and presents how to correct or improve them.

[2130] "Virtual Renewal Website Image" means an image or prototype of an improved website that is virtually created based on the proposed renovation.

[2131] "Feedback" refers to the evaluation or opinion provided by the user after checking the virtual renewal website image.

[2132] "Final Report" is a document detailing website or content optimization recommendations that take into account user feedback and emotional state.

[2133] "Personalized recommendations" are the act of suggesting appropriate content based on the attributes, behavioral history, and emotional state of individual users.

[2134] This invention is a system that utilizes generative AI and an emotion engine to improve the user experience in content distribution services. A specific implementation method of this system is described below.

[2135] First, when a user views content, the server retrieves the URL associated with the content and sends an HTTP request to retrieve the HTML content. In this process, the hardware used is the server, and the software required is a library to process the HTTP request. The retrieved HTML content is then stored in a database.

[2136] Next, the server loads a generative AI model and analyzes the content. For example, the "transformers" library is used as the generative AI model. At this stage, the server analyzes the acquired text, images, structural information, etc., and performs a quality score on the content. The analysis results are stored in a database and are used in a later step to generate improvement proposals.

[2137] After the analysis, the server executes a procedure to generate a modification plan based on the analysis results of the generative AI. The generated modification plan is visualized as a virtual renewal website image. The virtual renewal website image is presented to the user, who then confirms it. The software used here is an image processing library, and the user interface is a web browser.

[2138] When a user views the virtual renewal website image, the server uses an emotion engine to analyze the user's emotional state in real time. The emotion engine uses the "DeepFace" library to capture and analyze the user's facial expressions and voice. Personalized content recommendations are made based on the user's emotional state.

[2139] Finally, the server generates a final report that takes into account user feedback and sentiment data, including a virtual website redesign image, proposed improvements, and user feedback, leading to efficient website and content optimization and improved user satisfaction.

[2140] For example, if the emotion engine determines that the user is feeling stressed, a prompt can be used to recommend relaxing music or videos. For example, the prompt could be, "Please analyze the main topics and emotions of this web page" or "Please recommend content that will help the user relax."

[2141] As described above, the system of the present invention integrates generative AI and an emotion engine to provide personalized recommendations based on the user's emotional state, thereby significantly improving the user experience in content distribution services.

[2142] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2143] Step 1:

[2144] The user enters the URL of the website they wish to view on their device. The device then sends this URL to the server. The server receives the URL and sends an HTTP request to retrieve the HTML content of the website. The input data is the URL entered by the user, and the output data is the retrieved HTML content. This process uses the HTTP request library to download the website content.

[2145] Step 2:

[2146] The server saves the acquired HTML content in a database. The input data is the acquired HTML content, and the output data is the content saved in the database. The saving process is performed using a database operation library.

[2147] Step 3:

[2148] The server loads the generative AI model and retrieves HTML content from the database. The input data is the HTML content stored in the database, and the output data is the analysis results. The generative AI model uses the "transformers" library to analyze the retrieved text, images, and structural information. Specific operations include text tokenization and structural analysis.

[2149] Step 4:

[2150] The server scores the quality of the website based on the analysis results. The input data is the analysis results of the generative AI model, and the output data is a quality score. Scoring includes multiple indicators such as text readability and image optimization.

[2151] Step 5:

[2152] The server generates a repair plan based on the scoring results. The input data is the quality score, and the output data is the repair plan. Using a generative AI model, it identifies areas that need repair and uses prompts to suggest how to improve them.

[2153] Step 6:

[2154] The server creates a virtual renewal website image based on the proposed modifications. The input data is the modification proposal, and the output data is the virtual renewal website image. Here, an image processing library is used to visually represent the proposed modifications.

[2155] Step 7:

[2156] The server presents the virtual renewal website image to the user, and the user checks the virtual renewal website image and provides feedback, where the input data is the virtual renewal website image and the output data is the user's feedback.

[2157] Step 8:

[2158] When collecting feedback, the server uses an emotion engine to analyze the user's emotional state. The input data is the user's facial expressions and voice, and the output data is emotion data. Specifically, the server uses the "DeepFace" library to perform facial and voice analysis.

[2159] Step 9:

[2160] The server makes personalized content recommendations based on emotional data. The input data is emotional data, and the output data is recommended content. Using a generative AI model, it suggests songs and videos that correspond to the user's emotional state.

[2161] Step 10:

[2162] The server generates a final report by taking into account the user's feedback and emotion data. The input data is the user's feedback and emotion data, and the output data is the final report. The final report includes a virtual renewal website image, a modification proposal, and the user's feedback.

[2163] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2164] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2165] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2166] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2167] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2168] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2169] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2171] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2173] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2174] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2175] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2176] 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.

[2177] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2178] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2179] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2180] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2181] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2182] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2183] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2184] The following is further disclosed regarding the above embodiment.

[2185] (Claim 1)

[2186] Using generative AI to analyze website content and identify areas that need improvement,

[2187] A means for generating a modification plan based on the analysis results by the generation AI;

[2188] A means for creating a virtual renewal website image based on the proposed renovation;

[2189] means for presenting the virtual renewal website image to users and collecting feedback;

[2190] means for generating a final report based on said feedback;

[2191] A system including:

[2192] (Claim 2)

[2193] 10. The system of claim 1, further comprising means for collecting and storing the content of the website in a database.

[2194] (Claim 3)

[2195] The system of claim 1, further comprising means for using the generative AI to perform text, structure, and image analysis and scoring.

[2196] "Example 1"

[2197] (Claim 1)

[2198] a means for inputting a website URL provided by the user;

[2199] means for retrieving HTML content from the URL and storing it in a database;

[2200] a means for loading the generative AI model;

[2201] means for analyzing HTML content using the generative AI model;

[2202] A means for calculating a quality score of the website based on the analysis results and listing areas that need improvement;

[2203] means for generating a modification plan based on the analysis results;

[2204] A means for creating a virtual renewal website image based on the proposed renovation;

[2205] means for presenting the virtual renewal website image to users and collecting feedback;

[2206] means for generating a final report based on said feedback;

[2207] A system including:

[2208] (Claim 2)

[2209] 10. The system of claim 1, further comprising means for collecting and storing the content of the website in a database.

[2210] (Claim 3)

[2211] 10. The system of claim 1, further comprising means for performing text, structure, and image analysis and scoring using the generative AI model.

[2212] "Application Example 1"

[2213] (Claim 1)

[2214] Using generative AI to analyze website content and identify areas that need improvement,

[2215] A means for generating a modification plan based on the analysis results by the generation AI;

[2216] A means for creating a virtual renewal website image based on the proposed renovation;

[2217] means for presenting the virtual renewal website image to users and collecting feedback;

[2218] means for generating a final report based on said feedback;

[2219] means for collecting and storing the content of said website in a database;

[2220] A means for analyzing text, structure, and images using the generating AI and performing scoring;

[2221] A means for creating improvement proposals for the online shopping site based on the reviews and feedback analyzed using the generating AI;

[2222] means for presenting the improvement plan to a user and providing a virtual renewal site where the improvement plan can be previewed;

[2223] a means for generating a final improvement report based on user feedback on the virtual renewal site;

[2224] A system including:

[2225] (Claim 2)

[2226] The system of claim 1 , further comprising means for prioritizing modifications and scoring proposed modifications based on the analysis results.

[2227] (Claim 3)

[2228] The system of claim 1, further comprising means for performing detailed generative AI analysis based on the prompt sentence generated by the generative AI model and proposing specific points for improvement.

[2229] "Example 2: Combining Emotion Engines"

[2230] (Claim 1)

[2231] Using generative AI to analyze website content and identify areas that need improvement,

[2232] A means for generating a modification plan based on the analysis results by the generation AI;

[2233] A means for creating a virtual renewal website image based on the proposed renovation;

[2234] means for presenting the virtual renewal website image to users and collecting feedback;

[2235] means for generating a final report based on said feedback;

[2236] means for analyzing a user's emotions using an emotion engine;

[2237] means for improving the feedback based on the user's emotional data;

[2238] A system including:

[2239] (Claim 2)

[2240] 10. The system of claim 1, further comprising means for collecting and storing website content in a database.

[2241] (Claim 3)

[2242] 10. The system of claim 1, further comprising means for performing text, structure, and image analysis and scoring using generative AI.

[2243] "Application example 2 when combining emotion engines"

[2244] (Claim 1)

[2245] Using generative AI to analyze website content and identify areas that need improvement,

[2246] A means for generating a modification plan based on the analysis results by the generation AI;

[2247] A means for creating a virtual renewal website image based on the proposed renovation;

[2248] means for presenting the virtual renewal website image to users and collecting feedback;

[2249] means for generating a final report based on said feedback;

[2250] means for analyzing the user's emotional state using an emotion engine during the feedback collection;

[2251] means for making personalized recommendations based on said emotional state;

[2252] A system including:

[2253] (Claim 2)

[2254] 10. The system of claim 1, further comprising means for collecting and storing the content of the website in a database.

[2255] (Claim 3)

[2256] The system of claim 1, further comprising means for using the generative AI to perform text, structure, and image analysis and scoring. [Explanation of symbols]

[2257] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. Using generative AI to analyze website content and identify areas that need improvement, A means for generating a modification plan based on the analysis results by the generation AI; A means for creating a virtual renewal website image based on the proposed renovation; means for presenting the virtual renewal website image to users and collecting feedback; means for generating a final report based on said feedback; A system including:

2. 10. The system of claim 1, further comprising means for collecting and storing the content of said website in a database.

3. The system of claim 1 , further comprising means for using the generative AI to perform text, structure, and image analysis and scoring.

Images