System

Abstract

A system is provided.SOLUTION: Means for receiving a search keyword input by a user, means for searching a product database for the search keyword and calculating the number of hits, means for storing the search keyword and a search result thereof in the database, and means for analyzing history data of the stored search keyword, A system, comprising: means for extracting features of a good sought by a user; means for generating a pseudo-good based on the extracted features using a generative AI model; means for generating a good page based on detailed information of the generated pseudo-good; means for presenting the pseudo-good page to the user and collecting feedback; means for generating a customized product based on the feedback from the user; and means for presenting the generated customized product page to the user.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] When shopping online, users may not always be able to find the products they desire, even when they enter search keywords. If such disappointing experiences accumulate, users tend to stop using that shopping site. This puts the e-commerce site at risk of losing sales opportunities. The purpose of this invention is to reduce such disappointing user experiences and provide users with the products they want quickly and efficiently. [Means for solving the problem]

[0005] The present invention provides a system including: means for receiving search keywords entered by a user; means for searching a product database for the search keywords and calculating the number of hits; means for saving the search keywords and their search results in a database; means for analyzing historical data of the saved search keywords and extracting features of the product desired by the user; means for generating a pseudo-product using a generative AI model based on the extracted features; means for generating a product page based on detailed information of the generated pseudo-product; means for presenting the pseudo-product page to the user and collecting feedback; means for generating a custom-made product based on user feedback; and means for presenting the generated custom-made product page to the user. This system makes it possible to meet user needs and prevent disappointment by providing custom-made products based on the keywords searched by the user.

[0006] A "user" is a person who uses an e-commerce site to enter search keywords and search for products.

[0007] A "search keyword" is a word or phrase that a user types into a search box on an e-commerce site.

[0008] A "product database" is a digital database that stores information about products owned by an e-commerce site.

[0009] "Hits" refers to the number of times matching products are found in the product database based on the search keywords.

[0010] A "database" is a digital data structure for recording and storing search keywords and their results.

[0011] "History data" refers to information about search keywords entered by the user in the past and the search results thereof.

[0012] A "generative AI model" is an artificial intelligence technology that generates pseudo-products based on extracted features.

[0013] A "pseudo-product" is a product that is virtually generated using a generative AI model and does not actually exist.

[0014] A "product page" is a web page that displays detailed information about a pseudo-product to the user.

[0015] "Feedback" refers to opinions and requests provided by users when they check the pseudo-product page.

[0016] "Custom products" are items that are specially created based on user feedback. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] MODE FOR CARRYING OUT THE INVENTION

[0039] The system for implementing this invention receives search keywords entered by a user, and generates and provides a custom-made product that meets the user's needs based on the keywords.

[0040] Program processing

[0041] 1. Enter keywords

[0042] User: Visits an e-commerce site and types keywords into the search box.

[0043] Terminal: Sends the entered search keywords to the server.

[0044] 2. Keyword analysis and history saving

[0045] server:

[0046] A search keyword is received and a product database is searched based on the keyword.

[0047] Calculate the number of hits and analyze the results. If there are zero hits or the user does not click, save the keyword and its search results to a database.

[0048] 3. Historical data analysis and pseudo-product generation

[0049] server:

[0050] The system retrieves and analyzes historical search keyword data stored in the database, and extracts the characteristics of the products the user is looking for based on the analysis results.

[0051] The extracted features are then input as prompts into a generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0052] 4. Generate a pseudo-product page

[0053] server:

[0054] Build detailed product pages based on the generated pseudo-products.

[0055] The product page includes the generated product name, description, price, and image.

[0056] 5. Present to users and gather feedback

[0057] server:

[0058] The generated pseudo-product page is displayed on the screen to the user.

[0059] User:

[0060] Review the product page provided and submit feedback, including requests for color, size, additional features, etc.

[0061] 6. Feedback analysis and product generation

[0062] server:

[0063] Receive and analyze user feedback in detail.

[0064] Based on the analysis results, the AI ​​model is used again to generate a custom product, incorporating new product names, descriptions, images, etc.

[0065] 7. Final product proposal and order acceptance

[0066] server:

[0067] The final custom product page is displayed to the user.

[0068] User:

[0069] Check the product page provided and decide to purchase.

[0070] Specific examples

[0071] If a user types in "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses a generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with a description and image.

[0072] The generated product page is presented to the user, who then submits feedback such as "I would like a slightly larger size" or "I wish there was a blue variation." The server analyzes this feedback and again uses the AI ​​model to generate a custom-made product. Ultimately, the user decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[0073] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[0077] Step 2:

[0078] Device: Send the entered search keyword "large-capacity heat-resistant glass teacup" to the server.

[0079] Step 3:

[0080] Server: Receives search keywords. Searches the product database based on the received keywords and calculates the number of related product hits.

[0081] Step 4:

[0082] Server: Check that there are no hits. Or, if the user does not click on the product, save the search keywords and search results to the database. The search results are also saved along with the timestamp and user ID.

[0083] Step 5:

[0084] Server: Analyzes the search keywords and search result history data stored in the database. As a result of the analysis, the characteristics of the product the user is looking for are extracted. For example, characteristics such as "heat-resistant," "glass," "large capacity," and "teacup" are extracted.

[0085] Step 6:

[0086] Server: Inputs the extracted features as prompts into the generative AI model. The generative AI model is used to automatically generate pseudo-products. The generated pseudo-products include product names, descriptions, and images.

[0087] Step 7:

[0088] Server: Generates a product page based on the details of the generated pseudo-product. Specifically, it builds a page that includes the product name, description, price, and image.

[0089] Step 8:

[0090] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[0091] Step 9:

[0092] User: Review the provided mock product page and enter feedback about the product, including requests for color, size, and additional features.

[0093] Step 10:

[0094] Terminal: Sends the feedback entered by the user to the server.

[0095] Step 11:

[0096] Server: Receives feedback from users, analyzes the feedback, and uses the AI ​​model to generate a custom-made product based on the analysis results.

[0097] Step 12:

[0098] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0099] Step 13:

[0100] User: Review the final product page presented to them and ensure all requirements are met.

[0101] Step 14:

[0102] User: Makes a purchase decision on the final product page and orders a custom product.

[0103] In this way, the system of the present invention can efficiently and effectively execute a series of processes from when a user inputs search keywords to when they purchase a custom-made product. By performing specific operations at each step, the system reduces user disappointment and provides optimal products.

[0104] Example 1

[0105] 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."

[0106] Traditional e-commerce systems often fail to display satisfactory products for the search keywords entered by users. As a result, users are often unable to find the product they are looking for and are left feeling disappointed. Furthermore, when users have specific requirements, there is a lack of a mechanism to suggest customized products that meet those requirements. This leads to a poor customer experience and missed sales opportunities.

[0107] 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.

[0108] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a data store, means for analyzing history data of the saved search keywords and extracting features desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a detailed information page based on detailed information about the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, and means for presenting the generated custom-made product page to the user. This enables product suggestions that accurately reflect the user's search intent, improving the user experience and increasing sales opportunities.

[0109] A "user" is a user who accesses the system and inputs search keywords.

[0110] A "search keyword" is a string of characters that a user enters into a search box and is used to search for products.

[0111] A "database" is a data structure or system that stores product information corresponding to search keywords.

[0112] The "number of hits" refers to the number of related products retrieved from the database based on the search keyword.

[0113] A "data store" is a storage device or system for storing search keywords and their search results.

[0114] "History data" refers to data on search keywords and search results that have been saved in the past.

[0115] "Features" are a collection of product characteristics and elements that a user desires, extracted by analyzing historical data.

[0116] A "generative AI model" is an algorithm or technology that uses artificial intelligence to generate pseudo-products based on user requests.

[0117] "Pseudo-products" are product information virtually created using generative AI models, which may not actually exist.

[0118] A "details page" is a web page that contains product details such as the name, description, price, and images of the pseudo-product.

[0119] "Feedback" refers to opinions and requests that users provide regarding the content of a pseudo-product page after checking it.

[0120] "Custom-made products" are items specially created using generative AI models based on user feedback.

[0121] "Means of generating" refers to the technical methods or processes by which a program or system performs a specific function.

[0122] This invention is a system that generates and provides custom-made products that meet the user's needs based on search keywords entered by the user. By entering specific keywords, the system automatically suggests products that best suit the user's needs and provides further customized custom-made products.

[0123] Hardware and software configuration

[0124] This system mainly uses the following hardware and software:

[0125] Server: A server with a powerful processor and large memory performs search keyword analysis, database lookup, runs the generative AI model, and analyzes feedback. This server can be, for example, an Apache web server or an Nginx web server.

[0126] Database: A relational database management system (RDBMS) is used to store product information and search history data. Specifically, MySQL or PostgreSQL is preferred.

[0127] Generative AI model: To generate pseudo-products based on user requests, we use a generative AI model (e.g., OpenAI's GPT-3). This model takes appropriate prompts as input and generates text and images.

[0128] Terminal: The devices that users use to access the site include various devices such as PCs, tablets, smartphones, etc. These terminals connect to the server via a web browser.

[0129] Specific methods for data processing and calculation

[0130] This system receives search keywords entered by the user and performs the following processing based on those keywords.

[0131] 1. Keyword analysis: The server receives the keywords entered by the user and searches the database for related product information, using SQL queries to quickly retrieve data.

[0132] 2. Historical Data Storage: If the user does not click or if there are zero hits, the search keywords and their search results are stored in the database. This is usually done using an INSERT or UPDATE query.

[0133] 3. Feature extraction: The server analyzes the saved search history data and extracts the features of the product the user is looking for (e.g., "heat-resistant glass," "large capacity," "teacup," etc.). This analysis may use natural language processing (NLP) technology.

[0134] 4. Generate pseudo-products: Generate pseudo-products by inputting the extracted features into a generative AI model as prompts. For example, the following prompts can be used:

[0135] Prompt: "Create a product with heat-resistant glass, large capacity, and the characteristics of a teacup."

[0136] 5. Product page generation: A detailed information page is constructed based on the generated pseudo-product, using an HTML template to embed the necessary information such as product name, description, price, and images.

[0137] 6. Feedback collection and analysis: The user reviews the product page and provides feedback, including specific requests for color, size, additional features, etc. The server analyzes this feedback and generates an improved, custom-made product, again using the generative AI model.

[0138] Specific example explanation

[0139] Let's take the example of a user entering the search keyword "large-capacity heat-resistant glass teacup." In this case, the server first receives this keyword and searches the product database. If no related products are found, the server saves this keyword in the database and records it as historical data. The server then analyzes the historical data and extracts key features. These features are input into the generative AI model as prompt sentences to generate pseudo-products.

[0140] The generated pseudo-product includes the product name "Large Capacity Heat-Resistant Glass Teacup," along with its description and image. This product page is presented to the user, who provides feedback such as "I wish it was a little larger" and "I wish it came in blue." The server analyzes this feedback and again uses the AI ​​model to generate a custom product. Finally, the new product page is displayed to the user, who decides to purchase the "Large Capacity Custom Heat-Resistant Glass Teacup."

[0141] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] User: Visits an e-commerce site and types a search term like "large capacity heat-resistant glass teacup" into the search box.

[0145] Specific actions: A user opens a web browser, enters a URL, accesses a site, enters a desired keyword in the search box, and presses the search button.

[0146] Input: Search keyword

[0147] Output: A search request is sent to the server

[0148] Step 2:

[0149] Terminal: Sends the entered search keywords to the server.

[0150] Specific operation: The data from the search form is sent to the server as an HTTP request.

[0151] Input: The search term entered by the user

[0152] Output: HTTP request sent to server

[0153] Step 3:

[0154] Server: Receives search keywords and searches the database for related products.

[0155] Specific operation: The server extracts the search keywords from the HTTP request and executes an SQL query against the database.

[0156] Input: Search keyword

[0157] Output: A list of related products retrieved from the database

[0158] Step 4:

[0159] Server: Calculate the number of hits and analyze the results. If there are zero hits or the user does not click on a related product, save the search keywords and their search results to the data store.

[0160] What it does: Analyzes the query results and counts the number of hits. If there are zero hits or the user doesn't click on a result, it saves the keywords and results to the data store using an INSERT or UPDATE SQL query.

[0161] Input: Query results from the database

[0162] Output: Search keywords and results stored in the data store

[0163] Step 5:

[0164] Server: Analyzes the history data of saved search keywords and extracts the characteristics of the products the user is looking for.

[0165] Specific operation: Historical data is retrieved by scheduled jobs or triggers, and natural language processing (NLP) techniques are used to extract the features desired by the user.

[0166] Input: Historical data stored in a data store

[0167] Output: A set of extracted features

[0168] Step 6:

[0169] Server: The extracted features are input as prompts into the generative AI model to generate pseudo-products.

[0170] Specific operation: Send a prompt to the API of a generative AI model (e.g., GPT-3) and receive the generated text and images.

[0171] Input: Extracted features

[0172] Output: Generated pseudo-product information (product name, description, image, etc.)

[0173] Step 7:

[0174] Server: Generates a product page based on the details of the generated pseudo-product.

[0175] What it does: Embeds generated product information into an HTML template. Styles and generates the page using the necessary CSS and JavaScript.

[0176] Input: Details of the pseudo-product

[0177] Output: Completed product page HTML

[0178] Step 8:

[0179] Server: Presents the generated pseudo-product page to the user.

[0180] Specific operation: The product page is sent to the user's browser as an HTTP response.

[0181] Input: HTML for product page

[0182] Output: The product page that is displayed in the user's browser

[0183] Step 9:

[0184] User: Review the product page provided and provide feedback.

[0185] Specific actions: Refer to the product page, enter desired color, size, additional features, etc. in the feedback form, and press the submit button.

[0186] Input: Feedback information (new request)

[0187] Output: Feedback is sent to the server

[0188] Step 10:

[0189] Server: Receives and analyzes user feedback in detail.

[0190] Specific operation: Receives feedback data and creates and sends prompts to generate customized products using the generative AI model again.

[0191] Input: User feedback

[0192] Output: Improved custom product information

[0193] Step 11:

[0194] Server: Presents the generated custom product page to the user.

[0195] Specific operation: Reconstruct an HTML page based on the new product information and present it to the user.

[0196] Input: Improved custom product details

[0197] Output: The final product page is displayed in the user's browser

[0198] (Application example 1)

[0199] 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."

[0200] On traditional e-commerce sites, when a user searches for a specific product, if that product does not exist, the user cannot find the product they are looking for, resulting in a decrease in satisfaction. Furthermore, the site does not offer similar products or custom-made options, which means it is unable to meet the diverse needs of users. Furthermore, there is a lack of a mechanism for utilizing feedback to generate products that meet user requests.

[0201] 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.

[0202] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, and means for providing the generated pseudo-product in a format displayable on a specific hardware device, i.e., a smart device. This allows similar products or custom-made products to be presented when a user searches for a specific product even if the product does not exist, thereby improving user satisfaction.

[0203] A "search keyword" is a string of characters that a user enters when searching for a specific product or service.

[0204] A "product database" is a database in which information about each product or service is systematically stored.

[0205] "Hits" is the number of related products found in the database based on a particular search keyword.

[0206] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0207] "History data" refers to data that stores a user's past search keywords and the results thereof.

[0208] "Features" are important attributes or characteristics of a product that users desire.

[0209] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate new products and designs.

[0210] A "pseudo-product" is a virtual product generated based on a user's search intent.

[0211] "Detailed information" is specific information about the product, including the product name, description, price, and image.

[0212] A "product page" is a web page for presenting product information to a user.

[0213] "Feedback" refers to evaluations and opinions provided by users, and is information that serves as a reference for product improvement.

[0214] A "custom product" is a product that is customized based on a user's specific requirements.

[0215] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[0216] The system embodying the present invention generates and provides custom-made products based on user search keywords. The specific configuration and processing steps of this system will now be described.

[0217] First, a user accesses an e-commerce site via a device such as a smartphone and enters keywords into the search box. The device sends the entered search keywords to the server. The server searches a product database based on the received search keywords and calculates the number of hits. If no search results are found, the search keywords and the search results are saved in the database.

[0218] The server then analyzes the saved search keyword history data to extract the features of the product the user is looking for. These extracted features are input as prompts into a generative AI model to generate a pseudo-product. The generated pseudo-product includes detailed information such as the product name, description, and images. The server then generates a product page based on this information and presents it to the user.

[0219] The user reviews the product page presented to them and submits feedback, which may include requests for color, size, additional features, etc. The server receives and analyzes the user's feedback. Based on the analysis results, the generative AI model is used again to generate a custom-made product that reflects the user's feedback. Finally, the generated custom-made product page is presented to the user, and the purchase is confirmed.

[0220] The system configuration includes the following major hardware and software components:

[0221] Smart device: A terminal where users can enter search keywords and view and purchase custom-made products.

[0222] Server: Analyzes search keywords, searches the product database, analyzes feedback, and generates products using a generative AI model.

[0223] Generative AI models: Artificial intelligence techniques for generating pseudo-goods and custom-made products based on user requirements.

[0224] Database Management System (DBMS): Stores and manages search keywords and historical data.

[0225] For example, if a user enters "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses the generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with its description and image.

[0226] Examples of specific prompts to input to a generative AI model:

[0227] Create a product based on these features: {"material": "Heat-resistant glass", "size": "Large capacity", "type": "Teacup"}

[0228] This prompt is then fed into a generative AI model to generate custom product suggestions, which can then be further customized based on collected feedback to provide the perfect product for the user.

[0229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0230] Step 1:

[0231] A user accesses an e-commerce site through a device such as a smartphone and enters keywords into the search box. The device then sends the entered search keywords (input data) to the server (the output data is the search keywords). Specifically, the user enters the keyword "large-capacity heat-resistant glass teacup," which is then transferred to the server.

[0232] Step 2:

[0233] The server searches the product database based on the received search keywords (input data is the search keywords). As a result, it calculates the number of matching products in the product database (output data is the number of hits) and obtains this number of hits. For example, if the number of hits is zero, the result is also saved.

[0234] Step 3:

[0235] If the server does not get any search results, it saves the search keywords and the search results in a database (the input data is the search keywords and the number of hits). The saved data includes the keyword the user searched for, "large-capacity heat-resistant glass teacup," and the results.

[0236] Step 4:

[0237] The server analyzes the history data of saved search keywords (input data are past search keywords saved in the database). Through this analysis, the features of the product the user is looking for are extracted (output data are the extracted features). For example, the extracted features are "heat-resistant glass," "large capacity," and "teacup."

[0238] Step 5:

[0239] The server inputs the extracted features into a generative AI model (the input data is the extracted features). The generative AI model receives these features as prompts and generates a pseudo-product (the output data is the pseudo-product). For example, the generative AI model generates a pseudo-product called a "large-capacity heat-resistant glass teacup."

[0240] Step 6:

[0241] The server generates a product page based on the detailed information of the generated pseudo-product (input data is detailed information of the pseudo-product). The product page includes the product name, product description, price, image, etc. (output data is the product page). For example, a product page for "large-capacity heat-resistant glass teacup" is generated.

[0242] Step 7:

[0243] The server presents the generated product page to the user and collects feedback (the input data is the generated product page). For example, the user sends feedback such as "I want a bigger size" (the output data is the user feedback).

[0244] Step 8:

[0245] The server analyzes the user feedback (input data is the user feedback) and generates a custom-made product using the generative AI model again based on the results (output data is a customized custom-made product). For example, a new "custom heat-resistant glass large-capacity teacup" is generated based on the feedback.

[0246] Step 9:

[0247] The server presents the final custom-made product page to the user (input data is the customized custom-made product). The user reviews this page and decides to purchase (output data is the final custom-made product page). For example, the user reviews the new product page and decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[0248] 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.

[0249] MODE FOR CARRYING OUT THE INVENTION

[0250] The system embodying this invention receives search keywords entered by a user and generates and provides a custom-made product that meets the user's needs based on those keywords. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotions when entering search keywords and collecting feedback, and generating products that reflect those emotions.

[0251] Program processing

[0252] 1. Enter keywords

[0253] User: Visits an e-commerce site and types keywords into the search box.

[0254] Terminal: Sends the entered search keywords to the server.

[0255] Server: Receives search keywords and activates the emotion engine to recognize the user's emotions when entering search keywords.

[0256] 2. Keyword analysis and history saving

[0257] Server: Searches the product database based on the search keywords and calculates the number of related product hits.

[0258] Server: Checks if there are zero hits or if the user does not click on the product. If so, stores the search keywords and search results in a database, along with a timestamp, user ID, and user sentiment data.

[0259] 3. Historical data analysis and pseudo-product generation

[0260] Server: Acquires and analyzes search keywords, search result history data, and sentiment data stored in the database. As a result of the analysis, the characteristics of the products the user is looking for are extracted.

[0261] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0262] 4. Generate a pseudo-product page

[0263] Server: Builds detailed product pages based on the generated pseudo-products. Specifically, it generates pages that reflect the product name, product description, price, images, and user sentiment data.

[0264] 5. Present to users and gather feedback

[0265] Server: The generated pseudo-product page is sent to the user's device and presented to the user. The presented page includes an interface for inputting feedback.

[0266] User: Review the presented product page and enter feedback, including requests for color, size, additional features, and their emotions while entering the feedback.

[0267] Device: Sends user emotion data along with feedback to the server.

[0268] 6. Feedback analysis and product generation

[0269] Server: Receives user feedback and emotion data and analyzes it in detail.

[0270] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[0271] 7. Final product proposal and order acceptance

[0272] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0273] User: Review the final product page presented to them and ensure all their requirements are met. Confirm purchase and order the custom product.

[0274] Specific examples

[0275] If a user types in "large-capacity heat-resistant glass teacup," the server uses this keyword and the emotion engine to recognize that the user is "excited." The server searches the product database based on this keyword and the user's emotion data, and confirms that there are no hits. The search keyword, search results, and emotion data are saved in the database.

[0276] The accumulated keyword history and sentiment data are analyzed to extract the characteristics of "heat-resistant glass," "large capacity," and "teacup," as well as the sentiment of "excited." A generative AI model is then used to generate pseudo-products, such as a product name such as "Large capacity heat-resistant glass teacup," along with a description, image, and sentiment data such as "This teacup is made of heat-resistant glass, has a large capacity, and is particularly suitable for hot drinks."

[0277] The generated product page is presented to the user, who then enters "I'm looking forward to it" along with the feedback that "I want the blue one too." The server then analyzes this feedback and emotion data again to generate a custom-made product. The final "Custom Heat-Resistant Glass Large Capacity Teacup" product page is presented to the user, who then decides to purchase.

[0278] In this way, the system of the present invention provides optimal custom-made products based on the user's search keywords and emotional data, reducing disappointment for the user.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[0282] Step 2:

[0283] Device: Send the keyword "large capacity heat-resistant glass teacup" entered in the search box to the server.

[0284] Step 3:

[0285] Server: Receives search keywords. At the same time, it activates the emotion engine and recognizes the user's emotion when entering the search keywords. For example, it determines that the user is "excited."

[0286] Step 4:

[0287] Server: Query the search keywords against the product database and calculate the number of related product hits.

[0288] Step 5:

[0289] Server: Check that there are zero hits, or if the user does not click on the product, store the user's sentiment data in a database along with the search keywords and search results.

[0290] Step 6:

[0291] Server: Analyzes search keywords and search result history data stored in the database, as well as emotion data. As a result of the analysis, the characteristics of the product the user is looking for (e.g., "heat-resistant," "glass," "large capacity," "teacup") and emotion (e.g., "excited") are extracted.

[0292] Step 7:

[0293] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0294] Step 8:

[0295] Server: Generates a product page based on the generated pseudo-product details. The product page includes the product name, description, price, image, and user sentiment data.

[0296] Step 9:

[0297] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[0298] Step 10:

[0299] User: Review the presented mock product page and enter feedback about the product, including requests for color, size, additional features, and their emotions while entering the feedback.

[0300] Step 11:

[0301] Terminal: Sends user-entered feedback and emotion data to the server.

[0302] Step 12:

[0303] Server: Receives user feedback and emotion data and analyzes them in detail. For example, it analyzes feedback such as "I want blue too" and emotion such as "I'm looking forward to it."

[0304] Step 13:

[0305] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[0306] Step 14:

[0307] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0308] Step 15:

[0309] User: Checks the final custom product page, confirms that all requirements are met, requests revisions as necessary, and finally decides to purchase.

[0310] In this way, the system of the present invention incorporates the emotional information entered by the user along with the search keywords and executes a process to generate optimal custom-made products based on that information, thereby reducing disappointment for users and providing more appropriate products.

[0311] Example 2

[0312] 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."

[0313] In traditional e-commerce systems, if the product searched for by the user is not accurately hit, it is difficult for the user to find a product that meets their needs. Furthermore, because the system does not take into account the user's emotions, the specific product characteristics desired by the user are often not reflected. Furthermore, it is difficult to reflect user feedback in real time and generate a custom-made product. This results in a poor user experience and potentially leads to lost sales opportunities.

[0314] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features and the user's emotions, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on the user's feedback and emotion data, and means for presenting the generated custom-made product page to the user. This makes it possible to provide an optimal custom-made product based on the user's search keywords and emotions, improving the user experience and increasing sales.

[0315] A "user" is an individual or corporation that uses this system and enters search keywords to search for and purchase products.

[0316] A "search keyword" is a word or phrase that a user enters into the system and is information that identifies the product the user is looking for.

[0317] The "product database" is a database containing product information stored within the system, and is used to provide product information corresponding to search keywords.

[0318] The "number of hits" indicates the number of related products found in the product database based on the search keyword.

[0319] An "emotion engine" is a software or hardware function that recognizes and analyzes a user's emotions when they enter search keywords.

[0320] "History data" refers to data that includes keywords that a user has searched for in the past and the results of those searches, emotional data, and other related information.

[0321] A "generative AI model" is an artificial intelligence model that automatically generates text, images, etc. based on input prompts, for example, using machine learning algorithms.

[0322] "Pseudo-products" are virtual products that do not exist in real inventory but are created to meet user requirements.

[0323] A "product page" is a web page that contains product information presented to a user, including the product name, description, price, image, and emotion data.

[0324] "Feedback" refers to the input of opinions, requests, and emotional data from users, including evaluations of the provided products and requests for additional items.

[0325] "Custom-made products" are items that are customized based on user feedback and sentiment data.

[0326] "Emotion data" is data that indicates the emotional state of the user when entering search keywords or feedback.

[0327] MODE FOR CARRYING OUT THE INVENTION

[0328] The system for implementing this invention allows a user to input search keywords, and generates and provides custom-made products that meet the user's needs based on those keywords. This system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotional data and generating products that reflect those emotions.

[0329] Main system components

[0330] The system consists of the following main components:

[0331] 1. Search keyword receiving method

[0332] It starts when a user enters a keyword into the search box on their device. An example of an input would be "large-capacity heat-resistant glass teacup."

[0333] 2. Product database search method

[0334] Based on the search keywords received, the server performs a database search and calculates the number of related product hits, using either an SQL database or a NoSQL database.

[0335] 3. How to save search results

[0336] If there are no hits or the user does not click on the suggested product, the server stores the search keywords and results in a database, including a timestamp, user ID, and sentiment data.

[0337] 4. Historical Data Analysis Methods

[0338] The server analyzes the historical data stored in the database and extracts the characteristics of the products desired by the user. The historical data includes past search keywords, search results, and emotional data.

[0339] 5. Generative AI Models

[0340] The server inputs the analyzed features and the user's emotional data as a prompt into a generative AI model (e.g., GPT-4 or other machine learning model) to generate a pseudo-product. An example of this prompt would be, "The user excitedly searched for 'large-capacity heat-resistant glass teacup.'"

[0341] 6. Product page generation method

[0342] The server builds a detailed product page based on the generated pseudo-product, including the product name, description, price, image, and user sentiment data generated by the generative AI model.

[0343] 7. Feedback Collection Methods

[0344] The server sends the generated product page to the user's device and collects feedback. The user checks the product page and enters their requests for color, size, additional features, and their feelings at the time of input into a feedback form.

[0345] 8. Means of creating custom products

[0346] The server receives and analyzes user feedback and emotion data. Based on the analysis results, the generative AI model is used again to generate a custom-made product. For example, if the user provides feedback such as "I also want blue," the server generates product details that correspond to this.

[0347] 9. Final product page presentation method

[0348] The server sends the final generated custom product page to the user's device, where the user confirms that all of their requests have been fulfilled, including the new product name, description, image, and emotion data.

[0349] Specific examples

[0350] If a user enters "large-capacity heat-resistant glass teacup," the server searches the product database using this keyword and confirms that there are zero hits. It then saves the search keyword, search results, and the user's "excited" emotional data. Based on the analysis, the generative AI model generates a pseudo-product called "large-capacity heat-resistant glass teacup" and builds a product page. If the user provides feedback such as "I also want blue," the server uses this feedback to again use the generative AI model to generate the final custom-made product. In this way, the optimal custom-made product is provided based on the user's search keyword and emotional data.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1:

[0353] A user visits an e-commerce site and enters keywords into the search box.

[0354] Input: The search term entered by the user (e.g., "large-capacity heat-resistant glass teacup").

[0355] What happens: A user uses the keyboard to type characters into the search box and presses the enter key.

[0356] Output: Keyword input data is generated.

[0357] Step 2:

[0358] The terminal transmits the entered search keyword to the server.

[0359] Input: Keyword input data.

[0360] Specific operation: The device's web browser sends the keyword input data to the server as an HTTP POST request.

[0361] Output: The server receives the search keywords.

[0362] Step 3:

[0363] The server receives the search keywords and activates an emotion engine to recognize the user's emotions.

[0364] Input: Search keyword.

[0365] Specific operation: Calls the emotion recognition API implemented in the server and analyzes emotions based on the user's facial expressions, input speed, etc.

[0366] Output: Search keywords and sentiment data.

[0367] Step 4:

[0368] The server searches the product database based on the search keywords and calculates the number of hits for related products.

[0369] Input: Search keyword.

[0370] What it does: Searches a database using an SQL query and retrieves a result set.

[0371] Output: Number of hits and search results.

[0372] Step 5:

[0373] The server checks that there are zero hits or the user does not click on any of the products offered, in which case the search keywords and search results are saved in a database.

[0374] Input: number of hits, search results, sentiment data.

[0375] Specific actions: Builds data for saving and executes an INSERT query against the database.

[0376] Output: Search history stored in a database.

[0377] Step 6:

[0378] The server retrieves and analyzes the historical data stored in the database, and extracts the features of the products desired by the user.

[0379] Input: Search history data, sentiment data.

[0380] Specific operations: Apply data analysis algorithms and machine learning models to extract features.

[0381] Output: Feature data.

[0382] Step 7:

[0383] The server inputs the extracted features and emotion data as prompts into the generative AI model to generate pseudo-products.

[0384] Input: feature data, emotion data.

[0385] Specific operations: Generate a prompt text, send an API request to the generative AI model, and retrieve the generated text and image.

[0386] Output: Pseudo-product data (product name, description, price, image).

[0387] Step 8:

[0388] The server builds a detailed product page based on the generated pseudo-product.

[0389] Input: Pseudo-product data.

[0390] Specific operation: Embed the generated data into a web page template and generate an HTML file.

[0391] Output: HTML data of product page.

[0392] Step 9:

[0393] The server generates a product page, which is then sent to the user's device and presented to them. It includes an interface for inputting feedback.

[0394] Input: HTML data for product page.

[0395] Specific operation: The HTML of the product page is sent to the terminal as an HTTP response.

[0396] Output: The product page is displayed on the user's device.

[0397] Step 10:

[0398] The user reviews the presented product page and enters feedback, including requests for color, size, additional features, and feelings.

[0399] Input: Check the product page and enter your feedback information.

[0400] Specific Action: Enter information into the feedback form and click the submit button.

[0401] Output: Feedback data is generated.

[0402] Step 11:

[0403] The terminal transmits the feedback data to the server.

[0404] Input: Feedback data.

[0405] Specific behavior: Feedback data is sent to the server as an HTTP POST request.

[0406] Output: The server receives the feedback data.

[0407] Step 12:

[0408] A server receives and analyzes the feedback data and emotion data.

[0409] Input: Feedback data, emotion data.

[0410] Specific operation: Analyze the feedback content using a data analysis algorithm.

[0411] Output: Analysis result data.

[0412] Step 13:

[0413] The server then uses the generated AI model based on the analysis results to generate a custom-made product.

[0414] Input: Analysis result data.

[0415] What it does: Generate an updated prompt and feed it into the generative AI model to get new text and images.

[0416] Output: Custom product data (new product name, description, and image).

[0417] Step 14:

[0418] The server transmits the final generated custom-made product page to the user's terminal for presentation.

[0419] Input: Custom-made product data.

[0420] Specific operation: Builds the HTML of the final product page and sends it to the terminal as an HTTP response.

[0421] Output: The final product page is displayed on the user's device.

[0422] Step 15:

[0423] The user reviews the final product page, confirms that all of their requirements are met, and finally makes the purchase decision and orders the custom-made product.

[0424] Enter: Check the final product page.

[0425] Specific Action: Click the purchase button to complete the purchase process.

[0426] Output: A custom-made product order is completed.

[0427] (Application example 2)

[0428] 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."

[0429] Conventional custom-made product provision systems generate products without considering the user's emotions, which results in the problem of not being able to fully meet the user's expectations. Furthermore, if no products related to the keywords entered by the user are found, it is difficult to suggest appropriate alternatives. This can lead to increased user disappointment and reduced customer satisfaction.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0431] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, means for recognizing and analyzing user emotions when entering search keywords and when collecting feedback, and means for inputting prompt sentences to the generative AI model based on the search keywords and emotion data entered by the user to generate a pseudo-product. This enables product generation that takes user emotions into consideration and makes it possible to provide custom-made products that meet user expectations.

[0432] "Search keywords" are words or phrases that users enter when searching for custom products or services.

[0433] A "product database" is a database that contains various product information and is used to search for related products based on search keywords.

[0434] "History data" refers to data that stores search keywords entered by the user in the past and the search results.

[0435] "Features" are specific requirements or attributes of the product or service that a user is looking for.

[0436] A "generative AI model" is a system that uses generative artificial intelligence algorithms to automatically generate new ideas and proposals based on input data.

[0437] "Pseudo-products" are products or services that do not actually exist but are close to what the user wants, generated based on the user's search keywords and emotional data.

[0438] A "product page" is a web page or application screen that displays detailed information (product name, description, price, image, etc.) about a pseudo-product or custom-made product.

[0439] "Feedback" is data that records the user's opinions and requests regarding the presented pseudo-product.

[0440] The "emotion engine" is a system that analyzes the emotions of users when they enter search keywords or feedback.

[0441] A "prompt" is a context or instruction to be input into a generative AI model, and includes the user's search keywords and emotional data.

[0442] A "custom-made product" is a product or service that is individually created to reflect a user's specific requests and feedback.

[0443] The system embodying this invention uses the following procedures and devices to generate and provide custom-made products based on a user's search keywords and emotion data.

[0444] Hardware and Software

[0445] Hardware: Smartphones, servers.

[0446] Software: sentiment_analysis and ai_model modules for natural language processing.

[0447] Overview of data processing and calculation

[0448] Search keyword reception

[0449] A user uses a smartphone to input keywords to search for a product or service they wish to reserve or purchase. The device then sends the search keywords to the server. The server saves the received search keywords and simultaneously activates an emotion engine to analyze the user's emotions.

[0450] Search product database and save results

[0451] The server searches the product database for the searched keyword and evaluates whether there is a matching product or a similar product. If there are no matching products or if the user does not click on the presented product, the server saves the search keyword and the results in the database.

[0452] Historical data analysis and feature extraction

[0453] The server analyzes the stored history data and extracts the characteristics of the product the user is looking for. Specifically, it analyzes search keywords, past search results, and user emotion data to understand the user's needs in detail.

[0454] Generating pseudo-products using generative AI models

[0455] Based on the extracted features and emotion data, a prompt sentence is input into a generative AI model to generate pseudo-products. Based on the input data, this model suggests products that best fit the user's requirements.

[0456] Product page generation and user presentation

[0457] The server generates a product page based on the detailed information of the generated pseudo-product (product name, description, price, image, etc.) and presents this product page to the smartphone user.

[0458] Feedback collection and analysis

[0459] The user checks the product page and inputs feedback, including requests and feelings about the product's color, size, additional features, etc. The server receives this feedback and analyzes it in detail.

[0460] Custom-made product creation and final proposal

[0461] The server then uses the generative AI model again based on the analysis results to generate a custom-made product. The generated product page is then finally presented to the user, who reviews it and decides to purchase.

[0462] Specific examples

[0463] Suppose a user uses a smartphone app to enter the search keywords "fast" and "quiet car." At the same time, the emotion engine analyzes the user's emotion at that time as "I want to relax." Based on this information, the server searches the database for relevant autonomous vehicles. If no matching vehicle is found, the keywords and emotion data are saved for later analysis.

[0464] By analyzing the accumulated historical data, the system can understand the user's requirements in detail and generate a simulated vehicle by inputting the following prompt sentences into the generative AI model:

[0465] Example prompt sentence:

[0466] Keywords: fast, quiet, car

[0467] Emotion: I want to relax

[0468] Based on this prompt, the generative AI model generates a "fast and quiet self-driving vehicle" and displays it as detailed information on the product page. It then further optimizes the product based on user feedback, ultimately presenting a custom-made self-driving vehicle proposal to the user.

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1:

[0471] The user enters search keywords.

[0472] Input: A user types search terms such as "fast" or "quiet car" into a smartphone application.

[0473] Processing: The device sends the search keyword to the server.

[0474] Output: The search keywords are sent to the server.

[0475] Step 2:

[0476] The server starts an emotion engine and analyzes the user's emotions.

[0477] Input: The search keywords received in step 1.

[0478] Processing: The server launches the relevant emotion engine and analyzes the emotion generated when the user enters a search keyword, utilizing natural language processing technology.

[0479] Output: Emotional data (e.g., "I want to relax") is generated.

[0480] Step 3:

[0481] Search the product database and rate the relevant products.

[0482] Input: The search keywords received by the server.

[0483] Processing: The server searches the product database and evaluates whether there are any products that match the entered keywords.

[0484] Output: Hit count is calculated, e.g. 1 or 0 matching products found.

[0485] Step 4:

[0486] Save the search keywords and their results in a database.

[0487] Input: Search keyword and number of hits.

[0488] Processing: If there are no hits or the user does not click on any of the products presented, save the search keywords and search results to the database.

[0489] Output: Search keywords and search results are saved in a database.

[0490] Step 5:

[0491] Analyze historical data to gain a detailed understanding of user requirements.

[0492] Input: Saved search keywords and search result history data.

[0493] Processing: The server analyzes the history data and extracts the features of the product the user is looking for, including past history and emotional data.

[0494] Output: Extracted features (e.g., "fast" or "quiet") and emotion data.

[0495] Step 6:

[0496] Generate pseudo-products using generative AI models.

[0497] Input: Extracted features and sentiment data.

[0498] Processing: The server inputs a prompt sentence into the generative AI model based on the extracted features and emotion data, and generates a pseudo-product.

[0499] Example: "Keywords: fast, quiet, car" "Emotion: I want to relax"

[0500] Output: A pseudo-product (e.g., "Fast and quiet self-driving cars").

[0501] Step 7:

[0502] A product page is generated based on the information of the generated pseudo-product.

[0503] Input: Details of the pseudo-product.

[0504] Processing: The server generates a product page using the pseudo-product's detailed information (product name, description, price, image, etc.).

[0505] Output: A product page is generated.

[0506] Step 8:

[0507] Present the pseudo-product page to users and collect feedback.

[0508] Input: The generated product page.

[0509] Processing: The server sends the generated product page to the user's terminal and presents it to the user. The user checks the product page and enters feedback.

[0510] Output: User feedback.

[0511] Step 9:

[0512] Generate custom products based on user feedback.

[0513] Input: User feedback and sentiment data.

[0514] Processing: The server performs a detailed analysis of the received feedback and sentiment data, and again uses the generative AI model to generate a custom-made product.

[0515] Output: Optimized, tailor-made products.

[0516] Step 10:

[0517] The generated custom product page is presented to the user.

[0518] Input: Optimized custom-made product details.

[0519] Processing: The server generates the final product page based on the optimized custom-made product details and sends it to the user's device.

[0520] Output: The final product page is presented to the user.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] [Second embodiment]

[0525] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0526] 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.

[0527] 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).

[0528] 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.

[0529] 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.

[0530] 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).

[0531] 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. 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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."

[0537] MODE FOR CARRYING OUT THE INVENTION

[0538] The system for implementing this invention receives search keywords entered by a user, and generates and provides a custom-made product that meets the user's needs based on the keywords.

[0539] Program processing

[0540] 1. Enter keywords

[0541] User: Visits an e-commerce site and types keywords into the search box.

[0542] Terminal: Sends the entered search keywords to the server.

[0543] 2. Keyword analysis and history saving

[0544] server:

[0545] A search keyword is received and a product database is searched based on the keyword.

[0546] Calculate the number of hits and analyze the results. If there are zero hits or the user does not click, save the keyword and its search results to a database.

[0547] 3. Historical data analysis and pseudo-product generation

[0548] server:

[0549] The system retrieves and analyzes historical search keyword data stored in the database, and extracts the characteristics of the products the user is looking for based on the analysis results.

[0550] The extracted features are then input as prompts into a generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0551] 4. Generate a pseudo-product page

[0552] server:

[0553] Build detailed product pages based on the generated pseudo-products.

[0554] The product page includes the generated product name, description, price, and image.

[0555] 5. Present to users and gather feedback

[0556] server:

[0557] The generated pseudo-product page is displayed on the screen to the user.

[0558] User:

[0559] Review the product page provided and submit feedback, including requests for color, size, additional features, etc.

[0560] 6. Feedback analysis and product generation

[0561] server:

[0562] Receive and analyze user feedback in detail.

[0563] Based on the analysis results, the AI ​​model is used again to generate a custom product, incorporating new product names, descriptions, images, etc.

[0564] 7. Final product proposal and order acceptance

[0565] server:

[0566] The final custom product page is displayed to the user.

[0567] User:

[0568] Check the product page provided and decide to purchase.

[0569] Specific examples

[0570] If a user types in "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses a generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with a description and image.

[0571] The generated product page is presented to the user, who then submits feedback such as "I would like a slightly larger size" or "I wish there was a blue variation." The server analyzes this feedback and again uses the AI ​​model to generate a custom-made product. Ultimately, the user decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[0572] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[0573] The processing flow will be explained below.

[0574] Step 1:

[0575] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[0576] Step 2:

[0577] Device: Send the entered search keyword "large-capacity heat-resistant glass teacup" to the server.

[0578] Step 3:

[0579] Server: Receives search keywords. Searches the product database based on the received keywords and calculates the number of related product hits.

[0580] Step 4:

[0581] Server: Check that there are no hits. Or, if the user does not click on the product, save the search keywords and search results to the database. The search results are also saved along with the timestamp and user ID.

[0582] Step 5:

[0583] Server: Analyzes the search keywords and search result history data stored in the database. As a result of the analysis, the characteristics of the product the user is looking for are extracted. For example, characteristics such as "heat-resistant," "glass," "large capacity," and "teacup" are extracted.

[0584] Step 6:

[0585] Server: Inputs the extracted features as prompts into the generative AI model. The generative AI model is used to automatically generate pseudo-products. The generated pseudo-products include product names, descriptions, and images.

[0586] Step 7:

[0587] Server: Generates a product page based on the details of the generated pseudo-product. Specifically, it builds a page that includes the product name, description, price, and image.

[0588] Step 8:

[0589] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[0590] Step 9:

[0591] User: Review the provided mock product page and enter feedback about the product, including requests for color, size, and additional features.

[0592] Step 10:

[0593] Terminal: Sends the feedback entered by the user to the server.

[0594] Step 11:

[0595] Server: Receives feedback from users, analyzes the feedback, and uses the AI ​​model to generate a custom-made product based on the analysis results.

[0596] Step 12:

[0597] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0598] Step 13:

[0599] User: Review the final product page presented to them and ensure all requirements are met.

[0600] Step 14:

[0601] User: Makes a purchase decision on the final product page and orders a custom product.

[0602] In this way, the system of the present invention can efficiently and effectively execute a series of processes from when a user inputs search keywords to when they purchase a custom-made product. By performing specific operations at each step, the system reduces user disappointment and provides optimal products.

[0603] Example 1

[0604] 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."

[0605] Traditional e-commerce systems often fail to display satisfactory products for the search keywords entered by users. As a result, users are often unable to find the product they are looking for and are left feeling disappointed. Furthermore, when users have specific requirements, there is a lack of a mechanism to suggest customized products that meet those requirements. This leads to a poor customer experience and missed sales opportunities.

[0606] 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.

[0607] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a data store, means for analyzing history data of the saved search keywords and extracting features desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a detailed information page based on detailed information about the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, and means for presenting the generated custom-made product page to the user. This enables product suggestions that accurately reflect the user's search intent, improving the user experience and increasing sales opportunities.

[0608] A "user" is a user who accesses the system and inputs search keywords.

[0609] A "search keyword" is a string of characters that a user enters into a search box and is used to search for products.

[0610] A "database" is a data structure or system that stores product information corresponding to search keywords.

[0611] The "number of hits" refers to the number of related products retrieved from the database based on the search keyword.

[0612] A "data store" is a storage device or system for storing search keywords and their search results.

[0613] "History data" refers to data on search keywords and search results that have been saved in the past.

[0614] "Features" are a collection of product characteristics and elements that a user desires, extracted by analyzing historical data.

[0615] A "generative AI model" is an algorithm or technology that uses artificial intelligence to generate pseudo-products based on user requests.

[0616] "Pseudo-products" are product information virtually created using generative AI models, which may not actually exist.

[0617] A "details page" is a web page that contains product details such as the name, description, price, and images of the pseudo-product.

[0618] "Feedback" refers to opinions and requests that users provide regarding the content of a pseudo-product page after checking it.

[0619] "Custom-made products" are items specially created using generative AI models based on user feedback.

[0620] "Means of generating" refers to the technical methods or processes by which a program or system performs a specific function.

[0621] This invention is a system that generates and provides custom-made products that meet the user's needs based on search keywords entered by the user. By entering specific keywords, the system automatically suggests products that best suit the user's needs and provides further customized custom-made products.

[0622] Hardware and software configuration

[0623] This system mainly uses the following hardware and software:

[0624] Server: A server with a powerful processor and large memory performs search keyword analysis, database lookup, runs the generative AI model, and analyzes feedback. This server can be, for example, an Apache web server or an Nginx web server.

[0625] Database: A relational database management system (RDBMS) is used to store product information and search history data. Specifically, MySQL or PostgreSQL is preferred.

[0626] Generative AI model: To generate pseudo-products based on user requests, we use a generative AI model (e.g., OpenAI's GPT-3). This model takes appropriate prompts as input and generates text and images.

[0627] Terminal: The devices that users use to access the site include various devices such as PCs, tablets, smartphones, etc. These terminals connect to the server via a web browser.

[0628] Specific methods for data processing and calculation

[0629] This system receives search keywords entered by the user and performs the following processing based on those keywords.

[0630] 1. Keyword analysis: The server receives the keywords entered by the user and searches the database for related product information, using SQL queries to quickly retrieve data.

[0631] 2. Historical Data Storage: If the user does not click or if there are zero hits, the search keywords and their search results are stored in the database. This is usually done using an INSERT or UPDATE query.

[0632] 3. Feature extraction: The server analyzes the saved search history data and extracts the features of the product the user is looking for (e.g., "heat-resistant glass," "large capacity," "teacup," etc.). This analysis may use natural language processing (NLP) technology.

[0633] 4. Generate pseudo-products: Generate pseudo-products by inputting the extracted features into a generative AI model as prompts. For example, the following prompts can be used:

[0634] Prompt: "Create a product with heat-resistant glass, large capacity, and the characteristics of a teacup."

[0635] 5. Product page generation: A detailed information page is constructed based on the generated pseudo-product, using an HTML template to embed the necessary information such as product name, description, price, and images.

[0636] 6. Feedback collection and analysis: The user reviews the product page and provides feedback, including specific requests for color, size, additional features, etc. The server analyzes this feedback and generates an improved, custom-made product, again using the generative AI model.

[0637] Specific example explanation

[0638] Let's take the example of a user entering the search keyword "large-capacity heat-resistant glass teacup." In this case, the server first receives this keyword and searches the product database. If no related products are found, the server saves this keyword in the database and records it as historical data. The server then analyzes the historical data and extracts key features. These features are input into the generative AI model as prompt sentences to generate pseudo-products.

[0639] The generated pseudo-product includes the product name "Large Capacity Heat-Resistant Glass Teacup," along with its description and image. This product page is presented to the user, who provides feedback such as "I wish it was a little larger" and "I wish it came in blue." The server analyzes this feedback and again uses the AI ​​model to generate a custom product. Finally, the new product page is displayed to the user, who decides to purchase the "Large Capacity Custom Heat-Resistant Glass Teacup."

[0640] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[0641] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0642] Step 1:

[0643] User: Visits an e-commerce site and types a search term like "large capacity heat-resistant glass teacup" into the search box.

[0644] Specific actions: A user opens a web browser, enters a URL, accesses a site, enters a desired keyword in the search box, and presses the search button.

[0645] Input: Search keyword

[0646] Output: A search request is sent to the server

[0647] Step 2:

[0648] Terminal: Sends the entered search keywords to the server.

[0649] Specific operation: The data from the search form is sent to the server as an HTTP request.

[0650] Input: The search term entered by the user

[0651] Output: HTTP request sent to server

[0652] Step 3:

[0653] Server: Receives search keywords and searches the database for related products.

[0654] Specific operation: The server extracts the search keywords from the HTTP request and executes an SQL query against the database.

[0655] Input: Search keyword

[0656] Output: A list of related products retrieved from the database

[0657] Step 4:

[0658] Server: Calculate the number of hits and analyze the results. If there are zero hits or the user does not click on a related product, save the search keywords and their search results to the data store.

[0659] What it does: Analyzes the query results and counts the number of hits. If there are zero hits or the user doesn't click on a result, it saves the keywords and results to the data store using an INSERT or UPDATE SQL query.

[0660] Input: Query results from the database

[0661] Output: Search keywords and results stored in the data store

[0662] Step 5:

[0663] Server: Analyzes the history data of saved search keywords and extracts the characteristics of the products the user is looking for.

[0664] Specific operation: Historical data is retrieved by scheduled jobs or triggers, and natural language processing (NLP) techniques are used to extract the features desired by the user.

[0665] Input: Historical data stored in a data store

[0666] Output: A set of extracted features

[0667] Step 6:

[0668] Server: The extracted features are input as prompts into the generative AI model to generate pseudo-products.

[0669] Specific operation: Send a prompt to the API of a generative AI model (e.g., GPT-3) and receive the generated text and images.

[0670] Input: Extracted features

[0671] Output: Generated pseudo-product information (product name, description, image, etc.)

[0672] Step 7:

[0673] Server: Generates a product page based on the details of the generated pseudo-product.

[0674] What it does: Embeds generated product information into an HTML template. Styles and generates the page using the necessary CSS and JavaScript.

[0675] Input: Details of the pseudo-product

[0676] Output: Completed product page HTML

[0677] Step 8:

[0678] Server: Presents the generated pseudo-product page to the user.

[0679] Specific operation: The product page is sent to the user's browser as an HTTP response.

[0680] Input: HTML for product page

[0681] Output: The product page that is displayed in the user's browser

[0682] Step 9:

[0683] User: Review the product page provided and provide feedback.

[0684] Specific actions: Refer to the product page, enter desired color, size, additional features, etc. in the feedback form, and press the submit button.

[0685] Input: Feedback information (new request)

[0686] Output: Feedback is sent to the server

[0687] Step 10:

[0688] Server: Receives and analyzes user feedback in detail.

[0689] Specific operation: Receives feedback data and creates and sends prompts to generate customized products using the generative AI model again.

[0690] Input: User feedback

[0691] Output: Improved custom product information

[0692] Step 11:

[0693] Server: Presents the generated custom product page to the user.

[0694] Specific operation: Reconstruct an HTML page based on the new product information and present it to the user.

[0695] Input: Improved custom product details

[0696] Output: The final product page is displayed in the user's browser

[0697] (Application example 1)

[0698] 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."

[0699] On traditional e-commerce sites, when a user searches for a specific product, if that product does not exist, the user cannot find the product they are looking for, resulting in a decrease in satisfaction. Furthermore, the site does not offer similar products or custom-made options, which means it is unable to meet the diverse needs of users. Furthermore, there is a lack of a mechanism for utilizing feedback to generate products that meet user requests.

[0700] 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.

[0701] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, and means for providing the generated pseudo-product in a format displayable on a specific hardware device, i.e., a smart device. This allows similar products or custom-made products to be presented when a user searches for a specific product even if the product does not exist, thereby improving user satisfaction.

[0702] A "search keyword" is a string of characters that a user enters when searching for a specific product or service.

[0703] A "product database" is a database in which information about each product or service is systematically stored.

[0704] "Hits" is the number of related products found in the database based on a particular search keyword.

[0705] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[0706] "History data" refers to data that stores a user's past search keywords and the results thereof.

[0707] "Features" are important attributes or characteristics of a product that users desire.

[0708] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate new products and designs.

[0709] A "pseudo-product" is a virtual product generated based on a user's search intent.

[0710] "Detailed information" is specific information about the product, including the product name, description, price, and image.

[0711] A "product page" is a web page for presenting product information to a user.

[0712] "Feedback" refers to evaluations and opinions provided by users, and is information that serves as a reference for product improvement.

[0713] A "custom product" is a product that is customized based on a user's specific requirements.

[0714] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[0715] The system embodying the present invention generates and provides custom-made products based on user search keywords. The specific configuration and processing steps of this system will now be described.

[0716] First, a user accesses an e-commerce site via a device such as a smartphone and enters keywords into the search box. The device sends the entered search keywords to the server. The server searches a product database based on the received search keywords and calculates the number of hits. If no search results are found, the search keywords and the search results are saved in the database.

[0717] The server then analyzes the saved search keyword history data to extract the features of the product the user is looking for. These extracted features are input as prompts into a generative AI model to generate a pseudo-product. The generated pseudo-product includes detailed information such as the product name, description, and images. The server then generates a product page based on this information and presents it to the user.

[0718] The user reviews the product page presented to them and submits feedback, which may include requests for color, size, additional features, etc. The server receives and analyzes the user's feedback. Based on the analysis results, the generative AI model is used again to generate a custom-made product that reflects the user's feedback. Finally, the generated custom-made product page is presented to the user, and the purchase is confirmed.

[0719] The system configuration includes the following major hardware and software components:

[0720] Smart device: A terminal where users can enter search keywords and view and purchase custom-made products.

[0721] Server: Analyzes search keywords, searches the product database, analyzes feedback, and generates products using a generative AI model.

[0722] Generative AI models: Artificial intelligence techniques for generating pseudo-goods and custom-made products based on user requirements.

[0723] Database Management System (DBMS): Stores and manages search keywords and historical data.

[0724] For example, if a user enters "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses the generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with its description and image.

[0725] Examples of specific prompts to input to a generative AI model:

[0726] Create a product based on these features: {"material": "Heat-resistant glass", "size": "Large capacity", "type": "Teacup"}

[0727] This prompt is then fed into a generative AI model to generate custom product suggestions, which can then be further customized based on collected feedback to provide the perfect product for the user.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] A user accesses an e-commerce site through a device such as a smartphone and enters keywords into the search box. The device then sends the entered search keywords (input data) to the server (the output data is the search keywords). Specifically, the user enters the keyword "large-capacity heat-resistant glass teacup," which is then transferred to the server.

[0731] Step 2:

[0732] The server searches the product database based on the received search keywords (input data is the search keywords). As a result, it calculates the number of matching products in the product database (output data is the number of hits) and obtains this number of hits. For example, if the number of hits is zero, the result is also saved.

[0733] Step 3:

[0734] If the server does not get any search results, it saves the search keywords and the search results in a database (the input data is the search keywords and the number of hits). The saved data includes the keyword the user searched for, "large-capacity heat-resistant glass teacup," and the results.

[0735] Step 4:

[0736] The server analyzes the history data of saved search keywords (input data are past search keywords saved in the database). Through this analysis, the features of the product the user is looking for are extracted (output data are the extracted features). For example, the extracted features are "heat-resistant glass," "large capacity," and "teacup."

[0737] Step 5:

[0738] The server inputs the extracted features into a generative AI model (the input data is the extracted features). The generative AI model receives these features as prompts and generates a pseudo-product (the output data is the pseudo-product). For example, the generative AI model generates a pseudo-product called a "large-capacity heat-resistant glass teacup."

[0739] Step 6:

[0740] The server generates a product page based on the detailed information of the generated pseudo-product (input data is detailed information of the pseudo-product). The product page includes the product name, product description, price, image, etc. (output data is the product page). For example, a product page for "large-capacity heat-resistant glass teacup" is generated.

[0741] Step 7:

[0742] The server presents the generated product page to the user and collects feedback (the input data is the generated product page). For example, the user sends feedback such as "I want a bigger size" (the output data is the user feedback).

[0743] Step 8:

[0744] The server analyzes the user feedback (input data is the user feedback) and generates a custom-made product using the generative AI model again based on the results (output data is a customized custom-made product). For example, a new "custom heat-resistant glass large-capacity teacup" is generated based on the feedback.

[0745] Step 9:

[0746] The server presents the final custom-made product page to the user (input data is the customized custom-made product). The user reviews this page and decides to purchase (output data is the final custom-made product page). For example, the user reviews the new product page and decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[0747] 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.

[0748] MODE FOR CARRYING OUT THE INVENTION

[0749] The system embodying this invention receives search keywords entered by a user and generates and provides a custom-made product that meets the user's needs based on those keywords. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotions when entering search keywords and collecting feedback, and generating products that reflect those emotions.

[0750] Program processing

[0751] 1. Enter keywords

[0752] User: Visits an e-commerce site and types keywords into the search box.

[0753] Terminal: Sends the entered search keywords to the server.

[0754] Server: Receives search keywords and activates the emotion engine to recognize the user's emotions when entering search keywords.

[0755] 2. Keyword analysis and history saving

[0756] Server: Searches the product database based on the search keywords and calculates the number of related product hits.

[0757] Server: Checks if there are zero hits or if the user does not click on the product. If so, stores the search keywords and search results in a database, along with a timestamp, user ID, and user sentiment data.

[0758] 3. Historical data analysis and pseudo-product generation

[0759] Server: Acquires and analyzes search keywords, search result history data, and sentiment data stored in the database. As a result of the analysis, the characteristics of the products the user is looking for are extracted.

[0760] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0761] 4. Generate a pseudo-product page

[0762] Server: Builds detailed product pages based on the generated pseudo-products. Specifically, it generates pages that reflect the product name, product description, price, images, and user sentiment data.

[0763] 5. Present to users and gather feedback

[0764] Server: The generated pseudo-product page is sent to the user's device and presented to the user. The presented page includes an interface for inputting feedback.

[0765] User: Review the presented product page and enter feedback, including requests for color, size, additional features, and their emotions while entering the feedback.

[0766] Device: Sends user emotion data along with feedback to the server.

[0767] 6. Feedback analysis and product generation

[0768] Server: Receives user feedback and emotion data and analyzes it in detail.

[0769] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[0770] 7. Final product proposal and order acceptance

[0771] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0772] User: Review the final product page presented to them and ensure all their requirements are met. Confirm purchase and order the custom product.

[0773] Specific examples

[0774] If a user types in "large-capacity heat-resistant glass teacup," the server uses this keyword and the emotion engine to recognize that the user is "excited." The server searches the product database based on this keyword and the user's emotion data, and confirms that there are no hits. The search keyword, search results, and emotion data are saved in the database.

[0775] The accumulated keyword history and sentiment data are analyzed to extract the characteristics of "heat-resistant glass," "large capacity," and "teacup," as well as the sentiment of "excited." A generative AI model is then used to generate pseudo-products, such as a product name such as "Large capacity heat-resistant glass teacup," along with a description, image, and sentiment data such as "This teacup is made of heat-resistant glass, has a large capacity, and is particularly suitable for hot drinks."

[0776] The generated product page is presented to the user, who then enters "I'm looking forward to it" along with the feedback that "I want the blue one too." The server then analyzes this feedback and emotion data again to generate a custom-made product. The final "Custom Heat-Resistant Glass Large Capacity Teacup" product page is presented to the user, who then decides to purchase.

[0777] In this way, the system of the present invention provides optimal custom-made products based on the user's search keywords and emotional data, reducing disappointment for the user.

[0778] The processing flow will be explained below.

[0779] Step 1:

[0780] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[0781] Step 2:

[0782] Device: Send the keyword "large capacity heat-resistant glass teacup" entered in the search box to the server.

[0783] Step 3:

[0784] Server: Receives search keywords. At the same time, it activates the emotion engine and recognizes the user's emotion when entering the search keywords. For example, it determines that the user is "excited."

[0785] Step 4:

[0786] Server: Query the search keywords against the product database and calculate the number of related product hits.

[0787] Step 5:

[0788] Server: Check that there are zero hits, or if the user does not click on the product, store the user's sentiment data in a database along with the search keywords and search results.

[0789] Step 6:

[0790] Server: Analyzes search keywords and search result history data stored in the database, as well as emotion data. As a result of the analysis, the characteristics of the product the user is looking for (e.g., "heat-resistant," "glass," "large capacity," "teacup") and emotion (e.g., "excited") are extracted.

[0791] Step 7:

[0792] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[0793] Step 8:

[0794] Server: Generates a product page based on the generated pseudo-product details. The product page includes the product name, description, price, image, and user sentiment data.

[0795] Step 9:

[0796] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[0797] Step 10:

[0798] User: Review the presented mock product page and enter feedback about the product, including requests for color, size, additional features, and their emotions while entering the feedback.

[0799] Step 11:

[0800] Terminal: Sends user-entered feedback and emotion data to the server.

[0801] Step 12:

[0802] Server: Receives user feedback and emotion data and analyzes them in detail. For example, it analyzes feedback such as "I want blue too" and emotion such as "I'm looking forward to it."

[0803] Step 13:

[0804] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[0805] Step 14:

[0806] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[0807] Step 15:

[0808] User: Checks the final custom product page, confirms that all requirements are met, requests revisions as necessary, and finally decides to purchase.

[0809] In this way, the system of the present invention incorporates the emotional information entered by the user along with the search keywords and executes a process to generate optimal custom-made products based on that information, thereby reducing disappointment for users and providing more appropriate products.

[0810] Example 2

[0811] 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."

[0812] In traditional e-commerce systems, if the product searched for by the user is not accurately hit, it is difficult for the user to find a product that meets their needs. Furthermore, because the system does not take into account the user's emotions, the specific product characteristics desired by the user are often not reflected. Furthermore, it is difficult to reflect user feedback in real time and generate a custom-made product. This results in a poor user experience and potentially leads to lost sales opportunities.

[0813] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features and the user's emotions, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on the user's feedback and emotion data, and means for presenting the generated custom-made product page to the user. This makes it possible to provide an optimal custom-made product based on the user's search keywords and emotions, improving the user experience and increasing sales.

[0814] A "user" is an individual or corporation that uses this system and enters search keywords to search for and purchase products.

[0815] A "search keyword" is a word or phrase that a user enters into the system and is information that identifies the product the user is looking for.

[0816] The "product database" is a database containing product information stored within the system, and is used to provide product information corresponding to search keywords.

[0817] The "number of hits" indicates the number of related products found in the product database based on the search keyword.

[0818] An "emotion engine" is a software or hardware function that recognizes and analyzes a user's emotions when they enter search keywords.

[0819] "History data" refers to data that includes keywords that a user has searched for in the past and the results of those searches, emotional data, and other related information.

[0820] A "generative AI model" is an artificial intelligence model that automatically generates text, images, etc. based on input prompts, for example, using machine learning algorithms.

[0821] "Pseudo-products" are virtual products that do not exist in real inventory but are created to meet user requirements.

[0822] A "product page" is a web page that contains product information presented to a user, including the product name, description, price, image, and emotion data.

[0823] "Feedback" refers to the input of opinions, requests, and emotional data from users, including evaluations of the provided products and requests for additional items.

[0824] "Custom-made products" are items that are customized based on user feedback and sentiment data.

[0825] "Emotion data" is data that indicates the emotional state of the user when entering search keywords or feedback.

[0826] MODE FOR CARRYING OUT THE INVENTION

[0827] The system for implementing this invention allows a user to input search keywords, and generates and provides custom-made products that meet the user's needs based on those keywords. This system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotional data and generating products that reflect those emotions.

[0828] Main system components

[0829] The system consists of the following main components:

[0830] 1. Search keyword receiving method

[0831] It starts when a user enters a keyword into the search box on their device. An example of an input would be "large-capacity heat-resistant glass teacup."

[0832] 2. Product database search method

[0833] Based on the search keywords received, the server performs a database search and calculates the number of related product hits, using either an SQL database or a NoSQL database.

[0834] 3. How to save search results

[0835] If there are no hits or the user does not click on the suggested product, the server stores the search keywords and results in a database, including a timestamp, user ID, and sentiment data.

[0836] 4. Historical Data Analysis Methods

[0837] The server analyzes the historical data stored in the database and extracts the characteristics of the products desired by the user. The historical data includes past search keywords, search results, and emotional data.

[0838] 5. Generative AI Models

[0839] The server inputs the analyzed features and the user's emotional data as a prompt into a generative AI model (e.g., GPT-4 or other machine learning model) to generate a pseudo-product. An example of this prompt would be, "The user excitedly searched for 'large-capacity heat-resistant glass teacup.'"

[0840] 6. Product page generation method

[0841] The server builds a detailed product page based on the generated pseudo-product, including the product name, description, price, image, and user sentiment data generated by the generative AI model.

[0842] 7. Feedback Collection Methods

[0843] The server sends the generated product page to the user's device and collects feedback. The user checks the product page and enters their requests for color, size, additional features, and their feelings at the time of input into a feedback form.

[0844] 8. Means of creating custom products

[0845] The server receives and analyzes user feedback and emotion data. Based on the analysis results, the generative AI model is used again to generate a custom-made product. For example, if the user provides feedback such as "I also want blue," the server generates product details that correspond to this.

[0846] 9. Final product page presentation method

[0847] The server sends the final generated custom product page to the user's device, where the user confirms that all of their requests have been fulfilled, including the new product name, description, image, and emotion data.

[0848] Specific examples

[0849] If a user enters "large-capacity heat-resistant glass teacup," the server searches the product database using this keyword and confirms that there are zero hits. It then saves the search keyword, search results, and the user's "excited" emotional data. Based on the analysis, the generative AI model generates a pseudo-product called "large-capacity heat-resistant glass teacup" and builds a product page. If the user provides feedback such as "I also want blue," the server uses this feedback to again use the generative AI model to generate the final custom-made product. In this way, the optimal custom-made product is provided based on the user's search keyword and emotional data.

[0850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0851] Step 1:

[0852] A user visits an e-commerce site and enters keywords into the search box.

[0853] Input: The search term entered by the user (e.g., "large-capacity heat-resistant glass teacup").

[0854] What happens: A user uses the keyboard to type characters into the search box and presses the enter key.

[0855] Output: Keyword input data is generated.

[0856] Step 2:

[0857] The terminal transmits the entered search keyword to the server.

[0858] Input: Keyword input data.

[0859] Specific operation: The device's web browser sends the keyword input data to the server as an HTTP POST request.

[0860] Output: The server receives the search keywords.

[0861] Step 3:

[0862] The server receives the search keywords and activates an emotion engine to recognize the user's emotions.

[0863] Input: Search keyword.

[0864] Specific operation: Calls the emotion recognition API implemented in the server and analyzes emotions based on the user's facial expressions, input speed, etc.

[0865] Output: Search keywords and sentiment data.

[0866] Step 4:

[0867] The server searches the product database based on the search keywords and calculates the number of hits for related products.

[0868] Input: Search keyword.

[0869] What it does: Searches a database using an SQL query and retrieves a result set.

[0870] Output: Number of hits and search results.

[0871] Step 5:

[0872] The server checks that there are zero hits or the user does not click on any of the products offered, in which case the search keywords and search results are saved in a database.

[0873] Input: number of hits, search results, sentiment data.

[0874] Specific actions: Builds data for saving and executes an INSERT query against the database.

[0875] Output: Search history stored in a database.

[0876] Step 6:

[0877] The server retrieves and analyzes the historical data stored in the database, and extracts the features of the products desired by the user.

[0878] Input: Search history data, sentiment data.

[0879] Specific operations: Apply data analysis algorithms and machine learning models to extract features.

[0880] Output: Feature data.

[0881] Step 7:

[0882] The server inputs the extracted features and emotion data as prompts into the generative AI model to generate pseudo-products.

[0883] Input: feature data, emotion data.

[0884] Specific operations: Generate a prompt text, send an API request to the generative AI model, and retrieve the generated text and image.

[0885] Output: Pseudo-product data (product name, description, price, image).

[0886] Step 8:

[0887] The server builds a detailed product page based on the generated pseudo-product.

[0888] Input: Pseudo-product data.

[0889] Specific operation: Embed the generated data into a web page template and generate an HTML file.

[0890] Output: HTML data of product page.

[0891] Step 9:

[0892] The server generates a product page, which is then sent to the user's device and presented to them. It includes an interface for inputting feedback.

[0893] Input: HTML data for product page.

[0894] Specific operation: The HTML of the product page is sent to the terminal as an HTTP response.

[0895] Output: The product page is displayed on the user's device.

[0896] Step 10:

[0897] The user reviews the presented product page and enters feedback, including requests for color, size, additional features, and feelings.

[0898] Input: Check the product page and enter your feedback information.

[0899] Specific Action: Enter information into the feedback form and click the submit button.

[0900] Output: Feedback data is generated.

[0901] Step 11:

[0902] The terminal transmits the feedback data to the server.

[0903] Input: Feedback data.

[0904] Specific behavior: Feedback data is sent to the server as an HTTP POST request.

[0905] Output: The server receives the feedback data.

[0906] Step 12:

[0907] A server receives and analyzes the feedback data and emotion data.

[0908] Input: Feedback data, emotion data.

[0909] Specific operation: Analyze the feedback content using a data analysis algorithm.

[0910] Output: Analysis result data.

[0911] Step 13:

[0912] The server then uses the generated AI model based on the analysis results to generate a custom-made product.

[0913] Input: Analysis result data.

[0914] What it does: Generate an updated prompt and feed it into the generative AI model to get new text and images.

[0915] Output: Custom product data (new product name, description, and image).

[0916] Step 14:

[0917] The server transmits the final generated custom-made product page to the user's terminal for presentation.

[0918] Input: Custom-made product data.

[0919] Specific operation: Builds the HTML of the final product page and sends it to the terminal as an HTTP response.

[0920] Output: The final product page is displayed on the user's device.

[0921] Step 15:

[0922] The user reviews the final product page, confirms that all of their requirements are met, and finally makes the purchase decision and orders the custom-made product.

[0923] Enter: Check the final product page.

[0924] Specific Action: Click the purchase button to complete the purchase process.

[0925] Output: A custom-made product order is completed.

[0926] (Application example 2)

[0927] 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."

[0928] Conventional custom-made product provision systems generate products without considering the user's emotions, which results in the problem of not being able to fully meet the user's expectations. Furthermore, if no products related to the keywords entered by the user are found, it is difficult to suggest appropriate alternatives. This can lead to increased user disappointment and reduced customer satisfaction.

[0929] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0930] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, means for recognizing and analyzing user emotions when entering search keywords and when collecting feedback, and means for inputting prompt sentences to the generative AI model based on the search keywords and emotion data entered by the user to generate a pseudo-product. This enables product generation that takes user emotions into consideration and makes it possible to provide custom-made products that meet user expectations.

[0931] "Search keywords" are words or phrases that users enter when searching for custom products or services.

[0932] A "product database" is a database that contains various product information and is used to search for related products based on search keywords.

[0933] "History data" refers to data that stores search keywords entered by the user in the past and the search results.

[0934] "Features" are specific requirements or attributes of the product or service that a user is looking for.

[0935] A "generative AI model" is a system that uses generative artificial intelligence algorithms to automatically generate new ideas and proposals based on input data.

[0936] "Pseudo-products" are products or services that do not actually exist but are close to what the user wants, generated based on the user's search keywords and emotional data.

[0937] A "product page" is a web page or application screen that displays detailed information (product name, description, price, image, etc.) about a pseudo-product or custom-made product.

[0938] "Feedback" is data that records the user's opinions and requests regarding the presented pseudo-product.

[0939] The "emotion engine" is a system that analyzes the emotions of users when they enter search keywords or feedback.

[0940] A "prompt" is a context or instruction to be input into a generative AI model, and includes the user's search keywords and emotional data.

[0941] A "custom-made product" is a product or service that is individually created to reflect a user's specific requests and feedback.

[0942] The system embodying this invention uses the following procedures and devices to generate and provide custom-made products based on a user's search keywords and emotion data.

[0943] Hardware and Software

[0944] Hardware: Smartphones, servers.

[0945] Software: sentiment_analysis and ai_model modules for natural language processing.

[0946] Overview of data processing and calculation

[0947] Search keyword reception

[0948] A user uses a smartphone to input keywords to search for a product or service they wish to reserve or purchase. The device then sends the search keywords to the server. The server saves the received search keywords and simultaneously activates an emotion engine to analyze the user's emotions.

[0949] Search product database and save results

[0950] The server searches the product database for the searched keyword and evaluates whether there is a matching product or a similar product. If there are no matching products or if the user does not click on the presented product, the server saves the search keyword and the results in the database.

[0951] Historical data analysis and feature extraction

[0952] The server analyzes the stored history data and extracts the characteristics of the product the user is looking for. Specifically, it analyzes search keywords, past search results, and user emotion data to understand the user's needs in detail.

[0953] Generating pseudo-products using generative AI models

[0954] Based on the extracted features and emotion data, a prompt sentence is input into a generative AI model to generate pseudo-products. Based on the input data, this model suggests products that best fit the user's requirements.

[0955] Product page generation and user presentation

[0956] The server generates a product page based on the detailed information of the generated pseudo-product (product name, description, price, image, etc.) and presents this product page to the smartphone user.

[0957] Feedback collection and analysis

[0958] The user checks the product page and inputs feedback, including requests and feelings about the product's color, size, additional features, etc. The server receives this feedback and analyzes it in detail.

[0959] Custom-made product creation and final proposal

[0960] The server then uses the generative AI model again based on the analysis results to generate a custom-made product. The generated product page is then finally presented to the user, who reviews it and decides to purchase.

[0961] Specific examples

[0962] Suppose a user uses a smartphone app to enter the search keywords "fast" and "quiet car." At the same time, the emotion engine analyzes the user's emotion at that time as "I want to relax." Based on this information, the server searches the database for relevant autonomous vehicles. If no matching vehicle is found, the keywords and emotion data are saved for later analysis.

[0963] By analyzing the accumulated historical data, the system can understand the user's requirements in detail and generate a simulated vehicle by inputting the following prompt sentences into the generative AI model:

[0964] Example prompt sentence:

[0965] Keywords: fast, quiet, car

[0966] Emotion: I want to relax

[0967] Based on this prompt, the generative AI model generates a "fast and quiet self-driving vehicle" and displays it as detailed information on the product page. It then further optimizes the product based on user feedback, ultimately presenting a custom-made self-driving vehicle proposal to the user.

[0968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0969] Step 1:

[0970] The user enters search keywords.

[0971] Input: A user types search terms such as "fast" or "quiet car" into a smartphone application.

[0972] Processing: The device sends the search keyword to the server.

[0973] Output: The search keywords are sent to the server.

[0974] Step 2:

[0975] The server starts an emotion engine and analyzes the user's emotions.

[0976] Input: The search keywords received in step 1.

[0977] Processing: The server launches the relevant emotion engine and analyzes the emotion generated when the user enters a search keyword, utilizing natural language processing technology.

[0978] Output: Emotional data (e.g., "I want to relax") is generated.

[0979] Step 3:

[0980] Search the product database and rate the relevant products.

[0981] Input: The search keywords received by the server.

[0982] Processing: The server searches the product database and evaluates whether there are any products that match the entered keywords.

[0983] Output: Hit count is calculated, e.g. 1 or 0 matching products found.

[0984] Step 4:

[0985] Save the search keywords and their results in a database.

[0986] Input: Search keyword and number of hits.

[0987] Processing: If there are no hits or the user does not click on any of the products presented, save the search keywords and search results to the database.

[0988] Output: Search keywords and search results are saved in a database.

[0989] Step 5:

[0990] Analyze historical data to gain a detailed understanding of user requirements.

[0991] Input: Saved search keywords and search result history data.

[0992] Processing: The server analyzes the history data and extracts the features of the product the user is looking for, including past history and emotional data.

[0993] Output: Extracted features (e.g., "fast" or "quiet") and emotion data.

[0994] Step 6:

[0995] Generate pseudo-products using generative AI models.

[0996] Input: Extracted features and sentiment data.

[0997] Processing: The server inputs a prompt sentence into the generative AI model based on the extracted features and emotion data, and generates a pseudo-product.

[0998] Example: "Keywords: fast, quiet, car" "Emotion: I want to relax"

[0999] Output: A pseudo-product (e.g., "Fast and quiet self-driving cars").

[1000] Step 7:

[1001] A product page is generated based on the information of the generated pseudo-product.

[1002] Input: Details of the pseudo-product.

[1003] Processing: The server generates a product page using the pseudo-product's detailed information (product name, description, price, image, etc.).

[1004] Output: A product page is generated.

[1005] Step 8:

[1006] Present the pseudo-product page to users and collect feedback.

[1007] Input: The generated product page.

[1008] Processing: The server sends the generated product page to the user's terminal and presents it to the user. The user checks the product page and enters feedback.

[1009] Output: User feedback.

[1010] Step 9:

[1011] Generate custom products based on user feedback.

[1012] Input: User feedback and sentiment data.

[1013] Processing: The server performs a detailed analysis of the received feedback and sentiment data, and again uses the generative AI model to generate a custom-made product.

[1014] Output: Optimized, tailor-made products.

[1015] Step 10:

[1016] The generated custom product page is presented to the user.

[1017] Input: Optimized custom-made product details.

[1018] Processing: The server generates the final product page based on the optimized custom-made product details and sends it to the user's device.

[1019] Output: The final product page is presented to the user.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] [Third embodiment]

[1024] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1025] 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.

[1026] 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).

[1027] 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.

[1028] 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.

[1029] 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).

[1030] 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. 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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."

[1036] MODE FOR CARRYING OUT THE INVENTION

[1037] The system for implementing this invention receives search keywords entered by a user, and generates and provides a custom-made product that meets the user's needs based on the keywords.

[1038] Program processing

[1039] 1. Enter keywords

[1040] User: Visits an e-commerce site and types keywords into the search box.

[1041] Terminal: Sends the entered search keywords to the server.

[1042] 2. Keyword analysis and history saving

[1043] server:

[1044] A search keyword is received and a product database is searched based on the keyword.

[1045] Calculate the number of hits and analyze the results. If there are zero hits or the user does not click, save the keyword and its search results to a database.

[1046] 3. Historical data analysis and pseudo-product generation

[1047] server:

[1048] The system retrieves and analyzes historical search keyword data stored in the database, and extracts the characteristics of the products the user is looking for based on the analysis results.

[1049] The extracted features are then input as prompts into a generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1050] 4. Generate a pseudo-product page

[1051] server:

[1052] Build detailed product pages based on the generated pseudo-products.

[1053] The product page includes the generated product name, description, price, and image.

[1054] 5. Present to users and gather feedback

[1055] server:

[1056] The generated pseudo-product page is displayed on the screen to the user.

[1057] User:

[1058] Review the product page provided and submit feedback, including requests for color, size, additional features, etc.

[1059] 6. Feedback analysis and product generation

[1060] server:

[1061] Receive and analyze user feedback in detail.

[1062] Based on the analysis results, the AI ​​model is used again to generate a custom product, incorporating new product names, descriptions, images, etc.

[1063] 7. Final product proposal and order acceptance

[1064] server:

[1065] The final custom product page is displayed to the user.

[1066] User:

[1067] Check the product page provided and decide to purchase.

[1068] Specific examples

[1069] If a user types in "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses a generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with a description and image.

[1070] The generated product page is presented to the user, who then submits feedback such as "I would like a slightly larger size" or "I wish there was a blue variation." The server analyzes this feedback and again uses the AI ​​model to generate a custom-made product. Ultimately, the user decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[1071] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[1072] The processing flow will be explained below.

[1073] Step 1:

[1074] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[1075] Step 2:

[1076] Device: Send the entered search keyword "large-capacity heat-resistant glass teacup" to the server.

[1077] Step 3:

[1078] Server: Receives search keywords. Searches the product database based on the received keywords and calculates the number of related product hits.

[1079] Step 4:

[1080] Server: Check that there are no hits. Or, if the user does not click on the product, save the search keywords and search results to the database. The search results are also saved along with the timestamp and user ID.

[1081] Step 5:

[1082] Server: Analyzes the search keywords and search result history data stored in the database. As a result of the analysis, the characteristics of the product the user is looking for are extracted. For example, characteristics such as "heat-resistant," "glass," "large capacity," and "teacup" are extracted.

[1083] Step 6:

[1084] Server: Inputs the extracted features as prompts into the generative AI model. The generative AI model is used to automatically generate pseudo-products. The generated pseudo-products include product names, descriptions, and images.

[1085] Step 7:

[1086] Server: Generates a product page based on the details of the generated pseudo-product. Specifically, it builds a page that includes the product name, description, price, and image.

[1087] Step 8:

[1088] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[1089] Step 9:

[1090] User: Review the provided mock product page and enter feedback about the product, including requests for color, size, and additional features.

[1091] Step 10:

[1092] Terminal: Sends the feedback entered by the user to the server.

[1093] Step 11:

[1094] Server: Receives feedback from users, analyzes the feedback, and uses the AI ​​model to generate a custom-made product based on the analysis results.

[1095] Step 12:

[1096] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1097] Step 13:

[1098] User: Review the final product page presented to them and ensure all requirements are met.

[1099] Step 14:

[1100] User: Makes a purchase decision on the final product page and orders a custom product.

[1101] In this way, the system of the present invention can efficiently and effectively execute a series of processes from when a user inputs search keywords to when they purchase a custom-made product. By performing specific operations at each step, the system reduces user disappointment and provides optimal products.

[1102] Example 1

[1103] 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."

[1104] Traditional e-commerce systems often fail to display satisfactory products for the search keywords entered by users. As a result, users are often unable to find the product they are looking for and are left feeling disappointed. Furthermore, when users have specific requirements, there is a lack of a mechanism to suggest customized products that meet those requirements. This leads to a poor customer experience and missed sales opportunities.

[1105] 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.

[1106] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a data store, means for analyzing history data of the saved search keywords and extracting features desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a detailed information page based on detailed information about the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, and means for presenting the generated custom-made product page to the user. This enables product suggestions that accurately reflect the user's search intent, improving the user experience and increasing sales opportunities.

[1107] A "user" is a user who accesses the system and inputs search keywords.

[1108] A "search keyword" is a string of characters that a user enters into a search box and is used to search for products.

[1109] A "database" is a data structure or system that stores product information corresponding to search keywords.

[1110] The "number of hits" refers to the number of related products retrieved from the database based on the search keyword.

[1111] A "data store" is a storage device or system for storing search keywords and their search results.

[1112] "History data" refers to data on search keywords and search results that have been saved in the past.

[1113] "Features" are a collection of product characteristics and elements that a user desires, extracted by analyzing historical data.

[1114] A "generative AI model" is an algorithm or technology that uses artificial intelligence to generate pseudo-products based on user requests.

[1115] "Pseudo-products" are product information virtually created using generative AI models, which may not actually exist.

[1116] A "details page" is a web page that contains product details such as the name, description, price, and images of the pseudo-product.

[1117] "Feedback" refers to opinions and requests that users provide regarding the content of a pseudo-product page after checking it.

[1118] "Custom-made products" are items specially created using generative AI models based on user feedback.

[1119] "Means of generating" refers to the technical methods or processes by which a program or system performs a specific function.

[1120] This invention is a system that generates and provides custom-made products that meet the user's needs based on search keywords entered by the user. By entering specific keywords, the system automatically suggests products that best suit the user's needs and provides further customized custom-made products.

[1121] Hardware and software configuration

[1122] This system mainly uses the following hardware and software:

[1123] Server: A server with a powerful processor and large memory performs search keyword analysis, database lookup, runs the generative AI model, and analyzes feedback. This server can be, for example, an Apache web server or an Nginx web server.

[1124] Database: A relational database management system (RDBMS) is used to store product information and search history data. Specifically, MySQL or PostgreSQL is preferred.

[1125] Generative AI model: To generate pseudo-products based on user requests, we use a generative AI model (e.g., OpenAI's GPT-3). This model takes appropriate prompts as input and generates text and images.

[1126] Terminal: The devices that users use to access the site include various devices such as PCs, tablets, smartphones, etc. These terminals connect to the server via a web browser.

[1127] Specific methods for data processing and calculation

[1128] This system receives search keywords entered by the user and performs the following processing based on those keywords.

[1129] 1. Keyword analysis: The server receives the keywords entered by the user and searches the database for related product information, using SQL queries to quickly retrieve data.

[1130] 2. Historical Data Storage: If the user does not click or if there are zero hits, the search keywords and their search results are stored in the database. This is usually done using an INSERT or UPDATE query.

[1131] 3. Feature extraction: The server analyzes the saved search history data and extracts the features of the product the user is looking for (e.g., "heat-resistant glass," "large capacity," "teacup," etc.). This analysis may use natural language processing (NLP) technology.

[1132] 4. Generate pseudo-products: Generate pseudo-products by inputting the extracted features into a generative AI model as prompts. For example, the following prompts can be used:

[1133] Prompt: "Create a product with heat-resistant glass, large capacity, and the characteristics of a teacup."

[1134] 5. Product page generation: A detailed information page is constructed based on the generated pseudo-product, using an HTML template to embed the necessary information such as product name, description, price, and images.

[1135] 6. Feedback collection and analysis: The user reviews the product page and provides feedback, including specific requests for color, size, additional features, etc. The server analyzes this feedback and generates an improved, custom-made product, again using the generative AI model.

[1136] Specific example explanation

[1137] Let's take the example of a user entering the search keyword "large-capacity heat-resistant glass teacup." In this case, the server first receives this keyword and searches the product database. If no related products are found, the server saves this keyword in the database and records it as historical data. The server then analyzes the historical data and extracts key features. These features are input into the generative AI model as prompt sentences to generate pseudo-products.

[1138] The generated pseudo-product includes the product name "Large Capacity Heat-Resistant Glass Teacup," along with its description and image. This product page is presented to the user, who provides feedback such as "I wish it was a little larger" and "I wish it came in blue." The server analyzes this feedback and again uses the AI ​​model to generate a custom product. Finally, the new product page is displayed to the user, who decides to purchase the "Large Capacity Custom Heat-Resistant Glass Teacup."

[1139] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[1140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1141] Step 1:

[1142] User: Visits an e-commerce site and types a search term like "large capacity heat-resistant glass teacup" into the search box.

[1143] Specific actions: A user opens a web browser, enters a URL, accesses a site, enters a desired keyword in the search box, and presses the search button.

[1144] Input: Search keyword

[1145] Output: A search request is sent to the server

[1146] Step 2:

[1147] Terminal: Sends the entered search keywords to the server.

[1148] Specific operation: The data from the search form is sent to the server as an HTTP request.

[1149] Input: The search term entered by the user

[1150] Output: HTTP request sent to server

[1151] Step 3:

[1152] Server: Receives search keywords and searches the database for related products.

[1153] Specific operation: The server extracts the search keywords from the HTTP request and executes an SQL query against the database.

[1154] Input: Search keyword

[1155] Output: A list of related products retrieved from the database

[1156] Step 4:

[1157] Server: Calculate the number of hits and analyze the results. If there are zero hits or the user does not click on a related product, save the search keywords and their search results to the data store.

[1158] What it does: Analyzes the query results and counts the number of hits. If there are zero hits or the user doesn't click on a result, it saves the keywords and results to the data store using an INSERT or UPDATE SQL query.

[1159] Input: Query results from the database

[1160] Output: Search keywords and results stored in the data store

[1161] Step 5:

[1162] Server: Analyzes the history data of saved search keywords and extracts the characteristics of the products the user is looking for.

[1163] Specific operation: Historical data is retrieved by scheduled jobs or triggers, and natural language processing (NLP) techniques are used to extract the features desired by the user.

[1164] Input: Historical data stored in a data store

[1165] Output: A set of extracted features

[1166] Step 6:

[1167] Server: The extracted features are input as prompts into the generative AI model to generate pseudo-products.

[1168] Specific operation: Send a prompt to the API of a generative AI model (e.g., GPT-3) and receive the generated text and images.

[1169] Input: Extracted features

[1170] Output: Generated pseudo-product information (product name, description, image, etc.)

[1171] Step 7:

[1172] Server: Generates a product page based on the details of the generated pseudo-product.

[1173] What it does: Embeds generated product information into an HTML template. Styles and generates the page using the necessary CSS and JavaScript.

[1174] Input: Details of the pseudo-product

[1175] Output: Completed product page HTML

[1176] Step 8:

[1177] Server: Presents the generated pseudo-product page to the user.

[1178] Specific operation: The product page is sent to the user's browser as an HTTP response.

[1179] Input: HTML for product page

[1180] Output: The product page that is displayed in the user's browser

[1181] Step 9:

[1182] User: Review the product page provided and provide feedback.

[1183] Specific actions: Refer to the product page, enter desired color, size, additional features, etc. in the feedback form, and press the submit button.

[1184] Input: Feedback information (new request)

[1185] Output: Feedback is sent to the server

[1186] Step 10:

[1187] Server: Receives and analyzes user feedback in detail.

[1188] Specific operation: Receives feedback data and creates and sends prompts to generate customized products using the generative AI model again.

[1189] Input: User feedback

[1190] Output: Improved custom product information

[1191] Step 11:

[1192] Server: Presents the generated custom product page to the user.

[1193] Specific operation: Reconstruct an HTML page based on the new product information and present it to the user.

[1194] Input: Improved custom product details

[1195] Output: The final product page is displayed in the user's browser

[1196] (Application example 1)

[1197] 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."

[1198] On traditional e-commerce sites, when a user searches for a specific product, if that product does not exist, the user cannot find the product they are looking for, resulting in a decrease in satisfaction. Furthermore, the site does not offer similar products or custom-made options, which means it is unable to meet the diverse needs of users. Furthermore, there is a lack of a mechanism for utilizing feedback to generate products that meet user requests.

[1199] 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.

[1200] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, and means for providing the generated pseudo-product in a format displayable on a specific hardware device, i.e., a smart device. This allows similar products or custom-made products to be presented when a user searches for a specific product even if the product does not exist, thereby improving user satisfaction.

[1201] A "search keyword" is a string of characters that a user enters when searching for a specific product or service.

[1202] A "product database" is a database in which information about each product or service is systematically stored.

[1203] "Hits" is the number of related products found in the database based on a particular search keyword.

[1204] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1205] "History data" refers to data that stores a user's past search keywords and the results thereof.

[1206] "Features" are important attributes or characteristics of a product that users desire.

[1207] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate new products and designs.

[1208] A "pseudo-product" is a virtual product generated based on a user's search intent.

[1209] "Detailed information" is specific information about the product, including the product name, description, price, and image.

[1210] A "product page" is a web page for presenting product information to a user.

[1211] "Feedback" refers to evaluations and opinions provided by users, and is information that serves as a reference for product improvement.

[1212] A "custom product" is a product that is customized based on a user's specific requirements.

[1213] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[1214] The system embodying the present invention generates and provides custom-made products based on user search keywords. The specific configuration and processing steps of this system will now be described.

[1215] First, a user accesses an e-commerce site via a device such as a smartphone and enters keywords into the search box. The device sends the entered search keywords to the server. The server searches a product database based on the received search keywords and calculates the number of hits. If no search results are found, the search keywords and the search results are saved in the database.

[1216] The server then analyzes the saved search keyword history data to extract the features of the product the user is looking for. These extracted features are input as prompts into a generative AI model to generate a pseudo-product. The generated pseudo-product includes detailed information such as the product name, description, and images. The server then generates a product page based on this information and presents it to the user.

[1217] The user reviews the product page presented to them and submits feedback, which may include requests for color, size, additional features, etc. The server receives and analyzes the user's feedback. Based on the analysis results, the generative AI model is used again to generate a custom-made product that reflects the user's feedback. Finally, the generated custom-made product page is presented to the user, and the purchase is confirmed.

[1218] The system configuration includes the following major hardware and software components:

[1219] Smart device: A terminal where users can enter search keywords and view and purchase custom-made products.

[1220] Server: Analyzes search keywords, searches the product database, analyzes feedback, and generates products using a generative AI model.

[1221] Generative AI models: Artificial intelligence techniques for generating pseudo-goods and custom-made products based on user requirements.

[1222] Database Management System (DBMS): Stores and manages search keywords and historical data.

[1223] For example, if a user enters "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses the generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with its description and image.

[1224] Examples of specific prompts to input to a generative AI model:

[1225] Create a product based on these features: {"material": "Heat-resistant glass", "size": "Large capacity", "type": "Teacup"}

[1226] This prompt is then fed into a generative AI model to generate custom product suggestions, which can then be further customized based on collected feedback to provide the perfect product for the user.

[1227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1228] Step 1:

[1229] A user accesses an e-commerce site through a device such as a smartphone and enters keywords into the search box. The device then sends the entered search keywords (input data) to the server (the output data is the search keywords). Specifically, the user enters the keyword "large-capacity heat-resistant glass teacup," which is then transferred to the server.

[1230] Step 2:

[1231] The server searches the product database based on the received search keywords (input data is the search keywords). As a result, it calculates the number of matching products in the product database (output data is the number of hits) and obtains this number of hits. For example, if the number of hits is zero, the result is also saved.

[1232] Step 3:

[1233] If the server does not get any search results, it saves the search keywords and the search results in a database (the input data is the search keywords and the number of hits). The saved data includes the keyword the user searched for, "large-capacity heat-resistant glass teacup," and the results.

[1234] Step 4:

[1235] The server analyzes the history data of saved search keywords (input data are past search keywords saved in the database). Through this analysis, the features of the product the user is looking for are extracted (output data are the extracted features). For example, the extracted features are "heat-resistant glass," "large capacity," and "teacup."

[1236] Step 5:

[1237] The server inputs the extracted features into a generative AI model (the input data is the extracted features). The generative AI model receives these features as prompts and generates a pseudo-product (the output data is the pseudo-product). For example, the generative AI model generates a pseudo-product called a "large-capacity heat-resistant glass teacup."

[1238] Step 6:

[1239] The server generates a product page based on the detailed information of the generated pseudo-product (input data is detailed information of the pseudo-product). The product page includes the product name, product description, price, image, etc. (output data is the product page). For example, a product page for "large-capacity heat-resistant glass teacup" is generated.

[1240] Step 7:

[1241] The server presents the generated product page to the user and collects feedback (the input data is the generated product page). For example, the user sends feedback such as "I want a bigger size" (the output data is the user feedback).

[1242] Step 8:

[1243] The server analyzes the user feedback (input data is the user feedback) and generates a custom-made product using the generative AI model again based on the results (output data is a customized custom-made product). For example, a new "custom heat-resistant glass large-capacity teacup" is generated based on the feedback.

[1244] Step 9:

[1245] The server presents the final custom-made product page to the user (input data is the customized custom-made product). The user reviews this page and decides to purchase (output data is the final custom-made product page). For example, the user reviews the new product page and decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[1246] 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.

[1247] MODE FOR CARRYING OUT THE INVENTION

[1248] The system embodying this invention receives search keywords entered by a user and generates and provides a custom-made product that meets the user's needs based on those keywords. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotions when entering search keywords and collecting feedback, and generating products that reflect those emotions.

[1249] Program processing

[1250] 1. Enter keywords

[1251] User: Visits an e-commerce site and types keywords into the search box.

[1252] Terminal: Sends the entered search keywords to the server.

[1253] Server: Receives search keywords and activates the emotion engine to recognize the user's emotions when entering search keywords.

[1254] 2. Keyword analysis and history saving

[1255] Server: Searches the product database based on the search keywords and calculates the number of related product hits.

[1256] Server: Checks if there are zero hits or if the user does not click on the product. If so, stores the search keywords and search results in a database, along with a timestamp, user ID, and user sentiment data.

[1257] 3. Historical data analysis and pseudo-product generation

[1258] Server: Acquires and analyzes search keywords, search result history data, and sentiment data stored in the database. As a result of the analysis, the characteristics of the products the user is looking for are extracted.

[1259] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1260] 4. Generate a pseudo-product page

[1261] Server: Builds detailed product pages based on the generated pseudo-products. Specifically, it generates pages that reflect the product name, product description, price, images, and user sentiment data.

[1262] 5. Present to users and gather feedback

[1263] Server: The generated pseudo-product page is sent to the user's device and presented to the user. The presented page includes an interface for inputting feedback.

[1264] User: Review the presented product page and enter feedback, including requests for color, size, additional features, and their emotions while entering the feedback.

[1265] Device: Sends user emotion data along with feedback to the server.

[1266] 6. Feedback analysis and product generation

[1267] Server: Receives user feedback and emotion data and analyzes it in detail.

[1268] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[1269] 7. Final product proposal and order acceptance

[1270] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1271] User: Review the final product page presented to them and ensure all their requirements are met. Confirm purchase and order the custom product.

[1272] Specific examples

[1273] If a user types in "large-capacity heat-resistant glass teacup," the server uses this keyword and the emotion engine to recognize that the user is "excited." The server searches the product database based on this keyword and the user's emotion data, and confirms that there are no hits. The search keyword, search results, and emotion data are saved in the database.

[1274] The accumulated keyword history and sentiment data are analyzed to extract the characteristics of "heat-resistant glass," "large capacity," and "teacup," as well as the sentiment of "excited." A generative AI model is then used to generate pseudo-products, such as a product name such as "Large capacity heat-resistant glass teacup," along with a description, image, and sentiment data such as "This teacup is made of heat-resistant glass, has a large capacity, and is particularly suitable for hot drinks."

[1275] The generated product page is presented to the user, who then enters "I'm looking forward to it" along with the feedback that "I want the blue one too." The server then analyzes this feedback and emotion data again to generate a custom-made product. The final "Custom Heat-Resistant Glass Large Capacity Teacup" product page is presented to the user, who then decides to purchase.

[1276] In this way, the system of the present invention provides optimal custom-made products based on the user's search keywords and emotional data, reducing disappointment for the user.

[1277] The processing flow will be explained below.

[1278] Step 1:

[1279] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[1280] Step 2:

[1281] Device: Send the keyword "large capacity heat-resistant glass teacup" entered in the search box to the server.

[1282] Step 3:

[1283] Server: Receives search keywords. At the same time, it activates the emotion engine and recognizes the user's emotion when entering the search keywords. For example, it determines that the user is "excited."

[1284] Step 4:

[1285] Server: Query the search keywords against the product database and calculate the number of related product hits.

[1286] Step 5:

[1287] Server: Check that there are zero hits, or if the user does not click on the product, store the user's sentiment data in a database along with the search keywords and search results.

[1288] Step 6:

[1289] Server: Analyzes search keywords and search result history data stored in the database, as well as emotion data. As a result of the analysis, the characteristics of the product the user is looking for (e.g., "heat-resistant," "glass," "large capacity," "teacup") and emotion (e.g., "excited") are extracted.

[1290] Step 7:

[1291] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1292] Step 8:

[1293] Server: Generates a product page based on the generated pseudo-product details. The product page includes the product name, description, price, image, and user sentiment data.

[1294] Step 9:

[1295] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[1296] Step 10:

[1297] User: Review the presented mock product page and enter feedback about the product, including requests for color, size, additional features, and their emotions while entering the feedback.

[1298] Step 11:

[1299] Terminal: Sends user-entered feedback and emotion data to the server.

[1300] Step 12:

[1301] Server: Receives user feedback and emotion data and analyzes them in detail. For example, it analyzes feedback such as "I want blue too" and emotion such as "I'm looking forward to it."

[1302] Step 13:

[1303] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[1304] Step 14:

[1305] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1306] Step 15:

[1307] User: Checks the final custom product page, confirms that all requirements are met, requests revisions as necessary, and finally decides to purchase.

[1308] In this way, the system of the present invention incorporates the emotional information entered by the user along with the search keywords and executes a process to generate optimal custom-made products based on that information, thereby reducing disappointment for users and providing more appropriate products.

[1309] Example 2

[1310] 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."

[1311] In traditional e-commerce systems, if the product searched for by the user is not accurately hit, it is difficult for the user to find a product that meets their needs. Furthermore, because the system does not take into account the user's emotions, the specific product characteristics desired by the user are often not reflected. Furthermore, it is difficult to reflect user feedback in real time and generate a custom-made product. This results in a poor user experience and potentially leads to lost sales opportunities.

[1312] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features and the user's emotions, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on the user's feedback and emotion data, and means for presenting the generated custom-made product page to the user. This makes it possible to provide an optimal custom-made product based on the user's search keywords and emotions, improving the user experience and increasing sales.

[1313] A "user" is an individual or corporation that uses this system and enters search keywords to search for and purchase products.

[1314] A "search keyword" is a word or phrase that a user enters into the system and is information that identifies the product the user is looking for.

[1315] The "product database" is a database containing product information stored within the system, and is used to provide product information corresponding to search keywords.

[1316] The "number of hits" indicates the number of related products found in the product database based on the search keyword.

[1317] An "emotion engine" is a software or hardware function that recognizes and analyzes a user's emotions when they enter search keywords.

[1318] "History data" refers to data that includes keywords that a user has searched for in the past and the results of those searches, emotional data, and other related information.

[1319] A "generative AI model" is an artificial intelligence model that automatically generates text, images, etc. based on input prompts, for example, using machine learning algorithms.

[1320] "Pseudo-products" are virtual products that do not exist in real inventory but are created to meet user requirements.

[1321] A "product page" is a web page that contains product information presented to a user, including the product name, description, price, image, and emotion data.

[1322] "Feedback" refers to the input of opinions, requests, and emotional data from users, including evaluations of the provided products and requests for additional items.

[1323] "Custom-made products" are items that are customized based on user feedback and sentiment data.

[1324] "Emotion data" is data that indicates the emotional state of the user when entering search keywords or feedback.

[1325] MODE FOR CARRYING OUT THE INVENTION

[1326] The system for implementing this invention allows a user to input search keywords, and generates and provides custom-made products that meet the user's needs based on those keywords. This system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotional data and generating products that reflect those emotions.

[1327] Main system components

[1328] The system consists of the following main components:

[1329] 1. Search keyword receiving method

[1330] It starts when a user enters a keyword into the search box on their device. An example of an input would be "large-capacity heat-resistant glass teacup."

[1331] 2. Product database search method

[1332] Based on the search keywords received, the server performs a database search and calculates the number of related product hits, using either an SQL database or a NoSQL database.

[1333] 3. How to save search results

[1334] If there are no hits or the user does not click on the suggested product, the server stores the search keywords and results in a database, including a timestamp, user ID, and sentiment data.

[1335] 4. Historical Data Analysis Methods

[1336] The server analyzes the historical data stored in the database and extracts the characteristics of the products desired by the user. The historical data includes past search keywords, search results, and emotional data.

[1337] 5. Generative AI Models

[1338] The server inputs the analyzed features and the user's emotional data as a prompt into a generative AI model (e.g., GPT-4 or other machine learning model) to generate a pseudo-product. An example of this prompt would be, "The user excitedly searched for 'large-capacity heat-resistant glass teacup.'"

[1339] 6. Product page generation method

[1340] The server builds a detailed product page based on the generated pseudo-product, including the product name, description, price, image, and user sentiment data generated by the generative AI model.

[1341] 7. Feedback Collection Methods

[1342] The server sends the generated product page to the user's device and collects feedback. The user checks the product page and enters their requests for color, size, additional features, and their feelings at the time of input into a feedback form.

[1343] 8. Means of creating custom products

[1344] The server receives and analyzes user feedback and emotion data. Based on the analysis results, the generative AI model is used again to generate a custom-made product. For example, if the user provides feedback such as "I also want blue," the server generates product details that correspond to this.

[1345] 9. Final product page presentation method

[1346] The server sends the final generated custom product page to the user's device, where the user confirms that all of their requests have been fulfilled, including the new product name, description, image, and emotion data.

[1347] Specific examples

[1348] If a user enters "large-capacity heat-resistant glass teacup," the server searches the product database using this keyword and confirms that there are zero hits. It then saves the search keyword, search results, and the user's "excited" emotional data. Based on the analysis, the generative AI model generates a pseudo-product called "large-capacity heat-resistant glass teacup" and builds a product page. If the user provides feedback such as "I also want blue," the server uses this feedback to again use the generative AI model to generate the final custom-made product. In this way, the optimal custom-made product is provided based on the user's search keyword and emotional data.

[1349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1350] Step 1:

[1351] A user visits an e-commerce site and enters keywords into the search box.

[1352] Input: The search term entered by the user (e.g., "large-capacity heat-resistant glass teacup").

[1353] What happens: A user uses the keyboard to type characters into the search box and presses the enter key.

[1354] Output: Keyword input data is generated.

[1355] Step 2:

[1356] The terminal transmits the entered search keyword to the server.

[1357] Input: Keyword input data.

[1358] Specific operation: The device's web browser sends the keyword input data to the server as an HTTP POST request.

[1359] Output: The server receives the search keywords.

[1360] Step 3:

[1361] The server receives the search keywords and activates an emotion engine to recognize the user's emotions.

[1362] Input: Search keyword.

[1363] Specific operation: Calls the emotion recognition API implemented in the server and analyzes emotions based on the user's facial expressions, input speed, etc.

[1364] Output: Search keywords and sentiment data.

[1365] Step 4:

[1366] The server searches the product database based on the search keywords and calculates the number of hits for related products.

[1367] Input: Search keyword.

[1368] What it does: Searches a database using an SQL query and retrieves a result set.

[1369] Output: Number of hits and search results.

[1370] Step 5:

[1371] The server checks that there are zero hits or the user does not click on any of the products offered, in which case the search keywords and search results are saved in a database.

[1372] Input: number of hits, search results, sentiment data.

[1373] Specific actions: Builds data for saving and executes an INSERT query against the database.

[1374] Output: Search history stored in a database.

[1375] Step 6:

[1376] The server retrieves and analyzes the historical data stored in the database, and extracts the features of the products desired by the user.

[1377] Input: Search history data, sentiment data.

[1378] Specific operations: Apply data analysis algorithms and machine learning models to extract features.

[1379] Output: Feature data.

[1380] Step 7:

[1381] The server inputs the extracted features and emotion data as prompts into the generative AI model to generate pseudo-products.

[1382] Input: feature data, emotion data.

[1383] Specific operations: Generate a prompt text, send an API request to the generative AI model, and retrieve the generated text and image.

[1384] Output: Pseudo-product data (product name, description, price, image).

[1385] Step 8:

[1386] The server builds a detailed product page based on the generated pseudo-product.

[1387] Input: Pseudo-product data.

[1388] Specific operation: Embed the generated data into a web page template and generate an HTML file.

[1389] Output: HTML data of product page.

[1390] Step 9:

[1391] The server generates a product page, which is then sent to the user's device and presented to them. It includes an interface for inputting feedback.

[1392] Input: HTML data for product page.

[1393] Specific operation: The HTML of the product page is sent to the terminal as an HTTP response.

[1394] Output: The product page is displayed on the user's device.

[1395] Step 10:

[1396] The user reviews the presented product page and enters feedback, including requests for color, size, additional features, and feelings.

[1397] Input: Check the product page and enter your feedback information.

[1398] Specific Action: Enter information into the feedback form and click the submit button.

[1399] Output: Feedback data is generated.

[1400] Step 11:

[1401] The terminal transmits the feedback data to the server.

[1402] Input: Feedback data.

[1403] Specific behavior: Feedback data is sent to the server as an HTTP POST request.

[1404] Output: The server receives the feedback data.

[1405] Step 12:

[1406] A server receives and analyzes the feedback data and emotion data.

[1407] Input: Feedback data, emotion data.

[1408] Specific operation: Analyze the feedback content using a data analysis algorithm.

[1409] Output: Analysis result data.

[1410] Step 13:

[1411] The server then uses the generated AI model based on the analysis results to generate a custom-made product.

[1412] Input: Analysis result data.

[1413] What it does: Generate an updated prompt and feed it into the generative AI model to get new text and images.

[1414] Output: Custom product data (new product name, description, and image).

[1415] Step 14:

[1416] The server transmits the final generated custom-made product page to the user's terminal for presentation.

[1417] Input: Custom-made product data.

[1418] Specific operation: Builds the HTML of the final product page and sends it to the terminal as an HTTP response.

[1419] Output: The final product page is displayed on the user's device.

[1420] Step 15:

[1421] The user reviews the final product page, confirms that all of their requirements are met, and finally makes the purchase decision and orders the custom-made product.

[1422] Enter: Check the final product page.

[1423] Specific Action: Click the purchase button to complete the purchase process.

[1424] Output: A custom-made product order is completed.

[1425] (Application example 2)

[1426] 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."

[1427] Conventional custom-made product provision systems generate products without considering the user's emotions, which results in the problem of not being able to fully meet the user's expectations. Furthermore, if no products related to the keywords entered by the user are found, it is difficult to suggest appropriate alternatives. This can lead to increased user disappointment and reduced customer satisfaction.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1429] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, means for recognizing and analyzing user emotions when entering search keywords and when collecting feedback, and means for inputting prompt sentences to the generative AI model based on the search keywords and emotion data entered by the user to generate a pseudo-product. This enables product generation that takes user emotions into consideration and makes it possible to provide custom-made products that meet user expectations.

[1430] "Search keywords" are words or phrases that users enter when searching for custom products or services.

[1431] A "product database" is a database that contains various product information and is used to search for related products based on search keywords.

[1432] "History data" refers to data that stores search keywords entered by the user in the past and the search results.

[1433] "Features" are specific requirements or attributes of the product or service that a user is looking for.

[1434] A "generative AI model" is a system that uses generative artificial intelligence algorithms to automatically generate new ideas and proposals based on input data.

[1435] "Pseudo-products" are products or services that do not actually exist but are close to what the user wants, generated based on the user's search keywords and emotional data.

[1436] A "product page" is a web page or application screen that displays detailed information (product name, description, price, image, etc.) about a pseudo-product or custom-made product.

[1437] "Feedback" is data that records the user's opinions and requests regarding the presented pseudo-product.

[1438] The "emotion engine" is a system that analyzes the emotions of users when they enter search keywords or feedback.

[1439] A "prompt" is a context or instruction to be input into a generative AI model, and includes the user's search keywords and emotional data.

[1440] A "custom-made product" is a product or service that is individually created to reflect a user's specific requests and feedback.

[1441] The system embodying this invention uses the following procedures and devices to generate and provide custom-made products based on a user's search keywords and emotion data.

[1442] Hardware and Software

[1443] Hardware: Smartphones, servers.

[1444] Software: sentiment_analysis and ai_model modules for natural language processing.

[1445] Overview of data processing and calculation

[1446] Search keyword reception

[1447] A user uses a smartphone to input keywords to search for a product or service they wish to reserve or purchase. The device then sends the search keywords to the server. The server saves the received search keywords and simultaneously activates an emotion engine to analyze the user's emotions.

[1448] Search product database and save results

[1449] The server searches the product database for the searched keyword and evaluates whether there is a matching product or a similar product. If there are no matching products or if the user does not click on the presented product, the server saves the search keyword and the results in the database.

[1450] Historical data analysis and feature extraction

[1451] The server analyzes the stored history data and extracts the characteristics of the product the user is looking for. Specifically, it analyzes search keywords, past search results, and user emotion data to understand the user's needs in detail.

[1452] Generating pseudo-products using generative AI models

[1453] Based on the extracted features and emotion data, a prompt sentence is input into a generative AI model to generate pseudo-products. Based on the input data, this model suggests products that best fit the user's requirements.

[1454] Product page generation and user presentation

[1455] The server generates a product page based on the detailed information of the generated pseudo-product (product name, description, price, image, etc.) and presents this product page to the smartphone user.

[1456] Feedback collection and analysis

[1457] The user checks the product page and inputs feedback, including requests and feelings about the product's color, size, additional features, etc. The server receives this feedback and analyzes it in detail.

[1458] Custom-made product creation and final proposal

[1459] The server then uses the generative AI model again based on the analysis results to generate a custom-made product. The generated product page is then finally presented to the user, who reviews it and decides to purchase.

[1460] Specific examples

[1461] Suppose a user uses a smartphone app to enter the search keywords "fast" and "quiet car." At the same time, the emotion engine analyzes the user's emotion at that time as "I want to relax." Based on this information, the server searches the database for relevant autonomous vehicles. If no matching vehicle is found, the keywords and emotion data are saved for later analysis.

[1462] By analyzing the accumulated historical data, the system can understand the user's requirements in detail and generate a simulated vehicle by inputting the following prompt sentences into the generative AI model:

[1463] Example prompt sentence:

[1464] Keywords: fast, quiet, car

[1465] Emotion: I want to relax

[1466] Based on this prompt, the generative AI model generates a "fast and quiet self-driving vehicle" and displays it as detailed information on the product page. It then further optimizes the product based on user feedback, ultimately presenting a custom-made self-driving vehicle proposal to the user.

[1467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1468] Step 1:

[1469] The user enters search keywords.

[1470] Input: A user types search terms such as "fast" or "quiet car" into a smartphone application.

[1471] Processing: The device sends the search keyword to the server.

[1472] Output: The search keywords are sent to the server.

[1473] Step 2:

[1474] The server starts an emotion engine and analyzes the user's emotions.

[1475] Input: The search keywords received in step 1.

[1476] Processing: The server launches the relevant emotion engine and analyzes the emotion generated when the user enters a search keyword, utilizing natural language processing technology.

[1477] Output: Emotional data (e.g., "I want to relax") is generated.

[1478] Step 3:

[1479] Search the product database and rate the relevant products.

[1480] Input: The search keywords received by the server.

[1481] Processing: The server searches the product database and evaluates whether there are any products that match the entered keywords.

[1482] Output: Hit count is calculated, e.g. 1 or 0 matching products found.

[1483] Step 4:

[1484] Save the search keywords and their results in a database.

[1485] Input: Search keyword and number of hits.

[1486] Processing: If there are no hits or the user does not click on any of the products presented, save the search keywords and search results to the database.

[1487] Output: Search keywords and search results are saved in a database.

[1488] Step 5:

[1489] Analyze historical data to gain a detailed understanding of user requirements.

[1490] Input: Saved search keywords and search result history data.

[1491] Processing: The server analyzes the history data and extracts the features of the product the user is looking for, including past history and emotional data.

[1492] Output: Extracted features (e.g., "fast" or "quiet") and emotion data.

[1493] Step 6:

[1494] Generate pseudo-products using generative AI models.

[1495] Input: Extracted features and sentiment data.

[1496] Processing: The server inputs a prompt sentence into the generative AI model based on the extracted features and emotion data, and generates a pseudo-product.

[1497] Example: "Keywords: fast, quiet, car" "Emotion: I want to relax"

[1498] Output: A pseudo-product (e.g., "Fast and quiet self-driving cars").

[1499] Step 7:

[1500] A product page is generated based on the information of the generated pseudo-product.

[1501] Input: Details of the pseudo-product.

[1502] Processing: The server generates a product page using the pseudo-product's detailed information (product name, description, price, image, etc.).

[1503] Output: A product page is generated.

[1504] Step 8:

[1505] Present the pseudo-product page to users and collect feedback.

[1506] Input: The generated product page.

[1507] Processing: The server sends the generated product page to the user's terminal and presents it to the user. The user checks the product page and enters feedback.

[1508] Output: User feedback.

[1509] Step 9:

[1510] Generate custom products based on user feedback.

[1511] Input: User feedback and sentiment data.

[1512] Processing: The server performs a detailed analysis of the received feedback and sentiment data, and again uses the generative AI model to generate a custom-made product.

[1513] Output: Optimized, tailor-made products.

[1514] Step 10:

[1515] The generated custom product page is presented to the user.

[1516] Input: Optimized custom-made product details.

[1517] Processing: The server generates the final product page based on the optimized custom-made product details and sends it to the user's device.

[1518] Output: The final product page is presented to the user.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] [Fourth embodiment]

[1523] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1524] 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.

[1525] 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).

[1526] 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.

[1527] 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.

[1528] 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).

[1529] 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. 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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."

[1536] MODE FOR CARRYING OUT THE INVENTION

[1537] The system for implementing this invention receives search keywords entered by a user, and generates and provides a custom-made product that meets the user's needs based on the keywords.

[1538] Program processing

[1539] 1. Enter keywords

[1540] User: Visits an e-commerce site and types keywords into the search box.

[1541] Terminal: Sends the entered search keywords to the server.

[1542] 2. Keyword analysis and history saving

[1543] server:

[1544] A search keyword is received and a product database is searched based on the keyword.

[1545] Calculate the number of hits and analyze the results. If there are zero hits or the user does not click, save the keyword and its search results to a database.

[1546] 3. Historical data analysis and pseudo-product generation

[1547] server:

[1548] The system retrieves and analyzes historical search keyword data stored in the database, and extracts the characteristics of the products the user is looking for based on the analysis results.

[1549] The extracted features are then input as prompts into a generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1550] 4. Generate a pseudo-product page

[1551] server:

[1552] Build detailed product pages based on the generated pseudo-products.

[1553] The product page includes the generated product name, description, price, and image.

[1554] 5. Present to users and gather feedback

[1555] server:

[1556] The generated pseudo-product page is displayed on the screen to the user.

[1557] User:

[1558] Review the product page provided and submit feedback, including requests for color, size, additional features, etc.

[1559] 6. Feedback analysis and product generation

[1560] server:

[1561] Receive and analyze user feedback in detail.

[1562] Based on the analysis results, the AI ​​model is used again to generate a custom product, incorporating new product names, descriptions, images, etc.

[1563] 7. Final product proposal and order acceptance

[1564] server:

[1565] The final custom product page is displayed to the user.

[1566] User:

[1567] Check the product page provided and decide to purchase.

[1568] Specific examples

[1569] If a user types in "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses a generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with a description and image.

[1570] The generated product page is presented to the user, who then submits feedback such as "I would like a slightly larger size" or "I wish there was a blue variation." The server analyzes this feedback and again uses the AI ​​model to generate a custom-made product. Ultimately, the user decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[1571] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[1572] The processing flow will be explained below.

[1573] Step 1:

[1574] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[1575] Step 2:

[1576] Device: Send the entered search keyword "large-capacity heat-resistant glass teacup" to the server.

[1577] Step 3:

[1578] Server: Receives search keywords. Searches the product database based on the received keywords and calculates the number of related product hits.

[1579] Step 4:

[1580] Server: Check that there are no hits. Or, if the user does not click on the product, save the search keywords and search results to the database. The search results are also saved along with the timestamp and user ID.

[1581] Step 5:

[1582] Server: Analyzes the search keywords and search result history data stored in the database. As a result of the analysis, the characteristics of the product the user is looking for are extracted. For example, characteristics such as "heat-resistant," "glass," "large capacity," and "teacup" are extracted.

[1583] Step 6:

[1584] Server: Inputs the extracted features as prompts into the generative AI model. The generative AI model is used to automatically generate pseudo-products. The generated pseudo-products include product names, descriptions, and images.

[1585] Step 7:

[1586] Server: Generates a product page based on the details of the generated pseudo-product. Specifically, it builds a page that includes the product name, description, price, and image.

[1587] Step 8:

[1588] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[1589] Step 9:

[1590] User: Review the provided mock product page and enter feedback about the product, including requests for color, size, and additional features.

[1591] Step 10:

[1592] Terminal: Sends the feedback entered by the user to the server.

[1593] Step 11:

[1594] Server: Receives feedback from users, analyzes the feedback, and uses the AI ​​model to generate a custom-made product based on the analysis results.

[1595] Step 12:

[1596] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1597] Step 13:

[1598] User: Review the final product page presented to them and ensure all requirements are met.

[1599] Step 14:

[1600] User: Makes a purchase decision on the final product page and orders a custom product.

[1601] In this way, the system of the present invention can efficiently and effectively execute a series of processes from when a user inputs search keywords to when they purchase a custom-made product. By performing specific operations at each step, the system reduces user disappointment and provides optimal products.

[1602] Example 1

[1603] 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."

[1604] Traditional e-commerce systems often fail to display satisfactory products for the search keywords entered by users. As a result, users are often unable to find the product they are looking for and are left feeling disappointed. Furthermore, when users have specific requirements, there is a lack of a mechanism to suggest customized products that meet those requirements. This leads to a poor customer experience and missed sales opportunities.

[1605] 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.

[1606] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a data store, means for analyzing history data of the saved search keywords and extracting features desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a detailed information page based on detailed information about the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, and means for presenting the generated custom-made product page to the user. This enables product suggestions that accurately reflect the user's search intent, improving the user experience and increasing sales opportunities.

[1607] A "user" is a user who accesses the system and inputs search keywords.

[1608] A "search keyword" is a string of characters that a user enters into a search box and is used to search for products.

[1609] A "database" is a data structure or system that stores product information corresponding to search keywords.

[1610] The "number of hits" refers to the number of related products retrieved from the database based on the search keyword.

[1611] A "data store" is a storage device or system for storing search keywords and their search results.

[1612] "History data" refers to data on search keywords and search results that have been saved in the past.

[1613] "Features" are a collection of product characteristics and elements that a user desires, extracted by analyzing historical data.

[1614] A "generative AI model" is an algorithm or technology that uses artificial intelligence to generate pseudo-products based on user requests.

[1615] "Pseudo-products" are product information virtually created using generative AI models, which may not actually exist.

[1616] A "details page" is a web page that contains product details such as the name, description, price, and images of the pseudo-product.

[1617] "Feedback" refers to opinions and requests that users provide regarding the content of a pseudo-product page after checking it.

[1618] "Custom-made products" are items specially created using generative AI models based on user feedback.

[1619] "Means of generating" refers to the technical methods or processes by which a program or system performs a specific function.

[1620] This invention is a system that generates and provides custom-made products that meet the user's needs based on search keywords entered by the user. By entering specific keywords, the system automatically suggests products that best suit the user's needs and provides further customized custom-made products.

[1621] Hardware and software configuration

[1622] This system mainly uses the following hardware and software:

[1623] Server: A server with a powerful processor and large memory performs search keyword analysis, database lookup, runs the generative AI model, and analyzes feedback. This server can be, for example, an Apache web server or an Nginx web server.

[1624] Database: A relational database management system (RDBMS) is used to store product information and search history data. Specifically, MySQL or PostgreSQL is preferred.

[1625] Generative AI model: To generate pseudo-products based on user requests, we use a generative AI model (e.g., OpenAI's GPT-3). This model takes appropriate prompts as input and generates text and images.

[1626] Terminal: The devices that users use to access the site include various devices such as PCs, tablets, smartphones, etc. These terminals connect to the server via a web browser.

[1627] Specific methods for data processing and calculation

[1628] This system receives search keywords entered by the user and performs the following processing based on those keywords.

[1629] 1. Keyword analysis: The server receives the keywords entered by the user and searches the database for related product information, using SQL queries to quickly retrieve data.

[1630] 2. Historical Data Storage: If the user does not click or if there are zero hits, the search keywords and their search results are stored in the database. This is usually done using an INSERT or UPDATE query.

[1631] 3. Feature extraction: The server analyzes the saved search history data and extracts the features of the product the user is looking for (e.g., "heat-resistant glass," "large capacity," "teacup," etc.). This analysis may use natural language processing (NLP) technology.

[1632] 4. Generate pseudo-products: Generate pseudo-products by inputting the extracted features into a generative AI model as prompts. For example, the following prompts can be used:

[1633] Prompt: "Create a product with heat-resistant glass, large capacity, and the characteristics of a teacup."

[1634] 5. Product page generation: A detailed information page is constructed based on the generated pseudo-product, using an HTML template to embed the necessary information such as product name, description, price, and images.

[1635] 6. Feedback collection and analysis: The user reviews the product page and provides feedback, including specific requests for color, size, additional features, etc. The server analyzes this feedback and generates an improved, custom-made product, again using the generative AI model.

[1636] Specific example explanation

[1637] Let's take the example of a user entering the search keyword "large-capacity heat-resistant glass teacup." In this case, the server first receives this keyword and searches the product database. If no related products are found, the server saves this keyword in the database and records it as historical data. The server then analyzes the historical data and extracts key features. These features are input into the generative AI model as prompt sentences to generate pseudo-products.

[1638] The generated pseudo-product includes the product name "Large Capacity Heat-Resistant Glass Teacup," along with its description and image. This product page is presented to the user, who provides feedback such as "I wish it was a little larger" and "I wish it came in blue." The server analyzes this feedback and again uses the AI ​​model to generate a custom product. Finally, the new product page is displayed to the user, who decides to purchase the "Large Capacity Custom Heat-Resistant Glass Teacup."

[1639] In this way, the present invention realizes a system that provides optimal products based on the keywords searched by the user, thereby reducing disappointment.

[1640] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1641] Step 1:

[1642] User: Visits an e-commerce site and types a search term like "large capacity heat-resistant glass teacup" into the search box.

[1643] Specific actions: A user opens a web browser, enters a URL, accesses a site, enters a desired keyword in the search box, and presses the search button.

[1644] Input: Search keyword

[1645] Output: A search request is sent to the server

[1646] Step 2:

[1647] Terminal: Sends the entered search keywords to the server.

[1648] Specific operation: The data from the search form is sent to the server as an HTTP request.

[1649] Input: The search term entered by the user

[1650] Output: HTTP request sent to server

[1651] Step 3:

[1652] Server: Receives search keywords and searches the database for related products.

[1653] Specific operation: The server extracts the search keywords from the HTTP request and executes an SQL query against the database.

[1654] Input: Search keyword

[1655] Output: A list of related products retrieved from the database

[1656] Step 4:

[1657] Server: Calculate the number of hits and analyze the results. If there are zero hits or the user does not click on a related product, save the search keywords and their search results to the data store.

[1658] What it does: Analyzes the query results and counts the number of hits. If there are zero hits or the user doesn't click on a result, it saves the keywords and results to the data store using an INSERT or UPDATE SQL query.

[1659] Input: Query results from the database

[1660] Output: Search keywords and results stored in the data store

[1661] Step 5:

[1662] Server: Analyzes the history data of saved search keywords and extracts the characteristics of the products the user is looking for.

[1663] Specific operation: Historical data is retrieved by scheduled jobs or triggers, and natural language processing (NLP) techniques are used to extract the features desired by the user.

[1664] Input: Historical data stored in a data store

[1665] Output: A set of extracted features

[1666] Step 6:

[1667] Server: The extracted features are input as prompts into the generative AI model to generate pseudo-products.

[1668] Specific operation: Send a prompt to the API of a generative AI model (e.g., GPT-3) and receive the generated text and images.

[1669] Input: Extracted features

[1670] Output: Generated pseudo-product information (product name, description, image, etc.)

[1671] Step 7:

[1672] Server: Generates a product page based on the details of the generated pseudo-product.

[1673] What it does: Embeds generated product information into an HTML template. Styles and generates the page using the necessary CSS and JavaScript.

[1674] Input: Details of the pseudo-product

[1675] Output: Completed product page HTML

[1676] Step 8:

[1677] Server: Presents the generated pseudo-product page to the user.

[1678] Specific operation: The product page is sent to the user's browser as an HTTP response.

[1679] Input: HTML for product page

[1680] Output: The product page that is displayed in the user's browser

[1681] Step 9:

[1682] User: Review the product page provided and provide feedback.

[1683] Specific actions: Refer to the product page, enter desired color, size, additional features, etc. in the feedback form, and press the submit button.

[1684] Input: Feedback information (new request)

[1685] Output: Feedback is sent to the server

[1686] Step 10:

[1687] Server: Receives and analyzes user feedback in detail.

[1688] Specific operation: Receives feedback data and creates and sends prompts to generate customized products using the generative AI model again.

[1689] Input: User feedback

[1690] Output: Improved custom product information

[1691] Step 11:

[1692] Server: Presents the generated custom product page to the user.

[1693] Specific operation: Reconstruct an HTML page based on the new product information and present it to the user.

[1694] Input: Improved custom product details

[1695] Output: The final product page is displayed in the user's browser

[1696] (Application example 1)

[1697] 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."

[1698] On traditional e-commerce sites, when a user searches for a specific product, if that product does not exist, the user cannot find the product they are looking for, resulting in a decrease in satisfaction. Furthermore, the site does not offer similar products or custom-made options, which means it is unable to meet the diverse needs of users. Furthermore, there is a lack of a mechanism for utilizing feedback to generate products that meet user requests.

[1699] 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.

[1700] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, and means for providing the generated pseudo-product in a format displayable on a specific hardware device, i.e., a smart device. This allows similar products or custom-made products to be presented when a user searches for a specific product even if the product does not exist, thereby improving user satisfaction.

[1701] A "search keyword" is a string of characters that a user enters when searching for a specific product or service.

[1702] A "product database" is a database in which information about each product or service is systematically stored.

[1703] "Hits" is the number of related products found in the database based on a particular search keyword.

[1704] A "database" is a system for efficiently storing, searching, and managing large amounts of data.

[1705] "History data" refers to data that stores a user's past search keywords and the results thereof.

[1706] "Features" are important attributes or characteristics of a product that users desire.

[1707] A "generative AI model" is a model that uses artificial intelligence technology to automatically generate new products and designs.

[1708] A "pseudo-product" is a virtual product generated based on a user's search intent.

[1709] "Detailed information" is specific information about the product, including the product name, description, price, and image.

[1710] A "product page" is a web page for presenting product information to a user.

[1711] "Feedback" refers to evaluations and opinions provided by users, and is information that serves as a reference for product improvement.

[1712] A "custom product" is a product that is customized based on a user's specific requirements.

[1713] A "smart device" is an electronic device that has Internet connectivity and can run a variety of applications.

[1714] The system embodying the present invention generates and provides custom-made products based on user search keywords. The specific configuration and processing steps of this system will now be described.

[1715] First, a user accesses an e-commerce site via a device such as a smartphone and enters keywords into the search box. The device sends the entered search keywords to the server. The server searches a product database based on the received search keywords and calculates the number of hits. If no search results are found, the search keywords and the search results are saved in the database.

[1716] The server then analyzes the saved search keyword history data to extract the features of the product the user is looking for. These extracted features are input as prompts into a generative AI model to generate a pseudo-product. The generated pseudo-product includes detailed information such as the product name, description, and images. The server then generates a product page based on this information and presents it to the user.

[1717] The user reviews the product page presented to them and submits feedback, which may include requests for color, size, additional features, etc. The server receives and analyzes the user's feedback. Based on the analysis results, the generative AI model is used again to generate a custom-made product that reflects the user's feedback. Finally, the generated custom-made product page is presented to the user, and the purchase is confirmed.

[1718] The system configuration includes the following major hardware and software components:

[1719] Smart device: A terminal where users can enter search keywords and view and purchase custom-made products.

[1720] Server: Analyzes search keywords, searches the product database, analyzes feedback, and generates products using a generative AI model.

[1721] Generative AI models: Artificial intelligence techniques for generating pseudo-goods and custom-made products based on user requirements.

[1722] Database Management System (DBMS): Stores and manages search keywords and historical data.

[1723] For example, if a user enters "large-capacity heat-resistant glass teacup," the server receives this keyword and searches the product database. If there are no search results, the server saves the keyword in the database. It analyzes the accumulated keyword history data and extracts the characteristics "heat-resistant glass," "large capacity," and "teacup." It then uses the generative AI model to generate a pseudo-product, creating a product name, for example, "large-capacity heat-resistant glass teacup," along with its description and image.

[1724] Examples of specific prompts to input to a generative AI model:

[1725] Create a product based on these features: {"material": "Heat-resistant glass", "size": "Large capacity", "type": "Teacup"}

[1726] This prompt is then fed into a generative AI model to generate custom product suggestions, which can then be further customized based on collected feedback to provide the perfect product for the user.

[1727] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1728] Step 1:

[1729] A user accesses an e-commerce site through a device such as a smartphone and enters keywords into the search box. The device then sends the entered search keywords (input data) to the server (the output data is the search keywords). Specifically, the user enters the keyword "large-capacity heat-resistant glass teacup," which is then transferred to the server.

[1730] Step 2:

[1731] The server searches the product database based on the received search keywords (input data is the search keywords). As a result, it calculates the number of matching products in the product database (output data is the number of hits) and obtains this number of hits. For example, if the number of hits is zero, the result is also saved.

[1732] Step 3:

[1733] If the server does not get any search results, it saves the search keywords and the search results in a database (the input data is the search keywords and the number of hits). The saved data includes the keyword the user searched for, "large-capacity heat-resistant glass teacup," and the results.

[1734] Step 4:

[1735] The server analyzes the history data of saved search keywords (input data are past search keywords saved in the database). Through this analysis, the features of the product the user is looking for are extracted (output data are the extracted features). For example, the extracted features are "heat-resistant glass," "large capacity," and "teacup."

[1736] Step 5:

[1737] The server inputs the extracted features into a generative AI model (the input data is the extracted features). The generative AI model receives these features as prompts and generates a pseudo-product (the output data is the pseudo-product). For example, the generative AI model generates a pseudo-product called a "large-capacity heat-resistant glass teacup."

[1738] Step 6:

[1739] The server generates a product page based on the detailed information of the generated pseudo-product (input data is detailed information of the pseudo-product). The product page includes the product name, product description, price, image, etc. (output data is the product page). For example, a product page for "large-capacity heat-resistant glass teacup" is generated.

[1740] Step 7:

[1741] The server presents the generated product page to the user and collects feedback (the input data is the generated product page). For example, the user sends feedback such as "I want a bigger size" (the output data is the user feedback).

[1742] Step 8:

[1743] The server analyzes the user feedback (input data is the user feedback) and generates a custom-made product using the generative AI model again based on the results (output data is a customized custom-made product). For example, a new "custom heat-resistant glass large-capacity teacup" is generated based on the feedback.

[1744] Step 9:

[1745] The server presents the final custom-made product page to the user (input data is the customized custom-made product). The user reviews this page and decides to purchase (output data is the final custom-made product page). For example, the user reviews the new product page and decides to purchase a "Custom Heat-Resistant Glass Large Capacity Teacup."

[1746] 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.

[1747] MODE FOR CARRYING OUT THE INVENTION

[1748] The system embodying this invention receives search keywords entered by a user and generates and provides a custom-made product that meets the user's needs based on those keywords. Furthermore, the system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotions when entering search keywords and collecting feedback, and generating products that reflect those emotions.

[1749] Program processing

[1750] 1. Enter keywords

[1751] User: Visits an e-commerce site and types keywords into the search box.

[1752] Terminal: Sends the entered search keywords to the server.

[1753] Server: Receives search keywords and activates the emotion engine to recognize the user's emotions when entering search keywords.

[1754] 2. Keyword analysis and history saving

[1755] Server: Searches the product database based on the search keywords and calculates the number of related product hits.

[1756] Server: Checks if there are zero hits or if the user does not click on the product. If so, stores the search keywords and search results in a database, along with a timestamp, user ID, and user sentiment data.

[1757] 3. Historical data analysis and pseudo-product generation

[1758] Server: Acquires and analyzes search keywords, search result history data, and sentiment data stored in the database. As a result of the analysis, the characteristics of the products the user is looking for are extracted.

[1759] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1760] 4. Generate a pseudo-product page

[1761] Server: Builds detailed product pages based on the generated pseudo-products. Specifically, it generates pages that reflect the product name, product description, price, images, and user sentiment data.

[1762] 5. Present to users and gather feedback

[1763] Server: The generated pseudo-product page is sent to the user's device and presented to the user. The presented page includes an interface for inputting feedback.

[1764] User: Review the presented product page and enter feedback, including requests for color, size, additional features, and their emotions while entering the feedback.

[1765] Device: Sends user emotion data along with feedback to the server.

[1766] 6. Feedback analysis and product generation

[1767] Server: Receives user feedback and emotion data and analyzes it in detail.

[1768] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[1769] 7. Final product proposal and order acceptance

[1770] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1771] User: Review the final product page presented to them and ensure all their requirements are met. Confirm purchase and order the custom product.

[1772] Specific examples

[1773] If a user types in "large-capacity heat-resistant glass teacup," the server uses this keyword and the emotion engine to recognize that the user is "excited." The server searches the product database based on this keyword and the user's emotion data, and confirms that there are no hits. The search keyword, search results, and emotion data are saved in the database.

[1774] The accumulated keyword history and sentiment data are analyzed to extract the characteristics of "heat-resistant glass," "large capacity," and "teacup," as well as the sentiment of "excited." A generative AI model is then used to generate pseudo-products, such as a product name such as "Large capacity heat-resistant glass teacup," along with a description, image, and sentiment data such as "This teacup is made of heat-resistant glass, has a large capacity, and is particularly suitable for hot drinks."

[1775] The generated product page is presented to the user, who then enters "I'm looking forward to it" along with the feedback that "I want the blue one too." The server then analyzes this feedback and emotion data again to generate a custom-made product. The final "Custom Heat-Resistant Glass Large Capacity Teacup" product page is presented to the user, who then decides to purchase.

[1776] In this way, the system of the present invention provides optimal custom-made products based on the user's search keywords and emotional data, reducing disappointment for the user.

[1777] The processing flow will be explained below.

[1778] Step 1:

[1779] User: Visits an e-commerce site and types "large capacity heat-resistant glass teacups" into the search box.

[1780] Step 2:

[1781] Device: Send the keyword "large capacity heat-resistant glass teacup" entered in the search box to the server.

[1782] Step 3:

[1783] Server: Receives search keywords. At the same time, it activates the emotion engine and recognizes the user's emotion when entering the search keywords. For example, it determines that the user is "excited."

[1784] Step 4:

[1785] Server: Query the search keywords against the product database and calculate the number of related product hits.

[1786] Step 5:

[1787] Server: Check that there are zero hits, or if the user does not click on the product, store the user's sentiment data in a database along with the search keywords and search results.

[1788] Step 6:

[1789] Server: Analyzes search keywords and search result history data stored in the database, as well as emotion data. As a result of the analysis, the characteristics of the product the user is looking for (e.g., "heat-resistant," "glass," "large capacity," "teacup") and emotion (e.g., "excited") are extracted.

[1790] Step 7:

[1791] Server: The extracted features and user emotion data are input as prompts into the generative AI model to automatically generate pseudo-products, including product names, descriptions, and images.

[1792] Step 8:

[1793] Server: Generates a product page based on the generated pseudo-product details. The product page includes the product name, description, price, image, and user sentiment data.

[1794] Step 9:

[1795] Server: Sends the generated pseudo-product page to the user's device and presents it to the user.

[1796] Step 10:

[1797] User: Review the presented mock product page and enter feedback about the product, including requests for color, size, additional features, and their emotions while entering the feedback.

[1798] Step 11:

[1799] Terminal: Sends user-entered feedback and emotion data to the server.

[1800] Step 12:

[1801] Server: Receives user feedback and emotion data and analyzes them in detail. For example, it analyzes feedback such as "I want blue too" and emotion such as "I'm looking forward to it."

[1802] Step 13:

[1803] Server: Based on the analysis results, the generative AI model is used again to generate a custom product, incorporating new product names, descriptions, images, and user sentiment data.

[1804] Step 14:

[1805] Server: Sends the final generated custom product page to the user's device and presents it to the user.

[1806] Step 15:

[1807] User: Checks the final custom product page, confirms that all requirements are met, requests revisions as necessary, and finally decides to purchase.

[1808] In this way, the system of the present invention incorporates the emotional information entered by the user along with the search keywords and executes a process to generate optimal custom-made products based on that information, thereby reducing disappointment for users and providing more appropriate products.

[1809] Example 2

[1810] 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."

[1811] In traditional e-commerce systems, if the product searched for by the user is not accurately hit, it is difficult for the user to find a product that meets their needs. Furthermore, because the system does not take into account the user's emotions, the specific product characteristics desired by the user are often not reflected. Furthermore, it is difficult to reflect user feedback in real time and generate a custom-made product. This results in a poor user experience and potentially leads to lost sales opportunities.

[1812] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and their search results in a database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features and the user's emotions, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on the user's feedback and emotion data, and means for presenting the generated custom-made product page to the user. This makes it possible to provide an optimal custom-made product based on the user's search keywords and emotions, improving the user experience and increasing sales.

[1813] A "user" is an individual or corporation that uses this system and enters search keywords to search for and purchase products.

[1814] A "search keyword" is a word or phrase that a user enters into the system and is information that identifies the product the user is looking for.

[1815] The "product database" is a database containing product information stored within the system, and is used to provide product information corresponding to search keywords.

[1816] The "number of hits" indicates the number of related products found in the product database based on the search keyword.

[1817] An "emotion engine" is a software or hardware function that recognizes and analyzes a user's emotions when they enter search keywords.

[1818] "History data" refers to data that includes keywords that a user has searched for in the past and the results of those searches, emotional data, and other related information.

[1819] A "generative AI model" is an artificial intelligence model that automatically generates text, images, etc. based on input prompts, for example, using machine learning algorithms.

[1820] "Pseudo-products" are virtual products that do not exist in real inventory but are created to meet user requirements.

[1821] A "product page" is a web page that contains product information presented to a user, including the product name, description, price, image, and emotion data.

[1822] "Feedback" refers to the input of opinions, requests, and emotional data from users, including evaluations of the provided products and requests for additional items.

[1823] "Custom-made products" are items that are customized based on user feedback and sentiment data.

[1824] "Emotion data" is data that indicates the emotional state of the user when entering search keywords or feedback.

[1825] MODE FOR CARRYING OUT THE INVENTION

[1826] The system for implementing this invention allows a user to input search keywords, and generates and provides custom-made products that meet the user's needs based on those keywords. This system incorporates an emotion engine that recognizes the user's emotions, and has the function of analyzing the user's emotional data and generating products that reflect those emotions.

[1827] Main system components

[1828] The system consists of the following main components:

[1829] 1. Search keyword receiving method

[1830] It starts when a user enters a keyword into the search box on their device. An example of an input would be "large-capacity heat-resistant glass teacup."

[1831] 2. Product database search method

[1832] Based on the search keywords received, the server performs a database search and calculates the number of related product hits, using either an SQL database or a NoSQL database.

[1833] 3. How to save search results

[1834] If there are no hits or the user does not click on the suggested product, the server stores the search keywords and results in a database, including a timestamp, user ID, and sentiment data.

[1835] 4. Historical Data Analysis Methods

[1836] The server analyzes the historical data stored in the database and extracts the characteristics of the products desired by the user. The historical data includes past search keywords, search results, and emotional data.

[1837] 5. Generative AI Models

[1838] The server inputs the analyzed features and the user's emotional data as a prompt into a generative AI model (e.g., GPT-4 or other machine learning model) to generate a pseudo-product. An example of this prompt would be, "The user excitedly searched for 'large-capacity heat-resistant glass teacup.'"

[1839] 6. Product page generation method

[1840] The server builds a detailed product page based on the generated pseudo-product, including the product name, description, price, image, and user sentiment data generated by the generative AI model.

[1841] 7. Feedback Collection Methods

[1842] The server sends the generated product page to the user's device and collects feedback. The user checks the product page and enters their requests for color, size, additional features, and their feelings at the time of input into a feedback form.

[1843] 8. Means of creating custom products

[1844] The server receives and analyzes user feedback and emotion data. Based on the analysis results, the generative AI model is used again to generate a custom-made product. For example, if the user provides feedback such as "I also want blue," the server generates product details that correspond to this.

[1845] 9. Final product page presentation method

[1846] The server sends the final generated custom product page to the user's device, where the user confirms that all of their requests have been fulfilled, including the new product name, description, image, and emotion data.

[1847] Specific examples

[1848] If a user enters "large-capacity heat-resistant glass teacup," the server searches the product database using this keyword and confirms that there are zero hits. It then saves the search keyword, search results, and the user's "excited" emotional data. Based on the analysis, the generative AI model generates a pseudo-product called "large-capacity heat-resistant glass teacup" and builds a product page. If the user provides feedback such as "I also want blue," the server uses this feedback to again use the generative AI model to generate the final custom-made product. In this way, the optimal custom-made product is provided based on the user's search keyword and emotional data.

[1849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1850] Step 1:

[1851] A user visits an e-commerce site and enters keywords into the search box.

[1852] Input: The search term entered by the user (e.g., "large-capacity heat-resistant glass teacup").

[1853] What happens: A user uses the keyboard to type characters into the search box and presses the enter key.

[1854] Output: Keyword input data is generated.

[1855] Step 2:

[1856] The terminal transmits the entered search keyword to the server.

[1857] Input: Keyword input data.

[1858] Specific operation: The device's web browser sends the keyword input data to the server as an HTTP POST request.

[1859] Output: The server receives the search keywords.

[1860] Step 3:

[1861] The server receives the search keywords and activates an emotion engine to recognize the user's emotions.

[1862] Input: Search keyword.

[1863] Specific operation: Calls the emotion recognition API implemented in the server and analyzes emotions based on the user's facial expressions, input speed, etc.

[1864] Output: Search keywords and sentiment data.

[1865] Step 4:

[1866] The server searches the product database based on the search keywords and calculates the number of hits for related products.

[1867] Input: Search keyword.

[1868] What it does: Searches a database using an SQL query and retrieves a result set.

[1869] Output: Number of hits and search results.

[1870] Step 5:

[1871] The server checks that there are zero hits or the user does not click on any of the products offered, in which case the search keywords and search results are saved in a database.

[1872] Input: number of hits, search results, sentiment data.

[1873] Specific actions: Builds data for saving and executes an INSERT query against the database.

[1874] Output: Search history stored in a database.

[1875] Step 6:

[1876] The server retrieves and analyzes the historical data stored in the database, and extracts the features of the products desired by the user.

[1877] Input: Search history data, sentiment data.

[1878] Specific operations: Apply data analysis algorithms and machine learning models to extract features.

[1879] Output: Feature data.

[1880] Step 7:

[1881] The server inputs the extracted features and emotion data as prompts into the generative AI model to generate pseudo-products.

[1882] Input: feature data, emotion data.

[1883] Specific operations: Generate a prompt text, send an API request to the generative AI model, and retrieve the generated text and image.

[1884] Output: Pseudo-product data (product name, description, price, image).

[1885] Step 8:

[1886] The server builds a detailed product page based on the generated pseudo-product.

[1887] Input: Pseudo-product data.

[1888] Specific operation: Embed the generated data into a web page template and generate an HTML file.

[1889] Output: HTML data of product page.

[1890] Step 9:

[1891] The server generates a product page, which is then sent to the user's device and presented to them. It includes an interface for inputting feedback.

[1892] Input: HTML data for product page.

[1893] Specific operation: The HTML of the product page is sent to the terminal as an HTTP response.

[1894] Output: The product page is displayed on the user's device.

[1895] Step 10:

[1896] The user reviews the presented product page and enters feedback, including requests for color, size, additional features, and feelings.

[1897] Input: Check the product page and enter your feedback information.

[1898] Specific Action: Enter information into the feedback form and click the submit button.

[1899] Output: Feedback data is generated.

[1900] Step 11:

[1901] The terminal transmits the feedback data to the server.

[1902] Input: Feedback data.

[1903] Specific behavior: Feedback data is sent to the server as an HTTP POST request.

[1904] Output: The server receives the feedback data.

[1905] Step 12:

[1906] A server receives and analyzes the feedback data and emotion data.

[1907] Input: Feedback data, emotion data.

[1908] Specific operation: Analyze the feedback content using a data analysis algorithm.

[1909] Output: Analysis result data.

[1910] Step 13:

[1911] The server then uses the generated AI model based on the analysis results to generate a custom-made product.

[1912] Input: Analysis result data.

[1913] What it does: Generate an updated prompt and feed it into the generative AI model to get new text and images.

[1914] Output: Custom product data (new product name, description, and image).

[1915] Step 14:

[1916] The server transmits the final generated custom-made product page to the user's terminal for presentation.

[1917] Input: Custom-made product data.

[1918] Specific operation: Builds the HTML of the final product page and sends it to the terminal as an HTTP response.

[1919] Output: The final product page is displayed on the user's device.

[1920] Step 15:

[1921] The user reviews the final product page, confirms that all of their requirements are met, and finally makes the purchase decision and orders the custom-made product.

[1922] Enter: Check the final product page.

[1923] Specific Action: Click the purchase button to complete the purchase process.

[1924] Output: A custom-made product order is completed.

[1925] (Application example 2)

[1926] 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."

[1927] Conventional custom-made product provision systems generate products without considering the user's emotions, which results in the problem of not being able to fully meet the user's expectations. Furthermore, if no products related to the keywords entered by the user are found, it is difficult to suggest appropriate alternatives. This can lead to increased user disappointment and reduced customer satisfaction.

[1928] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1929] In this invention, the server includes means for receiving search keywords entered by a user, means for searching a product database for the search keywords and calculating the number of hits, means for saving the search keywords and the search results in the database, means for analyzing history data of the saved search keywords and extracting features of the product desired by the user, means for generating a pseudo-product using a generative AI model based on the extracted features, means for generating a product page based on detailed information of the generated pseudo-product, means for presenting the pseudo-product page to the user and collecting feedback, means for generating a custom-made product based on user feedback, means for presenting the generated custom-made product page to the user, means for recognizing and analyzing user emotions when entering search keywords and when collecting feedback, and means for inputting prompt sentences to the generative AI model based on the search keywords and emotion data entered by the user to generate a pseudo-product. This enables product generation that takes user emotions into consideration and makes it possible to provide custom-made products that meet user expectations.

[1930] "Search keywords" are words or phrases that users enter when searching for custom products or services.

[1931] A "product database" is a database that contains various product information and is used to search for related products based on search keywords.

[1932] "History data" refers to data that stores search keywords entered by the user in the past and the search results.

[1933] "Features" are specific requirements or attributes of the product or service that a user is looking for.

[1934] A "generative AI model" is a system that uses generative artificial intelligence algorithms to automatically generate new ideas and proposals based on input data.

[1935] "Pseudo-products" are products or services that do not actually exist but are close to what the user wants, generated based on the user's search keywords and emotional data.

[1936] A "product page" is a web page or application screen that displays detailed information (product name, description, price, image, etc.) about a pseudo-product or custom-made product.

[1937] "Feedback" is data that records the user's opinions and requests regarding the presented pseudo-product.

[1938] The "emotion engine" is a system that analyzes the emotions of users when they enter search keywords or feedback.

[1939] A "prompt" is a context or instruction to be input into a generative AI model, and includes the user's search keywords and emotional data.

[1940] A "custom-made product" is a product or service that is individually created to reflect a user's specific requests and feedback.

[1941] The system embodying this invention uses the following procedures and devices to generate and provide custom-made products based on a user's search keywords and emotion data.

[1942] Hardware and Software

[1943] Hardware: Smartphones, servers.

[1944] Software: sentiment_analysis and ai_model modules for natural language processing.

[1945] Overview of data processing and calculation

[1946] Search keyword reception

[1947] A user uses a smartphone to input keywords to search for a product or service they wish to reserve or purchase. The device then sends the search keywords to the server. The server saves the received search keywords and simultaneously activates an emotion engine to analyze the user's emotions.

[1948] Search product database and save results

[1949] The server searches the product database for the searched keyword and evaluates whether there is a matching product or a similar product. If there are no matching products or if the user does not click on the presented product, the server saves the search keyword and the results in the database.

[1950] Historical data analysis and feature extraction

[1951] The server analyzes the stored history data and extracts the characteristics of the product the user is looking for. Specifically, it analyzes search keywords, past search results, and user emotion data to understand the user's needs in detail.

[1952] Generating pseudo-products using generative AI models

[1953] Based on the extracted features and emotion data, a prompt sentence is input into a generative AI model to generate pseudo-products. Based on the input data, this model suggests products that best fit the user's requirements.

[1954] Product page generation and user presentation

[1955] The server generates a product page based on the detailed information of the generated pseudo-product (product name, description, price, image, etc.) and presents this product page to the smartphone user.

[1956] Feedback collection and analysis

[1957] The user checks the product page and inputs feedback, including requests and feelings about the product's color, size, additional features, etc. The server receives this feedback and analyzes it in detail.

[1958] Custom-made product creation and final proposal

[1959] The server then uses the generative AI model again based on the analysis results to generate a custom-made product. The generated product page is then finally presented to the user, who reviews it and decides to purchase.

[1960] Specific examples

[1961] Suppose a user uses a smartphone app to enter the search keywords "fast" and "quiet car." At the same time, the emotion engine analyzes the user's emotion at that time as "I want to relax." Based on this information, the server searches the database for relevant autonomous vehicles. If no matching vehicle is found, the keywords and emotion data are saved for later analysis.

[1962] By analyzing the accumulated historical data, the system can understand the user's requirements in detail and generate a simulated vehicle by inputting the following prompt sentences into the generative AI model:

[1963] Example prompt sentence:

[1964] Keywords: fast, quiet, car

[1965] Emotion: I want to relax

[1966] Based on this prompt, the generative AI model generates a "fast and quiet self-driving vehicle" and displays it as detailed information on the product page. It then further optimizes the product based on user feedback, ultimately presenting a custom-made self-driving vehicle proposal to the user.

[1967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1968] Step 1:

[1969] The user enters search keywords.

[1970] Input: A user types search terms such as "fast" or "quiet car" into a smartphone application.

[1971] Processing: The device sends the search keyword to the server.

[1972] Output: The search keywords are sent to the server.

[1973] Step 2:

[1974] The server starts an emotion engine and analyzes the user's emotions.

[1975] Input: The search keywords received in step 1.

[1976] Processing: The server launches the relevant emotion engine and analyzes the emotion generated when the user enters a search keyword, utilizing natural language processing technology.

[1977] Output: Emotional data (e.g., "I want to relax") is generated.

[1978] Step 3:

[1979] Search the product database and rate the relevant products.

[1980] Input: The search keywords received by the server.

[1981] Processing: The server searches the product database and evaluates whether there are any products that match the entered keywords.

[1982] Output: Hit count is calculated, e.g. 1 or 0 matching products found.

[1983] Step 4:

[1984] Save the search keywords and their results in a database.

[1985] Input: Search keyword and number of hits.

[1986] Processing: If there are no hits or the user does not click on any of the products presented, save the search keywords and search results to the database.

[1987] Output: Search keywords and search results are saved in a database.

[1988] Step 5:

[1989] Analyze historical data to gain a detailed understanding of user requirements.

[1990] Input: Saved search keywords and search result history data.

[1991] Processing: The server analyzes the history data and extracts the features of the product the user is looking for, including past history and emotional data.

[1992] Output: Extracted features (e.g., "fast" or "quiet") and emotion data.

[1993] Step 6:

[1994] Generate pseudo-products using generative AI models.

[1995] Input: Extracted features and sentiment data.

[1996] Processing: The server inputs a prompt sentence into the generative AI model based on the extracted features and emotion data, and generates a pseudo-product.

[1997] Example: "Keywords: fast, quiet, car" "Emotion: I want to relax"

[1998] Output: A pseudo-product (e.g., "Fast and quiet self-driving cars").

[1999] Step 7:

[2000] A product page is generated based on the information of the generated pseudo-product.

[2001] Input: Details of the pseudo-product.

[2002] Processing: The server generates a product page using the pseudo-product's detailed information (product name, description, price, image, etc.).

[2003] Output: A product page is generated.

[2004] Step 8:

[2005] Present the pseudo-product page to users and collect feedback.

[2006] Input: The generated product page.

[2007] Processing: The server sends the generated product page to the user's terminal and presents it to the user. The user checks the product page and enters feedback.

[2008] Output: User feedback.

[2009] Step 9:

[2010] Generate custom products based on user feedback.

[2011] Input: User feedback and sentiment data.

[2012] Processing: The server performs a detailed analysis of the received feedback and sentiment data, and again uses the generative AI model to generate a custom-made product.

[2013] Output: Optimized, tailor-made products.

[2014] Step 10:

[2015] The generated custom product page is presented to the user.

[2016] Input: Optimized custom-made product details.

[2017] Processing: The server generates the final product page based on the optimized custom-made product details and sends it to the user's device.

[2018] Output: The final product page is presented to the user.

[2019] 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.

[2020] 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.

[2021] 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 robot 414.

[2022] 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.

[2023] 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.

[2024] 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.

[2025] 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).

[2026] 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, motorcycles, and other devices, 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.

[2027] 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."

[2028] 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.

[2029] 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).

[2030] 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.

[2031] 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.

[2032] 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.

[2033] 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.

[2034] 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.

[2035] 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.

[2036] 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.

[2037] 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.

[2038] 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.

[2039] 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.

[2040] The following is further disclosed regarding the above embodiment.

[2041] (Claim 1)

[2042] means for receiving search keywords entered by a user;

[2043] A means for searching a product database for a search keyword and calculating the number of hits;

[2044] a means for storing search keywords and search results in a database;

[2045] A means for analyzing the history data of the saved search keywords and extracting the features of the product desired by the user;

[2046] A means for generating a pseudo-product using a generative AI model based on the extracted features;

[2047] A means for generating a product page based on detailed information of the generated pseudo-product;

[2048] means for presenting the pseudo-product page to users and collecting feedback;

[2049] a means for generating custom products based on user feedback;

[2050] means for presenting the generated customized product page to the user;

[2051] A system including:

[2052] (Claim 2)

[2053] 2. The system of claim 1, wherein the generated detailed information of the pseudo-product includes a product name, description, price, and image.

[2054] (Claim 3)

[2055] 2. The system according to claim 1, wherein if the number of hits for a search keyword is zero or if the user does not click, the search keyword and its search results are saved in a database.

[2056] "Example 1"

[2057] (Claim 1)

[2058] means for receiving search keywords entered by a user;

[2059] means for searching a database for search keywords and calculating the number of hits;

[2060] a means for storing search keywords and search results in a data store;

[2061] A means for analyzing the history data of saved search keywords and extracting the features desired by the user;

[2062] A means for generating a pseudo-product using a generative AI model based on the extracted features;

[2063] a means for generating a detailed information page based on the generated detailed information of the pseudo-product;

[2064] means for presenting the pseudo-product page to users and collecting feedback;

[2065] a means for generating custom products based on user feedback;

[2066] means for presenting the generated customized product page to the user;

[2067] A system including:

[2068] (Claim 2)

[2069] 2. The system of claim 1, wherein the generated pseudo-item detailed information includes a name, a description, a price, and an image.

[2070] (Claim 3)

[2071] 2. The system of claim 1, wherein the search keyword and its search results are saved in a data store when the number of hits for the search keyword is zero or the user does not select it.

[2072] "Application Example 1"

[2073] (Claim 1)

[2074] means for receiving search keywords entered by a user;

[2075] A means for searching a product database for a search keyword and calculating the number of hits;

[2076] a means for storing search keywords and search results in a database;

[2077] A means for analyzing the history data of the saved search keywords and extracting the features of the product desired by the user;

[2078] A means for generating a pseudo-product using a generative AI model based on the extracted features;

[2079] A means for generating a product page based on detailed information of the generated pseudo-product;

[2080] means for presenting the pseudo-product page to users and collecting feedback;

[2081] a means for generating custom products based on user feedback;

[2082] means for presenting the generated customized product page to the user;

[2083] A means for providing the generated pseudo-product in a format that can be displayed on a specific hardware, i.e., a smart device;

[2084] A system including:

[2085] (Claim 2)

[2086] 2. The system of claim 1, wherein the generated detailed information of the pseudo-product includes a product name, description, price, and image.

[2087] (Claim 3)

[2088] 2. The system according to claim 1, wherein if the number of hits for a search keyword is zero or if the user does not click, the search keyword and its search results are saved in a database.

[2089] "Example 2: Combining Emotion Engines"

[2090] (Claim 1)

[2091] means for receiving search keywords entered by a user;

[2092] A means for searching a product database for a search keyword and calculating the number of hits;

[2093] a means for storing search keywords and search results in a database;

[2094] A means for analyzing the history data of the saved search keywords and extracting the features of the product desired by the user;

[2095] A means for generating a pseudo-product using a generative AI model based on the extracted features and user emotions;

[2096] A means for generating a product page based on detailed information of the generated pseudo-product;

[2097] means for presenting the pseudo-product page to users and collecting feedback;

[2098] a means for generating a custom product based on user feedback and sentiment data;

[2099] means for presenting the generated customized product page to the user;

[2100] A system including:

[2101] (Claim 2)

[2102] 2. The system of claim 1, wherein the generated detailed information of the pseudo-product includes a product name, description, price, and image.

[2103] (Claim 3)

[2104] 2. The system according to claim 1, wherein if the number of hits for a search keyword is zero or if the user does not click, the search keyword, its search results, and emotion data are stored in the database.

[2105] "Application example 2 when combining emotion engines"

[2106] (Claim 1)

[2107] means for receiving search keywords entered by a user;

[2108] A means for searching a product database for a search keyword and calculating the number of hits;

[2109] a means for storing search keywords and search results in a database;

[2110] A means for analyzing the history data of the saved search keywords and extracting the features of the product desired by the user;

[2111] A means for generating a pseudo-product using a generative AI model based on the extracted features;

[2112] A means for generating a product page based on detailed information of the generated pseudo-product;

[2113] means for presenting the pseudo-product page to users and collecting feedback;

[2114] a means for generat...

Claims

1. means for receiving search keywords entered by a user; A means for searching a product database for a search keyword and calculating the number of hits; a means for storing search keywords and search results in a database; A means for analyzing the history data of the saved search keywords and extracting the features of the product desired by the user; A means for generating a pseudo-product using a generative AI model based on the extracted features; A means for generating a product page based on detailed information of the generated pseudo-product; means for presenting the pseudo-product page to users and collecting feedback; a means for generating custom products based on user feedback; means for presenting the generated customized product page to the user; A system including:

2. The system of claim 1 , wherein the generated detailed information of the pseudo-product includes a product name, a description, a price, and an image.

3. 2. The system according to claim 1, wherein if the number of hits for a search keyword is zero or if the user does not click, the search keyword and its search results are saved in the database.

Images