system

Abstract

We provide the system. [Solution] A means of providing an interface for processing requirements obtained from the user, A means for collecting product data from an e-commerce platform based on the said requirements, A method that uses a generative artificial intelligence model to analyze collected product data and generate optimal suggestions for user requirements, A means of sending the generated product suggestions to the user's terminal, A means for receiving user feedback on the proposal and generating a new product proposal, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In online shopping, it is difficult for users to quickly identify the products they want. This problem is particularly prominent for people who are not good at product searches or are busy, and generally requires a lot of time and effort. As a result, users often fail to reach their ideal products and compromise, and there is a problem that they cannot fully enjoy the convenience of online shopping.

Means for Solving the Problems

[0005] To address this challenge, the present invention proposes a system that provides an interface for processing user requirements and collects product data from an e-commerce platform based on these requirements. Furthermore, the collected product data is analyzed using a generative artificial intelligence model to generate product suggestions that are optimal for the user's requirements. These suggestions are sent to the user's terminal, and further suggestions can be made based on user feedback. This enables efficient product selection in online shopping.

[0006] An "interface" refers to the means by which a user interacts with a system to exchange information.

[0007] An "e-commerce platform" refers to a web-based system that enables online transactions of goods.

[0008] "Product data" refers to information about a specific product, including images, price, and description.

[0009] A "generative artificial intelligence model" refers to a system that uses machine learning algorithms designed for data analysis and prediction.

[0010] "Product proposal" refers to a presentation of information about products selected based on the user's requirements.

[0011] "User terminal" refers to electronic devices such as computers, smartphones, and tablets used by users.

[0012] "Feedback" refers to information such as opinions and suggestions for improvement provided by users to the system. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

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

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0034] This invention provides a system that offers an interface for users to quickly identify and obtain desired products. Users input their desired product requirements (e.g., color, brand, price range, etc.) into a chat interface on their device. This interface provides means for receiving and processing the user's input.

[0035] The terminal immediately transmits the user's requirements to the server. This server is connected to an e-commerce platform and has the means to collect product data based on the user's requirements. Specifically, the server accesses the relevant platform via the internet and collects images, prices, descriptions, etc., of products that are considered to match the requirements.

[0036] The server collects product data and then analyzes it using a generative artificial intelligence model. This AI model compares the input requirements information with the collected product data and has a means to suggest the most suitable product to the user. The suggested product includes product images, price information, and purchase links.

[0037] The generated product suggestions are sent from the server to the user's terminal. The user can review these suggestions on their terminal screen. The user can then determine if the suggested products meet their requirements, and if they feel they do not, they can use feedback to send new requirements or suggestions for improvement to the server. This feedback is used by the server to re-analyze the product data and generate new suggestions.

[0038] As a concrete example, consider a scenario where a user enters the requirements "blue sneakers, domestic brand, under 10,000 yen." The terminal sends this information to the server, which then collects information on matching sneakers from the corresponding e-commerce platform. A generative artificial intelligence model analyzes the information and generates optimal product suggestions, presenting the user with several options. This process allows the user to efficiently discover the desired product and make a purchase decision.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user enters the requirements for the desired product into the device's chat interface. Specifically, they specify the product's color, brand, price range, etc., in text format.

[0042] Step 2:

[0043] The terminal sends the requirements entered by the user to the server. This data transfer occurs in real time and uses a secure protocol.

[0044] Step 3:

[0045] The server analyzes the user's requirements. A generative artificial intelligence model extracts the necessary information from the user's requirements and sets criteria for use in product searches.

[0046] Step 4:

[0047] The server accesses the e-commerce platform's API to collect product data that meets the user's requirements. Specifically, it retrieves product images, prices, inventory information, descriptions, and other relevant data.

[0048] Step 5:

[0049] The server analyzes the collected product data using a generative artificial intelligence model. This model compares the content and selects the product that best matches the user's requirements.

[0050] Step 6:

[0051] The server generates product suggestions based on the analysis results. These suggestions include detailed information about suitable products and are formatted for display on the user's device.

[0052] Step 7:

[0053] The server sends the generated product suggestions to the user's terminal. Once the data transfer is complete, the terminal displays the received product suggestions on its screen.

[0054] Step 8:

[0055] The user reviews the product suggestions displayed on their device screen. If they are satisfied with the suggested products, they can access a link to proceed with the purchase.

[0056] Step 9:

[0057] If a user is not satisfied with the proposal, they can send feedback to the server via the chat interface. This includes redefining requirements or adding new conditions.

[0058] Step 10:

[0059] The server receives feedback from the user and collects and analyzes product data again based on the new requirements. New product suggestions are generated and sent back to the user.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Technology is needed to quickly identify the products consumers want and provide them with a suitable purchasing experience. Currently, consumers have to manually search through a vast amount of product information to find what suits their needs, which is time-consuming and laborious. Furthermore, inappropriate product suggestions can cause consumers stress. Solving this problem is essential.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for enabling data communication to process requests obtained from users, means for collecting information from a network marketplace, and means for analyzing the information using a machine learning algorithm and selecting the optimal product. This enables consumers to efficiently find products that meet their requirements and make purchasing decisions without stress.

[0065] "Requests obtained from users" refers to the preferences and requirements that consumers input as criteria for selecting products.

[0066] "Means that enable data communication" refers to technologies that have the functionality of communication protocols and interfaces for sending and receiving information between consumers and servers.

[0067] "Means of collecting information from network markets" refers to technologies for obtaining necessary product data from e-commerce platforms via the internet, and includes methods such as APIs and web scraping.

[0068] "Methods of analyzing information using machine learning algorithms" refer to algorithms that automatically evaluate collected product data and find the best option for consumer needs, and these may include neural networks and statistical models.

[0069] "Means for selecting the optimal product" refers to a function that automatically selects the product that best matches the consumer's needs from among multiple options based on analysis.

[0070] "Proposals containing purchase identifiers" refer to product proposals presented to consumers that include links or buttons to facilitate purchase.

[0071] The embodiments for carrying out the present invention will be described in detail below.

[0072] This invention begins with a user inputting the requirements for a specific product using a terminal. The user inputs the characteristics and conditions of the product they want (e.g., "blue sneakers, domestic brand, under 10,000 yen") as prompt text into the terminal's chat interface. The terminal recognizes this prompt text, converts it into the appropriate data format, and sends it to the server.

[0073] Based on the user's requirements received, the server uses APIs from multiple e-commerce platforms, such as major online malls and various e-commerce sites, via an internet-connected system to collect relevant product information. A secure communication protocol using HTTPS is employed for information collection.

[0074] Subsequently, the server analyzes the collected product information using a generative AI model. This AI model is implemented using machine learning libraries such as TENSORFLOW® and PyTorch, and employs advanced algorithms based on a large amount of training data for data analysis. The AI ​​compares the user's requirements with the data for each product and selects the most suitable product candidate.

[0075] The data for the suggested products (e.g., product name, price, image, purchase link) is sent from the server to the user's device. The device displays this information in a user-friendly format, allowing the user to intuitively evaluate the suggested products.

[0076] If a user is dissatisfied with a proposal, they can send new requirements or suggestions for improvement to the server through feedback. Based on this feedback, the server uses the AI ​​model to re-analyze the data and make revised suggestions, aiming to improve user satisfaction.

[0077] This system allows users to quickly and efficiently find products that meet their needs and make purchase decisions.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The user enters the requirements for the desired product as a prompt message into the chat interface via their device. This prompt message includes specific product characteristics and conditions (e.g., "blue sneakers, domestic brand, under 10,000 yen"). As a result of the input, the device generates data on the user's requirements.

[0081] Step 2:

[0082] The terminal formats the user's input requirements data and sends it to the server. Data formatting involves converting the user's natural language input into a structured data format (e.g., JSON). The output is the formatted data sent to the server.

[0083] Step 3:

[0084] The server requests product information from the e-commerce platform's API based on the user's requirements data received. Secure communication is ensured by including API keys and authentication information. The output is a collection of product data obtained from each platform.

[0085] Step 4:

[0086] The server analyzes the collected product data using a generative AI model. Machine learning algorithms are applied to compare and evaluate the user's requirements against the collected data. The input consists of requirement data and product data stored on the server, and the output is a list of highly suitable products. The server then selects the optimal recommendation based on the analysis results.

[0087] Step 5:

[0088] The server sends the selected, optimal product suggestions to the user's terminal in data format. This transmission uses JSON format data via a RESTful API. The output is product suggestion data that can be interpreted on the user's terminal.

[0089] Step 6:

[0090] The device displays received product suggestions on its screen, providing the user with visual information. A list including product names, images, prices, and purchase links is presented to the user. The user then reviews this list and makes selections and provides feedback.

[0091] Step 7:

[0092] Users input feedback on the proposed products via their terminals, including new requirements and improvement requests. The feedback data is sent to a server, which is then prepared to incorporate it into future proposals.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In today's world, it is difficult and time-consuming for consumers to efficiently select the right products from a vast amount of information. There is a need for a solution to this problem, enabling consumers to find products quickly and accurately.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for human-computer interaction to process requirements obtained from a user, means for collecting information from a digital marketplace platform based on those requirements, and means for analyzing the collected information and using a machine learning model to generate optimal suggestions for the user's requirements. This enables the user to efficiently obtain product information that meets their needs.

[0098] "Means of interaction between humans and computers" refers to interfaces that enable users and computers to exchange information through natural language or text.

[0099] A "digital marketplace platform" is an online trading infrastructure for buying and selling goods and services via the internet.

[0100] "Means of information gathering" refers to a system for collecting necessary information from the internet and other data sources.

[0101] A "machine learning model" is an algorithm that learns from data and provides the optimal output for a specific purpose.

[0102] A "computer device" is an electronic device capable of processing and storing information, and includes smartphones and personal computers.

[0103] "Enter product requirements by voice or text" means that the user communicates the specifications of the product they want to the system through speaking or keyboard input.

[0104] An "application that automatically provides relevant information" is a program that quickly presents relevant product data based on conditions entered by the user.

[0105] This invention utilizes a computer device (e.g., a smartphone) with an interface that allows the user to input product requirements via voice or text. Through this interface, the user can input product specifications without having to visit a store. The input information is then quickly transmitted to a server.

[0106] The server collects relevant information from the digital marketplace platform based on the user's requirements. The collected information is analyzed by a machine learning model (e.g., the "transformers" library) to generate product suggestions that best meet the user's requirements. These suggestions include product images, prices, and reference links.

[0107] The generated product suggestions are sent from the server to the user's computer, where the user can review them. If the suggestions do not meet the user's requirements, the user can provide feedback to the system. This feedback is processed by the server, a new suggestion is generated, and it is presented to the user again.

[0108] For example, if a user has the requirement "blue sneakers, Japanese brand, under 10,000 yen," the server will input this into a computer, gather relevant information, and suggest the best product. An example of a prompt would be, "When the user says 'blue sneakers, under 10,000 yen,' suggest only the best products." Through this process, users can easily and effectively select products and make purchasing decisions.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The user inputs the requirements for their desired product via voice or text through the computer's interface. This input includes product specifications (e.g., color, brand, price), and the computer retrieves this information and prepares to send it to the server. A "human interface device" is used to pre-process the input using natural language processing technology.

[0112] Step 2:

[0113] The terminal sends the acquired user requirements to the server. The server receives this input and, based on it, collects relevant product information from the digital marketplace platform. Using the entered keywords, information is collected using APIs and scraping techniques. The output is a data set of the relevant products.

[0114] Step 3:

[0115] The server analyzes the collected product information. Here, it uses a generative AI model (e.g., natural language understanding using "transformers") to select the product that best suits the user's requirements. The input is the collected data set, and the server performs data evaluation to identify the optimal product from it, outputting a list of highly suitable products.

[0116] Step 4:

[0117] The server generates product suggestions selected through analysis and sends this information to the terminal. The suggestions include product images, prices, and purchase links. The output here is a list of product suggestions that the user can review, allowing them to make specific product selections.

[0118] Step 5:

[0119] Users review the suggestions on their devices and provide feedback. This feedback may include satisfaction levels and new requirements. This feedback is sent to the server and used as input data to generate new product suggestions.

[0120] Step 6:

[0121] The server analyzes user feedback and uses the AI ​​model again to generate new suggestions. New user requirements are incorporated into the data, and steps 2 through 4 are repeated. This allows for more refined product suggestions, leading to improved user satisfaction.

[0122] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0123] This invention is a system that combines an emotion engine and provides an interface for users to quickly identify and obtain desired products. First, the user enters their desired product requirements into a chat interface via a terminal. This interface has the function of receiving user input in real time and sending it to the server.

[0124] The server analyzes the requirements entered by the user while simultaneously recognizing the user's emotional state through an emotion engine. The emotion engine infers emotions from the user's text input and generates data to adjust suggestions as needed. This information is considered a crucial factor in product selection by the generative artificial intelligence model.

[0125] The server accesses the e-commerce platform and collects appropriate product data based on the user's requirements and sentiments. Specifically, it retrieves product images, prices, descriptions, etc., from the platform's API. In this process, image recognition technology is also used to analyze the features of product images and identify products that meet the user's requirements.

[0126] The collected product data is analyzed using a generative artificial intelligence model. This model compares the product data with user requirements, including sentiment information, to select the most suitable product. The selected product is then reconstructed as a product suggestion, which includes detailed product information and a purchase link.

[0127] The generated product suggestions are sent to the user's device and displayed. The user can review these suggestions and select products they are satisfied with. If the user is dissatisfied with the suggestions, the sentiment engine checks the feedback and generates new suggestions as needed. These improved suggestions are then sent back to the device.

[0128] For example, if a user requests "blue sneakers, domestic brand, under 10,000 yen," and is in a negative and urgent emotional state, the server will use this information to quickly identify suitable products and highlight suggestions for items that can be delivered sooner. This system allows users to efficiently find products that meet their needs and proceed with their purchase.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The user enters the requirements for the desired product into the device's chat interface. This includes the product's color, brand, and price range.

[0132] Step 2:

[0133] The terminal transmits data entered by the user to the server in real time. During this process, the data is converted to an appropriate format and transferred using secure communication methods.

[0134] Step 3:

[0135] The server analyzes the received requirements data. Simultaneously, it activates the emotion engine to analyze the user's emotions from the input text information. This analysis is then used to refine the proposed content.

[0136] Step 4:

[0137] The server connects to the e-commerce platform's API and collects product data based on the user's requirements and emotional state. The collected data includes product images, prices, and detailed information, and is analyzed as needed using image recognition technology.

[0138] Step 5:

[0139] The server uses a generative artificial intelligence model to analyze collected product data and select the most suitable product based on user requirements and emotional state. This model optimizes itself by considering the characteristics of each product and the user's satisfaction and dissatisfaction.

[0140] Step 6:

[0141] The server generates product suggestions based on the selected product information. These suggestions include product images, prices, inventory information, and purchase links, formatted in a format suitable for the user's device.

[0142] Step 7:

[0143] The server sends the generated product suggestions to the user's device. A notification appears on the device so the user can immediately view and check the suggested items.

[0144] Step 8:

[0145] Users review the product suggestions displayed on their device and, if satisfied, click the purchase link included in the suggestion to proceed with the purchase. If dissatisfied, they can provide feedback via the chat interface.

[0146] Step 9:

[0147] The server receives user feedback and generates new suggestions. The user's requirements are redefined based on the feedback, and the sentiment engine takes this into consideration again.

[0148] Step 10:

[0149] The server generates improved product suggestions again and sends them back to the user's terminal. By repeating this process, the accuracy of the suggestions improves until the user is satisfied.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] Traditional e-commerce systems made it difficult for users to quickly identify the products they wanted, and also made it difficult for them to find products that suited their feelings and circumstances from among the suggested items. Furthermore, there was a lack of mechanisms to efficiently incorporate feedback into future suggestions when suggested products did not meet the user's expectations.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes communication means for processing information obtained from the user, means for collecting product information from an e-commerce system based on said information, and means for analyzing the user's emotions using emotion analysis means and reflecting this in product suggestions. This makes it possible to provide product suggestions optimized for the user's emotions and circumstances.

[0155] "Communication means for processing information obtained from users" refers to technical means for receiving product requirements transmitted by users through their terminals in real time and transmitting them to a server.

[0156] "Means of collecting product information from e-commerce systems" refers to a method by which a server obtains product-related data from a third-party e-commerce platform via a network.

[0157] "A means of generating proposals using a generation algorithm" refers to an algorithm that selects the most suitable product based on acquired product information and user requirements, and then proposes it to the user.

[0158] "Means for sending product suggestions to user devices" refers to a technology that sends product suggestions generated on a server to a user terminal and displays the results on the user's screen.

[0159] "A means of receiving user feedback and generating new product proposals" refers to a system that creates new product proposals based on user feedback and changes in requests, and then resends them.

[0160] "Emotional analysis methods" are technologies that analyze text input from users, identify the user's emotional state, and reflect that in the suggested content.

[0161] "Methods using image analysis technology" refer to techniques that analyze product images, extract their features, and select products that meet user requirements.

[0162] "Means of providing functionality including purchase links" refers to interface technology that presents users with a link that allows them to directly access the proposed product, and enables them to purchase the product through that link.

[0163] The system of this invention provides an interface for users to quickly identify and purchase products via a terminal. Users input their requirements for desired products using a chat interface on their terminal. The terminal transmits this information to the server in real time.

[0164] The server receives user input via communication methods and uses sentiment analysis technology to recognize the user's emotional state from the text. Natural language processing algorithms are used for sentiment analysis. Based on user requirements and emotional information, the server collects product data via the e-commerce system's API. Image recognition technology is used to extract characteristics from product images and identify the product best suited to the user's requirements.

[0165] The collected product information is analyzed using a generative AI model to create product suggestions that best suit the user's requirements. These suggestions include detailed product information and purchase links. The server sends the generated product suggestions to the user's device, allowing the user to select products that meet their needs. If the user is dissatisfied with the suggestions, they can submit feedback, and the server uses this feedback to generate new product suggestions.

[0166] As a concrete example, suppose a user specifies the conditions as "blue sneakers, domestic manufacturer, under 10,000 yen," and is emotionally in a hurry. In this case, the user can enter the prompt message as "I'm looking for blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry, so I need them as soon as possible." The server receives this and highlights suggestions for products that can be delivered the same day. This allows the user to quickly find and purchase a product that meets their needs.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The user enters the requirements for the desired product in the terminal's chat interface. The entered information includes specific elements such as the product's color, manufacturer, and price range. The terminal receives the user's requirements as text data and sends it to the server.

[0170] Step 2:

[0171] The server receives text data sent from the terminal and analyzes the user's requirements using natural language processing techniques. The analysis extracts information such as product category, price range, and brand. Simultaneously, sentiment analysis techniques are used to recognize the user's emotional state from the text and extract that sentiment information. The output at this stage consists of the analyzed requirements and sentiment information.

[0172] Step 3:

[0173] The server uses the e-commerce platform's API to collect relevant product information based on the analyzed requirements and sentiment data. This information includes product names, images, prices, and descriptions. Image recognition technology is used to analyze the features of product images and identify those that match the user's requirements. The collected data then serves as input for the next step.

[0174] Step 4:

[0175] The server inputs the collected product information into a generating AI model, which compares the product data with the user's requirements. The generating AI model selects the product best suited to the user and generates product suggestions, including detailed product information and purchase links. At this stage, a list of specific products to suggest is created.

[0176] Step 5:

[0177] The server sends the generated product suggestions to the terminal, which then displays the suggestions to the user. The user reviews the suggestions and selects a product that meets their needs. The output at this stage is the product suggestions that the user can review.

[0178] Step 6:

[0179] Users can submit feedback on product suggestions. The server analyzes the sentiment of the received feedback and generates new suggestions as needed. These new suggestions are then sent back to the user's device and presented to them. This process allows the suggestions to be iteratively improved.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] In modern e-commerce, users often struggle to quickly find the product that best suits their needs from a diverse range of options. Furthermore, since a user's emotional state influences their purchasing intent and satisfaction with suggestions, emotionally sensitive product recommendations are essential. However, traditional systems struggle to provide detailed product recommendations tailored to user requirements and emotional states, highlighting the need for improved user experience.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes means for providing an interface for processing requirements obtained from a user, means for collecting product data from an e-commerce platform based on those requirements, and means for analyzing the collected product data and using a generative artificial intelligence model to generate optimal suggestions for the user's requirements and emotional state. This makes it possible to quickly and accurately provide product suggestions that take the user's emotions into consideration.

[0185] An "interface for processing user requirements" is an interactive platform where users can input the features and conditions of the products they desire.

[0186] An "e-commerce platform" is a system that provides the foundation for trading goods and services over the internet.

[0187] "Means of collecting product data" refers to the processes and technologies used to obtain detailed product information from e-commerce platforms.

[0188] A "generative artificial intelligence model" is an artificial intelligence model designed to generate optimal product suggestions based on user requests and emotional states.

[0189] A "visual device" is a device that can present information to a user visually, and includes, for example, smart glasses and smartphones.

[0190] "Emotional state" refers to the psychological state or mood analyzed from the user's text input or voice.

[0191] "Image recognition technology" is a technology that analyzes image data to extract its content and features and identify them.

[0192] A "purchase link" is a web link that allows a user to initiate the purchase process by selecting it.

[0193] The system of this invention enables users to use smart glasses or other visual devices to search for products online and receive appropriate product recommendations.

[0194] The server receives requirements through voice and gesture input from the user and analyzes the user's emotional state based on these requirements. By combining an emotion engine and a generative artificial intelligence model, it identifies products that best match the user's needs and emotions using data collected from e-commerce platforms. When collecting this product data, the server obtains product images, prices, and descriptions via APIs and uses image recognition technology to analyze the features of the product images, easily selecting products that meet the requirements.

[0195] The device, specifically smart glasses, receives product suggestions generated from the server and displays them directly in the user's field of vision. This allows the user to intuitively view suggested products on their visual device and, if necessary, purchase them directly using the purchase link. User feedback on the suggestions is also taken into consideration, and an emotion engine analyzes this feedback to further optimize the suggestions.

[0196] For example, if a user voice-inputs "blue sneakers, domestic manufacturer, under 10,000 yen, in a hurry," the server will suggest and display blue sneakers that can be delivered quickly, which the user can then view using smart glasses. In this way, a system that combines an emotion engine and image recognition technology allows users to efficiently find products that meet their needs.

[0197] An example of a prompt message is, "Blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry."

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The user inputs product requirements via voice or gestures through smart glasses. The device receives this information in real time and converts it into text data. Input requirements might include phrases like, "Blue sneakers, domestic manufacturer, under 10,000 yen, urgent." The output is data ready to be sent to the server in text format.

[0201] Step 2:

[0202] The server analyzes the text data received from the terminal and uses an emotion engine to estimate the user's emotional state. The input includes the user's requirements and their context, obtained from step 1. The emotion engine recognizes, for example, "hurrying" as a negative emotion. The output of this analysis is information about the user's emotional state.

[0203] Step 3:

[0204] The server uses a generative artificial intelligence model to generate product suggestions based on received requirements and emotional states. In this process, the server collects product data via the e-commerce platform's API. The input is analyzed user requirements and emotional information, and the output is a list of suggested products. Specifically, products that best match the user's requirements and offer fast delivery are selected.

[0205] Step 4:

[0206] The server sends the generated product suggestions to the terminal, and the suggestions are displayed on the smart glasses. The input is the product list generated in step 3, and the output is the product information displayed in the user's field of view. The user can review the visual information and select a specific product.

[0207] Step 5:

[0208] The user uses smart glasses to review suggestions and purchase items directly by selecting a purchase link. The input is the purchase link for the selected item, and the output is a webpage containing the purchase procedure. Furthermore, an example of a prompt message used until the purchase is completed is, "Blue sneakers, domestic manufacturer, under 10,000 yen. In a hurry."

[0209] Step 6:

[0210] The system receives feedback on user suggestions again and generates new product suggestions as needed. The input is user feedback on the suggestions, which the emotion engine analyzes and uses to improve the next suggestion. The output is an improved suggestion for the next product.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] This invention provides a system that offers an interface for users to quickly identify and obtain desired products. Users input their desired product requirements (e.g., color, brand, price range, etc.) into a chat interface on their device. This interface provides means for receiving and processing the user's input.

[0228] The terminal immediately transmits the user's requirements to the server. This server is connected to an e-commerce platform and has the means to collect product data based on the user's requirements. Specifically, the server accesses the relevant platform via the internet and collects images, prices, descriptions, etc., of products that are considered to match the requirements.

[0229] The server collects product data and then analyzes it using a generative artificial intelligence model. This AI model compares the input requirements information with the collected product data and has a means to suggest the most suitable product to the user. The suggested product includes product images, price information, and purchase links.

[0230] The generated product suggestions are sent from the server to the user's terminal. The user can review these suggestions on their terminal screen. The user can then determine if the suggested products meet their requirements, and if they feel they do not, they can use feedback to send new requirements or suggestions for improvement to the server. This feedback is used by the server to re-analyze the product data and generate new suggestions.

[0231] As a concrete example, consider a scenario where a user enters the requirements "blue sneakers, domestic brand, under 10,000 yen." The terminal sends this information to the server, which then collects information on matching sneakers from the corresponding e-commerce platform. A generative artificial intelligence model analyzes the information and generates optimal product suggestions, presenting the user with several options. This process allows the user to efficiently discover the desired product and make a purchase decision.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The user enters the requirements for the desired product into the device's chat interface. Specifically, they specify the product's color, brand, price range, etc., in text format.

[0235] Step 2:

[0236] The terminal sends the requirements entered by the user to the server. This data transfer occurs in real time and uses a secure protocol.

[0237] Step 3:

[0238] The server analyzes the user's requirements. A generative artificial intelligence model extracts the necessary information from the user's requirements and sets criteria for use in product searches.

[0239] Step 4:

[0240] The server accesses the e-commerce platform's API to collect product data that meets the user's requirements. Specifically, it retrieves product images, prices, inventory information, descriptions, and other relevant data.

[0241] Step 5:

[0242] The server analyzes the collected product data using a generative artificial intelligence model. This model compares the content and selects the product that best matches the user's requirements.

[0243] Step 6:

[0244] The server generates product suggestions based on the analysis results. These suggestions include detailed information about suitable products and are formatted for display on the user's device.

[0245] Step 7:

[0246] The server sends the generated product suggestions to the user's terminal. Once the data transfer is complete, the terminal displays the received product suggestions on its screen.

[0247] Step 8:

[0248] The user reviews the product suggestions displayed on their device screen. If they are satisfied with the suggested products, they can access a link to proceed with the purchase.

[0249] Step 9:

[0250] If a user is not satisfied with the proposal, they can send feedback to the server via the chat interface. This includes redefining requirements or adding new conditions.

[0251] Step 10:

[0252] The server receives feedback from the user and collects and analyzes product data again based on the new requirements. New product suggestions are generated and sent back to the user.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] Technology is needed to quickly identify the products consumers want and provide them with a suitable purchasing experience. Currently, consumers have to manually search through a vast amount of product information to find what suits their needs, which is time-consuming and laborious. Furthermore, inappropriate product suggestions can cause consumers stress. Solving this problem is essential.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for enabling data communication to process requests obtained from users, means for collecting information from a network marketplace, and means for analyzing the information using a machine learning algorithm and selecting the optimal product. This enables consumers to efficiently find products that meet their requirements and make purchasing decisions without stress.

[0258] "Requests obtained from users" refers to the preferences and requirements that consumers input as criteria for selecting products.

[0259] "Means that enable data communication" refers to technologies that have the functionality of communication protocols and interfaces for sending and receiving information between consumers and servers.

[0260] "Means of collecting information from network markets" refers to technologies for obtaining necessary product data from e-commerce platforms via the internet, and includes methods such as APIs and web scraping.

[0261] "Methods of analyzing information using machine learning algorithms" refer to algorithms that automatically evaluate collected product data and find the best option for consumer needs, and these may include neural networks and statistical models.

[0262] "Means for selecting the optimal product" refers to a function that automatically selects the product that best matches the consumer's needs from among multiple options based on analysis.

[0263] "Proposals containing purchase identifiers" refer to product proposals presented to consumers that include links or buttons to facilitate purchase.

[0264] The embodiments for carrying out the present invention will be described in detail below.

[0265] This invention begins with a user inputting the requirements for a specific product using a terminal. The user inputs the characteristics and conditions of the product they want (e.g., "blue sneakers, domestic brand, under 10,000 yen") as prompt text into the terminal's chat interface. The terminal recognizes this prompt text, converts it into the appropriate data format, and sends it to the server.

[0266] Based on the user's requirements received, the server uses APIs from multiple e-commerce platforms, such as major online malls and various e-commerce sites, via an internet-connected system to collect relevant product information. A secure communication protocol using HTTPS is employed for information collection.

[0267] Subsequently, the server analyzes the collected product information using a generative AI model. This AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and employs sophisticated algorithms based on a large amount of training data for data analysis. The AI ​​compares the user's requirements with the data for each product and selects the most suitable product candidate.

[0268] The data for the suggested products (e.g., product name, price, image, purchase link) is sent from the server to the user's device. The device displays this information in a user-friendly format, allowing the user to intuitively evaluate the suggested products.

[0269] If a user is dissatisfied with a proposal, they can send new requirements or suggestions for improvement to the server through feedback. Based on this feedback, the server uses the AI ​​model to re-analyze the data and make revised suggestions, aiming to improve user satisfaction.

[0270] This system allows users to quickly and efficiently find products that meet their needs and make purchase decisions.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The user enters the requirements for the desired product as a prompt message into the chat interface via their device. This prompt message includes specific product characteristics and conditions (e.g., "blue sneakers, domestic brand, under 10,000 yen"). As a result of the input, the device generates data on the user's requirements.

[0274] Step 2:

[0275] The terminal formats the user's input requirements data and sends it to the server. Data formatting involves converting the user's natural language input into a structured data format (e.g., JSON). The output is the formatted data sent to the server.

[0276] Step 3:

[0277] The server requests product information from the e-commerce platform's API based on the user's requirements data received. Secure communication is ensured by including API keys and authentication information. The output is a collection of product data obtained from each platform.

[0278] Step 4:

[0279] The server analyzes the collected product data using a generative AI model. Machine learning algorithms are applied to compare and evaluate the user's requirements against the collected data. The input consists of requirement data and product data stored on the server, and the output is a list of highly suitable products. The server then selects the optimal recommendation based on the analysis results.

[0280] Step 5:

[0281] The server sends the selected optimal product proposal to the user's terminal in data format. For this transmission, data in JSON format using the RESTful API is used. The output is product proposal data interpretable on the user's terminal side.

[0282] Step 6:

[0283] The terminal displays the received product proposal on the screen and provides visual information to the user. A list including the product name, image, price, and purchase link is presented to the user. The user makes selections or provides feedback based on this.

[0284] Step 7:

[0285] The user inputs feedback on the proposed product through the terminal. This also includes new requirements or improvement requests. Prepare to send the feedback data to the server and reflect it in the next proposal.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] In modern times, it is difficult for consumers to efficiently select appropriate products from a vast amount of information, which requires a lot of time and effort. There is a need for means to solve such problems and enable consumers to quickly and accurately find products.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0290] In this invention, the server includes means for human-computer interaction to process requirements obtained from a user, means for collecting information from a digital marketplace platform based on those requirements, and means for analyzing the collected information and using a machine learning model to generate optimal suggestions for the user's requirements. This enables the user to efficiently obtain product information that meets their needs.

[0291] "Means of interaction between humans and computers" refers to interfaces that enable users and computers to exchange information through natural language or text.

[0292] A "digital marketplace platform" is an online trading infrastructure for buying and selling goods and services via the internet.

[0293] "Means of information gathering" refers to a system for collecting necessary information from the internet and other data sources.

[0294] A "machine learning model" is an algorithm that learns from data and provides the optimal output for a specific purpose.

[0295] A "computer device" is an electronic device capable of processing and storing information, and includes smartphones and personal computers.

[0296] "Enter product requirements by voice or text" means that the user communicates the specifications of the product they want to the system through speaking or keyboard input.

[0297] An "application that automatically provides relevant information" is a program that quickly presents relevant product data based on conditions entered by the user.

[0298] This invention utilizes a computer device (e.g., a smartphone) with an interface that allows the user to input product requirements via voice or text. Through this interface, the user can input product specifications without having to visit a store. The input information is then quickly transmitted to a server.

[0299] The server collects relevant information from the digital marketplace platform based on the user's requirements. The collected information is analyzed by a machine learning model (e.g., the "transformers" library) to generate product suggestions that best meet the user's requirements. These suggestions include product images, prices, and reference links.

[0300] The generated product suggestions are sent from the server to the user's computer, where the user can review them. If the suggestions do not meet the user's requirements, the user can provide feedback to the system. This feedback is processed by the server, a new suggestion is generated, and it is presented to the user again.

[0301] For example, if a user has the requirement "blue sneakers, Japanese brand, under 10,000 yen," the server will input this into a computer, gather relevant information, and suggest the best product. An example of a prompt would be, "When the user says 'blue sneakers, under 10,000 yen,' suggest only the best products." Through this process, users can easily and effectively select products and make purchasing decisions.

[0302] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0303] Step 1:

[0304] The user inputs the requirements of the desired product in voice or text through the interface of the computer device. The input here is the conditions related to the product (e.g., color, brand, price), and the computer device obtains this information and prepares to send it to the server. Use the "human interface device" to preprocess the input by natural language processing technology.

[0305] Step 2:

[0306] The terminal sends the obtained user requirements to the server. The server receives this input and collects relevant product information from the digital market platform based on it. Use API and scraping technology to collect information using the input keywords. The output is a group of data of the corresponding products.

[0307] Step 3:

[0308] The server analyzes the collected product information. Here, use a generative AI model (e.g., natural language understanding using "transformers") to select the products that best suit the user's requirements. The input is the collected data group, perform data evaluation to identify the optimal products from it, and output a list of products with high fitness.

[0309] Step 4:

[0310] <W The server generates product proposals selected by the analysis and sends the information to the terminal. The proposals include product images, prices, and purchase links. The output here is a list of product proposals that the user can confirm, whereby the user can make a specific product selection. <00W0978>

[0311] Step 5:

[0312] The user checks the proposals on the terminal and inputs feedback regarding them. The feedback may include satisfaction levels and new requirements. This feedback is sent to the server and used as input data for generating product proposals again.

[0313] Step 6:

[0314] The server analyzes user feedback and uses the AI ​​model again to generate new suggestions. New user requirements are incorporated into the data, and steps 2 through 4 are repeated. This allows for more refined product suggestions, leading to improved user satisfaction.

[0315] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0316] This invention is a system that combines an emotion engine and provides an interface for users to quickly identify and obtain desired products. First, the user enters their desired product requirements into a chat interface via a terminal. This interface has the function of receiving user input in real time and sending it to the server.

[0317] The server analyzes the requirements entered by the user while simultaneously recognizing the user's emotional state through an emotion engine. The emotion engine infers emotions from the user's text input and generates data to adjust suggestions as needed. This information is considered a crucial factor in product selection by the generative artificial intelligence model.

[0318] The server accesses the e-commerce platform and collects appropriate product data based on the user's requirements and sentiments. Specifically, it retrieves product images, prices, descriptions, etc., from the platform's API. In this process, image recognition technology is also used to analyze the features of product images and identify products that meet the user's requirements.

[0319] The collected product data is analyzed using a generative artificial intelligence model. This model compares the product data with user requirements, including sentiment information, to select the most suitable product. The selected product is then reconstructed as a product suggestion, which includes detailed product information and a purchase link.

[0320] The generated product suggestions are sent to the user's device and displayed. The user can review these suggestions and select products they are satisfied with. If the user is dissatisfied with the suggestions, the sentiment engine checks the feedback and generates new suggestions as needed. These improved suggestions are then sent back to the device.

[0321] For example, if a user requests "blue sneakers, domestic brand, under 10,000 yen," and is in a negative and urgent emotional state, the server will use this information to quickly identify suitable products and highlight suggestions for items that can be delivered sooner. This system allows users to efficiently find products that meet their needs and proceed with their purchase.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The user enters the requirements for the desired product into the device's chat interface. This includes the product's color, brand, and price range.

[0325] Step 2:

[0326] The terminal transmits data entered by the user to the server in real time. During this process, the data is converted to an appropriate format and transferred using secure communication methods.

[0327] Step 3:

[0328] The server analyzes the received requirements data. Simultaneously, it activates the emotion engine to analyze the user's emotions from the input text information. This analysis is then used to refine the proposed content.

[0329] Step 4:

[0330] The server connects to the e-commerce platform's API and collects product data based on the user's requirements and emotional state. The collected data includes product images, prices, and detailed information, and is analyzed as needed using image recognition technology.

[0331] Step 5:

[0332] The server uses a generative artificial intelligence model to analyze collected product data and select the most suitable product based on user requirements and emotional state. This model optimizes itself by considering the characteristics of each product and the user's satisfaction and dissatisfaction.

[0333] Step 6:

[0334] The server generates product suggestions based on the selected product information. These suggestions include product images, prices, inventory information, and purchase links, formatted in a format suitable for the user's device.

[0335] Step 7:

[0336] The server sends the generated product suggestions to the user's device. A notification appears on the device so the user can immediately view and check the suggested items.

[0337] Step 8:

[0338] Users review the product suggestions displayed on their device and, if satisfied, click the purchase link included in the suggestion to proceed with the purchase. If dissatisfied, they can provide feedback via the chat interface.

[0339] Step 9:

[0340] The server receives user feedback and generates new suggestions. The user's requirements are redefined based on the feedback, and the sentiment engine takes this into consideration again.

[0341] Step 10:

[0342] The server generates improved product suggestions again and sends them back to the user's terminal. By repeating this process, the accuracy of the suggestions improves until the user is satisfied.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0345] Traditional e-commerce systems made it difficult for users to quickly identify the products they wanted, and also made it difficult for them to find products that suited their feelings and circumstances from among the suggested items. Furthermore, there was a lack of mechanisms to efficiently incorporate feedback into future suggestions when suggested products did not meet the user's expectations.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes communication means for processing information obtained from the user, means for collecting product information from an e-commerce system based on said information, and means for analyzing the user's emotions using emotion analysis means and reflecting this in product suggestions. This makes it possible to provide product suggestions optimized for the user's emotions and circumstances.

[0348] "Communication means for processing information obtained from users" refers to technical means for receiving product requirements transmitted by users through their terminals in real time and transmitting them to a server.

[0349] "Means of collecting product information from e-commerce systems" refers to a method by which a server obtains product-related data from a third-party e-commerce platform via a network.

[0350] "A means of generating proposals using a generation algorithm" refers to an algorithm that selects the most suitable product based on acquired product information and user requirements, and then proposes it to the user.

[0351] "Means for sending product suggestions to user devices" refers to a technology that sends product suggestions generated on a server to a user terminal and displays the results on the user's screen.

[0352] "A means of receiving user feedback and generating new product proposals" refers to a system that creates new product proposals based on user feedback and changes in requests, and then resends them.

[0353] "Emotional analysis methods" are technologies that analyze text input from users, identify the user's emotional state, and reflect that in the suggested content.

[0354] "Methods using image analysis technology" refer to techniques that analyze product images, extract their features, and select products that meet user requirements.

[0355] "Means of providing functionality including purchase links" refers to interface technology that presents users with a link that allows them to directly access the proposed product, and enables them to purchase the product through that link.

[0356] The system of this invention provides an interface for users to quickly identify and purchase products via a terminal. Users input their requirements for desired products using a chat interface on their terminal. The terminal transmits this information to the server in real time.

[0357] The server receives user input via communication methods and uses sentiment analysis technology to recognize the user's emotional state from the text. Natural language processing algorithms are used for sentiment analysis. Based on user requirements and emotional information, the server collects product data via the e-commerce system's API. Image recognition technology is used to extract characteristics from product images and identify the product best suited to the user's requirements.

[0358] The collected product information is analyzed using a generative AI model to create product suggestions that best suit the user's requirements. These suggestions include detailed product information and purchase links. The server sends the generated product suggestions to the user's device, allowing the user to select products that meet their needs. If the user is dissatisfied with the suggestions, they can submit feedback, and the server uses this feedback to generate new product suggestions.

[0359] As a concrete example, suppose a user specifies the conditions as "blue sneakers, domestic manufacturer, under 10,000 yen," and is emotionally in a hurry. In this case, the user can enter the prompt message as "I'm looking for blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry, so I need them as soon as possible." The server receives this and highlights suggestions for products that can be delivered the same day. This allows the user to quickly find and purchase a product that meets their needs.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The user enters the requirements for the desired product in the terminal's chat interface. The entered information includes specific elements such as the product's color, manufacturer, and price range. The terminal receives the user's requirements as text data and sends it to the server.

[0363] Step 2:

[0364] The server receives text data sent from the terminal and analyzes the user's requirements using natural language processing techniques. The analysis extracts information such as product category, price range, and brand. Simultaneously, sentiment analysis techniques are used to recognize the user's emotional state from the text and extract that sentiment information. The output at this stage consists of the analyzed requirements and sentiment information.

[0365] Step 3:

[0366] The server uses the e-commerce platform's API to collect relevant product information based on the analyzed requirements and sentiment data. This information includes product names, images, prices, and descriptions. Image recognition technology is used to analyze the features of product images and identify those that match the user's requirements. The collected data then serves as input for the next step.

[0367] Step 4:

[0368] The server inputs the collected product information into a generating AI model, which compares the product data with the user's requirements. The generating AI model selects the product best suited to the user and generates product suggestions, including detailed product information and purchase links. At this stage, a list of specific products to suggest is created.

[0369] Step 5:

[0370] The server sends the generated product suggestions to the terminal, which then displays the suggestions to the user. The user reviews the suggestions and selects a product that meets their needs. The output at this stage is the product suggestions that the user can review.

[0371] Step 6:

[0372] Users can submit feedback on product suggestions. The server analyzes the sentiment of the received feedback and generates new suggestions as needed. These new suggestions are then sent back to the user's device and presented to them. This process allows the suggestions to be iteratively improved.

[0373] (Application Example 2)

[0374] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0375] In modern e-commerce, users often struggle to quickly find the product that best suits their needs from a diverse range of options. Furthermore, since a user's emotional state influences their purchasing intent and satisfaction with suggestions, emotionally sensitive product recommendations are essential. However, traditional systems struggle to provide detailed product recommendations tailored to user requirements and emotional states, highlighting the need for improved user experience.

[0376] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0377] In this invention, the server includes means for providing an interface for processing requirements obtained from a user, means for collecting product data from an e-commerce platform based on those requirements, and means for analyzing the collected product data and using a generative artificial intelligence model to generate optimal suggestions for the user's requirements and emotional state. This makes it possible to quickly and accurately provide product suggestions that take the user's emotions into consideration.

[0378] An "interface for processing user requirements" is an interactive platform where users can input the features and conditions of the products they desire.

[0379] An "e-commerce platform" is a system that provides the foundation for trading goods and services over the internet.

[0380] "Means of collecting product data" refers to the processes and technologies used to obtain detailed product information from e-commerce platforms.

[0381] A "generative artificial intelligence model" is an artificial intelligence model designed to generate optimal product suggestions based on user requests and emotional states.

[0382] A "visual device" is a device that can present information to a user visually, and includes, for example, smart glasses and smartphones.

[0383] "Emotional state" refers to the psychological state or mood analyzed from the user's text input or voice.

[0384] "Image recognition technology" is a technology that analyzes image data to extract its content and features and identify them.

[0385] A "purchase link" is a web link that allows a user to initiate the purchase process by selecting it.

[0386] The system of this invention enables users to use smart glasses or other visual devices to search for products online and receive appropriate product recommendations.

[0387] The server receives requirements through voice and gesture input from the user and analyzes the user's emotional state based on these requirements. By combining an emotion engine and a generative artificial intelligence model, it identifies products that best match the user's needs and emotions using data collected from e-commerce platforms. When collecting this product data, the server obtains product images, prices, and descriptions via APIs and uses image recognition technology to analyze the features of the product images, easily selecting products that meet the requirements.

[0388] The device, specifically smart glasses, receives product suggestions generated from the server and displays them directly in the user's field of vision. This allows the user to intuitively view suggested products on their visual device and, if necessary, purchase them directly using the purchase link. User feedback on the suggestions is also taken into consideration, and an emotion engine analyzes this feedback to further optimize the suggestions.

[0389] For example, if a user voice-inputs "blue sneakers, domestic manufacturer, under 10,000 yen, in a hurry," the server will suggest and display blue sneakers that can be delivered quickly, which the user can then view using smart glasses. In this way, a system that combines an emotion engine and image recognition technology allows users to efficiently find products that meet their needs.

[0390] An example of a prompt message is, "Blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry."

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The user inputs product requirements via voice or gestures through smart glasses. The device receives this information in real time and converts it into text data. Input requirements might include phrases like, "Blue sneakers, domestic manufacturer, under 10,000 yen, urgent." The output is data ready to be sent to the server in text format.

[0394] Step 2:

[0395] The server analyzes the text data received from the terminal and uses an emotion engine to estimate the user's emotional state. The input includes the user's requirements and their context, obtained from step 1. The emotion engine recognizes, for example, "hurrying" as a negative emotion. The output of this analysis is information about the user's emotional state.

[0396] Step 3:

[0397] The server uses a generative artificial intelligence model to generate product suggestions based on received requirements and emotional states. In this process, the server collects product data via the e-commerce platform's API. The input is analyzed user requirements and emotional information, and the output is a list of suggested products. Specifically, products that best match the user's requirements and offer fast delivery are selected.

[0398] Step 4:

[0399] The server sends the generated product suggestions to the terminal, and the suggestions are displayed on the smart glasses. The input is the product list generated in step 3, and the output is the product information displayed in the user's field of view. The user can review the visual information and select a specific product.

[0400] Step 5:

[0401] The user uses smart glasses to review suggestions and purchase items directly by selecting a purchase link. The input is the purchase link for the selected item, and the output is a webpage containing the purchase procedure. Furthermore, an example of a prompt message used until the purchase is completed is, "Blue sneakers, domestic manufacturer, under 10,000 yen. In a hurry."

[0402] Step 6:

[0403] The system receives feedback on user suggestions again and generates new product suggestions as needed. The input is user feedback on the suggestions, which the emotion engine analyzes and uses to improve the next suggestion. The output is an improved suggestion for the next product.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0405] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0410] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0412] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0414] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0415] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0416] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0419] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0420] This invention provides a system that offers an interface for users to quickly identify and obtain desired products. Users input their desired product requirements (e.g., color, brand, price range, etc.) into a chat interface on their device. This interface provides means for receiving and processing the user's input.

[0421] The terminal immediately transmits the user's requirements to the server. This server is connected to an e-commerce platform and has the means to collect product data based on the user's requirements. Specifically, the server accesses the relevant platform via the internet and collects images, prices, descriptions, etc., of products that are considered to match the requirements.

[0422] The server collects product data and then analyzes it using a generative artificial intelligence model. This AI model compares the input requirements information with the collected product data and has a means to suggest the most suitable product to the user. The suggested product includes product images, price information, and purchase links.

[0423] The generated product suggestions are sent from the server to the user's terminal. The user can review these suggestions on their terminal screen. The user can then determine if the suggested products meet their requirements, and if they feel they do not, they can use feedback to send new requirements or suggestions for improvement to the server. This feedback is used by the server to re-analyze the product data and generate new suggestions.

[0424] As a concrete example, consider a scenario where a user enters the requirements "blue sneakers, domestic brand, under 10,000 yen." The terminal sends this information to the server, which then collects information on matching sneakers from the corresponding e-commerce platform. A generative artificial intelligence model analyzes the information and generates optimal product suggestions, presenting the user with several options. This process allows the user to efficiently discover the desired product and make a purchase decision.

[0425] The following describes the processing flow.

[0426] Step 1:

[0427] The user enters the requirements for the desired product into the device's chat interface. Specifically, they specify the product's color, brand, price range, etc., in text format.

[0428] Step 2:

[0429] The terminal sends the requirements entered by the user to the server. This data transfer occurs in real time and uses a secure protocol.

[0430] Step 3:

[0431] The server analyzes the user's requirements. A generative artificial intelligence model extracts the necessary information from the user's requirements and sets criteria for use in product searches.

[0432] Step 4:

[0433] The server accesses the e-commerce platform's API to collect product data that meets the user's requirements. Specifically, it retrieves product images, prices, inventory information, descriptions, and other relevant data.

[0434] Step 5:

[0435] The server analyzes the collected product data using a generative artificial intelligence model. This model compares the content and selects the product that best matches the user's requirements.

[0436] Step 6:

[0437] The server generates product suggestions based on the analysis results. These suggestions include detailed information about suitable products and are formatted for display on the user's device.

[0438] Step 7:

[0439] The server sends the generated product suggestions to the user's terminal. Once the data transfer is complete, the terminal displays the received product suggestions on its screen.

[0440] Step 8:

[0441] The user reviews the product suggestions displayed on their device screen. If they are satisfied with the suggested products, they can access a link to proceed with the purchase.

[0442] Step 9:

[0443] If a user is not satisfied with the proposal, they can send feedback to the server via the chat interface. This includes redefining requirements or adding new conditions.

[0444] Step 10:

[0445] The server receives feedback from the user and collects and analyzes product data again based on the new requirements. New product suggestions are generated and sent back to the user.

[0446] (Example 1)

[0447] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0448] Technology is needed to quickly identify the products consumers want and provide them with a suitable purchasing experience. Currently, consumers have to manually search through a vast amount of product information to find what suits their needs, which is time-consuming and laborious. Furthermore, inappropriate product suggestions can cause consumers stress. Solving this problem is essential.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes means for enabling data communication to process requests obtained from users, means for collecting information from a network marketplace, and means for analyzing the information using a machine learning algorithm and selecting the optimal product. This enables consumers to efficiently find products that meet their requirements and make purchasing decisions without stress.

[0451] "Requests obtained from users" refers to the preferences and requirements that consumers input as criteria for selecting products.

[0452] "Means that enable data communication" refers to technologies that have the functionality of communication protocols and interfaces for sending and receiving information between consumers and servers.

[0453] "Means of collecting information from network markets" refers to technologies for obtaining necessary product data from e-commerce platforms via the internet, and includes methods such as APIs and web scraping.

[0454] "Methods of analyzing information using machine learning algorithms" refer to algorithms that automatically evaluate collected product data and find the best option for consumer needs, and these may include neural networks and statistical models.

[0455] "Means for selecting the optimal product" refers to a function that automatically selects the product that best matches the consumer's needs from among multiple options based on analysis.

[0456] "Proposals containing purchase identifiers" refer to product proposals presented to consumers that include links or buttons to facilitate purchase.

[0457] The embodiments for carrying out the present invention will be described in detail below.

[0458] This invention begins with a user inputting the requirements for a specific product using a terminal. The user inputs the characteristics and conditions of the product they want (e.g., "blue sneakers, domestic brand, under 10,000 yen") as prompt text into the terminal's chat interface. The terminal recognizes this prompt text, converts it into the appropriate data format, and sends it to the server.

[0459] Based on the user's requirements received, the server uses APIs from multiple e-commerce platforms, such as major online malls and various e-commerce sites, via an internet-connected system to collect relevant product information. A secure communication protocol using HTTPS is employed for information collection.

[0460] Subsequently, the server analyzes the collected product information using a generative AI model. This AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and employs sophisticated algorithms based on a large amount of training data for data analysis. The AI ​​compares the user's requirements with the data for each product and selects the most suitable product candidate.

[0461] The data for the suggested products (e.g., product name, price, image, purchase link) is sent from the server to the user's device. The device displays this information in a user-friendly format, allowing the user to intuitively evaluate the suggested products.

[0462] If a user is dissatisfied with a proposal, they can send new requirements or suggestions for improvement to the server through feedback. Based on this feedback, the server uses the AI ​​model to re-analyze the data and make revised suggestions, aiming to improve user satisfaction.

[0463] This system allows users to quickly and efficiently find products that meet their needs and make purchase decisions.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The user enters the requirements for the desired product as a prompt message into the chat interface via their device. This prompt message includes specific product characteristics and conditions (e.g., "blue sneakers, domestic brand, under 10,000 yen"). As a result of the input, the device generates data on the user's requirements.

[0467] Step 2:

[0468] The terminal formats the user's input requirements data and sends it to the server. Data formatting involves converting the user's natural language input into a structured data format (e.g., JSON). The output is the formatted data sent to the server.

[0469] Step 3:

[0470] The server requests product information from the e-commerce platform's API based on the user's requirements data received. Secure communication is ensured by including API keys and authentication information. The output is a collection of product data obtained from each platform.

[0471] Step 4:

[0472] The server analyzes the collected product data using a generative AI model. Machine learning algorithms are applied to compare and evaluate the user's requirements against the collected data. The input consists of requirement data and product data stored on the server, and the output is a list of highly suitable products. The server then selects the optimal recommendation based on the analysis results.

[0473] Step 5:

[0474] The server sends the selected, optimal product suggestions to the user's terminal in data format. This transmission uses JSON format data via a RESTful API. The output is product suggestion data that can be interpreted on the user's terminal.

[0475] Step 6:

[0476] The device displays received product suggestions on its screen, providing the user with visual information. A list including product names, images, prices, and purchase links is presented to the user. The user then reviews this list and makes selections and provides feedback.

[0477] Step 7:

[0478] Users input feedback on the proposed products via their terminals, including new requirements and improvement requests. The feedback data is sent to a server, which is then prepared to incorporate it into future proposals.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] In today's world, it is difficult and time-consuming for consumers to efficiently select the right products from a vast amount of information. There is a need for a solution to this problem, enabling consumers to find products quickly and accurately.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes means for human-computer interaction to process requirements obtained from a user, means for collecting information from a digital marketplace platform based on those requirements, and means for analyzing the collected information and using a machine learning model to generate optimal suggestions for the user's requirements. This enables the user to efficiently obtain product information that meets their needs.

[0484] "Means of interaction between humans and computers" refers to interfaces that enable users and computers to exchange information through natural language or text.

[0485] A "digital marketplace platform" is an online trading infrastructure for buying and selling goods and services via the internet.

[0486] "Means of information gathering" refers to a system for collecting necessary information from the internet and other data sources.

[0487] A "machine learning model" is an algorithm that learns from data and provides the optimal output for a specific purpose.

[0488] A "computer device" is an electronic device capable of processing and storing information, and includes smartphones and personal computers.

[0489] "Enter product requirements by voice or text" means that the user communicates the specifications of the product they want to the system through speaking or keyboard input.

[0490] An "application that automatically provides relevant information" is a program that quickly presents relevant product data based on conditions entered by the user.

[0491] This invention utilizes a computer device (e.g., a smartphone) with an interface that allows the user to input product requirements via voice or text. Through this interface, the user can input product specifications without having to visit a store. The input information is then quickly transmitted to a server.

[0492] The server collects relevant information from the digital marketplace platform based on the user's requirements. The collected information is analyzed by a machine learning model (e.g., the "transformers" library) to generate product suggestions that best meet the user's requirements. These suggestions include product images, prices, and reference links.

[0493] The generated product suggestions are sent from the server to the user's computer, where the user can review them. If the suggestions do not meet the user's requirements, the user can provide feedback to the system. This feedback is processed by the server, a new suggestion is generated, and it is presented to the user again.

[0494] For example, if a user has the requirement "blue sneakers, Japanese brand, under 10,000 yen," the server will input this into a computer, gather relevant information, and suggest the best product. An example of a prompt would be, "When the user says 'blue sneakers, under 10,000 yen,' suggest only the best products." Through this process, users can easily and effectively select products and make purchasing decisions.

[0495] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0496] Step 1:

[0497] The user inputs the requirements for their desired product via voice or text through the computer's interface. This input includes product specifications (e.g., color, brand, price), and the computer retrieves this information and prepares to send it to the server. A "human interface device" is used to pre-process the input using natural language processing technology.

[0498] Step 2:

[0499] The terminal sends the acquired user requirements to the server. The server receives this input and, based on it, collects relevant product information from the digital marketplace platform. Using the entered keywords, information is collected using APIs and scraping techniques. The output is a data set of the relevant products.

[0500] Step 3:

[0501] The server analyzes the collected product information. Here, it uses a generative AI model (e.g., natural language understanding using "transformers") to select the product that best suits the user's requirements. The input is the collected data set, and the server performs data evaluation to identify the optimal product from it, outputting a list of highly suitable products.

[0502] Step 4:

[0503] The server generates product suggestions selected through analysis and sends this information to the terminal. The suggestions include product images, prices, and purchase links. The output here is a list of product suggestions that the user can review, allowing them to make specific product selections.

[0504] Step 5:

[0505] Users review the suggestions on their devices and provide feedback. This feedback may include satisfaction levels and new requirements. This feedback is sent to the server and used as input data to generate new product suggestions.

[0506] Step 6:

[0507] The server analyzes user feedback and uses the AI ​​model again to generate new suggestions. New user requirements are incorporated into the data, and steps 2 through 4 are repeated. This allows for more refined product suggestions, leading to improved user satisfaction.

[0508] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0509] This invention is a system that combines an emotion engine and provides an interface for users to quickly identify and obtain desired products. First, the user enters their desired product requirements into a chat interface via a terminal. This interface has the function of receiving user input in real time and sending it to the server.

[0510] The server analyzes the requirements entered by the user while simultaneously recognizing the user's emotional state through an emotion engine. The emotion engine infers emotions from the user's text input and generates data to adjust suggestions as needed. This information is considered a crucial factor in product selection by the generative artificial intelligence model.

[0511] The server accesses the e-commerce platform and collects appropriate product data based on the user's requirements and sentiments. Specifically, it retrieves product images, prices, descriptions, etc., from the platform's API. In this process, image recognition technology is also used to analyze the features of product images and identify products that meet the user's requirements.

[0512] The collected product data is analyzed using a generative artificial intelligence model. This model compares the product data with user requirements, including sentiment information, to select the most suitable product. The selected product is then reconstructed as a product suggestion, which includes detailed product information and a purchase link.

[0513] The generated product suggestions are sent to the user's device and displayed. The user can review these suggestions and select products they are satisfied with. If the user is dissatisfied with the suggestions, the sentiment engine checks the feedback and generates new suggestions as needed. These improved suggestions are then sent back to the device.

[0514] For example, if a user requests "blue sneakers, domestic brand, under 10,000 yen," and is in a negative and urgent emotional state, the server will use this information to quickly identify suitable products and highlight suggestions for items that can be delivered sooner. This system allows users to efficiently find products that meet their needs and proceed with their purchase.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The user enters the requirements for the desired product into the device's chat interface. This includes the product's color, brand, and price range.

[0518] Step 2:

[0519] The terminal transmits data entered by the user to the server in real time. During this process, the data is converted to an appropriate format and transferred using secure communication methods.

[0520] Step 3:

[0521] The server analyzes the received requirements data. Simultaneously, it activates the emotion engine to analyze the user's emotions from the input text information. This analysis is then used to refine the proposed content.

[0522] Step 4:

[0523] The server connects to the e-commerce platform's API and collects product data based on the user's requirements and emotional state. The collected data includes product images, prices, and detailed information, and is analyzed as needed using image recognition technology.

[0524] Step 5:

[0525] The server uses a generative artificial intelligence model to analyze collected product data and select the most suitable product based on user requirements and emotional state. This model optimizes itself by considering the characteristics of each product and the user's satisfaction and dissatisfaction.

[0526] Step 6:

[0527] The server generates product suggestions based on the selected product information. These suggestions include product images, prices, inventory information, and purchase links, formatted in a format suitable for the user's device.

[0528] Step 7:

[0529] The server sends the generated product suggestions to the user's device. A notification appears on the device so the user can immediately view and check the suggested items.

[0530] Step 8:

[0531] Users review the product suggestions displayed on their device and, if satisfied, click the purchase link included in the suggestion to proceed with the purchase. If dissatisfied, they can provide feedback via the chat interface.

[0532] Step 9:

[0533] The server receives user feedback and generates new suggestions. The user's requirements are redefined based on the feedback, and the sentiment engine takes this into consideration again.

[0534] Step 10:

[0535] The server generates improved product suggestions again and sends them back to the user's terminal. By repeating this process, the accuracy of the suggestions improves until the user is satisfied.

[0536] (Example 2)

[0537] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0538] Traditional e-commerce systems made it difficult for users to quickly identify the products they wanted, and also made it difficult for them to find products that suited their feelings and circumstances from among the suggested items. Furthermore, there was a lack of mechanisms to efficiently incorporate feedback into future suggestions when suggested products did not meet the user's expectations.

[0539] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0540] In this invention, the server includes communication means for processing information obtained from the user, means for collecting product information from an e-commerce system based on said information, and means for analyzing the user's emotions using emotion analysis means and reflecting this in product suggestions. This makes it possible to provide product suggestions optimized for the user's emotions and circumstances.

[0541] "Communication means for processing information obtained from users" refers to technical means for receiving product requirements transmitted by users through their terminals in real time and transmitting them to a server.

[0542] "Means of collecting product information from e-commerce systems" refers to a method by which a server obtains product-related data from a third-party e-commerce platform via a network.

[0543] "A means of generating proposals using a generation algorithm" refers to an algorithm that selects the most suitable product based on acquired product information and user requirements, and then proposes it to the user.

[0544] "Means for sending product suggestions to user devices" refers to a technology that sends product suggestions generated on a server to a user terminal and displays the results on the user's screen.

[0545] "A means of receiving user feedback and generating new product proposals" refers to a system that creates new product proposals based on user feedback and changes in requests, and then resends them.

[0546] "Emotional analysis methods" are technologies that analyze text input from users, identify the user's emotional state, and reflect that in the suggested content.

[0547] "Methods using image analysis technology" refer to techniques that analyze product images, extract their features, and select products that meet user requirements.

[0548] "Means of providing functionality including purchase links" refers to interface technology that presents users with a link that allows them to directly access the proposed product, and enables them to purchase the product through that link.

[0549] The system of this invention provides an interface for users to quickly identify and purchase products via a terminal. Users input their requirements for desired products using a chat interface on their terminal. The terminal transmits this information to the server in real time.

[0550] The server receives user input via communication methods and uses sentiment analysis technology to recognize the user's emotional state from the text. Natural language processing algorithms are used for sentiment analysis. Based on user requirements and emotional information, the server collects product data via the e-commerce system's API. Image recognition technology is used to extract characteristics from product images and identify the product best suited to the user's requirements.

[0551] The collected product information is analyzed using a generative AI model to create product suggestions that best suit the user's requirements. These suggestions include detailed product information and purchase links. The server sends the generated product suggestions to the user's device, allowing the user to select products that meet their needs. If the user is dissatisfied with the suggestions, they can submit feedback, and the server uses this feedback to generate new product suggestions.

[0552] As a concrete example, suppose a user specifies the conditions as "blue sneakers, domestic manufacturer, under 10,000 yen," and is emotionally in a hurry. In this case, the user can enter the prompt message as "I'm looking for blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry, so I need them as soon as possible." The server receives this and highlights suggestions for products that can be delivered the same day. This allows the user to quickly find and purchase a product that meets their needs.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1:

[0555] The user enters the requirements for the desired product in the terminal's chat interface. The entered information includes specific elements such as the product's color, manufacturer, and price range. The terminal receives the user's requirements as text data and sends it to the server.

[0556] Step 2:

[0557] The server receives text data sent from the terminal and analyzes the user's requirements using natural language processing techniques. The analysis extracts information such as product category, price range, and brand. Simultaneously, sentiment analysis techniques are used to recognize the user's emotional state from the text and extract that sentiment information. The output at this stage consists of the analyzed requirements and sentiment information.

[0558] Step 3:

[0559] The server uses the e-commerce platform's API to collect relevant product information based on the analyzed requirements and sentiment data. This information includes product names, images, prices, and descriptions. Image recognition technology is used to analyze the features of product images and identify those that match the user's requirements. The collected data then serves as input for the next step.

[0560] Step 4:

[0561] The server inputs the collected product information into a generating AI model, which compares the product data with the user's requirements. The generating AI model selects the product best suited to the user and generates product suggestions, including detailed product information and purchase links. At this stage, a list of specific products to suggest is created.

[0562] Step 5:

[0563] The server sends the generated product suggestions to the terminal, which then displays the suggestions to the user. The user reviews the suggestions and selects a product that meets their needs. The output at this stage is the product suggestions that the user can review.

[0564] Step 6:

[0565] Users can submit feedback on product suggestions. The server analyzes the sentiment of the received feedback and generates new suggestions as needed. These new suggestions are then sent back to the user's device and presented to them. This process allows the suggestions to be iteratively improved.

[0566] (Application Example 2)

[0567] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0568] In modern e-commerce, users often struggle to quickly find the product that best suits their needs from a diverse range of options. Furthermore, since a user's emotional state influences their purchasing intent and satisfaction with suggestions, emotionally sensitive product recommendations are essential. However, traditional systems struggle to provide detailed product recommendations tailored to user requirements and emotional states, highlighting the need for improved user experience.

[0569] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0570] In this invention, the server includes means for providing an interface for processing requirements obtained from a user, means for collecting product data from an e-commerce platform based on those requirements, and means for analyzing the collected product data and using a generative artificial intelligence model to generate optimal suggestions for the user's requirements and emotional state. This makes it possible to quickly and accurately provide product suggestions that take the user's emotions into consideration.

[0571] An "interface for processing user requirements" is an interactive platform where users can input the features and conditions of the products they desire.

[0572] An "e-commerce platform" is a system that provides the foundation for trading goods and services over the internet.

[0573] "Means of collecting product data" refers to the processes and technologies used to obtain detailed product information from e-commerce platforms.

[0574] A "generative artificial intelligence model" is an artificial intelligence model designed to generate optimal product suggestions based on user requests and emotional states.

[0575] A "visual device" is a device that can present information to a user visually, and includes, for example, smart glasses and smartphones.

[0576] "Emotional state" refers to the psychological state or mood analyzed from the user's text input or voice.

[0577] "Image recognition technology" is a technology that analyzes image data to extract its content and features and identify them.

[0578] A "purchase link" is a web link that allows a user to initiate the purchase process by selecting it.

[0579] The system of this invention enables users to use smart glasses or other visual devices to search for products online and receive appropriate product recommendations.

[0580] The server receives requirements through voice and gesture input from the user and analyzes the user's emotional state based on these requirements. By combining an emotion engine and a generative artificial intelligence model, it identifies products that best match the user's needs and emotions using data collected from e-commerce platforms. When collecting this product data, the server obtains product images, prices, and descriptions via APIs and uses image recognition technology to analyze the features of the product images, easily selecting products that meet the requirements.

[0581] The device, specifically smart glasses, receives product suggestions generated from the server and displays them directly in the user's field of vision. This allows the user to intuitively view suggested products on their visual device and, if necessary, purchase them directly using the purchase link. User feedback on the suggestions is also taken into consideration, and an emotion engine analyzes this feedback to further optimize the suggestions.

[0582] For example, if a user voice-inputs "blue sneakers, domestic manufacturer, under 10,000 yen, in a hurry," the server will suggest and display blue sneakers that can be delivered quickly, which the user can then view using smart glasses. In this way, a system that combines an emotion engine and image recognition technology allows users to efficiently find products that meet their needs.

[0583] An example of a prompt message is, "Blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry."

[0584] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0585] Step 1:

[0586] The user inputs product requirements via voice or gestures through smart glasses. The device receives this information in real time and converts it into text data. Input requirements might include phrases like, "Blue sneakers, domestic manufacturer, under 10,000 yen, urgent." The output is data ready to be sent to the server in text format.

[0587] Step 2:

[0588] The server analyzes the text data received from the terminal and uses an emotion engine to estimate the user's emotional state. The input includes the user's requirements and their context, obtained from step 1. The emotion engine recognizes, for example, "hurrying" as a negative emotion. The output of this analysis is information about the user's emotional state.

[0589] Step 3:

[0590] The server uses a generative artificial intelligence model to generate product suggestions based on received requirements and emotional states. In this process, the server collects product data via the e-commerce platform's API. The input is analyzed user requirements and emotional information, and the output is a list of suggested products. Specifically, products that best match the user's requirements and offer fast delivery are selected.

[0591] Step 4:

[0592] The server sends the generated product suggestions to the terminal, and the suggestions are displayed on the smart glasses. The input is the product list generated in step 3, and the output is the product information displayed in the user's field of view. The user can review the visual information and select a specific product.

[0593] Step 5:

[0594] The user uses smart glasses to review suggestions and purchase items directly by selecting a purchase link. The input is the purchase link for the selected item, and the output is a webpage containing the purchase procedure. Furthermore, an example of a prompt message used until the purchase is completed is, "Blue sneakers, domestic manufacturer, under 10,000 yen. In a hurry."

[0595] Step 6:

[0596] The system receives feedback on user suggestions again and generates new product suggestions as needed. The input is user feedback on the suggestions, which the emotion engine analyzes and uses to improve the next suggestion. The output is an improved suggestion for the next product.

[0597] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0598] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0599] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0600] [Fourth Embodiment]

[0601] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0602] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0603] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0604] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0605] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0606] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0607] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0608] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0609] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0610] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0611] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0612] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0613] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] This invention provides a system that offers an interface for users to quickly identify and obtain desired products. Users input their desired product requirements (e.g., color, brand, price range, etc.) into a chat interface on their device. This interface provides means for receiving and processing the user's input.

[0615] The terminal immediately transmits the user's requirements to the server. This server is connected to an e-commerce platform and has the means to collect product data based on the user's requirements. Specifically, the server accesses the relevant platform via the internet and collects images, prices, descriptions, etc., of products that are considered to match the requirements.

[0616] The server collects product data and then analyzes it using a generative artificial intelligence model. This AI model compares the input requirements information with the collected product data and has a means to suggest the most suitable product to the user. The suggested product includes product images, price information, and purchase links.

[0617] The generated product suggestions are sent from the server to the user's terminal. The user can review these suggestions on their terminal screen. The user can then determine if the suggested products meet their requirements, and if they feel they do not, they can use feedback to send new requirements or suggestions for improvement to the server. This feedback is used by the server to re-analyze the product data and generate new suggestions.

[0618] As a concrete example, consider a scenario where a user enters the requirements "blue sneakers, domestic brand, under 10,000 yen." The terminal sends this information to the server, which then collects information on matching sneakers from the corresponding e-commerce platform. A generative artificial intelligence model analyzes the information and generates optimal product suggestions, presenting the user with several options. This process allows the user to efficiently discover the desired product and make a purchase decision.

[0619] The following describes the processing flow.

[0620] Step 1:

[0621] The user enters the requirements for the desired product into the device's chat interface. Specifically, they specify the product's color, brand, price range, etc., in text format.

[0622] Step 2:

[0623] The terminal sends the requirements entered by the user to the server. This data transfer occurs in real time and uses a secure protocol.

[0624] Step 3:

[0625] The server analyzes the user's requirements. A generative artificial intelligence model extracts the necessary information from the user's requirements and sets criteria for use in product searches.

[0626] Step 4:

[0627] The server accesses the e-commerce platform's API to collect product data that meets the user's requirements. Specifically, it retrieves product images, prices, inventory information, descriptions, and other relevant data.

[0628] Step 5:

[0629] The server analyzes the collected product data using a generative artificial intelligence model. This model compares the content and selects the product that best matches the user's requirements.

[0630] Step 6:

[0631] The server generates product suggestions based on the analysis results. These suggestions include detailed information about suitable products and are formatted for display on the user's device.

[0632] Step 7:

[0633] The server sends the generated product suggestions to the user's terminal. Once the data transfer is complete, the terminal displays the received product suggestions on its screen.

[0634] Step 8:

[0635] The user reviews the product suggestions displayed on their device screen. If they are satisfied with the suggested products, they can access a link to proceed with the purchase.

[0636] Step 9:

[0637] If a user is not satisfied with the proposal, they can send feedback to the server via the chat interface. This includes redefining requirements or adding new conditions.

[0638] Step 10:

[0639] The server receives feedback from the user and collects and analyzes product data again based on the new requirements. New product suggestions are generated and sent back to the user.

[0640] (Example 1)

[0641] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] Technology is needed to quickly identify the products consumers want and provide them with a suitable purchasing experience. Currently, consumers have to manually search through a vast amount of product information to find what suits their needs, which is time-consuming and laborious. Furthermore, inappropriate product suggestions can cause consumers stress. Solving this problem is essential.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0644] In this invention, the server includes means for enabling data communication to process requests obtained from users, means for collecting information from a network marketplace, and means for analyzing the information using a machine learning algorithm and selecting the optimal product. This enables consumers to efficiently find products that meet their requirements and make purchasing decisions without stress.

[0645] "Requests obtained from users" refers to the preferences and requirements that consumers input as criteria for selecting products.

[0646] "Means that enable data communication" refers to technologies that have the functionality of communication protocols and interfaces for sending and receiving information between consumers and servers.

[0647] "Means of collecting information from network markets" refers to technologies for obtaining necessary product data from e-commerce platforms via the internet, and includes methods such as APIs and web scraping.

[0648] "Methods of analyzing information using machine learning algorithms" refer to algorithms that automatically evaluate collected product data and find the best option for consumer needs, and these may include neural networks and statistical models.

[0649] "Means for selecting the optimal product" refers to a function that automatically selects the product that best matches the consumer's needs from among multiple options based on analysis.

[0650] "Proposals containing purchase identifiers" refer to product proposals presented to consumers that include links or buttons to facilitate purchase.

[0651] The embodiments for carrying out the present invention will be described in detail below.

[0652] This invention begins with a user inputting the requirements for a specific product using a terminal. The user inputs the characteristics and conditions of the product they want (e.g., "blue sneakers, domestic brand, under 10,000 yen") as prompt text into the terminal's chat interface. The terminal recognizes this prompt text, converts it into the appropriate data format, and sends it to the server.

[0653] Based on the user's requirements received, the server uses APIs from multiple e-commerce platforms, such as major online malls and various e-commerce sites, via an internet-connected system to collect relevant product information. A secure communication protocol using HTTPS is employed for information collection.

[0654] Subsequently, the server analyzes the collected product information using a generative AI model. This AI model is implemented using machine learning libraries such as TensorFlow and PyTorch, and employs sophisticated algorithms based on a large amount of training data for data analysis. The AI ​​compares the user's requirements with the data for each product and selects the most suitable product candidate.

[0655] The data for the suggested products (e.g., product name, price, image, purchase link) is sent from the server to the user's device. The device displays this information in a user-friendly format, allowing the user to intuitively evaluate the suggested products.

[0656] If a user is dissatisfied with a proposal, they can send new requirements or suggestions for improvement to the server through feedback. Based on this feedback, the server uses the AI ​​model to re-analyze the data and make revised suggestions, aiming to improve user satisfaction.

[0657] This system allows users to quickly and efficiently find products that meet their needs and make purchase decisions.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The user enters the requirements for the desired product as a prompt message into the chat interface via their device. This prompt message includes specific product characteristics and conditions (e.g., "blue sneakers, domestic brand, under 10,000 yen"). As a result of the input, the device generates data on the user's requirements.

[0661] Step 2:

[0662] The terminal formats the user's input requirements data and sends it to the server. Data formatting involves converting the user's natural language input into a structured data format (e.g., JSON). The output is the formatted data sent to the server.

[0663] Step 3:

[0664] The server requests product information from the e-commerce platform's API based on the user's requirements data received. Secure communication is ensured by including API keys and authentication information. The output is a collection of product data obtained from each platform.

[0665] Step 4:

[0666] The server analyzes the collected product data using a generative AI model. Machine learning algorithms are applied to compare and evaluate the user's requirements against the collected data. The input consists of requirement data and product data stored on the server, and the output is a list of highly suitable products. The server then selects the optimal recommendation based on the analysis results.

[0667] Step 5:

[0668] The server sends the selected, optimal product suggestions to the user's terminal in data format. This transmission uses JSON format data via a RESTful API. The output is product suggestion data that can be interpreted on the user's terminal.

[0669] Step 6:

[0670] The device displays received product suggestions on its screen, providing the user with visual information. A list including product names, images, prices, and purchase links is presented to the user. The user then reviews this list and makes selections and provides feedback.

[0671] Step 7:

[0672] Users input feedback on the proposed products via their terminals, including new requirements and improvement requests. The feedback data is sent to a server, which is then prepared to incorporate it into future proposals.

[0673] (Application Example 1)

[0674] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0675] In today's world, it is difficult and time-consuming for consumers to efficiently select the right products from a vast amount of information. There is a need for a solution to this problem, enabling consumers to find products quickly and accurately.

[0676] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0677] In this invention, the server includes means for human-computer interaction to process requirements obtained from a user, means for collecting information from a digital marketplace platform based on those requirements, and means for analyzing the collected information and using a machine learning model to generate optimal suggestions for the user's requirements. This enables the user to efficiently obtain product information that meets their needs.

[0678] "Means of interaction between humans and computers" refers to interfaces that enable users and computers to exchange information through natural language or text.

[0679] A "digital marketplace platform" is an online trading infrastructure for buying and selling goods and services via the internet.

[0680] "Means of information gathering" refers to a system for collecting necessary information from the internet and other data sources.

[0681] A "machine learning model" is an algorithm that learns from data and provides the optimal output for a specific purpose.

[0682] A "computer device" is an electronic device capable of processing and storing information, and includes smartphones and personal computers.

[0683] "Enter product requirements by voice or text" means that the user communicates the specifications of the product they want to the system through speaking or keyboard input.

[0684] An "application that automatically provides relevant information" is a program that quickly presents relevant product data based on conditions entered by the user.

[0685] This invention utilizes a computer device (e.g., a smartphone) with an interface that allows the user to input product requirements via voice or text. Through this interface, the user can input product specifications without having to visit a store. The input information is then quickly transmitted to a server.

[0686] The server collects relevant information from the digital marketplace platform based on the user's requirements. The collected information is analyzed by a machine learning model (e.g., the "transformers" library) to generate product suggestions that best meet the user's requirements. These suggestions include product images, prices, and reference links.

[0687] The generated product suggestions are sent from the server to the user's computer, where the user can review them. If the suggestions do not meet the user's requirements, the user can provide feedback to the system. This feedback is processed by the server, a new suggestion is generated, and it is presented to the user again.

[0688] For example, if a user has the requirement "blue sneakers, Japanese brand, under 10,000 yen," the server will input this into a computer, gather relevant information, and suggest the best product. An example of a prompt would be, "When the user says 'blue sneakers, under 10,000 yen,' suggest only the best products." Through this process, users can easily and effectively select products and make purchasing decisions.

[0689] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0690] Step 1:

[0691] The user inputs the requirements for their desired product via voice or text through the computer's interface. This input includes product specifications (e.g., color, brand, price), and the computer retrieves this information and prepares to send it to the server. A "human interface device" is used to pre-process the input using natural language processing technology.

[0692] Step 2:

[0693] The terminal sends the acquired user requirements to the server. The server receives this input and, based on it, collects relevant product information from the digital marketplace platform. Using the entered keywords, information is collected using APIs and scraping techniques. The output is a data set of the relevant products.

[0694] Step 3:

[0695] The server analyzes the collected product information. Here, it uses a generative AI model (e.g., natural language understanding using "transformers") to select the product that best suits the user's requirements. The input is the collected data set, and the server performs data evaluation to identify the optimal product from it, outputting a list of highly suitable products.

[0696] Step 4:

[0697] The server generates product suggestions selected through analysis and sends this information to the terminal. The suggestions include product images, prices, and purchase links. The output here is a list of product suggestions that the user can review, allowing them to make specific product selections.

[0698] Step 5:

[0699] Users review the suggestions on their devices and provide feedback. This feedback may include satisfaction levels and new requirements. This feedback is sent to the server and used as input data to generate new product suggestions.

[0700] Step 6:

[0701] The server analyzes user feedback and uses the AI ​​model again to generate new suggestions. New user requirements are incorporated into the data, and steps 2 through 4 are repeated. This allows for more refined product suggestions, leading to improved user satisfaction.

[0702] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0703] This invention is a system that combines an emotion engine and provides an interface for users to quickly identify and obtain desired products. First, the user enters their desired product requirements into a chat interface via a terminal. This interface has the function of receiving user input in real time and sending it to the server.

[0704] The server analyzes the requirements entered by the user while simultaneously recognizing the user's emotional state through an emotion engine. The emotion engine infers emotions from the user's text input and generates data to adjust suggestions as needed. This information is considered a crucial factor in product selection by the generative artificial intelligence model.

[0705] The server accesses the e-commerce platform and collects appropriate product data based on the user's requirements and sentiments. Specifically, it retrieves product images, prices, descriptions, etc., from the platform's API. In this process, image recognition technology is also used to analyze the features of product images and identify products that meet the user's requirements.

[0706] The collected product data is analyzed using a generative artificial intelligence model. This model compares the product data with user requirements, including sentiment information, to select the most suitable product. The selected product is then reconstructed as a product suggestion, which includes detailed product information and a purchase link.

[0707] The generated product suggestions are sent to the user's device and displayed. The user can review these suggestions and select products they are satisfied with. If the user is dissatisfied with the suggestions, the sentiment engine checks the feedback and generates new suggestions as needed. These improved suggestions are then sent back to the device.

[0708] For example, if a user requests "blue sneakers, domestic brand, under 10,000 yen," and is in a negative and urgent emotional state, the server will use this information to quickly identify suitable products and highlight suggestions for items that can be delivered sooner. This system allows users to efficiently find products that meet their needs and proceed with their purchase.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] The user enters the requirements for the desired product into the device's chat interface. This includes the product's color, brand, and price range.

[0712] Step 2:

[0713] The terminal transmits data entered by the user to the server in real time. During this process, the data is converted to an appropriate format and transferred using secure communication methods.

[0714] Step 3:

[0715] The server analyzes the received requirements data. Simultaneously, it activates the emotion engine to analyze the user's emotions from the input text information. This analysis is then used to refine the proposed content.

[0716] Step 4:

[0717] The server connects to the e-commerce platform's API and collects product data based on the user's requirements and emotional state. The collected data includes product images, prices, and detailed information, and is analyzed as needed using image recognition technology.

[0718] Step 5:

[0719] The server uses a generative artificial intelligence model to analyze collected product data and select the most suitable product based on user requirements and emotional state. This model optimizes itself by considering the characteristics of each product and the user's satisfaction and dissatisfaction.

[0720] Step 6:

[0721] The server generates product suggestions based on the selected product information. These suggestions include product images, prices, inventory information, and purchase links, formatted in a format suitable for the user's device.

[0722] Step 7:

[0723] The server sends the generated product suggestions to the user's device. A notification appears on the device so the user can immediately view and check the suggested items.

[0724] Step 8:

[0725] Users review the product suggestions displayed on their device and, if satisfied, click the purchase link included in the suggestion to proceed with the purchase. If dissatisfied, they can provide feedback via the chat interface.

[0726] Step 9:

[0727] The server receives user feedback and generates new suggestions. The user's requirements are redefined based on the feedback, and the sentiment engine takes this into consideration again.

[0728] Step 10:

[0729] The server generates improved product suggestions again and sends them back to the user's terminal. By repeating this process, the accuracy of the suggestions improves until the user is satisfied.

[0730] (Example 2)

[0731] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] Traditional e-commerce systems made it difficult for users to quickly identify the products they wanted, and also made it difficult for them to find products that suited their feelings and circumstances from among the suggested items. Furthermore, there was a lack of mechanisms to efficiently incorporate feedback into future suggestions when suggested products did not meet the user's expectations.

[0733] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0734] In this invention, the server includes communication means for processing information obtained from the user, means for collecting product information from an e-commerce system based on said information, and means for analyzing the user's emotions using emotion analysis means and reflecting this in product suggestions. This makes it possible to provide product suggestions optimized for the user's emotions and circumstances.

[0735] "Communication means for processing information obtained from users" refers to technical means for receiving product requirements transmitted by users through their terminals in real time and transmitting them to a server.

[0736] "Means of collecting product information from e-commerce systems" refers to a method by which a server obtains product-related data from a third-party e-commerce platform via a network.

[0737] "A means of generating proposals using a generation algorithm" refers to an algorithm that selects the most suitable product based on acquired product information and user requirements, and then proposes it to the user.

[0738] "Means for sending product suggestions to user devices" refers to a technology that sends product suggestions generated on a server to a user terminal and displays the results on the user's screen.

[0739] "A means of receiving user feedback and generating new product proposals" refers to a system that creates new product proposals based on user feedback and changes in requests, and then resends them.

[0740] "Emotional analysis methods" are technologies that analyze text input from users, identify the user's emotional state, and reflect that in the suggested content.

[0741] "Methods using image analysis technology" refer to techniques that analyze product images, extract their features, and select products that meet user requirements.

[0742] "Means of providing functionality including purchase links" refers to interface technology that presents users with a link that allows them to directly access the proposed product, and enables them to purchase the product through that link.

[0743] The system of this invention provides an interface for users to quickly identify and purchase products via a terminal. Users input their requirements for desired products using a chat interface on their terminal. The terminal transmits this information to the server in real time.

[0744] The server receives user input via communication methods and uses sentiment analysis technology to recognize the user's emotional state from the text. Natural language processing algorithms are used for sentiment analysis. Based on user requirements and emotional information, the server collects product data via the e-commerce system's API. Image recognition technology is used to extract characteristics from product images and identify the product best suited to the user's requirements.

[0745] The collected product information is analyzed using a generative AI model to create product suggestions that best suit the user's requirements. These suggestions include detailed product information and purchase links. The server sends the generated product suggestions to the user's device, allowing the user to select products that meet their needs. If the user is dissatisfied with the suggestions, they can submit feedback, and the server uses this feedback to generate new product suggestions.

[0746] As a concrete example, suppose a user specifies the conditions as "blue sneakers, domestic manufacturer, under 10,000 yen," and is emotionally in a hurry. In this case, the user can enter the prompt message as "I'm looking for blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry, so I need them as soon as possible." The server receives this and highlights suggestions for products that can be delivered the same day. This allows the user to quickly find and purchase a product that meets their needs.

[0747] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0748] Step 1:

[0749] The user enters the requirements for the desired product in the terminal's chat interface. The entered information includes specific elements such as the product's color, manufacturer, and price range. The terminal receives the user's requirements as text data and sends it to the server.

[0750] Step 2:

[0751] The server receives text data sent from the terminal and analyzes the user's requirements using natural language processing techniques. The analysis extracts information such as product category, price range, and brand. Simultaneously, sentiment analysis techniques are used to recognize the user's emotional state from the text and extract that sentiment information. The output at this stage consists of the analyzed requirements and sentiment information.

[0752] Step 3:

[0753] The server uses the e-commerce platform's API to collect relevant product information based on the analyzed requirements and sentiment data. This information includes product names, images, prices, and descriptions. Image recognition technology is used to analyze the features of product images and identify those that match the user's requirements. The collected data then serves as input for the next step.

[0754] Step 4:

[0755] The server inputs the collected product information into a generating AI model, which compares the product data with the user's requirements. The generating AI model selects the product best suited to the user and generates product suggestions, including detailed product information and purchase links. At this stage, a list of specific products to suggest is created.

[0756] Step 5:

[0757] The server sends the generated product suggestions to the terminal, which then displays the suggestions to the user. The user reviews the suggestions and selects a product that meets their needs. The output at this stage is the product suggestions that the user can review.

[0758] Step 6:

[0759] Users can submit feedback on product suggestions. The server analyzes the sentiment of the received feedback and generates new suggestions as needed. These new suggestions are then sent back to the user's device and presented to them. This process allows the suggestions to be iteratively improved.

[0760] (Application Example 2)

[0761] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] In modern e-commerce, users often struggle to quickly find the product that best suits their needs from a diverse range of options. Furthermore, since a user's emotional state influences their purchasing intent and satisfaction with suggestions, emotionally sensitive product recommendations are essential. However, traditional systems struggle to provide detailed product recommendations tailored to user requirements and emotional states, highlighting the need for improved user experience.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0764] In this invention, the server includes means for providing an interface for processing requirements obtained from a user, means for collecting product data from an e-commerce platform based on those requirements, and means for analyzing the collected product data and using a generative artificial intelligence model to generate optimal suggestions for the user's requirements and emotional state. This makes it possible to quickly and accurately provide product suggestions that take the user's emotions into consideration.

[0765] An "interface for processing user requirements" is an interactive platform where users can input the features and conditions of the products they desire.

[0766] An "e-commerce platform" is a system that provides the foundation for trading goods and services over the internet.

[0767] "Means of collecting product data" refers to the processes and technologies used to obtain detailed product information from e-commerce platforms.

[0768] A "generative artificial intelligence model" is an artificial intelligence model designed to generate optimal product suggestions based on user requests and emotional states.

[0769] A "visual device" is a device that can present information to a user visually, and includes, for example, smart glasses and smartphones.

[0770] "Emotional state" refers to the psychological state or mood analyzed from the user's text input or voice.

[0771] "Image recognition technology" is a technology that analyzes image data to extract its content and features and identify them.

[0772] A "purchase link" is a web link that allows a user to initiate the purchase process by selecting it.

[0773] The system of this invention enables users to use smart glasses or other visual devices to search for products online and receive appropriate product recommendations.

[0774] The server receives requirements through voice and gesture input from the user and analyzes the user's emotional state based on these requirements. By combining an emotion engine and a generative artificial intelligence model, it identifies products that best match the user's needs and emotions using data collected from e-commerce platforms. When collecting this product data, the server obtains product images, prices, and descriptions via APIs and uses image recognition technology to analyze the features of the product images, easily selecting products that meet the requirements.

[0775] The device, specifically smart glasses, receives product suggestions generated from the server and displays them directly in the user's field of vision. This allows the user to intuitively view suggested products on their visual device and, if necessary, purchase them directly using the purchase link. User feedback on the suggestions is also taken into consideration, and an emotion engine analyzes this feedback to further optimize the suggestions.

[0776] For example, if a user voice-inputs "blue sneakers, domestic manufacturer, under 10,000 yen, in a hurry," the server will suggest and display blue sneakers that can be delivered quickly, which the user can then view using smart glasses. In this way, a system that combines an emotion engine and image recognition technology allows users to efficiently find products that meet their needs.

[0777] An example of a prompt message is, "Blue sneakers, domestic manufacturer, under 10,000 yen. I'm in a hurry."

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] The user inputs product requirements via voice or gestures through smart glasses. The device receives this information in real time and converts it into text data. Input requirements might include phrases like, "Blue sneakers, domestic manufacturer, under 10,000 yen, urgent." The output is data ready to be sent to the server in text format.

[0781] Step 2:

[0782] The server analyzes the text data received from the terminal and uses an emotion engine to estimate the user's emotional state. The input includes the user's requirements and their context, obtained from step 1. The emotion engine recognizes, for example, "hurrying" as a negative emotion. The output of this analysis is information about the user's emotional state.

[0783] Step 3:

[0784] The server uses a generative artificial intelligence model to generate product suggestions based on received requirements and emotional states. In this process, the server collects product data via the e-commerce platform's API. The input is analyzed user requirements and emotional information, and the output is a list of suggested products. Specifically, products that best match the user's requirements and offer fast delivery are selected.

[0785] Step 4:

[0786] The server sends the generated product suggestions to the terminal, and the suggestions are displayed on the smart glasses. The input is the product list generated in step 3, and the output is the product information displayed in the user's field of view. The user can review the visual information and select a specific product.

[0787] Step 5:

[0788] The user uses smart glasses to review suggestions and purchase items directly by selecting a purchase link. The input is the purchase link for the selected item, and the output is a webpage containing the purchase procedure. Furthermore, an example of a prompt message used until the purchase is completed is, "Blue sneakers, domestic manufacturer, under 10,000 yen. In a hurry."

[0789] Step 6:

[0790] The system receives feedback on user suggestions again and generates new product suggestions as needed. The input is user feedback on the suggestions, which the emotion engine analyzes and uses to improve the next suggestion. The output is an improved suggestion for the next product.

[0791] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0792] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0793] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0794] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0795] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0796] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0797] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0798] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0799] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0800] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0801] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0802] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0803] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0804] 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.

[0805] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0806] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0807] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0808] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0809] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0810] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0811] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0812] The following is further disclosed regarding the embodiments described above.

[0813] (Claim 1)

[0814] A means of providing an interface for processing requirements obtained from the user,

[0815] A means for collecting product data from an e-commerce platform based on the said requirements,

[0816] A method that uses a generative artificial intelligence model to analyze collected product data and generate optimal suggestions for user requirements,

[0817] A means of sending the generated product suggestions to the user's terminal,

[0818] A means for receiving user feedback on the proposal and generating a new product proposal,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, further comprising means for analyzing the features of product images using image recognition technology when collecting product data and for selecting products based on user requirements.

[0822] (Claim 3)

[0823] The system according to claim 1, further comprising means for providing an interface in which a suggestion to a user includes a purchase link, and the user can directly purchase the product by clicking the link.

[0824] "Example 1"

[0825] (Claim 1)

[0826] A means to enable data communication for processing requests obtained from users,

[0827] A means for collecting information from the network market based on this requirement,

[0828] A method that uses machine learning algorithms to analyze collected information and select the product best suited to the user's needs,

[0829] A means for notifying the user device of the generated product suggestions,

[0830] A means for receiving a user's response to the proposal and generating a new product proposal,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, further comprising means for analyzing the characteristics of product images using image processing technology when collecting information and for selecting products based on user requirements.

[0834] (Claim 3)

[0835] The system according to claim 1, further comprising means for providing an interface in which a suggestion to a user includes a purchase identifier, and the user can directly purchase the product by selecting the identifier.

[0836] "Application Example 1"

[0837] (Claim 1)

[0838] A means of processing requirements obtained from users through human-computer interaction,

[0839] Means for collecting information from a digital market platform based on the said requirements,

[0840] A method that uses machine learning models to analyze collected information and generate optimal suggestions for user requirements,

[0841] Means for transmitting the generated proposal to a computer,

[0842] A means for receiving user feedback on the proposal and generating the proposal again,

[0843] A means having an application installed on a computer that allows product requirements to be entered via voice or text and automatically provides relevant information,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, further comprising means for analyzing image features using computer vision technology when collecting information and for making selections based on user requirements.

[0847] (Claim 3)

[0848] The system according to claim 1, further comprising means for providing an interface that allows the user to directly obtain information by manipulating the reference, wherein the suggestion to the user includes a reference for purchase.

[0849] "Example 2 of combining an emotion engine"

[0850] (Claim 1)

[0851] A means of communication for processing information obtained from the user,

[0852] A means for collecting product information from an e-commerce system based on the said information,

[0853] A means for analyzing collected product information and generating optimal suggestions based on the user's information using a generation algorithm,

[0854] A means for transmitting the generated product proposal to the user device,

[0855] A means for receiving user feedback on the proposal and generating a new product proposal,

[0856] A means of analyzing user emotions using emotion analysis tools and reflecting them in product proposals,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for analyzing the characteristics of product images using image analysis technology when collecting product information and for selecting products based on user information.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for providing a function that allows the user to directly purchase the product by selecting the link, wherein the suggestion to the user includes a purchase link.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means of providing an interface for processing requirements obtained from the user,

[0865] A means for collecting product data from an e-commerce platform based on the said requirements,

[0866] A means of analyzing collected product data and using a generative artificial intelligence model to generate optimal suggestions based on user requirements and emotional state,

[0867] A means for sending the generated product suggestions to the user terminal and displaying them on a visual device,

[0868] A means for receiving user feedback on the proposal and generating a new product proposal,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, further comprising means for analyzing the features of product images using image recognition technology when collecting product data, and for selecting products based on user requirements and emotions.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for providing an interface that allows the user to directly purchase the product by selecting the link, wherein the suggestion to the user includes a purchase link, and further comprising means for displaying the interface on a visual device. [Explanation of Symbols]

[0874] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of providing an interface for processing requirements obtained from the user, A means for collecting product data from an e-commerce platform based on the said requirements, A method that uses a generative artificial intelligence model to analyze collected product data and generate optimal suggestions for user requirements, A means of sending the generated product suggestions to the user's terminal, A means for receiving user feedback on the proposal and generating a new product proposal, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the features of product images using image recognition technology when collecting product data and for selecting products based on user requirements.

3. The system according to claim 1, further comprising means for providing an interface in which a suggestion to a user includes a purchase link, and the user can directly purchase the product by clicking the link.

Images