System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a query from a user device; means for analyzing user query content using a generative AI model to extract a potential need; means for searching a database for relevant products or services based on the extracted need to generate a personalized recommendation result; and means for sending the generated recommendation result to the user device for display to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] On conventional e-commerce sites, users have to search for products based on their own subjective opinions and knowledge, making it difficult to find the products and services they are actually looking for. Furthermore, search results can be inaccurate or fail to capture users' latent needs, reducing their motivation to purchase. Another problem is that post-purchase feedback is not fully utilized, resulting in a decrease in the accuracy of recommendations for the next purchase. [Means for solving the problem]

[0005] To address the above-mentioned issues, the present invention provides a system that includes the following: a means for receiving an inquiry from a user terminal; a means for analyzing the user's inquiry using a generative AI model to extract latent needs; a means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results; and a means for transmitting the generated recommendation results to the user terminal and displaying them to the user. The system also includes a means for the generative AI model to generate additional questions as needed and transmit them to the user terminal; a means for generating a product or service comparison table based on the generated recommendation results and transmitting it to the user terminal; and a means for collecting feedback from the user after a purchase and storing it in a database. The system also includes a means for using the collected feedback to improve the accuracy of subsequent recommendations; a means for analyzing the collected big data to generate trend and fashion information and provide it to users and manufacturers; and a means for using a sales bot function to interactively provide users with detailed product information to stimulate their purchasing desire. In this way, effective product recommendations based on the user's actual needs can be realized, significantly improving the purchasing experience.

[0006] A "user terminal" is an electronic device operated by a user, and includes a personal computer, a smartphone, and the like.

[0007] An "inquiry" is an action in which a user inputs their wishes or requests in natural language, in order to request information from the system.

[0008] A "generative AI model" is an artificial intelligence program that uses machine learning algorithms to analyze input natural language, understand its meaning, and generate an appropriate response.

[0009] "Analysis" is the process by which a generative AI model processes input natural language text to identify the user's intent and needs.

[0010] "Latent needs" are essential user desires and requests that are not explicitly stated by the user but are inferred through analysis.

[0011] A "database" is a structured collection of data that contains information about related products and services.

[0012] "Personalized recommendation results" are product and service recommendations that are individually tailored based on the user's needs.

[0013] A "comparison table" is a table that compares the features, ratings, prices, etc. of multiple products or services, and is intended for users to compare and consider.

[0014] "Feedback" refers to impressions and opinions such as ratings and reviews submitted by users after purchase.

[0015] "Big data" is a collection of large amounts of diverse data that can be analyzed to discover trends and patterns.

[0016] The "salesbot function" is an automatic response system that uses AI, providing detailed product information to users in an interactive format, stimulating their desire to purchase.

[0017] "Trend information" is information about the latest trends and consumer trends obtained from analyzed big data.

[0018] "Additional questions" are questions that the generative AI model automatically generates to gain a more detailed understanding of the user's inquiry. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This system is an e-commerce concierge service that uses a generative AI model and includes multiple means for proposing optimal products and services based on user inquiries. A specific embodiment of this system is described below.

[0041] User inquiries

[0042] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they can make a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0043] Receiving and analyzing inquiries

[0044] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even those not explicitly stated by the user.

[0045] For example, if a user enters, "I'm planning a family trip this summer," the server can generate follow-up questions such as, "Where are we going, what is our budget, and what are the specific activities?" to elicit further information from the user.

[0046] Generate and present recommendations based on needs

[0047] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the device, which then displays the recommendations to the user.

[0048] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0049] Compare recommendations and get detailed information

[0050] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0051] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0052] Purchasing support and feedback collection

[0053] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0054] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0055] Big data analysis and trend information provision

[0056] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0057] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0058] Sales Bot Features

[0059] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0060] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0061] As described above, this system utilizes generative AI models to recommend optimal products and services based on user needs, significantly improving the user's purchasing experience.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0065] Step 2:

[0066] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0067] Step 3:

[0068] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0069] Step 4:

[0070] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?"

[0071] Step 5:

[0072] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0073] Step 6:

[0074] The user answers additional questions and inputs specific information into the terminal (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity").

[0075] Step 7:

[0076] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0077] Step 8:

[0078] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0079] Step 9:

[0080] The device receives the recommendation results from the server and displays them to the user. The sales bot function interactively explains the product's appeal, encouraging the user to purchase.

[0081] Step 10:

[0082] Users can compare the recommendations and select the most suitable product or service. A comparison table is provided to check detailed information such as features, ratings, and prices.

[0083] Step 11:

[0084] Once the user decides to purchase, the device provides a purchase link and assists in the purchase process, which the user clicks to complete the purchase.

[0085] Step 12:

[0086] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0087] Step 13:

[0088] Users input ratings and reviews of purchased products into their devices and send them to the server, which stores the feedback in a database.

[0089] Step 14:

[0090] The server analyzes the collected feedback and uses it as data to improve the accuracy of the next recommendation. It also generates trend information and provides it to other users and manufacturers.

[0091] Step 15:

[0092] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[0093] Step 16:

[0094] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern e-commerce, users have difficulty quickly and accurately selecting the most suitable product or service from a wide variety of options. Furthermore, there is a lack of methods to improve the purchasing experience by deeply understanding users' needs and making recommendations based on those needs. Current systems are unable to properly extract users' latent needs and make recommendations that increase satisfaction. Furthermore, there is an insufficient mechanism for incorporating user feedback into future recommendations.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for receiving inquiries from user devices, means for analyzing the content of the user's inquiries using a generative artificial intelligence model and extracting latent demand, means for searching a data storage device for related products and services based on the extracted demand and generating personalized recommendation results, means for transmitting the generated recommendation results to the user device and displaying them to the user, and means for collecting feedback submitted by the user and storing the feedback in the data storage device. This enables more accurate product and service recommendations based on the user's needs, improving the user's purchasing experience. Furthermore, the collected feedback is used to improve the accuracy of future recommendations, enabling continuous service improvement.

[0100] "User device" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0101] "Inquiry" means a question or request for information or assistance sought by a User.

[0102] A "generative artificial intelligence model" refers to a machine learning model that analyzes the content of a user's inquiry and understands their intentions and latent needs.

[0103] "Latent needs" refer to relevant requests and desires that users have not explicitly stated but that need to be taken into consideration.

[0104] "Data storage device" refers to a database or storage system for storing information about products or services.

[0105] "Personalized recommendation results" refer to suggestions and recommendations that are optimized for a particular user and are generated based on the user's inquiry and extracted needs.

[0106] "Feedback" refers to opinions and ratings provided by users after purchasing a product or using a service.

[0107] This invention relates to an e-commerce concierge service system that uses a generative AI model. The system aims to propose optimal products and services based on user inquiries.

[0108] User inquiries

[0109] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0110] Receiving and analyzing inquiries

[0111] The user's device sends the inputted inquiry to the server, which then uses a generative AI model (e.g., GPT-4) to analyze the user's inquiry and extract latent needs. The analysis process infers needs, even if the user has not explicitly stated them.

[0112] For example, if a user enters "I'm planning a family trip this summer," the server can generate follow-up questions such as "Where do you want to go, what is your budget, and what specific activities do you want to do?" to elicit further information from the user. The user then enters answers to the follow-up questions, which are then sent back to the server.

[0113] Generate and present recommendations based on needs

[0114] The server searches a database based on the collected information to find related products and services. The server then generates personalized recommendation results based on the products and services found. For example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling." The generated recommendation results are then sent to the terminal and displayed to the user.

[0115] Comparison of recommendation results

[0116] The server creates a comparison table of multiple products and services based on the generated recommendation results. This comparison table includes detailed information such as prices, ratings, and activities offered. The server sends the comparison table to the terminal, which displays it to the user. The user can make the best choice based on the detailed information.

[0117] Purchasing support and feedback collection

[0118] If the user decides to purchase after viewing the recommendations, the user's device will present a purchase link and assist in the purchase process. After the purchase, the server collects the user's feedback and stores it in a database. This feedback is used to improve the accuracy of recommendations next time. For example, a user may book a resort hotel and provide feedback after their stay such as, "It was comfortable. The staff were very helpful." The server will store this feedback and use it to make suggestions to future users.

[0119] Big data analysis and trend information provision

[0120] The server analyzes the big data collected from all users and generates information on fashion and trends. This information is provided to users and also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies. For example, the server analyzes data that shows "demand for camping is high this summer," and based on that, proposes a sales strategy for new camping equipment to an e-commerce site.

[0121] Sales Bot Features

[0122] Users interact with the sales bot to obtain detailed information about products they are interested in. The server uses the sales bot's functionality to communicate detailed product information and appeal to users, encouraging them to make a purchase. For example, the server might explain, "The seaside resort offers all meals and a wide range of activities. The mountain camping offers an attractive opportunity to experience nature," thereby increasing the user's desire to make a purchase.

[0123] Prompt Sentence Examples

[0124] An example of a user sending a query to a generative AI model:

[0125] "I'm planning a summer trip with my family. Can you recommend some places to go and where to stay?"

[0126] An example where the server generates a follow-up question after parsing:

[0127] "Do you have any destinations, budgets, or specific activities you'd like to do?"

[0128] As a result, this system utilizes generative AI models to recommend optimal products and services based on user needs, improving the user's purchasing experience.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1:

[0131] A user accesses the website or application of the e-commerce concierge service using their own device (PC or smartphone) and inputs a query in natural language. The input query is sent to the server in the form of a prompt sentence such as, "I'm planning a summer trip with my family. What are your recommended destinations and accommodations?"

[0132] Step 2:

[0133] The terminal sends the query entered by the user to the server. The input is text data and is securely transmitted using the HTTPS protocol. The server receives this text data.

[0134] Step 3:

[0135] The server inputs the received text data into a generative AI model (e.g., GPT-4). The generative AI model analyzes this input data, understands the user's inquiry, and extracts latent demands. For example, it infers "destination, budget, and specific activities" from "family trip" and "summer." As output, it generates a follow-up question: "Do you have any preferences for destination, budget, or specific activities?"

[0136] Step 4:

[0137] The server sends the generated follow-up question to the terminal, which displays the question to the user and requests further information, which is then sent as input back to the server.

[0138] Step 5:

[0139] The user inputs answers to the additional questions. For example, the user inputs text such as "Destination: Okinawa. Activity: I would like snorkeling." and sends it to the server via the terminal. The server receives this input data.

[0140] Step 6:

[0141] The server then searches the database using the additional information to find related products and services. Keywords such as "Okinawa" for the destination and "snorkeling" for the activity are used to search the database. The output is a list of related resort hotels and tours.

[0142] Step 7:

[0143] The server creates a personalized recommendation list based on the generated recommendation results. For example, a list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" may be generated. The generated recommendation list is sent from the server to the device.

[0144] Step 8:

[0145] The terminal displays the recommendation list sent from the server to the user, who then begins making a selection based on the displayed list.

[0146] Step 9:

[0147] The server generates a comparison table of multiple products and services based on the generated recommendation results. The comparison table includes detailed information such as prices, ratings, and activities offered. For example, a comparison table of "Hotel A vs. Hotel B vs. Hotel C" is generated. This comparison table is sent to the terminal.

[0148] Step 10:

[0149] The terminal displays the comparison table sent from the server to the user, allowing the user to compare detailed information and make the best choice.

[0150] Step 11:

[0151] If the user decides to purchase after viewing the recommended results, the device will provide a purchase link to assist in the purchase process. This link is sent from the server, and the user clicks on it to complete the purchase.

[0152] Step 12:

[0153] After a purchase, the user provides feedback. The terminal provides a feedback input form, allowing the user to enter their opinions and thoughts. The input feedback is sent from the terminal to the server.

[0154] Step 13:

[0155] The server collects user feedback and stores it in a data storage device, and the feedback data is analyzed to improve the accuracy of the next recommendation.

[0156] Step 14:

[0157] The server generates fashion and trend information based on the collected big data, which is provided to users, manufacturers, and e-commerce sites for use in new product development and sales strategies.

[0158] Step 15:

[0159] Users can use the sales bot function to obtain more detailed information. The server communicates product details and appeal in a conversational format through the sales bot, increasing the user's desire to purchase. Explanations tailored to the user's specific needs are provided in real time.

[0160] (Application example 1)

[0161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0162] Conventional product recommendation systems on e-commerce sites typically display related products when users input search keywords. However, this method makes it difficult to fully reflect the user's specific needs and implicit desires, and does not improve the user experience. Furthermore, users must search for related information themselves, which takes a lot of time and effort. This leads to issues such as a decrease in purchasing motivation and difficulty in finding optimal products and services.

[0163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0164] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, and means for installing a smartphone application that extracts specific needs based on the content of the user's inquiry and finds and recommends related products and services based on the analysis results, thereby making it possible to quickly and accurately provide optimal products and services based on the user's specific needs and wishes.

[0165] A "user terminal" is an electronic device used by a user, and includes devices such as smartphones, tablets, and personal computers.

[0166] An "inquiry" is a request or question that a user inputs to the system, and is input in natural language.

[0167] A "generative AI model" is an artificial intelligence model that uses natural language processing to analyze inquiries entered by users and understand their meaning and intent.

[0168] "Latent needs" refer to expectations and requests that are not explicitly stated by the user but can be inferred from the content of the inquiry.

[0169] "Personalized recommendations" refers to product and service suggestions tailored to a user's specific needs and preferences.

[0170] A "smartphone application" is software that runs on a smartphone and provides a means for receiving user inquiries and displaying analysis results.

[0171] This system is implemented using a user terminal. Specifically, the user terminal is used by installing a smartphone application. This application provides an interface for users to input queries.

[0172] Users launch the smartphone app and input their requests or questions in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0173] The smartphone app sends the user's inquiry to a server, which then uses OpenAI's generative AI model to analyze the inquiry and extract the user's potential needs, such as estimating the necessary camping gear, budget, and number of participants.

[0174] Based on the analysis results, the server then uses the e-commerce platform's search API to search for related products and services and generate personalized recommendations, such as suggesting specific products like a "three-person tent with excellent waterproofing."

[0175] The personalized recommendation results are sent from the server to the user's device and displayed on the smartphone app. The user can compare the presented recommendation results and check detailed information.

[0176] As a concrete example, if a user asks, "I'm going camping with friends in the spring. Do you have any recommended tents?", the generative AI model will extract needs such as "a three-person tent with good waterproofing" and recommend the most suitable product based on that. An example of a prompt is as follows:

[0177] Example prompt sentence:

[0178] User Question: I'm going camping with friends this spring. Can you recommend a tent?

[0179] Identify user needs and provide relevant information.

[0180] This system allows users to quickly and accurately select the best products and services based on their specific needs and desires, improving their purchasing experience.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] (Input) The user launches their smartphone app and inputs their request or question in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0184] (Operation) The terminal receives this natural language input.

[0185] (Output) Prepare the received inquiry as data to be passed on to the next processing step.

[0186] Step 2:

[0187] (Input) The natural language query entered by the user.

[0188] (Operation) The device sends the received query to the server, which analyzes the query using OpenAI's generative AI model.

[0189] (Data processing and calculation) The generative AI model analyzes the input natural language and extracts the user's latent needs, such as guessing the equipment needed for camping, budget, and number of participants.

[0190] (Output) Extracted needs and specific information (e.g., a three-person tent with excellent waterproofing).

[0191] Step 3:

[0192] (Input) Extracted needs and specific information.

[0193] (Operation) Based on the analysis results, the server uses the search API of the EC platform to search for related products and services.

[0194] (Data processing and calculation) A search query is generated and a list of relevant products is obtained by querying the EC platform database.

[0195] (Output) Personalized recommendations (e.g., a list of specific products or services).

[0196] Step 4:

[0197] (Input) Personalized recommendation results.

[0198] (Operation) The server transmits the generated recommendation results to the user terminal.

[0199] (Data processing) Format the recommendation results in a way that is easy for users to understand.

[0200] (Output) Formatted recommendation result data.

[0201] Step 5:

[0202] (Input) The formatted recommendation results sent from the server.

[0203] (Operation) The terminal displays the recommendation results to the user, who can compare the presented recommendation results and check detailed information.

[0204] (Output) Based on the user's confirmation and comparison, further inquiries and feedback information may be provided as needed.

[0205] By going through the above steps, users can be provided with the most suitable products and services quickly and accurately based on their specific needs and desires.

[0206] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0207] This system combines a generative AI model and an emotion engine to suggest optimal products and services based on user inquiries and increase purchasing motivation. A specific embodiment of this system is described below.

[0208] User inquiries

[0209] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). At this time, users input their wishes and requests in natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0210] Receiving and analyzing inquiries

[0211] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even if the user has not explicitly stated them.

[0212] At the same time, the emotion engine recognizes emotions from the user's input and comments during the conversation, and generates appropriate responses accordingly.

[0213] For example, if a user types, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion" and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[0214] Generate and present recommendations based on needs

[0215] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the terminal, which then displays the recommendations to the user.

[0216] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0217] Compare recommendations and get detailed information

[0218] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0219] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0220] Purchasing support and feedback collection

[0221] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0222] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0223] Big data analysis and trend information provision

[0224] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0225] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0226] Sales Bot Features

[0227] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0228] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0229] Utilizing the Emotion Engine

[0230] The emotion engine analyzes the user's emotions in real time and adjusts the way it presents follow-up questions and recommendation results based on that analysis. For example, if the user is determined to be "concerned" after looking at a comparison chart, the emotion engine will support the user by generating follow-up questions such as "What are you unsure about?"

[0231] In this way, an e-commerce concierge service that combines a generative AI model with an emotion engine can recommend optimal products and services based on the user's needs and emotions, significantly improving the purchasing experience.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0235] Step 2:

[0236] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0237] Step 3:

[0238] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0239] Step 4:

[0240] At the same time, the server uses an emotion engine to recognize emotions from the user's input, such as "anxious" or "excited."

[0241] Step 5:

[0242] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?", and generates questions based on the recognized emotions.

[0243] Step 6:

[0244] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0245] Step 7:

[0246] The user answers additional questions and enters specific information into the device (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity."). The emotion engine continues to analyze emotions from the user's answers.

[0247] Step 8:

[0248] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0249] Step 9:

[0250] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0251] Step 10:

[0252] The device displays the recommendation results received from the server to the user. The sales bot function explains the product's appeal in a conversational format, stimulating the user's desire to purchase. For example, it might explain, "Seaside resorts offer all meals and a wide range of activities. Mountain camping offers the appealing opportunity to experience nature."

[0253] Step 11:

[0254] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal.

[0255] Step 12:

[0256] The device displays the comparison table received from the server to the user to help them make a comparison. The emotion engine analyzes the user's reaction and provides additional support based on their emotions. For example, it displays follow-up questions such as "Are you still undecided?"

[0257] Step 13:

[0258] If the user decides to purchase after viewing the recommended results, the device will present the user with a purchase link and assist in the purchase process. The user clicks the link to complete the purchase.

[0259] Step 14:

[0260] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0261] Step 15:

[0262] Users input ratings and reviews of purchased products into their devices and send them to the server. The emotion engine also analyzes the user's emotions from the feedback, including questions such as, "Was it a pleasant experience?"

[0263] Step 16:

[0264] The server stores the feedback in a database and uses it to improve the accuracy of recommendations next time.The server analyzes the collected big data and generates information on trends and fashions.

[0265] Step 17:

[0266] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[0267] Step 18:

[0268] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[0269] The system utilizes generative AI models and an emotion engine to recommend optimal products and services based on users' needs and emotions, improving the purchasing experience.

[0270] Example 2

[0271] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0272] Conventional e-commerce concierge systems provide simple responses to user inquiries and do not fully consider the user's latent needs and emotions. This makes it difficult to efficiently stimulate users' purchasing motivation and to recommend appropriate products and services.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0274] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user inquiry using a generative AI model and extracting latent needs, means for identifying the user's emotions using an emotion engine and generating an appropriate response, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, and means for transmitting the generated recommendation results to the user terminal and displaying them to the user. This makes it possible to recommend products and services that appropriately consider the user's latent needs and emotions, thereby efficiently increasing the user's purchasing motivation.

[0275] A "user terminal" is an electronic device used by a user, such as a personal computer or smartphone, that can communicate with a server via the Internet.

[0276] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to analyze the content of a user's inquiry and extract the latent needs and information contained in the inquiry.

[0277] An "emotion engine" is a system that has the ability to identify a user's emotional state from their input and statements during a conversation, and generate an appropriate response.

[0278] A "database" is an information management system that stores information about products and services and is designed to allow that information to be searched and retrieved.

[0279] "Personalized recommendation results" are proposals for products and services that are customized based on the user's inquiry and needs, and are provided in a form that meets the individual requests of the user.

[0280] "Follow-up questions" are questions generated by the generative AI model as needed to further clarify the user's needs and prompt the user to provide additional information.

[0281] A "comparison table" is a format that displays detailed information such as features, ratings, and prices of multiple products or services in a list format, allowing users to compare them.

[0282] This invention relates to a system for recommending optimal products and services based on user inquiries. The system combines a generative AI model and an emotion engine to analyze the user's needs and emotions, and recommends products and services based on the results.

[0283] Hardware and software used

[0284] The system is implemented using the following hardware and software.

[0285] User terminal: A device that can connect to the Internet, such as a personal computer (PC) or smartphone.

[0286] Server: A computer system for data processing and analysis. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[0287] Generative AI model: An artificial intelligence that performs natural language processing. For example, OpenAI's GPT-4 can be used.

[0288] Emotion engine: An algorithm that identifies emotions from user utterances and generates appropriate responses.

[0289] Database: An information management system that stores and searches information about products and services. For example, you can use AWS's RDS.

[0290] System Operation

[0291] 1. User Inquiries

[0292] Users access the website or application of the e-commerce concierge service using a device such as a PC or smartphone, and input their wishes and requests in natural language. For example, they send a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0293] 2. Receiving and analyzing inquiries

[0294] The device sends the user's input to the server. The server uses a generative AI model to analyze the received inquiry. This analysis extracts the user's latent needs. At the same time, the emotion engine identifies the user's emotions and generates an appropriate response. For example, if the user inputs, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion," and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[0295] 3. Needs-based recommendation generation

[0296] The server searches for relevant products and services from a database based on the extracted needs, and generates personalized recommendations based on the results.

[0297] 4. Display of recommendation results

[0298] The generated recommendation results are sent from the server to the user's device, and the device displays them to the user. For example, if the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the device.

[0299] Examples of concrete examples and prompts

[0300] Examples:

[0301] If the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.The server then generates a comparison table of information such as "Hotel A vs. Hotel B vs. Hotel C: Price, Review Rating, Activities Offered," and displays it to the user.

[0302] Example prompt sentence:

[0303] "Analyze user input and recommend the best products and services based on travel destinations and activities. Focus on using an emotion engine to generate responses based on the user's emotions."

[0304] In this way, by combining a generative AI model with an emotion engine, it becomes possible to make personalized recommendations for products and services that take into account the user's needs and emotions, significantly improving the user's purchasing experience.

[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0306] Step 1:

[0307] Users access the website or application of the e-commerce concierge service using a device such as a personal computer (PC) or smartphone, and input their wishes and requests in natural language. Specifically, they input and submit a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0308] Input: User's inquiry

[0309] Output: Sending query content from user terminal to server

[0310] Step 2:

[0311] The terminal sends the query entered by the user to the server as natural language text.

[0312] Input: The inquiry entered by the user

[0313] Output: Sending query content to the server

[0314] Step 3:

[0315] The server passes the received inquiry to the generative AI model, which analyzes it. This analysis extracts the user's latent needs. The generative AI model uses a natural language processing algorithm to understand the user's inquiry and analyze related keywords and intent. It also uses the extracted information to clarify the user's specific needs.

[0316] Input: Enquiry (natural language text)

[0317] Output: Extraction of potential needs

[0318] Step 4:

[0319] At the same time, the server uses an emotion engine to identify emotions from the user's input. For example, if a user inputs "I don't know where to go," the emotion engine will identify emotions such as "anxiety" or "hesitation." Depending on the identified emotion, the generative AI model will generate an appropriate response.

[0320] Input: Enquiry (natural language text)

[0321] Output: Identified emotions and appropriate responses

[0322] Step 5:

[0323] Based on the extracted needs and emotions, the server searches for relevant products and services from a database that stores information such as product features, ratings, and prices. Based on this information, the server generates personalized recommendation results.

[0324] Input: Potential needs, identified emotions

[0325] Output: Personalized recommendation results

[0326] Step 6:

[0327] The server then sends the generated personalized recommendation results to the user's device. The recommendation results include a list of products and services that meet the user's needs. For example, the recommendation may include specific content such as "Three resort hotels in Okinawa where you can enjoy snorkeling."

[0328] Input: Personalized recommendation results

[0329] Output: Sending recommendation results to the user's device

[0330] Step 7:

[0331] The terminal displays the recommendation results received from the server to the user, who can then browse the displayed recommendation results and check detailed information about the products or services that interest them.

[0332] Input: Recommendation results from the server

[0333] Output: Displaying the recommendations to the user

[0334] Step 8:

[0335] The server generates a comparison table of multiple products and services based on the recommendation results. This comparison table includes detailed information such as features, ratings, and prices. The server transmits this comparison table to the user's terminal, allowing the user to easily compare and consider each product or service.

[0336] Input: Information about products and services based on the recommendation results

[0337] Output: Comparison table

[0338] Step 9:

[0339] The terminal displays the comparison table received from the server to the user, who can then compare the detailed information of each product or service and make the best choice for themselves.

[0340] Input: Comparison table from the server

[0341] Output: Displaying a comparison table to the user

[0342] Step 10:

[0343] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database.

[0344] Input: User's purchase decision

[0345] Output: Provide purchase link and collect feedback

[0346] In this way, the system uses generative AI models and emotion engines to carry out a series of processes to recommend optimal products and services based on user inquiries.

[0347] (Application example 2)

[0348] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0349] Conventional e-commerce concierge systems are unable to make proposals that take into account the user's emotions and real-time stress levels, and are therefore unable to fully increase user satisfaction or purchasing motivation. Furthermore, when presenting personalized recommendations to users, they are unable to respond to changes in the user's emotions, resulting in a limited user experience.

[0350] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0351] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, means for analyzing the user's emotions and adjusting the recommendation results and responses based on the emotions, and means for evaluating the user's comments and actions in real time and making optimal suggestions based on the user's stress level. This enables detailed personalized suggestions that correspond to the user's emotions and stress level and a more satisfying purchasing experience.

[0352] A "user terminal" is a device through which a user enters input and receives information.

[0353] "Inquiry content" refers to information such as wishes, requests, questions, etc. that the user inputs via the terminal.

[0354] A "generative AI model" is a program that uses artificial intelligence technology to analyze input information and generate appropriate responses or suggestions.

[0355] "Latent needs" are requests or necessities that are not explicitly stated by the user but are inferred.

[0356] "Personalized recommendations" are suggestions and information that are customized based on a user's individual characteristics and needs.

[0357] A "database" is a system that stores and manages information about related products and services.

[0358] "Analyzing emotions" means recognizing the user's feelings and emotions at that time from their input and actions.

[0359] "Stress level" refers to the degree of mental tension or strain felt by the user.

[0360] "Real-time evaluation" means instantly analyzing users' comments and actions and taking appropriate action.

[0361] The system for implementing this invention comprises a user terminal, a server, and a database. The user terminal is a device such as a smartphone or a PC, and is used by users to input inquiries and receive related information.

[0362] The server is built using the following hardware and software:

[0363] OpenAI's generative AI model: Used to analyze user inquiries and extract latent needs.

[0364] Sentiment Analysis Engine: Used to analyze emotions from user input, real-time statements, and actions. This engine analyzes voice tone and text data to identify user emotions.

[0365] Database management system: Used to store information on related products and services.

[0366] When a user enters an inquiry from a smartphone or PC, the server analyzes the content using a generative AI model. Potential needs are extracted from the analyzed data, and related products and services are searched for in the database based on these. The server then generates personalized recommendations based on the results and sends them to the user's device.

[0367] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions in real time and generate responses according to their emotions. For example, if the user indicates that they want to relax, the server will suggest routes with beautiful natural scenery and relaxing music.

[0368] For example, if a user inputs "I want to relax on a route with lots of nature," the server will analyze this request using a generative AI model and make a personalized suggestion of "a route with lots of nature." At the same time, the emotion analysis engine will recognize the user's emotion of "wanting to relax" and recommend the most suitable scenic route and music based on that.

[0369] In this way, it is possible to provide more personalized information in real time based on the user's inquiry and their feelings.

[0370] Examples of specific prompts include:

[0371] Example prompt sentence:

[0372] User: I want to relax on a route with lots of nature.

[0373] System: Finding optimal route...

[0374] System: Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory.

[0375] This system provides detailed personalized suggestions based on the user's emotions and stress level, and a more satisfying purchasing experience.

[0376] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0377] Step 1:

[0378] The user inputs the inquiry through the terminal and sends it to the server. This input includes requests and questions in natural language. For example, "I want to relax on a route with lots of nature." The server receives this inquiry.

[0379] Step 2:

[0380] The server analyzes the received inquiry using a generative AI model. The generative AI model processes the text entered by the user and extracts latent needs. For example, needs such as "route with lots of nature" and "want to relax" are analyzed. The input is the user's inquiry, and the output is the extracted latent needs.

[0381] Step 3:

[0382] The server searches a database based on the extracted needs to identify related products and services. Specifically, it searches for information on "routes with plenty of nature" or "places to relax." The input is the potential need, and the output is a list of related products and services.

[0383] Step 4:

[0384] The server uses a sentiment analysis engine to analyze the sentiment from the user's inquiry. For example, if the user wants to relax, the sentiment analysis engine will recognize the sentiment of "relaxation." The input is the user's inquiry, and the output is the analyzed sentiment.

[0385] Step 5:

[0386] Based on the emotional information analyzed by the emotion analysis engine, the server generates optimal recommendation results. These results include personalized information based on the user's emotions. For example, a "Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory" may be generated. The input is the analyzed emotion and a list of related products, and the output is personalized recommendation results.

[0387] Step 6:

[0388] The server sends the generated recommendation results to the user's terminal and displays them to the user. The user receives them and checks the information displayed on the screen. The input is the personalized recommendation results, and the output is the information displayed on the user's terminal.

[0389] Step 7:

[0390] If the user inputs further questions or requests based on the results, the server can generate additional questions and continue the dialogue with the user. The generative AI model again analyzes this information and reassesses underlying needs and emotions. This process can be repeated as necessary. The input is the user's new questions or requests, and the output is additional dialogue content or recommendations.

[0391] This series of steps makes it possible to provide optimal products and services based on the user's emotions and needs.

[0392] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0393] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0394] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0395] [Second embodiment]

[0396] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0397] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0398] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0399] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0400] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0401] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0402] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0403] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0404] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0405] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0406] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0407] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0408] This system is an e-commerce concierge service that uses a generative AI model and includes multiple means for proposing optimal products and services based on user inquiries. A specific embodiment of this system is described below.

[0409] User inquiries

[0410] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they can make a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0411] Receiving and analyzing inquiries

[0412] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even those not explicitly stated by the user.

[0413] For example, if a user enters, "I'm planning a family trip this summer," the server can generate follow-up questions such as, "Where are we going, what is our budget, and what are the specific activities?" to elicit further information from the user.

[0414] Generate and present recommendations based on needs

[0415] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the device, which then displays the recommendations to the user.

[0416] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0417] Compare recommendations and get detailed information

[0418] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0419] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0420] Purchasing support and feedback collection

[0421] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0422] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0423] Big data analysis and trend information provision

[0424] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0425] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0426] Sales Bot Features

[0427] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0428] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0429] As described above, this system utilizes generative AI models to recommend optimal products and services based on user needs, significantly improving the user's purchasing experience.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0433] Step 2:

[0434] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0435] Step 3:

[0436] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0437] Step 4:

[0438] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?"

[0439] Step 5:

[0440] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0441] Step 6:

[0442] The user answers additional questions and inputs specific information into the terminal (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity").

[0443] Step 7:

[0444] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0445] Step 8:

[0446] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0447] Step 9:

[0448] The device receives the recommendation results from the server and displays them to the user. The sales bot function interactively explains the product's appeal, encouraging the user to purchase.

[0449] Step 10:

[0450] Users can compare the recommendations and select the most suitable product or service. A comparison table is provided to check detailed information such as features, ratings, and prices.

[0451] Step 11:

[0452] Once the user decides to purchase, the device provides a purchase link and assists in the purchase process, which the user clicks to complete the purchase.

[0453] Step 12:

[0454] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0455] Step 13:

[0456] Users input ratings and reviews of purchased products into their devices and send them to the server, which stores the feedback in a database.

[0457] Step 14:

[0458] The server analyzes the collected feedback and uses it as data to improve the accuracy of the next recommendation. It also generates trend information and provides it to other users and manufacturers.

[0459] Step 15:

[0460] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[0461] Step 16:

[0462] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[0463] Example 1

[0464] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0465] In modern e-commerce, users have difficulty quickly and accurately selecting the most suitable product or service from a wide variety of options. Furthermore, there is a lack of methods to improve the purchasing experience by deeply understanding users' needs and making recommendations based on those needs. Current systems are unable to properly extract users' latent needs and make recommendations that increase satisfaction. Furthermore, there is an insufficient mechanism for incorporating user feedback into future recommendations.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0467] In this invention, the server includes means for receiving inquiries from user devices, means for analyzing the content of the user's inquiries using a generative artificial intelligence model and extracting latent demand, means for searching a data storage device for related products and services based on the extracted demand and generating personalized recommendation results, means for transmitting the generated recommendation results to the user device and displaying them to the user, and means for collecting feedback submitted by the user and storing the feedback in the data storage device. This enables more accurate product and service recommendations based on the user's needs, improving the user's purchasing experience. Furthermore, the collected feedback is used to improve the accuracy of future recommendations, enabling continuous service improvement.

[0468] "User device" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0469] "Inquiry" means a question or request for information or assistance sought by a User.

[0470] A "generative artificial intelligence model" refers to a machine learning model that analyzes the content of a user's inquiry and understands their intentions and latent needs.

[0471] "Latent needs" refer to relevant requests and desires that users have not explicitly stated but that need to be taken into consideration.

[0472] "Data storage device" refers to a database or storage system for storing information about products or services.

[0473] "Personalized recommendation results" refer to suggestions and recommendations that are optimized for a particular user and are generated based on the user's inquiry and extracted needs.

[0474] "Feedback" refers to opinions and ratings provided by users after purchasing a product or using a service.

[0475] This invention relates to an e-commerce concierge service system that uses a generative AI model. The system aims to propose optimal products and services based on user inquiries.

[0476] User inquiries

[0477] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0478] Receiving and analyzing inquiries

[0479] The user's device sends the inputted inquiry to the server, which then uses a generative AI model (e.g., GPT-4) to analyze the user's inquiry and extract latent needs. The analysis process infers needs, even if the user has not explicitly stated them.

[0480] For example, if a user enters "I'm planning a family trip this summer," the server can generate follow-up questions such as "Where do you want to go, what is your budget, and what specific activities do you want to do?" to elicit further information from the user. The user then enters answers to the follow-up questions, which are then sent back to the server.

[0481] Generate and present recommendations based on needs

[0482] The server searches a database based on the collected information to find related products and services. The server then generates personalized recommendation results based on the products and services found. For example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling." The generated recommendation results are then sent to the terminal and displayed to the user.

[0483] Comparison of recommendation results

[0484] The server creates a comparison table of multiple products and services based on the generated recommendation results. This comparison table includes detailed information such as prices, ratings, and activities offered. The server sends the comparison table to the terminal, which displays it to the user. The user can make the best choice based on the detailed information.

[0485] Purchasing support and feedback collection

[0486] If the user decides to purchase after viewing the recommendations, the user's device will present a purchase link and assist in the purchase process. After the purchase, the server collects the user's feedback and stores it in a database. This feedback is used to improve the accuracy of recommendations next time. For example, a user may book a resort hotel and provide feedback after their stay such as, "It was comfortable. The staff were very helpful." The server will store this feedback and use it to make suggestions to future users.

[0487] Big data analysis and trend information provision

[0488] The server analyzes the big data collected from all users and generates information on fashion and trends. This information is provided to users and also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies. For example, the server analyzes data that shows "demand for camping is high this summer," and based on that, proposes a sales strategy for new camping equipment to an e-commerce site.

[0489] Sales Bot Features

[0490] Users interact with the sales bot to obtain detailed information about products they are interested in. The server uses the sales bot's functionality to communicate detailed product information and appeal to users, encouraging them to make a purchase. For example, the server might explain, "The seaside resort offers all meals and a wide range of activities. The mountain camping offers an attractive opportunity to experience nature," thereby increasing the user's desire to make a purchase.

[0491] Prompt Sentence Examples

[0492] An example of a user sending a query to a generative AI model:

[0493] "I'm planning a summer trip with my family. Can you recommend some places to go and where to stay?"

[0494] An example where the server generates a follow-up question after parsing:

[0495] "Do you have any destinations, budgets, or specific activities you'd like to do?"

[0496] As a result, this system utilizes generative AI models to recommend optimal products and services based on user needs, improving the user's purchasing experience.

[0497] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0498] Step 1:

[0499] A user accesses the website or application of the e-commerce concierge service using their own device (PC or smartphone) and inputs a query in natural language. The input query is sent to the server in the form of a prompt sentence such as, "I'm planning a summer trip with my family. What are your recommended destinations and accommodations?"

[0500] Step 2:

[0501] The terminal sends the query entered by the user to the server. The input is text data and is securely transmitted using the HTTPS protocol. The server receives this text data.

[0502] Step 3:

[0503] The server inputs the received text data into a generative AI model (e.g., GPT-4). The generative AI model analyzes this input data, understands the user's inquiry, and extracts latent demands. For example, it infers "destination, budget, and specific activities" from "family trip" and "summer." As output, it generates a follow-up question: "Do you have any preferences for destination, budget, or specific activities?"

[0504] Step 4:

[0505] The server sends the generated follow-up question to the terminal, which displays the question to the user and requests further information, which is then sent as input back to the server.

[0506] Step 5:

[0507] The user inputs answers to the additional questions. For example, the user inputs text such as "Destination: Okinawa. Activity: I would like snorkeling." and sends it to the server via the terminal. The server receives this input data.

[0508] Step 6:

[0509] The server then searches the database using the additional information to find related products and services. Keywords such as "Okinawa" for the destination and "snorkeling" for the activity are used to search the database. The output is a list of related resort hotels and tours.

[0510] Step 7:

[0511] The server creates a personalized recommendation list based on the generated recommendation results. For example, a list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" may be generated. The generated recommendation list is sent from the server to the device.

[0512] Step 8:

[0513] The terminal displays the recommendation list sent from the server to the user, who then begins making a selection based on the displayed list.

[0514] Step 9:

[0515] The server generates a comparison table of multiple products and services based on the generated recommendation results. The comparison table includes detailed information such as prices, ratings, and activities offered. For example, a comparison table of "Hotel A vs. Hotel B vs. Hotel C" is generated. This comparison table is sent to the terminal.

[0516] Step 10:

[0517] The terminal displays the comparison table sent from the server to the user, allowing the user to compare detailed information and make the best choice.

[0518] Step 11:

[0519] If the user decides to purchase after viewing the recommended results, the device will provide a purchase link to assist in the purchase process. This link is sent from the server, and the user clicks on it to complete the purchase.

[0520] Step 12:

[0521] After a purchase, the user provides feedback. The terminal provides a feedback input form, allowing the user to enter their opinions and thoughts. The input feedback is sent from the terminal to the server.

[0522] Step 13:

[0523] The server collects user feedback and stores it in a data storage device, and the feedback data is analyzed to improve the accuracy of the next recommendation.

[0524] Step 14:

[0525] The server generates fashion and trend information based on the collected big data, which is provided to users, manufacturers, and e-commerce sites for use in new product development and sales strategies.

[0526] Step 15:

[0527] Users can use the sales bot function to obtain more detailed information. The server communicates product details and appeal in a conversational format through the sales bot, increasing the user's desire to purchase. Explanations tailored to the user's specific needs are provided in real time.

[0528] (Application example 1)

[0529] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0530] Conventional product recommendation systems on e-commerce sites typically display related products when users input search keywords. However, this method makes it difficult to fully reflect the user's specific needs and implicit desires, and does not improve the user experience. Furthermore, users must search for related information themselves, which takes a lot of time and effort. This leads to issues such as a decrease in purchasing motivation and difficulty in finding optimal products and services.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0532] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, and means for installing a smartphone application that extracts specific needs based on the content of the user's inquiry and finds and recommends related products and services based on the analysis results, thereby making it possible to quickly and accurately provide optimal products and services based on the user's specific needs and wishes.

[0533] A "user terminal" is an electronic device used by a user, and includes devices such as smartphones, tablets, and personal computers.

[0534] An "inquiry" is a request or question that a user inputs to the system, and is input in natural language.

[0535] A "generative AI model" is an artificial intelligence model that uses natural language processing to analyze inquiries entered by users and understand their meaning and intent.

[0536] "Latent needs" refer to expectations and requests that are not explicitly stated by the user but can be inferred from the content of the inquiry.

[0537] "Personalized recommendations" refers to product and service suggestions tailored to a user's specific needs and preferences.

[0538] A "smartphone application" is software that runs on a smartphone and provides a means for receiving user inquiries and displaying analysis results.

[0539] This system is implemented using a user terminal. Specifically, the user terminal is used by installing a smartphone application. This application provides an interface for users to input queries.

[0540] Users launch the smartphone app and input their requests or questions in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0541] The smartphone app sends the user's inquiry to a server, which then uses OpenAI's generative AI model to analyze the inquiry and extract the user's potential needs, such as estimating the necessary camping gear, budget, and number of participants.

[0542] Based on the analysis results, the server then uses the e-commerce platform's search API to search for related products and services and generate personalized recommendations, such as suggesting specific products like a "three-person tent with excellent waterproofing."

[0543] The personalized recommendation results are sent from the server to the user's device and displayed on the smartphone app. The user can compare the presented recommendation results and check detailed information.

[0544] As a concrete example, if a user asks, "I'm going camping with friends in the spring. Do you have any recommended tents?", the generative AI model will extract needs such as "a three-person tent with good waterproofing" and recommend the most suitable product based on that. An example of a prompt is as follows:

[0545] Example prompt sentence:

[0546] User Question: I'm going camping with friends this spring. Can you recommend a tent?

[0547] Identify user needs and provide relevant information.

[0548] This system allows users to quickly and accurately select the best products and services based on their specific needs and desires, improving their purchasing experience.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] (Input) The user launches their smartphone app and inputs their request or question in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0552] (Operation) The terminal receives this natural language input.

[0553] (Output) Prepare the received inquiry as data to be passed on to the next processing step.

[0554] Step 2:

[0555] (Input) The natural language query entered by the user.

[0556] (Operation) The device sends the received query to the server, which analyzes the query using OpenAI's generative AI model.

[0557] (Data processing and calculation) The generative AI model analyzes the input natural language and extracts the user's latent needs, such as guessing the equipment needed for camping, budget, and number of participants.

[0558] (Output) Extracted needs and specific information (e.g., a three-person tent with excellent waterproofing).

[0559] Step 3:

[0560] (Input) Extracted needs and specific information.

[0561] (Operation) Based on the analysis results, the server uses the search API of the EC platform to search for related products and services.

[0562] (Data processing and calculation) A search query is generated and a list of relevant products is obtained by querying the EC platform database.

[0563] (Output) Personalized recommendations (e.g., a list of specific products or services).

[0564] Step 4:

[0565] (Input) Personalized recommendation results.

[0566] (Operation) The server transmits the generated recommendation results to the user terminal.

[0567] (Data processing) Format the recommendation results in a way that is easy for users to understand.

[0568] (Output) Formatted recommendation result data.

[0569] Step 5:

[0570] (Input) The formatted recommendation results sent from the server.

[0571] (Operation) The terminal displays the recommendation results to the user, who can compare the presented recommendation results and check detailed information.

[0572] (Output) Based on the user's confirmation and comparison, further inquiries and feedback information may be provided as needed.

[0573] By going through the above steps, users can be provided with the most suitable products and services quickly and accurately based on their specific needs and desires.

[0574] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0575] This system combines a generative AI model and an emotion engine to suggest optimal products and services based on user inquiries and increase purchasing motivation. A specific embodiment of this system is described below.

[0576] User inquiries

[0577] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). At this time, users input their wishes and requests in natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0578] Receiving and analyzing inquiries

[0579] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even if the user has not explicitly stated them.

[0580] At the same time, the emotion engine recognizes emotions from the user's input and comments during the conversation, and generates appropriate responses accordingly.

[0581] For example, if a user types, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion" and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[0582] Generate and present recommendations based on needs

[0583] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the terminal, which then displays the recommendations to the user.

[0584] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0585] Compare recommendations and get detailed information

[0586] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0587] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0588] Purchasing support and feedback collection

[0589] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0590] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0591] Big data analysis and trend information provision

[0592] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0593] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0594] Sales Bot Features

[0595] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0596] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0597] Utilizing the Emotion Engine

[0598] The emotion engine analyzes the user's emotions in real time and adjusts the way it presents follow-up questions and recommendation results based on that analysis. For example, if the user is determined to be "concerned" after looking at a comparison chart, the emotion engine will support the user by generating follow-up questions such as "What are you unsure about?"

[0599] In this way, an e-commerce concierge service that combines a generative AI model with an emotion engine can recommend optimal products and services based on the user's needs and emotions, significantly improving the purchasing experience.

[0600] The processing flow will be explained below.

[0601] Step 1:

[0602] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0603] Step 2:

[0604] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0605] Step 3:

[0606] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0607] Step 4:

[0608] At the same time, the server uses an emotion engine to recognize emotions from the user's input, such as "anxious" or "excited."

[0609] Step 5:

[0610] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?", and generates questions based on the recognized emotions.

[0611] Step 6:

[0612] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0613] Step 7:

[0614] The user answers additional questions and enters specific information into the device (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity."). The emotion engine continues to analyze emotions from the user's answers.

[0615] Step 8:

[0616] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0617] Step 9:

[0618] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0619] Step 10:

[0620] The device displays the recommendation results received from the server to the user. The sales bot function explains the product's appeal in a conversational format, stimulating the user's desire to purchase. For example, it might explain, "Seaside resorts offer all meals and a wide range of activities. Mountain camping offers the appealing opportunity to experience nature."

[0621] Step 11:

[0622] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal.

[0623] Step 12:

[0624] The device displays the comparison table received from the server to the user to help them make a comparison. The emotion engine analyzes the user's reaction and provides additional support based on their emotions. For example, it displays follow-up questions such as "Are you still undecided?"

[0625] Step 13:

[0626] If the user decides to purchase after viewing the recommended results, the device will present the user with a purchase link and assist in the purchase process. The user clicks the link to complete the purchase.

[0627] Step 14:

[0628] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0629] Step 15:

[0630] Users input ratings and reviews of purchased products into their devices and send them to the server. The emotion engine also analyzes the user's emotions from the feedback, including questions such as, "Was it a pleasant experience?"

[0631] Step 16:

[0632] The server stores the feedback in a database and uses it to improve the accuracy of recommendations next time.The server analyzes the collected big data and generates information on trends and fashions.

[0633] Step 17:

[0634] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[0635] Step 18:

[0636] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[0637] The system utilizes generative AI models and an emotion engine to recommend optimal products and services based on users' needs and emotions, improving the purchasing experience.

[0638] Example 2

[0639] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] Conventional e-commerce concierge systems provide simple responses to user inquiries and do not fully consider the user's latent needs and emotions. This makes it difficult to efficiently stimulate users' purchasing motivation and to recommend appropriate products and services.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0642] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user inquiry using a generative AI model and extracting latent needs, means for identifying the user's emotions using an emotion engine and generating an appropriate response, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, and means for transmitting the generated recommendation results to the user terminal and displaying them to the user. This makes it possible to recommend products and services that appropriately consider the user's latent needs and emotions, thereby efficiently increasing the user's purchasing motivation.

[0643] A "user terminal" is an electronic device used by a user, such as a personal computer or smartphone, that can communicate with a server via the Internet.

[0644] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to analyze the content of a user's inquiry and extract the latent needs and information contained in the inquiry.

[0645] An "emotion engine" is a system that has the ability to identify a user's emotional state from their input and statements during a conversation, and generate an appropriate response.

[0646] A "database" is an information management system that stores information about products and services and is designed to allow that information to be searched and retrieved.

[0647] "Personalized recommendation results" are proposals for products and services that are customized based on the user's inquiry and needs, and are provided in a form that meets the individual requests of the user.

[0648] "Follow-up questions" are questions generated by the generative AI model as needed to further clarify the user's needs and prompt the user to provide additional information.

[0649] A "comparison table" is a format that displays detailed information such as features, ratings, and prices of multiple products or services in a list format, allowing users to compare them.

[0650] This invention relates to a system for recommending optimal products and services based on user inquiries. The system combines a generative AI model and an emotion engine to analyze the user's needs and emotions, and recommends products and services based on the results.

[0651] Hardware and software used

[0652] The system is implemented using the following hardware and software.

[0653] User terminal: A device that can connect to the Internet, such as a personal computer (PC) or smartphone.

[0654] Server: A computer system for data processing and analysis. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[0655] Generative AI model: An artificial intelligence that performs natural language processing. For example, OpenAI's GPT-4 can be used.

[0656] Emotion engine: An algorithm that identifies emotions from user utterances and generates appropriate responses.

[0657] Database: An information management system that stores and searches information about products and services. For example, you can use AWS's RDS.

[0658] System Operation

[0659] 1. User Inquiries

[0660] Users access the website or application of the e-commerce concierge service using a device such as a PC or smartphone, and input their wishes and requests in natural language. For example, they send a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0661] 2. Receiving and analyzing inquiries

[0662] The device sends the user's input to the server. The server uses a generative AI model to analyze the received inquiry. This analysis extracts the user's latent needs. At the same time, the emotion engine identifies the user's emotions and generates an appropriate response. For example, if the user inputs, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion," and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[0663] 3. Needs-based recommendation generation

[0664] The server searches for relevant products and services from a database based on the extracted needs, and generates personalized recommendations based on the results.

[0665] 4. Display of recommendation results

[0666] The generated recommendation results are sent from the server to the user's device, and the device displays them to the user. For example, if the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the device.

[0667] Examples of concrete examples and prompts

[0668] Examples:

[0669] If the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.The server then generates a comparison table of information such as "Hotel A vs. Hotel B vs. Hotel C: Price, Review Rating, Activities Offered," and displays it to the user.

[0670] Example prompt sentence:

[0671] "Analyze user input and recommend the best products and services based on travel destinations and activities. Focus on using an emotion engine to generate responses based on the user's emotions."

[0672] In this way, by combining a generative AI model with an emotion engine, it becomes possible to make personalized recommendations for products and services that take into account the user's needs and emotions, significantly improving the user's purchasing experience.

[0673] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0674] Step 1:

[0675] Users access the website or application of the e-commerce concierge service using a device such as a personal computer (PC) or smartphone, and input their wishes and requests in natural language. Specifically, they input and submit a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0676] Input: User's inquiry

[0677] Output: Sending query content from user terminal to server

[0678] Step 2:

[0679] The terminal sends the query entered by the user to the server as natural language text.

[0680] Input: The inquiry entered by the user

[0681] Output: Sending query content to the server

[0682] Step 3:

[0683] The server passes the received inquiry to the generative AI model, which analyzes it. This analysis extracts the user's latent needs. The generative AI model uses a natural language processing algorithm to understand the user's inquiry and analyze related keywords and intent. It also uses the extracted information to clarify the user's specific needs.

[0684] Input: Enquiry (natural language text)

[0685] Output: Extraction of potential needs

[0686] Step 4:

[0687] At the same time, the server uses an emotion engine to identify emotions from the user's input. For example, if a user inputs "I don't know where to go," the emotion engine will identify emotions such as "anxiety" or "hesitation." Depending on the identified emotion, the generative AI model will generate an appropriate response.

[0688] Input: Enquiry (natural language text)

[0689] Output: Identified emotions and appropriate responses

[0690] Step 5:

[0691] Based on the extracted needs and emotions, the server searches for relevant products and services from a database that stores information such as product features, ratings, and prices. Based on this information, the server generates personalized recommendation results.

[0692] Input: Potential needs, identified emotions

[0693] Output: Personalized recommendation results

[0694] Step 6:

[0695] The server then sends the generated personalized recommendation results to the user's device. The recommendation results include a list of products and services that meet the user's needs. For example, the recommendation may include specific content such as "Three resort hotels in Okinawa where you can enjoy snorkeling."

[0696] Input: Personalized recommendation results

[0697] Output: Sending recommendation results to the user's device

[0698] Step 7:

[0699] The terminal displays the recommendation results received from the server to the user, who can then browse the displayed recommendation results and check detailed information about the products or services that interest them.

[0700] Input: Recommendation results from the server

[0701] Output: Displaying the recommendations to the user

[0702] Step 8:

[0703] The server generates a comparison table of multiple products and services based on the recommendation results. This comparison table includes detailed information such as features, ratings, and prices. The server transmits this comparison table to the user's terminal, allowing the user to easily compare and consider each product or service.

[0704] Input: Information about products and services based on the recommendation results

[0705] Output: Comparison table

[0706] Step 9:

[0707] The terminal displays the comparison table received from the server to the user, who can then compare the detailed information of each product or service and make the best choice for themselves.

[0708] Input: Comparison table from the server

[0709] Output: Displaying a comparison table to the user

[0710] Step 10:

[0711] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database.

[0712] Input: User's purchase decision

[0713] Output: Provide purchase link and collect feedback

[0714] In this way, the system uses generative AI models and emotion engines to carry out a series of processes to recommend optimal products and services based on user inquiries.

[0715] (Application example 2)

[0716] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] Conventional e-commerce concierge systems are unable to make proposals that take into account the user's emotions and real-time stress levels, and are therefore unable to fully increase user satisfaction or purchasing motivation. Furthermore, when presenting personalized recommendations to users, they are unable to respond to changes in the user's emotions, resulting in a limited user experience.

[0718] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0719] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, means for analyzing the user's emotions and adjusting the recommendation results and responses based on the emotions, and means for evaluating the user's comments and actions in real time and making optimal suggestions based on the user's stress level. This enables detailed personalized suggestions that correspond to the user's emotions and stress level and a more satisfying purchasing experience.

[0720] A "user terminal" is a device through which a user enters input and receives information.

[0721] "Inquiry content" refers to information such as wishes, requests, questions, etc. that the user inputs via the terminal.

[0722] A "generative AI model" is a program that uses artificial intelligence technology to analyze input information and generate appropriate responses or suggestions.

[0723] "Latent needs" are requests or necessities that are not explicitly stated by the user but are inferred.

[0724] "Personalized recommendations" are suggestions and information that are customized based on a user's individual characteristics and needs.

[0725] A "database" is a system that stores and manages information about related products and services.

[0726] "Analyzing emotions" means recognizing the user's feelings and emotions at that time from their input and actions.

[0727] "Stress level" refers to the degree of mental tension or strain felt by the user.

[0728] "Real-time evaluation" means instantly analyzing users' comments and actions and taking appropriate action.

[0729] The system for implementing this invention comprises a user terminal, a server, and a database. The user terminal is a device such as a smartphone or a PC, and is used by users to input inquiries and receive related information.

[0730] The server is built using the following hardware and software:

[0731] OpenAI's generative AI model: Used to analyze user inquiries and extract latent needs.

[0732] Sentiment Analysis Engine: Used to analyze emotions from user input, real-time statements, and actions. This engine analyzes voice tone and text data to identify user emotions.

[0733] Database management system: Used to store information on related products and services.

[0734] When a user enters an inquiry from a smartphone or PC, the server analyzes the content using a generative AI model. Potential needs are extracted from the analyzed data, and related products and services are searched for in the database based on these. The server then generates personalized recommendations based on the results and sends them to the user's device.

[0735] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions in real time and generate responses according to their emotions. For example, if the user indicates that they want to relax, the server will suggest routes with beautiful natural scenery and relaxing music.

[0736] For example, if a user inputs "I want to relax on a route with lots of nature," the server will analyze this request using a generative AI model and make a personalized suggestion of "a route with lots of nature." At the same time, the emotion analysis engine will recognize the user's emotion of "wanting to relax" and recommend the most suitable scenic route and music based on that.

[0737] In this way, it is possible to provide more personalized information in real time based on the user's inquiry and their feelings.

[0738] Examples of specific prompts include:

[0739] Example prompt sentence:

[0740] User: I want to relax on a route with lots of nature.

[0741] System: Finding optimal route...

[0742] System: Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory.

[0743] This system provides detailed personalized suggestions based on the user's emotions and stress level, and a more satisfying purchasing experience.

[0744] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0745] Step 1:

[0746] The user inputs the inquiry through the terminal and sends it to the server. This input includes requests and questions in natural language. For example, "I want to relax on a route with lots of nature." The server receives this inquiry.

[0747] Step 2:

[0748] The server analyzes the received inquiry using a generative AI model. The generative AI model processes the text entered by the user and extracts latent needs. For example, needs such as "route with lots of nature" and "want to relax" are analyzed. The input is the user's inquiry, and the output is the extracted latent needs.

[0749] Step 3:

[0750] The server searches a database based on the extracted needs to identify related products and services. Specifically, it searches for information on "routes with plenty of nature" or "places to relax." The input is the potential need, and the output is a list of related products and services.

[0751] Step 4:

[0752] The server uses a sentiment analysis engine to analyze the sentiment from the user's inquiry. For example, if the user wants to relax, the sentiment analysis engine will recognize the sentiment of "relaxation." The input is the user's inquiry, and the output is the analyzed sentiment.

[0753] Step 5:

[0754] Based on the emotional information analyzed by the emotion analysis engine, the server generates optimal recommendation results. These results include personalized information based on the user's emotions. For example, a "Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory" may be generated. The input is the analyzed emotion and a list of related products, and the output is personalized recommendation results.

[0755] Step 6:

[0756] The server sends the generated recommendation results to the user's terminal and displays them to the user. The user receives them and checks the information displayed on the screen. The input is the personalized recommendation results, and the output is the information displayed on the user's terminal.

[0757] Step 7:

[0758] If the user inputs further questions or requests based on the results, the server can generate additional questions and continue the dialogue with the user. The generative AI model again analyzes this information and reassesses underlying needs and emotions. This process can be repeated as necessary. The input is the user's new questions or requests, and the output is additional dialogue content or recommendations.

[0759] This series of steps makes it possible to provide optimal products and services based on the user's emotions and needs.

[0760] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0761] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0762] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0763] [Third embodiment]

[0764] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0765] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0766] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0767] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0768] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0769] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0770] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0771] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0772] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0773] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0774] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0775] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0776] This system is an e-commerce concierge service that uses a generative AI model and includes multiple means for proposing optimal products and services based on user inquiries. A specific embodiment of this system is described below.

[0777] User inquiries

[0778] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they can make a query such as, "I'm planning a family trip this summer. What do you recommend?"

[0779] Receiving and analyzing inquiries

[0780] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even those not explicitly stated by the user.

[0781] For example, if a user enters, "I'm planning a family trip this summer," the server can generate follow-up questions such as, "Where are we going, what is our budget, and what are the specific activities?" to elicit further information from the user.

[0782] Generate and present recommendations based on needs

[0783] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the device, which then displays the recommendations to the user.

[0784] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0785] Compare recommendations and get detailed information

[0786] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0787] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0788] Purchasing support and feedback collection

[0789] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0790] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0791] Big data analysis and trend information provision

[0792] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0793] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0794] Sales Bot Features

[0795] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0796] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0797] As described above, this system utilizes generative AI models to recommend optimal products and services based on user needs, significantly improving the user's purchasing experience.

[0798] The processing flow will be explained below.

[0799] Step 1:

[0800] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0801] Step 2:

[0802] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0803] Step 3:

[0804] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0805] Step 4:

[0806] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?"

[0807] Step 5:

[0808] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0809] Step 6:

[0810] The user answers additional questions and inputs specific information into the terminal (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity").

[0811] Step 7:

[0812] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0813] Step 8:

[0814] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0815] Step 9:

[0816] The device receives the recommendation results from the server and displays them to the user. The sales bot function interactively explains the product's appeal, encouraging the user to purchase.

[0817] Step 10:

[0818] Users can compare the recommendations and select the most suitable product or service. A comparison table is provided to check detailed information such as features, ratings, and prices.

[0819] Step 11:

[0820] Once the user decides to purchase, the device provides a purchase link and assists in the purchase process, which the user clicks to complete the purchase.

[0821] Step 12:

[0822] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0823] Step 13:

[0824] Users input ratings and reviews of purchased products into their devices and send them to the server, which stores the feedback in a database.

[0825] Step 14:

[0826] The server analyzes the collected feedback and uses it as data to improve the accuracy of the next recommendation. It also generates trend information and provides it to other users and manufacturers.

[0827] Step 15:

[0828] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[0829] Step 16:

[0830] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[0831] Example 1

[0832] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0833] In modern e-commerce, users have difficulty quickly and accurately selecting the most suitable product or service from a wide variety of options. Furthermore, there is a lack of methods to improve the purchasing experience by deeply understanding users' needs and making recommendations based on those needs. Current systems are unable to properly extract users' latent needs and make recommendations that increase satisfaction. Furthermore, there is an insufficient mechanism for incorporating user feedback into future recommendations.

[0834] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0835] In this invention, the server includes means for receiving inquiries from user devices, means for analyzing the content of the user's inquiries using a generative artificial intelligence model and extracting latent demand, means for searching a data storage device for related products and services based on the extracted demand and generating personalized recommendation results, means for transmitting the generated recommendation results to the user device and displaying them to the user, and means for collecting feedback submitted by the user and storing the feedback in the data storage device. This enables more accurate product and service recommendations based on the user's needs, improving the user's purchasing experience. Furthermore, the collected feedback is used to improve the accuracy of future recommendations, enabling continuous service improvement.

[0836] "User device" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[0837] "Inquiry" means a question or request for information or assistance sought by a User.

[0838] A "generative artificial intelligence model" refers to a machine learning model that analyzes the content of a user's inquiry and understands their intentions and latent needs.

[0839] "Latent needs" refer to relevant requests and desires that users have not explicitly stated but that need to be taken into consideration.

[0840] "Data storage device" refers to a database or storage system for storing information about products or services.

[0841] "Personalized recommendation results" refer to suggestions and recommendations that are optimized for a particular user and are generated based on the user's inquiry and extracted needs.

[0842] "Feedback" refers to opinions and ratings provided by users after purchasing a product or using a service.

[0843] This invention relates to an e-commerce concierge service system that uses a generative AI model. The system aims to propose optimal products and services based on user inquiries.

[0844] User inquiries

[0845] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0846] Receiving and analyzing inquiries

[0847] The user's device sends the inputted inquiry to the server, which then uses a generative AI model (e.g., GPT-4) to analyze the user's inquiry and extract latent needs. The analysis process infers needs, even if the user has not explicitly stated them.

[0848] For example, if a user enters "I'm planning a family trip this summer," the server can generate follow-up questions such as "Where do you want to go, what is your budget, and what specific activities do you want to do?" to elicit further information from the user. The user then enters answers to the follow-up questions, which are then sent back to the server.

[0849] Generate and present recommendations based on needs

[0850] The server searches a database based on the collected information to find related products and services. The server then generates personalized recommendation results based on the products and services found. For example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling." The generated recommendation results are then sent to the terminal and displayed to the user.

[0851] Comparison of recommendation results

[0852] The server creates a comparison table of multiple products and services based on the generated recommendation results. This comparison table includes detailed information such as prices, ratings, and activities offered. The server sends the comparison table to the terminal, which displays it to the user. The user can make the best choice based on the detailed information.

[0853] Purchasing support and feedback collection

[0854] If the user decides to purchase after viewing the recommendations, the user's device will present a purchase link and assist in the purchase process. After the purchase, the server collects the user's feedback and stores it in a database. This feedback is used to improve the accuracy of recommendations next time. For example, a user may book a resort hotel and provide feedback after their stay such as, "It was comfortable. The staff were very helpful." The server will store this feedback and use it to make suggestions to future users.

[0855] Big data analysis and trend information provision

[0856] The server analyzes the big data collected from all users and generates information on fashion and trends. This information is provided to users and also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies. For example, the server analyzes data that shows "demand for camping is high this summer," and based on that, proposes a sales strategy for new camping equipment to an e-commerce site.

[0857] Sales Bot Features

[0858] Users interact with the sales bot to obtain detailed information about products they are interested in. The server uses the sales bot's functionality to communicate detailed product information and appeal to users, encouraging them to make a purchase. For example, the server might explain, "The seaside resort offers all meals and a wide range of activities. The mountain camping offers an attractive opportunity to experience nature," thereby increasing the user's desire to make a purchase.

[0859] Prompt Sentence Examples

[0860] An example of a user sending a query to a generative AI model:

[0861] "I'm planning a summer trip with my family. Can you recommend some places to go and where to stay?"

[0862] An example where the server generates a follow-up question after parsing:

[0863] "Do you have any destinations, budgets, or specific activities you'd like to do?"

[0864] As a result, this system utilizes generative AI models to recommend optimal products and services based on user needs, improving the user's purchasing experience.

[0865] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0866] Step 1:

[0867] A user accesses the website or application of the e-commerce concierge service using their own device (PC or smartphone) and inputs a query in natural language. The input query is sent to the server in the form of a prompt sentence such as, "I'm planning a summer trip with my family. What are your recommended destinations and accommodations?"

[0868] Step 2:

[0869] The terminal sends the query entered by the user to the server. The input is text data and is securely transmitted using the HTTPS protocol. The server receives this text data.

[0870] Step 3:

[0871] The server inputs the received text data into a generative AI model (e.g., GPT-4). The generative AI model analyzes this input data, understands the user's inquiry, and extracts latent demands. For example, it infers "destination, budget, and specific activities" from "family trip" and "summer." As output, it generates a follow-up question: "Do you have any preferences for destination, budget, or specific activities?"

[0872] Step 4:

[0873] The server sends the generated follow-up question to the terminal, which displays the question to the user and requests further information, which is then sent as input back to the server.

[0874] Step 5:

[0875] The user inputs answers to the additional questions. For example, the user inputs text such as "Destination: Okinawa. Activity: I would like snorkeling." and sends it to the server via the terminal. The server receives this input data.

[0876] Step 6:

[0877] The server then searches the database using the additional information to find related products and services. Keywords such as "Okinawa" for the destination and "snorkeling" for the activity are used to search the database. The output is a list of related resort hotels and tours.

[0878] Step 7:

[0879] The server creates a personalized recommendation list based on the generated recommendation results. For example, a list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" may be generated. The generated recommendation list is sent from the server to the device.

[0880] Step 8:

[0881] The terminal displays the recommendation list sent from the server to the user, who then begins making a selection based on the displayed list.

[0882] Step 9:

[0883] The server generates a comparison table of multiple products and services based on the generated recommendation results. The comparison table includes detailed information such as prices, ratings, and activities offered. For example, a comparison table of "Hotel A vs. Hotel B vs. Hotel C" is generated. This comparison table is sent to the terminal.

[0884] Step 10:

[0885] The terminal displays the comparison table sent from the server to the user, allowing the user to compare detailed information and make the best choice.

[0886] Step 11:

[0887] If the user decides to purchase after viewing the recommended results, the device will provide a purchase link to assist in the purchase process. This link is sent from the server, and the user clicks on it to complete the purchase.

[0888] Step 12:

[0889] After a purchase, the user provides feedback. The terminal provides a feedback input form, allowing the user to enter their opinions and thoughts. The input feedback is sent from the terminal to the server.

[0890] Step 13:

[0891] The server collects user feedback and stores it in a data storage device, and the feedback data is analyzed to improve the accuracy of the next recommendation.

[0892] Step 14:

[0893] The server generates fashion and trend information based on the collected big data, which is provided to users, manufacturers, and e-commerce sites for use in new product development and sales strategies.

[0894] Step 15:

[0895] Users can use the sales bot function to obtain more detailed information. The server communicates product details and appeal in a conversational format through the sales bot, increasing the user's desire to purchase. Explanations tailored to the user's specific needs are provided in real time.

[0896] (Application example 1)

[0897] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0898] Conventional product recommendation systems on e-commerce sites typically display related products when users input search keywords. However, this method makes it difficult to fully reflect the user's specific needs and implicit desires, and does not improve the user experience. Furthermore, users must search for related information themselves, which takes a lot of time and effort. This leads to issues such as a decrease in purchasing motivation and difficulty in finding optimal products and services.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0900] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, and means for installing a smartphone application that extracts specific needs based on the content of the user's inquiry and finds and recommends related products and services based on the analysis results, thereby making it possible to quickly and accurately provide optimal products and services based on the user's specific needs and wishes.

[0901] A "user terminal" is an electronic device used by a user, and includes devices such as smartphones, tablets, and personal computers.

[0902] An "inquiry" is a request or question that a user inputs to the system, and is input in natural language.

[0903] A "generative AI model" is an artificial intelligence model that uses natural language processing to analyze inquiries entered by users and understand their meaning and intent.

[0904] "Latent needs" refer to expectations and requests that are not explicitly stated by the user but can be inferred from the content of the inquiry.

[0905] "Personalized recommendations" refers to product and service suggestions tailored to a user's specific needs and preferences.

[0906] A "smartphone application" is software that runs on a smartphone and provides a means for receiving user inquiries and displaying analysis results.

[0907] This system is implemented using a user terminal. Specifically, the user terminal is used by installing a smartphone application. This application provides an interface for users to input queries.

[0908] Users launch the smartphone app and input their requests or questions in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0909] The smartphone app sends the user's inquiry to a server, which then uses OpenAI's generative AI model to analyze the inquiry and extract the user's potential needs, such as estimating the necessary camping gear, budget, and number of participants.

[0910] Based on the analysis results, the server then uses the e-commerce platform's search API to search for related products and services and generate personalized recommendations, such as suggesting specific products like a "three-person tent with excellent waterproofing."

[0911] The personalized recommendation results are sent from the server to the user's device and displayed on the smartphone app. The user can compare the presented recommendation results and check detailed information.

[0912] As a concrete example, if a user asks, "I'm going camping with friends in the spring. Do you have any recommended tents?", the generative AI model will extract needs such as "a three-person tent with good waterproofing" and recommend the most suitable product based on that. An example of a prompt is as follows:

[0913] Example prompt sentence:

[0914] User Question: I'm going camping with friends this spring. Can you recommend a tent?

[0915] Identify user needs and provide relevant information.

[0916] This system allows users to quickly and accurately select the best products and services based on their specific needs and desires, improving their purchasing experience.

[0917] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0918] Step 1:

[0919] (Input) The user launches their smartphone app and inputs their request or question in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[0920] (Operation) The terminal receives this natural language input.

[0921] (Output) Prepare the received inquiry as data to be passed on to the next processing step.

[0922] Step 2:

[0923] (Input) The natural language query entered by the user.

[0924] (Operation) The device sends the received query to the server, which analyzes the query using OpenAI's generative AI model.

[0925] (Data processing and calculation) The generative AI model analyzes the input natural language and extracts the user's latent needs, such as guessing the equipment needed for camping, budget, and number of participants.

[0926] (Output) Extracted needs and specific information (e.g., a three-person tent with excellent waterproofing).

[0927] Step 3:

[0928] (Input) Extracted needs and specific information.

[0929] (Operation) Based on the analysis results, the server uses the search API of the EC platform to search for related products and services.

[0930] (Data processing and calculation) A search query is generated and a list of relevant products is obtained by querying the EC platform database.

[0931] (Output) Personalized recommendations (e.g., a list of specific products or services).

[0932] Step 4:

[0933] (Input) Personalized recommendation results.

[0934] (Operation) The server transmits the generated recommendation results to the user terminal.

[0935] (Data processing) Format the recommendation results in a way that is easy for users to understand.

[0936] (Output) Formatted recommendation result data.

[0937] Step 5:

[0938] (Input) The formatted recommendation results sent from the server.

[0939] (Operation) The terminal displays the recommendation results to the user, who can compare the presented recommendation results and check detailed information.

[0940] (Output) Based on the user's confirmation and comparison, further inquiries and feedback information may be provided as needed.

[0941] By going through the above steps, users can be provided with the most suitable products and services quickly and accurately based on their specific needs and desires.

[0942] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0943] This system combines a generative AI model and an emotion engine to suggest optimal products and services based on user inquiries and increase purchasing motivation. A specific embodiment of this system is described below.

[0944] User inquiries

[0945] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). At this time, users input their wishes and requests in natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[0946] Receiving and analyzing inquiries

[0947] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even if the user has not explicitly stated them.

[0948] At the same time, the emotion engine recognizes emotions from the user's input and comments during the conversation, and generates appropriate responses accordingly.

[0949] For example, if a user types, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion" and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[0950] Generate and present recommendations based on needs

[0951] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the terminal, which then displays the recommendations to the user.

[0952] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[0953] Compare recommendations and get detailed information

[0954] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[0955] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[0956] Purchasing support and feedback collection

[0957] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[0958] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[0959] Big data analysis and trend information provision

[0960] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[0961] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[0962] Sales Bot Features

[0963] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[0964] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[0965] Utilizing the Emotion Engine

[0966] The emotion engine analyzes the user's emotions in real time and adjusts the way it presents follow-up questions and recommendation results based on that analysis. For example, if the user is determined to be "concerned" after looking at a comparison chart, the emotion engine will support the user by generating follow-up questions such as "What are you unsure about?"

[0967] In this way, an e-commerce concierge service that combines a generative AI model with an emotion engine can recommend optimal products and services based on the user's needs and emotions, significantly improving the purchasing experience.

[0968] The processing flow will be explained below.

[0969] Step 1:

[0970] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[0971] Step 2:

[0972] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[0973] Step 3:

[0974] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[0975] Step 4:

[0976] At the same time, the server uses an emotion engine to recognize emotions from the user's input, such as "anxious" or "excited."

[0977] Step 5:

[0978] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?", and generates questions based on the recognized emotions.

[0979] Step 6:

[0980] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[0981] Step 7:

[0982] The user answers additional questions and enters specific information into the device (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity."). The emotion engine continues to analyze emotions from the user's answers.

[0983] Step 8:

[0984] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[0985] Step 9:

[0986] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[0987] Step 10:

[0988] The device displays the recommendation results received from the server to the user. The sales bot function explains the product's appeal in a conversational format, stimulating the user's desire to purchase. For example, it might explain, "Seaside resorts offer all meals and a wide range of activities. Mountain camping offers the appealing opportunity to experience nature."

[0989] Step 11:

[0990] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal.

[0991] Step 12:

[0992] The device displays the comparison table received from the server to the user to help them make a comparison. The emotion engine analyzes the user's reaction and provides additional support based on their emotions. For example, it displays follow-up questions such as "Are you still undecided?"

[0993] Step 13:

[0994] If the user decides to purchase after viewing the recommended results, the device will present the user with a purchase link and assist in the purchase process. The user clicks the link to complete the purchase.

[0995] Step 14:

[0996] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[0997] Step 15:

[0998] Users input ratings and reviews of purchased products into their devices and send them to the server. The emotion engine also analyzes the user's emotions from the feedback, including questions such as, "Was it a pleasant experience?"

[0999] Step 16:

[1000] The server stores the feedback in a database and uses it to improve the accuracy of recommendations next time.The server analyzes the collected big data and generates information on trends and fashions.

[1001] Step 17:

[1002] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[1003] Step 18:

[1004] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[1005] The system utilizes generative AI models and an emotion engine to recommend optimal products and services based on users' needs and emotions, improving the purchasing experience.

[1006] Example 2

[1007] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] Conventional e-commerce concierge systems provide simple responses to user inquiries and do not fully consider the user's latent needs and emotions. This makes it difficult to efficiently stimulate users' purchasing motivation and to recommend appropriate products and services.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1010] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user inquiry using a generative AI model and extracting latent needs, means for identifying the user's emotions using an emotion engine and generating an appropriate response, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, and means for transmitting the generated recommendation results to the user terminal and displaying them to the user. This makes it possible to recommend products and services that appropriately consider the user's latent needs and emotions, thereby efficiently increasing the user's purchasing motivation.

[1011] A "user terminal" is an electronic device used by a user, such as a personal computer or smartphone, that can communicate with a server via the Internet.

[1012] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to analyze the content of a user's inquiry and extract the latent needs and information contained in the inquiry.

[1013] An "emotion engine" is a system that has the ability to identify a user's emotional state from their input and statements during a conversation, and generate an appropriate response.

[1014] A "database" is an information management system that stores information about products and services and is designed to allow that information to be searched and retrieved.

[1015] "Personalized recommendation results" are proposals for products and services that are customized based on the user's inquiry and needs, and are provided in a form that meets the individual requests of the user.

[1016] "Follow-up questions" are questions generated by the generative AI model as needed to further clarify the user's needs and prompt the user to provide additional information.

[1017] A "comparison table" is a format that displays detailed information such as features, ratings, and prices of multiple products or services in a list format, allowing users to compare them.

[1018] This invention relates to a system for recommending optimal products and services based on user inquiries. The system combines a generative AI model and an emotion engine to analyze the user's needs and emotions, and recommends products and services based on the results.

[1019] Hardware and software used

[1020] The system is implemented using the following hardware and software.

[1021] User terminal: A device that can connect to the Internet, such as a personal computer (PC) or smartphone.

[1022] Server: A computer system for data processing and analysis. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[1023] Generative AI model: An artificial intelligence that performs natural language processing. For example, OpenAI's GPT-4 can be used.

[1024] Emotion engine: An algorithm that identifies emotions from user utterances and generates appropriate responses.

[1025] Database: An information management system that stores and searches information about products and services. For example, you can use AWS's RDS.

[1026] System Operation

[1027] 1. User Inquiries

[1028] Users access the website or application of the e-commerce concierge service using a device such as a PC or smartphone, and input their wishes and requests in natural language. For example, they send a query such as, "I'm planning a family trip this summer. What do you recommend?"

[1029] 2. Receiving and analyzing inquiries

[1030] The device sends the user's input to the server. The server uses a generative AI model to analyze the received inquiry. This analysis extracts the user's latent needs. At the same time, the emotion engine identifies the user's emotions and generates an appropriate response. For example, if the user inputs, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion," and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[1031] 3. Needs-based recommendation generation

[1032] The server searches for relevant products and services from a database based on the extracted needs, and generates personalized recommendations based on the results.

[1033] 4. Display of recommendation results

[1034] The generated recommendation results are sent from the server to the user's device, and the device displays them to the user. For example, if the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the device.

[1035] Examples of concrete examples and prompts

[1036] Examples:

[1037] If the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.The server then generates a comparison table of information such as "Hotel A vs. Hotel B vs. Hotel C: Price, Review Rating, Activities Offered," and displays it to the user.

[1038] Example prompt sentence:

[1039] "Analyze user input and recommend the best products and services based on travel destinations and activities. Focus on using an emotion engine to generate responses based on the user's emotions."

[1040] In this way, by combining a generative AI model with an emotion engine, it becomes possible to make personalized recommendations for products and services that take into account the user's needs and emotions, significantly improving the user's purchasing experience.

[1041] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1042] Step 1:

[1043] Users access the website or application of the e-commerce concierge service using a device such as a personal computer (PC) or smartphone, and input their wishes and requests in natural language. Specifically, they input and submit a query such as, "I'm planning a family trip this summer. What do you recommend?"

[1044] Input: User's inquiry

[1045] Output: Sending query content from user terminal to server

[1046] Step 2:

[1047] The terminal sends the query entered by the user to the server as natural language text.

[1048] Input: The inquiry entered by the user

[1049] Output: Sending query content to the server

[1050] Step 3:

[1051] The server passes the received inquiry to the generative AI model, which analyzes it. This analysis extracts the user's latent needs. The generative AI model uses a natural language processing algorithm to understand the user's inquiry and analyze related keywords and intent. It also uses the extracted information to clarify the user's specific needs.

[1052] Input: Enquiry (natural language text)

[1053] Output: Extraction of potential needs

[1054] Step 4:

[1055] At the same time, the server uses an emotion engine to identify emotions from the user's input. For example, if a user inputs "I don't know where to go," the emotion engine will identify emotions such as "anxiety" or "hesitation." Depending on the identified emotion, the generative AI model will generate an appropriate response.

[1056] Input: Enquiry (natural language text)

[1057] Output: Identified emotions and appropriate responses

[1058] Step 5:

[1059] Based on the extracted needs and emotions, the server searches for relevant products and services from a database that stores information such as product features, ratings, and prices. Based on this information, the server generates personalized recommendation results.

[1060] Input: Potential needs, identified emotions

[1061] Output: Personalized recommendation results

[1062] Step 6:

[1063] The server then sends the generated personalized recommendation results to the user's device. The recommendation results include a list of products and services that meet the user's needs. For example, the recommendation may include specific content such as "Three resort hotels in Okinawa where you can enjoy snorkeling."

[1064] Input: Personalized recommendation results

[1065] Output: Sending recommendation results to the user's device

[1066] Step 7:

[1067] The terminal displays the recommendation results received from the server to the user, who can then browse the displayed recommendation results and check detailed information about the products or services that interest them.

[1068] Input: Recommendation results from the server

[1069] Output: Displaying the recommendations to the user

[1070] Step 8:

[1071] The server generates a comparison table of multiple products and services based on the recommendation results. This comparison table includes detailed information such as features, ratings, and prices. The server transmits this comparison table to the user's terminal, allowing the user to easily compare and consider each product or service.

[1072] Input: Information about products and services based on the recommendation results

[1073] Output: Comparison table

[1074] Step 9:

[1075] The terminal displays the comparison table received from the server to the user, who can then compare the detailed information of each product or service and make the best choice for themselves.

[1076] Input: Comparison table from the server

[1077] Output: Displaying a comparison table to the user

[1078] Step 10:

[1079] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database.

[1080] Input: User's purchase decision

[1081] Output: Provide purchase link and collect feedback

[1082] In this way, the system uses generative AI models and emotion engines to carry out a series of processes to recommend optimal products and services based on user inquiries.

[1083] (Application example 2)

[1084] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1085] Conventional e-commerce concierge systems are unable to make proposals that take into account the user's emotions and real-time stress levels, and are therefore unable to fully increase user satisfaction or purchasing motivation. Furthermore, when presenting personalized recommendations to users, they are unable to respond to changes in the user's emotions, resulting in a limited user experience.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1087] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, means for analyzing the user's emotions and adjusting the recommendation results and responses based on the emotions, and means for evaluating the user's comments and actions in real time and making optimal suggestions based on the user's stress level. This enables detailed personalized suggestions that correspond to the user's emotions and stress level and a more satisfying purchasing experience.

[1088] A "user terminal" is a device through which a user enters input and receives information.

[1089] "Inquiry content" refers to information such as wishes, requests, questions, etc. that the user inputs via the terminal.

[1090] A "generative AI model" is a program that uses artificial intelligence technology to analyze input information and generate appropriate responses or suggestions.

[1091] "Latent needs" are requests or necessities that are not explicitly stated by the user but are inferred.

[1092] "Personalized recommendations" are suggestions and information that are customized based on a user's individual characteristics and needs.

[1093] A "database" is a system that stores and manages information about related products and services.

[1094] "Analyzing emotions" means recognizing the user's feelings and emotions at that time from their input and actions.

[1095] "Stress level" refers to the degree of mental tension or strain felt by the user.

[1096] "Real-time evaluation" means instantly analyzing users' comments and actions and taking appropriate action.

[1097] The system for implementing this invention comprises a user terminal, a server, and a database. The user terminal is a device such as a smartphone or a PC, and is used by users to input inquiries and receive related information.

[1098] The server is built using the following hardware and software:

[1099] OpenAI's generative AI model: Used to analyze user inquiries and extract latent needs.

[1100] Sentiment Analysis Engine: Used to analyze emotions from user input, real-time statements, and actions. This engine analyzes voice tone and text data to identify user emotions.

[1101] Database management system: Used to store information on related products and services.

[1102] When a user enters an inquiry from a smartphone or PC, the server analyzes the content using a generative AI model. Potential needs are extracted from the analyzed data, and related products and services are searched for in the database based on these. The server then generates personalized recommendations based on the results and sends them to the user's device.

[1103] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions in real time and generate responses according to their emotions. For example, if the user indicates that they want to relax, the server will suggest routes with beautiful natural scenery and relaxing music.

[1104] For example, if a user inputs "I want to relax on a route with lots of nature," the server will analyze this request using a generative AI model and make a personalized suggestion of "a route with lots of nature." At the same time, the emotion analysis engine will recognize the user's emotion of "wanting to relax" and recommend the most suitable scenic route and music based on that.

[1105] In this way, it is possible to provide more personalized information in real time based on the user's inquiry and their feelings.

[1106] Examples of specific prompts include:

[1107] Example prompt sentence:

[1108] User: I want to relax on a route with lots of nature.

[1109] System: Finding optimal route...

[1110] System: Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory.

[1111] This system provides detailed personalized suggestions based on the user's emotions and stress level, and a more satisfying purchasing experience.

[1112] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1113] Step 1:

[1114] The user inputs the inquiry through the terminal and sends it to the server. This input includes requests and questions in natural language. For example, "I want to relax on a route with lots of nature." The server receives this inquiry.

[1115] Step 2:

[1116] The server analyzes the received inquiry using a generative AI model. The generative AI model processes the text entered by the user and extracts latent needs. For example, needs such as "route with lots of nature" and "want to relax" are analyzed. The input is the user's inquiry, and the output is the extracted latent needs.

[1117] Step 3:

[1118] The server searches a database based on the extracted needs to identify related products and services. Specifically, it searches for information on "routes with plenty of nature" or "places to relax." The input is the potential need, and the output is a list of related products and services.

[1119] Step 4:

[1120] The server uses a sentiment analysis engine to analyze the sentiment from the user's inquiry. For example, if the user wants to relax, the sentiment analysis engine will recognize the sentiment of "relaxation." The input is the user's inquiry, and the output is the analyzed sentiment.

[1121] Step 5:

[1122] Based on the emotional information analyzed by the emotion analysis engine, the server generates optimal recommendation results. These results include personalized information based on the user's emotions. For example, a "Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory" may be generated. The input is the analyzed emotion and a list of related products, and the output is personalized recommendation results.

[1123] Step 6:

[1124] The server sends the generated recommendation results to the user's terminal and displays them to the user. The user receives them and checks the information displayed on the screen. The input is the personalized recommendation results, and the output is the information displayed on the user's terminal.

[1125] Step 7:

[1126] If the user inputs further questions or requests based on the results, the server can generate additional questions and continue the dialogue with the user. The generative AI model again analyzes this information and reassesses underlying needs and emotions. This process can be repeated as necessary. The input is the user's new questions or requests, and the output is additional dialogue content or recommendations.

[1127] This series of steps makes it possible to provide optimal products and services based on the user's emotions and needs.

[1128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1130] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1131] [Fourth embodiment]

[1132] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1133] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1135] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1136] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1139] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1140] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1141] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1143] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1144] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1145] This system is an e-commerce concierge service that uses a generative AI model and includes multiple means for proposing optimal products and services based on user inquiries. A specific embodiment of this system is described below.

[1146] User inquiries

[1147] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they can make a query such as, "I'm planning a family trip this summer. What do you recommend?"

[1148] Receiving and analyzing inquiries

[1149] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even those not explicitly stated by the user.

[1150] For example, if a user enters, "I'm planning a family trip this summer," the server can generate follow-up questions such as, "Where are we going, what is our budget, and what are the specific activities?" to elicit further information from the user.

[1151] Generate and present recommendations based on needs

[1152] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the device, which then displays the recommendations to the user.

[1153] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[1154] Compare recommendations and get detailed information

[1155] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[1156] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[1157] Purchasing support and feedback collection

[1158] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[1159] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[1160] Big data analysis and trend information provision

[1161] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[1162] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[1163] Sales Bot Features

[1164] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[1165] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[1166] As described above, this system utilizes generative AI models to recommend optimal products and services based on user needs, significantly improving the user's purchasing experience.

[1167] The processing flow will be explained below.

[1168] Step 1:

[1169] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[1170] Step 2:

[1171] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[1172] Step 3:

[1173] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[1174] Step 4:

[1175] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?"

[1176] Step 5:

[1177] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[1178] Step 6:

[1179] The user answers additional questions and inputs specific information into the terminal (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity").

[1180] Step 7:

[1181] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[1182] Step 8:

[1183] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[1184] Step 9:

[1185] The device receives the recommendation results from the server and displays them to the user. The sales bot function interactively explains the product's appeal, encouraging the user to purchase.

[1186] Step 10:

[1187] Users can compare the recommendations and select the most suitable product or service. A comparison table is provided to check detailed information such as features, ratings, and prices.

[1188] Step 11:

[1189] Once the user decides to purchase, the device provides a purchase link and assists in the purchase process, which the user clicks to complete the purchase.

[1190] Step 12:

[1191] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[1192] Step 13:

[1193] Users input ratings and reviews of purchased products into their devices and send them to the server, which stores the feedback in a database.

[1194] Step 14:

[1195] The server analyzes the collected feedback and uses it as data to improve the accuracy of the next recommendation. It also generates trend information and provides it to other users and manufacturers.

[1196] Step 15:

[1197] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[1198] Step 16:

[1199] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[1200] Example 1

[1201] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1202] In modern e-commerce, users have difficulty quickly and accurately selecting the most suitable product or service from a wide variety of options. Furthermore, there is a lack of methods to improve the purchasing experience by deeply understanding users' needs and making recommendations based on those needs. Current systems are unable to properly extract users' latent needs and make recommendations that increase satisfaction. Furthermore, there is an insufficient mechanism for incorporating user feedback into future recommendations.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1204] In this invention, the server includes means for receiving inquiries from user devices, means for analyzing the content of the user's inquiries using a generative artificial intelligence model and extracting latent demand, means for searching a data storage device for related products and services based on the extracted demand and generating personalized recommendation results, means for transmitting the generated recommendation results to the user device and displaying them to the user, and means for collecting feedback submitted by the user and storing the feedback in the data storage device. This enables more accurate product and service recommendations based on the user's needs, improving the user's purchasing experience. Furthermore, the collected feedback is used to improve the accuracy of future recommendations, enabling continuous service improvement.

[1205] "User device" refers to a device operated by a user, such as a computer, smartphone, or tablet.

[1206] "Inquiry" means a question or request for information or assistance sought by a User.

[1207] A "generative artificial intelligence model" refers to a machine learning model that analyzes the content of a user's inquiry and understands their intentions and latent needs.

[1208] "Latent needs" refer to relevant requests and desires that users have not explicitly stated but that need to be taken into consideration.

[1209] "Data storage device" refers to a database or storage system for storing information about products or services.

[1210] "Personalized recommendation results" refer to suggestions and recommendations that are optimized for a particular user and are generated based on the user's inquiry and extracted needs.

[1211] "Feedback" refers to opinions and ratings provided by users after purchasing a product or using a service.

[1212] This invention relates to an e-commerce concierge service system that uses a generative AI model. The system aims to propose optimal products and services based on user inquiries.

[1213] User inquiries

[1214] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). Here, users input their wishes and requests using natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[1215] Receiving and analyzing inquiries

[1216] The user's device sends the inputted inquiry to the server, which then uses a generative AI model (e.g., GPT-4) to analyze the user's inquiry and extract latent needs. The analysis process infers needs, even if the user has not explicitly stated them.

[1217] For example, if a user enters "I'm planning a family trip this summer," the server can generate follow-up questions such as "Where do you want to go, what is your budget, and what specific activities do you want to do?" to elicit further information from the user. The user then enters answers to the follow-up questions, which are then sent back to the server.

[1218] Generate and present recommendations based on needs

[1219] The server searches a database based on the collected information to find related products and services. The server then generates personalized recommendation results based on the products and services found. For example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling." The generated recommendation results are then sent to the terminal and displayed to the user.

[1220] Comparison of recommendation results

[1221] The server creates a comparison table of multiple products and services based on the generated recommendation results. This comparison table includes detailed information such as prices, ratings, and activities offered. The server sends the comparison table to the terminal, which displays it to the user. The user can make the best choice based on the detailed information.

[1222] Purchasing support and feedback collection

[1223] If the user decides to purchase after viewing the recommendations, the user's device will present a purchase link and assist in the purchase process. After the purchase, the server collects the user's feedback and stores it in a database. This feedback is used to improve the accuracy of recommendations next time. For example, a user may book a resort hotel and provide feedback after their stay such as, "It was comfortable. The staff were very helpful." The server will store this feedback and use it to make suggestions to future users.

[1224] Big data analysis and trend information provision

[1225] The server analyzes the big data collected from all users and generates information on fashion and trends. This information is provided to users and also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies. For example, the server analyzes data that shows "demand for camping is high this summer," and based on that, proposes a sales strategy for new camping equipment to an e-commerce site.

[1226] Sales Bot Features

[1227] Users interact with the sales bot to obtain detailed information about products they are interested in. The server uses the sales bot's functionality to communicate detailed product information and appeal to users, encouraging them to make a purchase. For example, the server might explain, "The seaside resort offers all meals and a wide range of activities. The mountain camping offers an attractive opportunity to experience nature," thereby increasing the user's desire to make a purchase.

[1228] Prompt Sentence Examples

[1229] An example of a user sending a query to a generative AI model:

[1230] "I'm planning a summer trip with my family. Can you recommend some places to go and where to stay?"

[1231] An example where the server generates a follow-up question after parsing:

[1232] "Do you have any destinations, budgets, or specific activities you'd like to do?"

[1233] As a result, this system utilizes generative AI models to recommend optimal products and services based on user needs, improving the user's purchasing experience.

[1234] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1235] Step 1:

[1236] A user accesses the website or application of the e-commerce concierge service using their own device (PC or smartphone) and inputs a query in natural language. The input query is sent to the server in the form of a prompt sentence such as, "I'm planning a summer trip with my family. What are your recommended destinations and accommodations?"

[1237] Step 2:

[1238] The terminal sends the query entered by the user to the server. The input is text data and is securely transmitted using the HTTPS protocol. The server receives this text data.

[1239] Step 3:

[1240] The server inputs the received text data into a generative AI model (e.g., GPT-4). The generative AI model analyzes this input data, understands the user's inquiry, and extracts latent demands. For example, it infers "destination, budget, and specific activities" from "family trip" and "summer." As output, it generates a follow-up question: "Do you have any preferences for destination, budget, or specific activities?"

[1241] Step 4:

[1242] The server sends the generated follow-up question to the terminal, which displays the question to the user and requests further information, which is then sent as input back to the server.

[1243] Step 5:

[1244] The user inputs answers to the additional questions. For example, the user inputs text such as "Destination: Okinawa. Activity: I would like snorkeling." and sends it to the server via the terminal. The server receives this input data.

[1245] Step 6:

[1246] The server then searches the database using the additional information to find related products and services. Keywords such as "Okinawa" for the destination and "snorkeling" for the activity are used to search the database. The output is a list of related resort hotels and tours.

[1247] Step 7:

[1248] The server creates a personalized recommendation list based on the generated recommendation results. For example, a list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" may be generated. The generated recommendation list is sent from the server to the device.

[1249] Step 8:

[1250] The terminal displays the recommendation list sent from the server to the user, who then begins making a selection based on the displayed list.

[1251] Step 9:

[1252] The server generates a comparison table of multiple products and services based on the generated recommendation results. The comparison table includes detailed information such as prices, ratings, and activities offered. For example, a comparison table of "Hotel A vs. Hotel B vs. Hotel C" is generated. This comparison table is sent to the terminal.

[1253] Step 10:

[1254] The terminal displays the comparison table sent from the server to the user, allowing the user to compare detailed information and make the best choice.

[1255] Step 11:

[1256] If the user decides to purchase after viewing the recommended results, the device will provide a purchase link to assist in the purchase process. This link is sent from the server, and the user clicks on it to complete the purchase.

[1257] Step 12:

[1258] After a purchase, the user provides feedback. The terminal provides a feedback input form, allowing the user to enter their opinions and thoughts. The input feedback is sent from the terminal to the server.

[1259] Step 13:

[1260] The server collects user feedback and stores it in a data storage device, and the feedback data is analyzed to improve the accuracy of the next recommendation.

[1261] Step 14:

[1262] The server generates fashion and trend information based on the collected big data, which is provided to users, manufacturers, and e-commerce sites for use in new product development and sales strategies.

[1263] Step 15:

[1264] Users can use the sales bot function to obtain more detailed information. The server communicates product details and appeal in a conversational format through the sales bot, increasing the user's desire to purchase. Explanations tailored to the user's specific needs are provided in real time.

[1265] (Application example 1)

[1266] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1267] Conventional product recommendation systems on e-commerce sites typically display related products when users input search keywords. However, this method makes it difficult to fully reflect the user's specific needs and implicit desires, and does not improve the user experience. Furthermore, users must search for related information themselves, which takes a lot of time and effort. This leads to issues such as a decrease in purchasing motivation and difficulty in finding optimal products and services.

[1268] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1269] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, and means for installing a smartphone application that extracts specific needs based on the content of the user's inquiry and finds and recommends related products and services based on the analysis results, thereby making it possible to quickly and accurately provide optimal products and services based on the user's specific needs and wishes.

[1270] A "user terminal" is an electronic device used by a user, and includes devices such as smartphones, tablets, and personal computers.

[1271] An "inquiry" is a request or question that a user inputs to the system, and is input in natural language.

[1272] A "generative AI model" is an artificial intelligence model that uses natural language processing to analyze inquiries entered by users and understand their meaning and intent.

[1273] "Latent needs" refer to expectations and requests that are not explicitly stated by the user but can be inferred from the content of the inquiry.

[1274] "Personalized recommendations" refers to product and service suggestions tailored to a user's specific needs and preferences.

[1275] A "smartphone application" is software that runs on a smartphone and provides a means for receiving user inquiries and displaying analysis results.

[1276] This system is implemented using a user terminal. Specifically, the user terminal is used by installing a smartphone application. This application provides an interface for users to input queries.

[1277] Users launch the smartphone app and input their requests or questions in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[1278] The smartphone app sends the user's inquiry to a server, which then uses OpenAI's generative AI model to analyze the inquiry and extract the user's potential needs, such as estimating the necessary camping gear, budget, and number of participants.

[1279] Based on the analysis results, the server then uses the e-commerce platform's search API to search for related products and services and generate personalized recommendations, such as suggesting specific products like a "three-person tent with excellent waterproofing."

[1280] The personalized recommendation results are sent from the server to the user's device and displayed on the smartphone app. The user can compare the presented recommendation results and check detailed information.

[1281] As a concrete example, if a user asks, "I'm going camping with friends in the spring. Do you have any recommended tents?", the generative AI model will extract needs such as "a three-person tent with good waterproofing" and recommend the most suitable product based on that. An example of a prompt is as follows:

[1282] Example prompt sentence:

[1283] User Question: I'm going camping with friends this spring. Can you recommend a tent?

[1284] Identify user needs and provide relevant information.

[1285] This system allows users to quickly and accurately select the best products and services based on their specific needs and desires, improving their purchasing experience.

[1286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1287] Step 1:

[1288] (Input) The user launches their smartphone app and inputs their request or question in natural language. For example, "I'm going camping with friends this spring. Do you have any recommended tents?"

[1289] (Operation) The terminal receives this natural language input.

[1290] (Output) Prepare the received inquiry as data to be passed on to the next processing step.

[1291] Step 2:

[1292] (Input) The natural language query entered by the user.

[1293] (Operation) The device sends the received query to the server, which analyzes the query using OpenAI's generative AI model.

[1294] (Data processing and calculation) The generative AI model analyzes the input natural language and extracts the user's latent needs, such as guessing the equipment needed for camping, budget, and number of participants.

[1295] (Output) Extracted needs and specific information (e.g., a three-person tent with excellent waterproofing).

[1296] Step 3:

[1297] (Input) Extracted needs and specific information.

[1298] (Operation) Based on the analysis results, the server uses the search API of the EC platform to search for related products and services.

[1299] (Data processing and calculation) A search query is generated and a list of relevant products is obtained by querying the EC platform database.

[1300] (Output) Personalized recommendations (e.g., a list of specific products or services).

[1301] Step 4:

[1302] (Input) Personalized recommendation results.

[1303] (Operation) The server transmits the generated recommendation results to the user terminal.

[1304] (Data processing) Format the recommendation results in a way that is easy for users to understand.

[1305] (Output) Formatted recommendation result data.

[1306] Step 5:

[1307] (Input) The formatted recommendation results sent from the server.

[1308] (Operation) The terminal displays the recommendation results to the user, who can compare the presented recommendation results and check detailed information.

[1309] (Output) Based on the user's confirmation and comparison, further inquiries and feedback information may be provided as needed.

[1310] By going through the above steps, users can be provided with the most suitable products and services quickly and accurately based on their specific needs and desires.

[1311] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1312] This system combines a generative AI model and an emotion engine to suggest optimal products and services based on user inquiries and increase purchasing motivation. A specific embodiment of this system is described below.

[1313] User inquiries

[1314] Users access the website or application of the e-commerce concierge service using their own devices (PCs or smartphones). At this time, users input their wishes and requests in natural language. For example, they could ask, "I'm planning a family trip this summer. What do you recommend?"

[1315] Receiving and analyzing inquiries

[1316] The device sends the user's input (query) to the server, which uses a generative AI model to analyze the user's query and extract latent needs. This analysis process infers needs, even if the user has not explicitly stated them.

[1317] At the same time, the emotion engine recognizes emotions from the user's input and comments during the conversation, and generates appropriate responses accordingly.

[1318] For example, if a user types, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion" and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[1319] Generate and present recommendations based on needs

[1320] The server searches for relevant products and services from a database based on the extracted needs, generates personalized recommendations based on the results, and sends them to the terminal, which then displays the recommendations to the user.

[1321] As a specific example, if a user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list such as "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.

[1322] Compare recommendations and get detailed information

[1323] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal, which then displays it to the user.

[1324] For example, the server generates a comparison table such as "Hotel A vs. Hotel B vs. Hotel C: price, review rating, and activities offered" and sends it to the terminal. The terminal displays the detailed information to the user, helping the user to make a comparison.

[1325] Purchasing support and feedback collection

[1326] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database. This feedback will be used to improve the accuracy of the next recommendation.

[1327] For example, a user may book a resort hotel and provide feedback after their stay, such as, "It was comfortable. The staff were very helpful." The server stores this feedback and uses it to make suggestions to future users.

[1328] Big data analysis and trend information provision

[1329] The server analyzes the collected big data and generates information on fashion and trends. This information is provided to users and is also shared with manufacturers and e-commerce sites. This information can be used to develop new products and improve sales strategies.

[1330] For example, the server analyzes data that shows there is high demand for camping this summer, and based on that, proposes a sales strategy for new camping equipment to the e-commerce site.

[1331] Sales Bot Features

[1332] Using the sales bot function, the server interactively provides detailed product information to the user, encouraging them to make a purchase. This function allows the user to obtain more detailed information and make a purchase decision with confidence.

[1333] For example, they might explain things like, "Seaside resorts offer all meals and plenty of activities, while mountain camping offers the appeal of experiencing nature," to increase users' desire to purchase.

[1334] Utilizing the Emotion Engine

[1335] The emotion engine analyzes the user's emotions in real time and adjusts the way it presents follow-up questions and recommendation results based on that analysis. For example, if the user is determined to be "concerned" after looking at a comparison chart, the emotion engine will support the user by generating follow-up questions such as "What are you unsure about?"

[1336] In this way, an e-commerce concierge service that combines a generative AI model with an emotion engine can recommend optimal products and services based on the user's needs and emotions, significantly improving the purchasing experience.

[1337] The processing flow will be explained below.

[1338] Step 1:

[1339] A user accesses the website or application of an e-commerce concierge service using their own device and inputs their wishes and requests into the interface in natural language (e.g., "I'm planning a family trip this summer. What do you recommend?").

[1340] Step 2:

[1341] The device sends the user's input to the server, and may also send additional relevant information, such as login information or past purchase history, to the server.

[1342] Step 3:

[1343] The server passes the received user input to a generative AI model, which uses natural language processing (NLP) to analyze the inquiry and extract potential needs.

[1344] Step 4:

[1345] At the same time, the server uses an emotion engine to recognize emotions from the user's input, such as "anxious" or "excited."

[1346] Step 5:

[1347] Based on the analysis results, the server generates follow-up questions to clarify any unclear points, such as "What is your travel destination, budget, and specific activities?", and generates questions based on the recognized emotions.

[1348] Step 6:

[1349] The server generates a follow-up question and sends it to the terminal, which displays it to the user, prompting for further information.

[1350] Step 7:

[1351] The user answers additional questions and enters specific information into the device (e.g., "I'm going to Okinawa, and I'd like to do snorkeling as an activity."). The emotion engine continues to analyze emotions from the user's answers.

[1352] Step 8:

[1353] The device sends the user's additional responses to the server, which again uses the generative AI model to analyze the additional information and determine the final need.

[1354] Step 9:

[1355] The server searches the database based on the identified needs, extracts relevant products and services, and generates personalized recommendations that are sent to the device.

[1356] Step 10:

[1357] The device displays the recommendation results received from the server to the user. The sales bot function explains the product's appeal in a conversational format, stimulating the user's desire to purchase. For example, it might explain, "Seaside resorts offer all meals and a wide range of activities. Mountain camping offers the appealing opportunity to experience nature."

[1358] Step 11:

[1359] The server generates a comparison table of multiple products or services based on the generated recommendation results, which includes detailed information such as features, ratings, and prices. The server transmits the comparison table to the terminal.

[1360] Step 12:

[1361] The device displays the comparison table received from the server to the user to help them make a comparison. The emotion engine analyzes the user's reaction and provides additional support based on their emotions. For example, it displays follow-up questions such as "Are you still undecided?"

[1362] Step 13:

[1363] If the user decides to purchase after viewing the recommended results, the device will present the user with a purchase link and assist in the purchase process. The user clicks the link to complete the purchase.

[1364] Step 14:

[1365] The server generates a request to collect user feedback after a purchase and sends it to the device, which displays it to the user and asks for a rating or review.

[1366] Step 15:

[1367] Users input ratings and reviews of purchased products into their devices and send them to the server. The emotion engine also analyzes the user's emotions from the feedback, including questions such as, "Was it a pleasant experience?"

[1368] Step 16:

[1369] The server stores the feedback in a database and uses it to improve the accuracy of recommendations next time.The server analyzes the collected big data and generates information on trends and fashions.

[1370] Step 17:

[1371] Based on the generated trend information, the server proposes new product development and sales strategies to manufacturers and e-commerce sites, and provides users with the latest trend information to maintain and increase their purchasing motivation.

[1372] Step 18:

[1373] The sales bot function provides users with further details in a conversational format, encouraging them to repurchase, thereby significantly improving the user's purchasing experience.

[1374] The system utilizes generative AI models and an emotion engine to recommend optimal products and services based on users' needs and emotions, improving the purchasing experience.

[1375] Example 2

[1376] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1377] Conventional e-commerce concierge systems provide simple responses to user inquiries and do not fully consider the user's latent needs and emotions. This makes it difficult to efficiently stimulate users' purchasing motivation and to recommend appropriate products and services.

[1378] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1379] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user inquiry using a generative AI model and extracting latent needs, means for identifying the user's emotions using an emotion engine and generating an appropriate response, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, and means for transmitting the generated recommendation results to the user terminal and displaying them to the user. This makes it possible to recommend products and services that appropriately consider the user's latent needs and emotions, thereby efficiently increasing the user's purchasing motivation.

[1380] A "user terminal" is an electronic device used by a user, such as a personal computer or smartphone, that can communicate with a server via the Internet.

[1381] A "generative AI model" is an artificial intelligence algorithm that uses natural language processing to analyze the content of a user's inquiry and extract the latent needs and information contained in the inquiry.

[1382] An "emotion engine" is a system that has the ability to identify a user's emotional state from their input and statements during a conversation, and generate an appropriate response.

[1383] A "database" is an information management system that stores information about products and services and is designed to allow that information to be searched and retrieved.

[1384] "Personalized recommendation results" are proposals for products and services that are customized based on the user's inquiry and needs, and are provided in a form that meets the individual requests of the user.

[1385] "Follow-up questions" are questions generated by the generative AI model as needed to further clarify the user's needs and prompt the user to provide additional information.

[1386] A "comparison table" is a format that displays detailed information such as features, ratings, and prices of multiple products or services in a list format, allowing users to compare them.

[1387] This invention relates to a system for recommending optimal products and services based on user inquiries. The system combines a generative AI model and an emotion engine to analyze the user's needs and emotions, and recommends products and services based on the results.

[1388] Hardware and software used

[1389] The system is implemented using the following hardware and software.

[1390] User terminal: A device that can connect to the Internet, such as a personal computer (PC) or smartphone.

[1391] Server: A computer system for data processing and analysis. Cloud services such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[1392] Generative AI model: An artificial intelligence that performs natural language processing. For example, OpenAI's GPT-4 can be used.

[1393] Emotion engine: An algorithm that identifies emotions from user utterances and generates appropriate responses.

[1394] Database: An information management system that stores and searches information about products and services. For example, you can use AWS's RDS.

[1395] System Operation

[1396] 1. User Inquiries

[1397] Users access the website or application of the e-commerce concierge service using a device such as a PC or smartphone, and input their wishes and requests in natural language. For example, they send a query such as, "I'm planning a family trip this summer. What do you recommend?"

[1398] 2. Receiving and analyzing inquiries

[1399] The device sends the user's input to the server. The server uses a generative AI model to analyze the received inquiry. This analysis extracts the user's latent needs. At the same time, the emotion engine identifies the user's emotions and generates an appropriate response. For example, if the user inputs, "I want to go on a trip, but I don't know where," the emotion engine will recognize the emotions of "anxiety" and "confusion," and generate a response such as, "We'll suggest some travel destinations that are perfect for you, so please feel free to ask us."

[1400] 3. Needs-based recommendation generation

[1401] The server searches for relevant products and services from a database based on the extracted needs, and generates personalized recommendations based on the results.

[1402] 4. Display of recommendation results

[1403] The generated recommendation results are sent from the server to the user's device, and the device displays them to the user. For example, if the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the device.

[1404] Examples of concrete examples and prompts

[1405] Examples:

[1406] If the user provides additional information such as "Destination: Okinawa, Activity: Snorkeling," the server generates a recommendation list of "Top 3 resort hotels in Okinawa where you can enjoy snorkeling" and sends it to the terminal.The server then generates a comparison table of information such as "Hotel A vs. Hotel B vs. Hotel C: Price, Review Rating, Activities Offered," and displays it to the user.

[1407] Example prompt sentence:

[1408] "Analyze user input and recommend the best products and services based on travel destinations and activities. Focus on using an emotion engine to generate responses based on the user's emotions."

[1409] In this way, by combining a generative AI model with an emotion engine, it becomes possible to make personalized recommendations for products and services that take into account the user's needs and emotions, significantly improving the user's purchasing experience.

[1410] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1411] Step 1:

[1412] Users access the website or application of the e-commerce concierge service using a device such as a personal computer (PC) or smartphone, and input their wishes and requests in natural language. Specifically, they input and submit a query such as, "I'm planning a family trip this summer. What do you recommend?"

[1413] Input: User's inquiry

[1414] Output: Sending query content from user terminal to server

[1415] Step 2:

[1416] The terminal sends the query entered by the user to the server as natural language text.

[1417] Input: The inquiry entered by the user

[1418] Output: Sending query content to the server

[1419] Step 3:

[1420] The server passes the received inquiry to the generative AI model, which analyzes it. This analysis extracts the user's latent needs. The generative AI model uses a natural language processing algorithm to understand the user's inquiry and analyze related keywords and intent. It also uses the extracted information to clarify the user's specific needs.

[1421] Input: Enquiry (natural language text)

[1422] Output: Extraction of potential needs

[1423] Step 4:

[1424] At the same time, the server uses an emotion engine to identify emotions from the user's input. For example, if a user inputs "I don't know where to go," the emotion engine will identify emotions such as "anxiety" or "hesitation." Depending on the identified emotion, the generative AI model will generate an appropriate response.

[1425] Input: Enquiry (natural language text)

[1426] Output: Identified emotions and appropriate responses

[1427] Step 5:

[1428] Based on the extracted needs and emotions, the server searches for relevant products and services from a database that stores information such as product features, ratings, and prices. Based on this information, the server generates personalized recommendation results.

[1429] Input: Potential needs, identified emotions

[1430] Output: Personalized recommendation results

[1431] Step 6:

[1432] The server then sends the generated personalized recommendation results to the user's device. The recommendation results include a list of products and services that meet the user's needs. For example, the recommendation may include specific content such as "Three resort hotels in Okinawa where you can enjoy snorkeling."

[1433] Input: Personalized recommendation results

[1434] Output: Sending recommendation results to the user's device

[1435] Step 7:

[1436] The terminal displays the recommendation results received from the server to the user, who can then browse the displayed recommendation results and check detailed information about the products or services that interest them.

[1437] Input: Recommendation results from the server

[1438] Output: Displaying the recommendations to the user

[1439] Step 8:

[1440] The server generates a comparison table of multiple products and services based on the recommendation results. This comparison table includes detailed information such as features, ratings, and prices. The server transmits this comparison table to the user's terminal, allowing the user to easily compare and consider each product or service.

[1441] Input: Information about products and services based on the recommendation results

[1442] Output: Comparison table

[1443] Step 9:

[1444] The terminal displays the comparison table received from the server to the user, who can then compare the detailed information of each product or service and make the best choice for themselves.

[1445] Input: Comparison table from the server

[1446] Output: Displaying a comparison table to the user

[1447] Step 10:

[1448] If the user decides to purchase after seeing the recommendation results, the device will present the user with a purchase link and assist in the purchase process. After the purchase, the server will collect the user's feedback and store it in a database.

[1449] Input: User's purchase decision

[1450] Output: Provide purchase link and collect feedback

[1451] In this way, the system uses generative AI models and emotion engines to carry out a series of processes to recommend optimal products and services based on user inquiries.

[1452] (Application example 2)

[1453] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1454] Conventional e-commerce concierge systems are unable to make proposals that take into account the user's emotions and real-time stress levels, and are therefore unable to fully increase user satisfaction or purchasing motivation. Furthermore, when presenting personalized recommendations to users, they are unable to respond to changes in the user's emotions, resulting in a limited user experience.

[1455] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1456] In this invention, the server includes means for receiving an inquiry from a user terminal, means for analyzing the content of the user's inquiry using a generative AI model and extracting latent needs, means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results, means for transmitting the generated recommendation results to the user terminal and displaying them to the user, means for analyzing the user's emotions and adjusting the recommendation results and responses based on the emotions, and means for evaluating the user's comments and actions in real time and making optimal suggestions based on the user's stress level. This enables detailed personalized suggestions that correspond to the user's emotions and stress level and a more satisfying purchasing experience.

[1457] A "user terminal" is a device through which a user enters input and receives information.

[1458] "Inquiry content" refers to information such as wishes, requests, questions, etc. that the user inputs via the terminal.

[1459] A "generative AI model" is a program that uses artificial intelligence technology to analyze input information and generate appropriate responses or suggestions.

[1460] "Latent needs" are requests or necessities that are not explicitly stated by the user but are inferred.

[1461] "Personalized recommendations" are suggestions and information that are customized based on a user's individual characteristics and needs.

[1462] A "database" is a system that stores and manages information about related products and services.

[1463] "Analyzing emotions" means recognizing the user's feelings and emotions at that time from their input and actions.

[1464] "Stress level" refers to the degree of mental tension or strain felt by the user.

[1465] "Real-time evaluation" means instantly analyzing users' comments and actions and taking appropriate action.

[1466] The system for implementing this invention comprises a user terminal, a server, and a database. The user terminal is a device such as a smartphone or a PC, and is used by users to input inquiries and receive related information.

[1467] The server is built using the following hardware and software:

[1468] OpenAI's generative AI model: Used to analyze user inquiries and extract latent needs.

[1469] Sentiment Analysis Engine: Used to analyze emotions from user input, real-time statements, and actions. This engine analyzes voice tone and text data to identify user emotions.

[1470] Database management system: Used to store information on related products and services.

[1471] When a user enters an inquiry from a smartphone or PC, the server analyzes the content using a generative AI model. Potential needs are extracted from the analyzed data, and related products and services are searched for in the database based on these. The server then generates personalized recommendations based on the results and sends them to the user's device.

[1472] Furthermore, the server uses an emotion analysis engine to analyze the user's emotions in real time and generate responses according to their emotions. For example, if the user indicates that they want to relax, the server will suggest routes with beautiful natural scenery and relaxing music.

[1473] For example, if a user inputs "I want to relax on a route with lots of nature," the server will analyze this request using a generative AI model and make a personalized suggestion of "a route with lots of nature." At the same time, the emotion analysis engine will recognize the user's emotion of "wanting to relax" and recommend the most suitable scenic route and music based on that.

[1474] In this way, it is possible to provide more personalized information in real time based on the user's inquiry and their feelings.

[1475] Examples of specific prompts include:

[1476] Example prompt sentence:

[1477] User: I want to relax on a route with lots of nature.

[1478] System: Finding optimal route...

[1479] System: Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory.

[1480] This system provides detailed personalized suggestions based on the user's emotions and stress level, and a more satisfying purchasing experience.

[1481] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1482] Step 1:

[1483] The user inputs the inquiry through the terminal and sends it to the server. This input includes requests and questions in natural language. For example, "I want to relax on a route with lots of nature." The server receives this inquiry.

[1484] Step 2:

[1485] The server analyzes the received inquiry using a generative AI model. The generative AI model processes the text entered by the user and extracts latent needs. For example, needs such as "route with lots of nature" and "want to relax" are analyzed. The input is the user's inquiry, and the output is the extracted latent needs.

[1486] Step 3:

[1487] The server searches a database based on the extracted needs to identify related products and services. Specifically, it searches for information on "routes with plenty of nature" or "places to relax." The input is the potential need, and the output is a list of related products and services.

[1488] Step 4:

[1489] The server uses a sentiment analysis engine to analyze the sentiment from the user's inquiry. For example, if the user wants to relax, the sentiment analysis engine will recognize the sentiment of "relaxation." The input is the user's inquiry, and the output is the analyzed sentiment.

[1490] Step 5:

[1491] Based on the emotional information analyzed by the emotion analysis engine, the server generates optimal recommendation results. These results include personalized information based on the user's emotions. For example, a "Relaxing natural scenery route: XXX Park -> YYY Lake -> ZZZ Observatory" may be generated. The input is the analyzed emotion and a list of related products, and the output is personalized recommendation results.

[1492] Step 6:

[1493] The server sends the generated recommendation results to the user's terminal and displays them to the user. The user receives them and checks the information displayed on the screen. The input is the personalized recommendation results, and the output is the information displayed on the user's terminal.

[1494] Step 7:

[1495] If the user inputs further questions or requests based on the results, the server can generate additional questions and continue the dialogue with the user. The generative AI model again analyzes this information and reassesses underlying needs and emotions. This process can be repeated as necessary. The input is the user's new questions or requests, and the output is additional dialogue content or recommendations.

[1496] This series of steps makes it possible to provide optimal products and services based on the user's emotions and needs.

[1497] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1498] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1499] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1500] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1501] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1502] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1503] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1504] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1505] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1506] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1507] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1508] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1509] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1510] 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.

[1511] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1512] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1513] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1514] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1515] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1516] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1517] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1518] The following is further disclosed regarding the above embodiment.

[1519] (Claim 1)

[1520] means for receiving an inquiry from a user terminal;

[1521] A means of analyzing user inquiries using a generative AI model and extracting latent needs;

[1522] A means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results;

[1523] means for transmitting the generated recommendation results to a user terminal and displaying them to the user;

[1524] A system including:

[1525] (Claim 2)

[1526] The system of claim 1, wherein the generative AI model generates additional questions as needed and sends them to the user terminal.

[1527] (Claim 3)

[1528] 2. The system according to claim 1, further comprising: a comparison table of products and services generated based on the generated recommendation results, and transmitting the comparison table to the user terminal.

[1529] (Claim 4)

[1530] A means of collecting user feedback after purchase and storing it in a database;

[1531] How to use the collected feedback to improve the accuracy of next recommendations; and

[1532] 10. The system of claim 1, comprising:

[1533] (Claim 5)

[1534] A means for analyzing the collected big data, generating trend and fashion information, and providing it to users and manufacturers;

[1535] 10. The system of claim 1, comprising:

[1536] (Claim 6)

[1537] A means for providing detailed product information to users in an interactive format using a sales bot function to stimulate their desire to purchase;

[1538] 10. The system of claim 1, comprising:

[1539] "Example 1"

[1540] (Claim 1)

[1541] means for receiving a query from a user device;

[1542] A means for analyzing user inquiries using a generative artificial intelligence model and extracting potential demands;

[1543] A means for searching a data storage device for relevant products and services based on the extracted demand and generating personalized recommendation results;

[1544] means for transmitting the generated recommendation results to a user device and displaying them to the user;

[1545] means for collecting user-submitted feedback and storing the feedback in a data storage device;

[1546] A system including:

[1547] (Claim 2)

[1548] 10. The system of claim 1, wherein the generative artificial intelligence model generates and transmits follow-up questions to the user device as needed.

[1549] (Claim 3)

[1550] 10. The system according to claim 1, further comprising: generating a comparison table of a plurality of products and services based on the generated recommendation results, and transmitting the comparison table to the user device.

[1551] "Application Example 1"

[1552] (Claim 1)

[1553] means for receiving an inquiry from a user terminal;

[1554] A means of analyzing user inquiries using a generative AI model and extracting latent needs;

[1555] A means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results;

[1556] means for transmitting the generated recommendation results to a user terminal and displaying them to the user;

[1557] A method to install a smartphone application that extracts specific needs based on the content of the user's inquiry and finds and recommends related products and services based on the analysis results, and

[1558] A system including:

[1559] (Claim 2)

[1560] The system of claim 1, wherein the generative AI model generates additional questions as needed and sends them to the user terminal.

[1561] (Claim 3)

[1562] 2. The system according to claim 1, further comprising: a comparison table of products and services generated based on the generated recommendation results, and transmitting the comparison table to the user terminal.

[1563] "Example 2: Combining Emotion Engines"

[1564] (Claim 1)

[1565] means for receiving an inquiry from a user terminal;

[1566] A means of analyzing user inquiries using a generative AI model and extracting latent needs;

[1567] means for identifying a user's emotion using an emotion engine and generating an appropriate response;

[1568] A means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results;

[1569] means for transmitting the generated recommendation results to a user terminal and displaying them to the user;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, further comprising means for the generative AI model to generate and send follow-up questions to the user terminal as needed.

[1573] (Claim 3)

[1574] 2. The system according to claim 1, further comprising means for generating a comparison table of products and services based on the generated recommendation results and transmitting the comparison table to the user terminal.

[1575] "Application example 2 when combining emotion engines"

[1576] (Claim 1)

[1577] means for receiving an inquiry from a user terminal;

[1578] A means of analyzing user inquiries using a generative AI model and extracting latent needs;

[1579] A means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results;

[1580] means for transmitting the generated recommendation results to a user terminal and displaying them to the user;

[1581] means for analyzing a user's emotions and adjusting recommendations and responses based on the emotions;

[1582] A system including:

[1583] (Claim 2)

[1584] The system of claim 1, wherein the generative AI model generates additional questions as needed and sends them to the user terminal.

[1585] (Claim 3)

[1586] 2. The system according to claim 1, further comprising: a comparison table of products and services generated based on the generated recommendation results, and transmitting the comparison table to the user terminal.

[1587] (Claim 4)

[1588] 2. The system according to claim 1, further comprising means for evaluating the user's statements and actions in real time and making optimal suggestions according to the user's stress level. [Explanation of symbols]

[1589] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving an inquiry from a user terminal; A means of analyzing user inquiries using a generative AI model and extracting latent needs; A means for searching a database for related products and services based on the extracted needs and generating personalized recommendation results; means for transmitting the generated recommendation results to a user terminal and displaying them to the user; A system including:

2. The system of claim 1, wherein the generative AI model generates additional questions as needed and sends them to the user terminal.

3. 2. The system according to claim 1, further comprising: a comparison table of products and services generated based on the generated recommendation results, and transmitting the comparison table to the user terminal.

4. A means of collecting user feedback after purchase and storing it in a database; How to use the collected feedback to improve the accuracy of next recommendations; and The system of claim 1 , comprising:

5. A means for analyzing the collected big data, generating trend and fashion information, and providing it to users and manufacturers; The system of claim 1 , comprising:

6. A means for providing detailed product information to users in an interactive format using a sales bot function to stimulate their desire to purchase; The system of claim 1 , comprising:

Images