System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting an ambiguous request of a user; means for analyzing the ambiguous request to extract related keywords; means for generating and presenting a question to the user based on the related keywords; means for receiving an answer from the user and further analyzing the received answer to identify a specific candidate item; and means for presenting the specific candidate item 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 shopping sites, unless users know specific product names or specific search criteria, search results contain a lot of noise, making it difficult for users to efficiently find the products they are looking for. Furthermore, the lack of functionality to suggest specific products in response to users' vague requests has led to frustration. Therefore, the objective of this invention is to provide users with a stress-free search experience by efficiently suggesting appropriate products, even when users enter vague requests. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. That is, a system is provided that includes a means for inputting a user's vague request, a means for analyzing the vague request and extracting related keywords, a means for generating and presenting a question to the user based on the related keywords, a means for receiving an answer from the user and further analyzing the received answer to identify specific product candidates, and a means for presenting the specific product candidates to the user. This allows a user to efficiently find appropriate products simply by inputting a vague request.

[0006] "User" means an individual or organization that uses the System to search for and purchase Products.

[0007] "Ambiguous requests" are vague requests or demands made by users without specifying specific product names or conditions.

[0008] "Input means" refers to the interface or device through which a user inputs vague requests into the system.

[0009] "Means of analysis" refers to technology or devices that use machine learning or natural language processing technology to understand the meaning of ambiguous input requests and extract related keywords.

[0010] "Related keywords" are words or phrases that are extracted from vague requirements and are useful for product searches.

[0011] "Generation means" refers to technology or devices that create appropriate questions for users based on related keywords.

[0012] "Presentation means" refers to an interface or device that shows the generated questions and product candidates to the user.

[0013] "Means for receiving a response" refers to the technology or device that receives the response from the user.

[0014] "Means for further analysis" refers to technologies or devices that use machine learning or natural language processing technology to re-analyze user response data and extract more specific information.

[0015] "Specific product candidates" is a list of products that can be suggested based on the user's request and the analysis results.

[0016] The "means for presenting product candidates" refers to an interface or device for displaying identified specific product candidates to the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This allows the user to have a less stressful search experience. The following describes in detail the embodiments of the invention.

[0039] Overall system overview

[0040] A user uses a device to input a vague request into the search box of a shopping site. This request is sent to a server, which uses a generative AI model to analyze the request. Then, based on the analysis results, the server generates questions for the user and identifies and suggests suitable products to the user while receiving the user's answers.

[0041] System configuration for implementation

[0042] The system includes the following major components:

[0043] User Interface (UI): The interface through which users input requests and interact with the system.

[0044] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[0045] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0046] Program processing

[0047] The program of this system proceeds in the following order:

[0048] User request input

[0049] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[0050] Parsing the request

[0051] The server uses the generative AI model to analyze the vague request received from the user. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "information program," "yesterday," and "cooking equipment" are identified.

[0052] Question Generation

[0053] The server generates a question for the user based on the extracted related keywords, for example, "What is the name of that information program?", and sends it to the user's device.

[0054] User interaction

[0055] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "Please tell me the specific uses and features of that cookware," and collect information from the user through dialogue.

[0056] Product candidate suggestions

[0057] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The identified product candidates are sent to the user's device and suggested to the user.

[0058] User Choices and Purchases

[0059] Users can select products of interest from the suggested options, check out the details, and finally complete the purchase process.

[0060] Specific examples

[0061] 1. User Input

[0062] User: "I want this thing I saw on yesterday's TV show."

[0063] Terminal: Send this input to the server.

[0064] 2. Server-based analysis and query generation

[0065] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[0066] 3. User interaction

[0067] Terminal: Display the question to the user.

[0068] User: "It's 'Good Morning' from yesterday."

[0069] Server: Generate the next question: "What is the specific use of that cookware?"

[0070] User: "It's a steamer that can be used in the microwave."

[0071] 4. Final product proposal

[0072] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0073] Device: Show suggested content to the user.

[0074] User: Selects a product and proceeds with the purchase.

[0075] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[0076] The processing flow will be explained below.

[0077] Specific processing flow of the program

[0078] Step 1:

[0079] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[0080] Step 2:

[0081] The device sends the user's input to the server.

[0082] Step 3:

[0083] The server receives an ambiguous request from a user.

[0084] Step 4:

[0085] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[0086] Step 5:

[0087] The server generates appropriate questions for the user (e.g., "What is the name of that information program?") based on the extracted related keywords.

[0088] Step 6:

[0089] The server generates a question and sends it to the user's device.

[0090] Step 7:

[0091] The device displays the questions received from the server on the screen and prompts the user to interact.

[0092] Step 8:

[0093] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[0094] Step 9:

[0095] The server receives the user's response and analyzes it again using the generative AI model.

[0096] Step 10:

[0097] The server generates a more specific question (e.g., "Please tell me the specific uses and features of that cookware") and sends it to the terminal.

[0098] Step 11:

[0099] The device asks the user additional questions, and the user enters a specific answer (e.g., "It's a microwaveable steamer"), which the device then sends to the server.

[0100] Step 12:

[0101] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[0102] Step 13:

[0103] The server identifies the best product candidates (e.g., "The microwave steamer featured on yesterday's Good Morning") and generates content to suggest them to the user.

[0104] Step 14:

[0105] The server sends the generated suggested content to the user's terminal.

[0106] Step 15:

[0107] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[0108] Step 16:

[0109] The user selects a product and proceeds with the purchase.

[0110] In this way, the process of identifying specific product candidates from vague requests and proposing them to the user is completed.

[0111] Example 1

[0112] 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."

[0113] On conventional shopping sites, it is difficult for users to find suitable products unless they enter specific keywords. In addition, there is a lack of efficient means to suggest related products to users with vague requirements. This causes users to feel stressed and waste time when searching for products. Therefore, a system is needed that can efficiently and appropriately suggest products even when users enter vague requirements.

[0114] 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.

[0115] In this invention, the server includes a means for analyzing a user's vague request using a generative AI model and extracting related keywords, a means for generating and presenting questions to the user based on the related keywords, and a means for reanalyzing the user's answers to identify specific product candidates, thereby enabling efficient and appropriate product suggestions even from a user's vague request.

[0116] "User" means an individual or corporation that uses this system to search for and purchase products.

[0117] "Vague requests" are vaguely expressed wishes or requests that do not include specific product names or detailed information.

[0118] A "generative AI model" is an artificial intelligence model that learns from large amounts of data, analyzes ambiguous requests, and extracts relevant keywords.

[0119] "Related keywords" are important words and phrases related to product search and suggestions that are extracted by analyzing a user's vague requirements.

[0120] "Question generation and presentation means" refers to the function or device that creates and presents questions to users based on the extracted related keywords.

[0121] "Reanalysis" refers to the process of reanalyzing user responses to identify more specific product candidates.

[0122] "Product Candidates" refers to a list or set of products that may be of interest to the user, identified from the user's vague requests and responses.

[0123] A "database" is a collection of information that systematically stores and manages user requests, responses, product information, etc., and is referenced when analyzing and making proposals.

[0124] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This system allows the user to have a less stressful search experience. The following describes in detail the embodiments of the present invention.

[0125] System Configuration

[0126] The system includes the following major hardware and software components:

[0127] User Interface (UI): The interface through which a user inputs requests and interacts with a system. Examples include a web browser or a mobile application.

[0128] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server. An internet connection is mainly used.

[0129] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers. It also contains the computing resources to run the generative AI model.

[0130] Program processing

[0131] The program of this system executes a series of processes from user request input to product proposal in the following order.

[0132] User request input

[0133] A user accesses a shopping site and inputs a vague request such as "I want this and that thing I saw on yesterday's news program." The device sends this input to the server. The device can be a PC or a smartphone.

[0134] Parsing the request

[0135] The server uses a generative AI model to analyze ambiguous requests received from users. The generative AI model has been trained with a large amount of ambiguous data in advance. This analysis method extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request.

[0136] Question Generation

[0137] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated and sent to the terminal. The terminal then displays the received question to the user.

[0138] User interaction

[0139] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "What are the specific uses and features of that cookware?", and collect information through dialogue with the user.

[0140] Product candidate suggestions

[0141] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server then sends the identified product candidates to the device and suggests them to the user.

[0142] User Choices and Purchases

[0143] The user selects the product of interest from the suggested product candidates, checks the detailed information, and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server, and the server stores the purchase history in a database.

[0144] Specific examples

[0145] 1. User Input

[0146] User: "I want this thing I saw on yesterday's TV show."

[0147] Terminal: Send this input to the server.

[0148] 2. Server-based analysis and query generation

[0149] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[0150] 3. User interaction

[0151] Terminal: Display the question to the user.

[0152] User: "It's 'Good Morning' from yesterday."

[0153] Server: Generate the next question: "What is the specific use of that cookware?"

[0154] User: "It's a steamer that can be used in the microwave."

[0155] 4. Final product proposal

[0156] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0157] Device: Show suggested content to the user.

[0158] User: Selects a product and proceeds with the purchase.

[0159] Prompt Sentence Examples

[0160] "I want this thing I saw on yesterday's news program. How do I search for it?"

[0161] "The name of this information program is 'Good Morning.' I would like to find the product that was featured on this program."

[0162] Please tell me about a steamer that can be used in a microwave.

[0163] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[0164] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0165] Program processing flow

[0166] Step 1: User Request Input

[0167] The user accesses a shopping site and inputs a vague request. For example, a request such as "I want this and that thing I saw on yesterday's news program." The terminal sends this input to the server. In this step, the input is the user's vague request, and the output is the request data sent to the server.

[0168] Step 2: Parsing the request

[0169] The server uses a generative AI model to analyze the received ambiguous request. The generative AI model has been trained with a large amount of ambiguous expression data in advance. The server extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request. In this step, the input is the ambiguous request data, and the output is the related keywords.

[0170] Step 3: Generate questions

[0171] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated. The server sends the generated question to the terminal. In this step, the input is the related keywords, and the output is the generated question.

[0172] Step 4: Present the question to the user

[0173] The terminal displays the received question to the user, and allows the user to enter an answer to the question. In this step, input: generated question, output: question presented to the user.

[0174] Step 5: User answers

[0175] The user answers the question displayed on the terminal. For example, the user might answer, "The name of the information program is 'Good Morning.'" The terminal then sends this answer to the server. In this step, the input is the user's answer, and the output is the answer data sent to the server.

[0176] Step 6: Reanalyze the answers

[0177] The server reanalyzes the received answer and generates a more specific question if necessary. For example, it generates an additional question such as, "Please tell me the specific uses and features of the cookware." The server then sends the generated additional question to the terminal. In this step, the input is the user's answer data, and the output is the generated additional question.

[0178] Step 7: Ask questions again and collect answers

[0179] The process from step 4 to step 6 is repeated until enough information is gathered. The device asks the user another question and sends the user's answer to the server again. This cycle is: Input: additional question and answer; Output: identified information.

[0180] Step 8: Identify product candidates

[0181] The server uses a generative AI model to identify the most suitable product candidate based on all the information obtained from the user. For example, "The microwave steamer featured on yesterday's Good Morning" is identified. The server sends the identified product candidate and its details to the terminal. In this step, the input is the user's specific request information, and the output is the identified product candidate.

[0182] Step 9: Propose the product to the user

[0183] The terminal displays the received product candidates to the user. The user selects the product of interest from the suggested product candidates and checks the detailed information. In this step, input: identified product candidates, output: products presented to the user.

[0184] Step 10: User selection and checkout

[0185] The user checks the detailed information from the suggested product candidates and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server. The server stores the purchase history in a database and uses it as reference data for future operations. In this step, input: user's purchase selection, output: purchase history stored on the server.

[0186] (Application example 1)

[0187] 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."

[0188] In modern content distribution services, users often have difficulty finding the appropriate content when the title or content of the video or movie they want to watch is unclear. Users often spend a lot of time and effort trying to identify content that meets their needs from the vast amount of content available. Furthermore, traditional search functions are unable to fully respond to ambiguous requests, resulting in a decline in user satisfaction.

[0189] 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.

[0190] In this invention, the server includes a means for inputting a user's ambiguous request, a means for analyzing the ambiguous request and extracting related keywords, and a means for generating and presenting questions to the user based on the related keywords. This makes it possible to effectively analyze the user's ambiguous request and suggest appropriate content. Furthermore, by utilizing a generative AI model, the server can specify the request through dialogue with the user and identify content candidates by learning the latest trends and information, thereby improving user satisfaction.

[0191] An "ambiguous request" refers to a request where the specific details are unclear and the user's intentions and wishes are partially unclear.

[0192] "Analysis" refers to the process of extracting meaning and relationships based on input data and information.

[0193] "Related keywords" refer to important, highly relevant words and phrases that are obtained as a result of analyzing a user's request.

[0194] "Means for generating and presenting questions" refers to the function for creating appropriate questions for the user based on the analysis results and displaying them to the user.

[0195] "Means for receiving responses" refers to the functionality for receiving replies or responses from users.

[0196] "Specific content suggestions" refers to a list of content that the user is likely to want, identified after specifying the user's request.

[0197] "Means for presenting content candidates" refers to functionality for displaying identified content candidates to a user.

[0198] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate questions or content based on user input or requests.

[0199] "Dialogue" refers to the process in which a user and a system exchange questions and answers with each other.

[0200] "Means of learning trends and information" refers to a function that collects the latest trends and information as data and uses that data to make appropriate suggestions to users.

[0201] As an embodiment of the present invention, we will explain a system that analyzes vague requests entered by a user and efficiently suggests appropriate content. This system utilizes a generative AI model to concretize the user's vague requests and provide optimal content.

[0202] Overall system overview

[0203] A user uses a smartphone to input a vague request into the search box of a content delivery service. This request is sent to a server, which uses a generative AI model to analyze the request. Based on the analysis results, the server generates questions for the user, and while receiving the user's answers, identifies and suggests appropriate content candidates to the user.

[0204] System configuration for implementation

[0205] The system includes the following major components:

[0206] User Interface (UI): The interface through which users input requests and interact with the system.

[0207] Communication means: A communication means for sending user requests and answers to the server and receiving questions and content suggestions from the server.

[0208] Server: A central device that analyzes user requests, generates appropriate questions, and identifies content suggestions based on the user's answers.

[0209] Generative AI model: A model that analyzes vague user requests, gathers specific information through dialogue, and suggests optimal content.

[0210] Examples and prompts

[0211] User Input:

[0212] User: "I want to watch a drama like the movie I saw on streaming last week."

[0213] Terminal: Send this input to the server.

[0214] The server uses a generative AI model to analyze the vague requests received from users. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "last week's broadcasts," "movies," and "dramas" are identified.

[0215] The server generates a question for the user based on the extracted related keywords, for example, "Who was the main character in that movie?", and sends it to the user's device.

[0216] The user answers a question displayed on the device. For example, they might say, "Maybe it's a famous actor." The device then sends this answer to the server. The server then re-analyzes the answer and generates a more specific question if necessary. For example, it might generate a follow-up question like, "What genre is that movie?", and collect information from the user through dialogue.

[0217] Below is an example of a prompt sentence to input to the generative AI model.

[0218] A user makes a request like: "I want to watch a drama like the movie I saw on streaming last week."

[0219] What questions should I ask next?

[0220] Finally, the server uses a generative AI model to identify the most suitable content candidates based on all the information obtained from the user. For example, it might identify "dramas starring famous actors that were featured in last week's stream." The identified content candidates are sent to the user's device and suggested to the user.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] A user uses a smartphone's user interface (UI) to input a vague request, such as, "I want to watch a TV show like the movie I saw streaming last week."

[0224] Input: User's vague request

[0225] Output: Sends the request data to the server

[0226] Specific operation: When the user enters a request in the text box and taps the "Search" button, the device will send this request to the server.

[0227] Step 2:

[0228] The server uses a generative AI model to analyze the ambiguous request it receives. The analysis extracts relevant keywords from the user's request. For example, keywords such as "last week's streams," "movies," and "dramas" are identified.

[0229] Input: Request data, Generative AI model

[0230] Output: Related keywords

[0231] Specific operation: The server passes the request data to the generative AI model, which then extracts relevant keywords.

[0232] Step 3:

[0233] The server generates questions for the user based on the extracted related keywords, such as "Who was the main character in that movie?"

[0234] Input: Related keywords

[0235] Output: Question text

[0236] Specific operation: Based on relevant keywords, the server uses a generative AI model to construct an appropriate question and sends this question to the user.

[0237] Step 4:

[0238] The device displays the generated question text to the user, who then enters an answer to the question, for example, "Maybe he's a famous actor."

[0239] Input: Question text

[0240] Output: User's answer

[0241] Specific operation: The device receives the user's answer to the displayed question and sends it to the server.

[0242] Step 5:

[0243] The server re-analyzes the user's answers and, if necessary, generates more specific questions to present to the user, such as "What genre is that movie?"

[0244] Input: User's answer

[0245] Output: Next question text

[0246] Specific operation: The server uses the generative AI model based on the user's answers to generate the next question to obtain additional information and sends it to the device.

[0247] Step 6:

[0248] The terminal displays the following question text to the user, who then enters a more specific answer, and this interactive process is repeated as necessary.

[0249] Input: Next question text

[0250] Output: Additional user answers

[0251] Specific operation: Each time a user answers a question, the answer is sent to the server.

[0252] Step 7:

[0253] The server then re-analyzes all the collected information and uses a generative AI model to identify the best content candidates, for example, "dramas starring famous actors featured in last week's streams."

[0254] Input: All user responses

[0255] Output: Best content candidates

[0256] How it works: The server uses collected data and generative AI models to identify content candidates and generate suggestions for the user.

[0257] Step 8:

[0258] The device presents the identified content candidates to the user, who can then review and select the suggested content.

[0259] Input: Best content suggestions

[0260] Output: Content suggestions presented to the user

[0261] Specific operation: The device displays content suggestions received from the server, and the user selects and watches the content of interest.

[0262] 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.

[0263] This invention combines a system that analyzes a user's vague requests and proposes specific product candidates with an emotion engine that recognizes the user's emotions and optimizes the content of questions and product proposals based on those emotions. By taking the user's emotions into consideration, it is possible to provide an optimal shopping experience with even less stress for the user.

[0264] Overall system overview

[0265] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which uses a generative AI model and an emotion engine to analyze the request and generate and present appropriate questions. As the server receives the user's responses, it adjusts the content of the questions and product candidates in response to changes in emotion, suggesting the most suitable products.

[0266] System configuration for implementation

[0267] The system includes the following major components:

[0268] User Interface (UI): The interface through which users input requests and interact with the system.

[0269] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[0270] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0271] Emotion engine: An engine for recognizing user emotions and reflecting them in analysis.

[0272] Program processing

[0273] The program of this system proceeds in the following order:

[0274] User request input

[0275] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[0276] Parsing the request

[0277] The server uses a generative AI model to analyze vague requests received from users and extract related keywords (e.g., "information program," "yesterday," "cooking equipment"), while an emotion engine recognizes the user's emotions and incorporates them into the analysis.

[0278] Question Generation

[0279] The server generates a question for the user (e.g., "What is the name of that information program?") based on the extracted related keywords and the recognition results of the emotion engine. The question is adjusted according to the user's emotions.

[0280] User interaction

[0281] The user answers a question displayed on the device (e.g., "The name of the information program is 'Good Morning'"). The device then sends this answer to the server. The server then re-analyzes the received answer and re-evaluates the user's emotions using the emotion engine. If necessary, when generating a more specific question (e.g., "What are the specific uses and features of that cookware?"), the content is adjusted taking the user's emotions into account.

[0282] Product candidate suggestions

[0283] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the emotion engine's evaluation. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server optimizes the presentation order of the identified product candidates based on the user's emotions and sends them to the device.

[0284] User Choices and Purchases

[0285] The device displays suggested products to the user, who can then review the details, select the products they are interested in, and finally complete the purchase process.

[0286] Specific examples

[0287] 1. User Input

[0288] User: "I want this thing I saw on yesterday's TV show."

[0289] Terminal: Send this input to the server.

[0290] 2. Server-based analysis and query generation

[0291] Server: Generates "What is the name of that information program?" and then the emotion engine recognizes the user's emotion.

[0292] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer, such as "Please don't hesitate to tell me, what is the name of that information program?"

[0293] 3. User interaction

[0294] Terminal: Display the question to the user.

[0295] User: "Good morning," and reevaluate the emotion engine's recognition results.

[0296] Server: Re-analyzes the answer and takes into account the sentiment engine's evaluation when generating the next question.

[0297] 4. Final product proposal

[0298] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0299] Server: Optimize the product presentation order based on user sentiment.

[0300] Device: Show suggested content to the user.

[0301] User: Selects a product and proceeds with the purchase.

[0302] In this way, the system efficiently embodies the user's vague requests and further proposes optimal products taking into account their emotions.

[0303] The processing flow will be explained below.

[0304] Specific processing flow of the program

[0305] Step 1:

[0306] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[0307] Step 2:

[0308] The device sends the user's input to the server.

[0309] Step 3:

[0310] The server receives an ambiguous request from a user.

[0311] Step 4:

[0312] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[0313] Step 5:

[0314] The server generates appropriate questions for the user based on the extracted related keywords.

[0315] Step 6:

[0316] The server generates a question and sends it to the user's device.

[0317] Step 7:

[0318] The device displays the questions received from the server on the screen and prompts the user to interact.

[0319] Step 8:

[0320] The emotion engine analyzes the user's emotions and evaluates their current emotional state. For example, if it recognizes that the user looks anxious, it will adjust the tone of the question to something like, "Please relax and answer freely. What is the name of that news program?"

[0321] Step 9:

[0322] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[0323] Step 10:

[0324] The server receives the user's response and analyzes it again using the generative AI model.

[0325] Step 11:

[0326] The emotion engine reevaluates the user's emotional state at the time of answering and generates more appropriate questions, with the server adapting the questions accordingly (e.g., "Please tell me the specific uses and features of that cookware").

[0327] Step 12:

[0328] The server sends additional questions to the terminal, which displays the questions to the user.

[0329] Step 13:

[0330] The user enters a specific answer (e.g., "It's a steamer that can be used in a microwave"), and the device sends the answer to the server.

[0331] Step 14:

[0332] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[0333] Step 15:

[0334] The server identifies appropriate product candidates based on the evaluation results of the emotion engine and optimizes the order of presentation, making friendly suggestions based on the user's emotions, such as "Here's a microwave steamer that everyone has highly rated."

[0335] Step 16:

[0336] The server sends the generated suggested content to the user's terminal.

[0337] Step 17:

[0338] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[0339] Step 18:

[0340] As users select products and proceed with the purchase process, the emotion engine monitors their emotions and provides support to ensure a stress-free experience.

[0341] This series of steps will realize a system that takes emotions into account, efficiently clarifies the user's vague requests, and suggests optimal product candidates.

[0342] Example 2

[0343] 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."

[0344] Conventional shopping systems have difficulty identifying appropriate products based on vague user input. Furthermore, questions and suggestions are often made without considering the user's feelings, resulting in a poor user experience. As a result, it takes a lot of time and effort for users to find the product they are looking for, which increases their stress.

[0345] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's vague request and extracting related information, means for generating and presenting appropriate questions based on the related information and the user's emotions, means for reanalyzing the user's answers and emotions to identify product candidates, means for presenting the product candidates in an optimal order based on the user's emotions, means for specifying the request through dialogue with the user using a generative AI model and an emotion recognition engine, and means for learning the latest market trends and information and using them to identify product candidates and present them in accordance with the user's emotions. This makes it possible to quickly and appropriately suggest products while taking emotions into consideration, even based on a user's vague request.

[0346] "Ambiguous user requests" are requests that express vague needs or desires without clear specific product names or details.

[0347] "Related information" refers to keywords and concepts extracted from a user's vague request that are useful for making the request more specific.

[0348] An "emotion recognition engine" is a program or software that analyzes and recognizes a user's emotional state (e.g., anxiety, excitement, satisfaction, etc.) from their input or dialogue.

[0349] A "generative AI model" is an artificial intelligence model that generates questions and responses in natural language from input data.

[0350] "Question generation and presentation" is the process of creating appropriate questions based on user requests and presenting them to the user.

[0351] "Product Candidate" means a specific product or service that is recommended based on the user's request and analysis results.

[0352] "Latest market trends" refers to information related to current market trends and user interests.

[0353] "Presenting in the appropriate order" means taking into consideration the user's emotions and interests and displaying information and product candidates in the order that will attract the most attention.

[0354] "User interface (UI)" refers to an interface such as a screen or input means that allows a user to interact with a system.

[0355] This system analyzes the user's vague requests and proposes optimal questions and products based on the user's emotions, thereby providing the user with a stress-free shopping experience.

[0356] Overall system overview

[0357] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which analyzes the request using a generative AI model and an emotion recognition engine to generate and present an appropriate question. As the server receives the user's response, it adjusts the question content and product candidates in response to changes in emotion, suggesting the most suitable product.

[0358] System configuration for implementation

[0359] The system includes the following major components:

[0360] User Interface (UI): The interface through which the user enters requests and interacts with the system.

[0361] Communication method: This is the communication method used to send user requests and answers to the server and receive questions and product suggestions from the server. Specifically, HTTPS is used.

[0362] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0363] Emotion recognition engine: An engine that recognizes user emotions and reflects them in analysis. An example is IBM Watson Tone Analyzer.

[0364] Generative AI model: A model that performs natural language processing and generates appropriate questions and product suggestions based on user requests and answers. An example is OpenAI GPT-4.

[0365] Specific examples

[0366] 1. User Input

[0367] User: "I want this thing I saw on yesterday's TV show."

[0368] Terminal: Send this input to the server.

[0369] 2. Server-based analysis and query generation

[0370] Server: Generates "What is the name of that information program?" and then the emotion recognition engine recognizes the user's emotion.

[0371] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer like, "Please don't hesitate to tell me, what is the name of that information program?"

[0372] 3. User interaction

[0373] Terminal: Display the question to the user.

[0374] User: "Good morning," and the device sends this response to the server.

[0375] Server: Re-analyzes the answer and takes into account the emotion recognition engine's evaluation when generating the next question.

[0376] 4. Final product proposal

[0377] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0378] Server: Optimize the product presentation order based on user sentiment.

[0379] Device: Display suggested content to the user.

[0380] User: Selects a product and proceeds with the purchase.

[0381] Prompt Sentence Examples

[0382] "Please provide a prompt for the system that uses a corresponding emotion recognition engine and generative AI model to parse a user's vague request and identify specific product candidates."

[0383] As described above, the present invention provides a system that efficiently embodies the vague needs of a user and further proposes optimal products taking emotions into consideration.

[0384] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0385] Step 1: User Request Input

[0386] A user visits a shopping site and enters a vague request into the search box (e.g., "I want this and that thing I saw on yesterday's news program"). As input, vague natural language text is obtained. The device receives this input and sends it to the server. As output, data containing the user's request is sent to the server.

[0387] Step 2: Submitting the request

[0388] The terminal sends an ambiguous request entered by the user to the server using the HTTPS protocol. It receives the user's text data as input and sends an HTTPS request to the server as output.

[0389] Step 3: Parsing the request

[0390] The server inputs the text data into a generative AI model (e.g., OpenAI GPT-4) to analyze the received user request. The user's request text is passed to the model as input, and data processing involves extracting related keywords and specifying the information. The text is also passed to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The output is related keywords and the user's emotional information.

[0391] Step 4: Generate and submit your question

[0392] The server generates an appropriate question based on the extracted related keywords and the results of emotion recognition. For example, it generates a question such as, "What is the name of that information program?" It receives related keywords and emotion information as input and generates a specific question through data calculations using a generative AI model. If the user feels uneasy, it adjusts the question to, "Please feel free to tell me, what is the name of that information program?" The generated question is sent to the device as output.

[0393] Step 5: Receiving and sending user responses

[0394] The terminal displays the generated question on the user's screen. It receives the generated question as input and presents it to the user. The user enters an answer (e.g., "The name of the information program is 'Good Morning'"), and the terminal sends this answer to the server. As output, the user's answer data is sent to the server.

[0395] Step 6: Reanalyze the answers

[0396] The server re-analyzes the received user response. The response text is input into the generative AI model, relevant information is extracted again, and the user's emotions are re-evaluated through the emotion recognition engine. The server receives the user's response text as input, and processes it to extract information and evaluate emotions. The re-analyzed information and emotion evaluation are obtained as output.

[0397] Step 7: Product candidate proposals

[0398] The server uses a generative AI model to identify suitable product candidates based on the reanalyzed information and emotional evaluation. It receives the reanalyzed information and emotional evaluation as input and performs data calculations to identify the best product candidates from the product database. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." As output, it generates a presentation order based on detailed product information and emotional evaluation, and sends it to the device.

[0399] Step 8: User Selection and Purchase

[0400] The terminal displays the suggested product candidates to the user. As input, it receives product candidate information and displays it to the user. The user checks the details and selects the product they are interested in. Finally, the terminal receives the user's selection and proceeds with the purchase. As output, the server is notified of the user's selection information and the completion of the purchase process.

[0401] Through the above processing steps, the system converts the user's vague requests into specific product suggestions, providing an optimal shopping experience that takes emotions into consideration.

[0402] (Application example 2)

[0403] 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."

[0404] Conventional shopping systems have difficulty analyzing users' vague requests, which means it takes a long time to accurately find the product they are looking for. Furthermore, because they do not take users' emotions into consideration, the experience is often stressful for users.

[0405] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's vague request, means for analyzing the vague request and extracting related keywords, means for generating and presenting a question to the user based on the related keywords, means for receiving an answer from the user and further analyzing the received answer to identify specific product candidates, means for presenting specific product candidates to the user, and means for recognizing the user's emotions and optimizing the question content and product candidates based on the emotions. This makes it possible to efficiently specify the user's vague request and provide an optimal shopping experience that takes emotions into consideration.

[0406] "Vague user requests" are vague requests or wishes that do not include specific product names or specific information, but indicate what the user is looking for.

[0407] "Related keywords" are important words and phrases that are extracted in the process of analyzing a user's vague request and that make the request more specific.

[0408] "Means for generating and presenting" refers to the means for automatically creating questions based on related keywords and showing them to users.

[0409] "User response" refers to the information entered by the user in response to a question posed by the system.

[0410] "Specific Product Candidates" are specific products that a user may be looking for, identified based on the user's request and related keywords.

[0411] "User emotions" refers to the psychological state and reactions exhibited by users during the shopping process.

[0412] "Means for recognizing and analyzing emotions" refers to technologies and systems that identify and analyze emotions from user input and behavior.

[0413] "Means for optimizing question content and product suggestions" refers to means for adjusting the content and order of questions and the way product suggestions are presented based on recognized user sentiment, in order to improve the user experience.

[0414] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to concretize a user's vague requests and generate appropriate questions and suggestions.

[0415] System configuration

[0416] This invention is a shopping system that analyzes a user's vague requests and proposes specific product candidates based on them. The system consists of a user interface (UI), communication means, a server, an emotion recognition engine, and a generative AI model.

[0417] Hardware and software used

[0418] User Interface: Smartphone application

[0419] Communication method: 4G / 5G network, Wi-Fi

[0420] Server: Cloud server (AWS, Google Cloud, etc.)

[0421] Emotion recognition engine: EmotionRecognition library

[0422] Generative AI model: OpenAI's GPT-3

[0423] What the program does

[0424] User request input

[0425] The user inputs a vague request using a smartphone application, such as "I want this and that thing I saw on yesterday's news program." The device then transmits this input to the server via a communication means.

[0426] Parsing the request

[0427] The server uses a generative AI model to analyze ambiguous requests received from users and extract related keywords. It also uses an emotion recognition engine to recognize the user's emotions and incorporates that information into the analysis. For example, related keywords such as "information program," "yesterday," and "cooking equipment" are extracted.

[0428] Question Generation

[0429] The server generates questions for the user based on the extracted related keywords and the results of the emotion recognition engine. The generated questions are adjusted according to the user's emotions. For example, if the user is feeling anxious, the question is softened to say, "Please don't hesitate to tell me, what is the name of that information program?"

[0430] User interaction

[0431] The user answers questions displayed on the device. For example, "What is the name of that news program?", the device receives a response such as "Good Morning." The device then sends this response to the server, which then re-analyzes the response. At the same time, the emotion recognition engine re-evaluates the user's emotions and adjusts the content of the generated questions to take their emotions into account.

[0432] Product candidate suggestions

[0433] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the evaluation by the emotion recognition engine. For example, it identifies "the microwave steamer featured on yesterday's Good Morning," optimizes the presentation order of the product candidates based on the user's emotions, and sends them to the device.

[0434] User Choices and Purchases

[0435] The device displays suggested products to the user, and the user can check the details and select the product they are interested in. Finally, the purchase process is completed. For example, the device may suggest, "This is the microwave steamer that was featured on 'Good Morning' yesterday," and the user can select the product and proceed to the purchase process.

[0436] Prompt Sentence Examples

[0437] "User's vague request: I want this and that thing I saw on yesterday's news program.

[0438] Emotion: I want to be introduced

[0439] Generate specific questions."

[0440] In this way, it is possible to efficiently materialize the user's vague requests and propose optimal products taking their emotions into consideration.

[0441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0442] Step 1:

[0443] A user uses a smartphone application to input a vague request, such as "I want this and that thing I saw on yesterday's news program." Once the input is complete, the device sends this data to the server.

[0444] Step 2:

[0445] The server inputs the received ambiguous request into a generative AI model (OpenAI GPT-3) to extract related keywords, providing the following prompt sentence to the generative AI model:

[0446] Vague user requests: I want this and that thing I saw on yesterday's news program.

[0447] Extract specific keywords.

[0448] The generative AI model outputs related keywords such as "information program," "yesterday," and "cooking utensils."

[0449] Step 3:

[0450] The server uses the extracted related keywords to generate questions for the user. It also uses an emotion recognition engine to analyze the user's emotions and reflects the results in the questions. For example, if the emotion recognition engine detects "anxiety" in the user's text, the generated question will be softer-phrased, such as "Please feel free to tell me, what is the name of that information program?"

[0451] Step 4:

[0452] The device displays the generated question to the user, who then answers the question. For example, in response to the question "What is the name of that information program?", the user answers "It's 'Good Morning.'"

[0453] Step 5:

[0454] The device sends the user's answer to the server. The server receives the answer and again uses the generative AI model to analyze it and extract relevant information. At the same time, it re-evaluates the user's emotions with an emotion recognition engine. The following prompt sentence is used to generate a new question:

[0455] User Answer: "Good morning"

[0456] Please extract specific relevant information.

[0457] The generative AI model outputs related information such as "information programs," "good morning," and "cooking utensils."

[0458] Step 6:

[0459] The server identifies the best product candidates for the user based on the re-evaluated emotion data and newly extracted information, and uses the generative AI model again to list the product candidates. It also optimizes the product presentation order taking into account the results of the emotion recognition engine. For example, it identifies "the microwave steamer that was featured on 'Good Morning' yesterday" and uses the following prompt sentence:

[0460] Keywords: Good Morning, microwave, steamer

[0461] Please suggest the best product options.

[0462] The generative AI model outputs relevant product candidates.

[0463] Step 7:

[0464] The terminal displays the product suggestions sent from the server to the user. The user checks the detailed information and selects the product to purchase. For example, the user selects a suggested product such as "This is the microwave steamer that was featured on yesterday's Good Morning," and proceeds with the purchase process.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] [Second embodiment]

[0469] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0470] 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.

[0471] 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).

[0472] 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.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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."

[0481] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This allows the user to have a less stressful search experience. The following describes in detail the embodiments of the invention.

[0482] Overall system overview

[0483] A user uses a device to input a vague request into the search box of a shopping site. This request is sent to a server, which uses a generative AI model to analyze the request. Then, based on the analysis results, the server generates questions for the user and identifies and suggests suitable products to the user while receiving the user's answers.

[0484] System configuration for implementation

[0485] The system includes the following major components:

[0486] User Interface (UI): The interface through which users input requests and interact with the system.

[0487] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[0488] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0489] Program processing

[0490] The program of this system proceeds in the following order:

[0491] User request input

[0492] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[0493] Parsing the request

[0494] The server uses the generative AI model to analyze the vague request received from the user. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "information program," "yesterday," and "cooking equipment" are identified.

[0495] Question Generation

[0496] The server generates a question for the user based on the extracted related keywords, for example, "What is the name of that information program?", and sends it to the user's device.

[0497] User interaction

[0498] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "Please tell me the specific uses and features of that cookware," and collect information from the user through dialogue.

[0499] Product candidate suggestions

[0500] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The identified product candidates are sent to the user's device and suggested to the user.

[0501] User Choices and Purchases

[0502] Users can select products of interest from the suggested options, check out the details, and finally complete the purchase process.

[0503] Specific examples

[0504] 1. User Input

[0505] User: "I want this thing I saw on yesterday's TV show."

[0506] Terminal: Send this input to the server.

[0507] 2. Server-based analysis and query generation

[0508] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[0509] 3. User interaction

[0510] Terminal: Display the question to the user.

[0511] User: "It's 'Good Morning' from yesterday."

[0512] Server: Generate the next question: "What is the specific use of that cookware?"

[0513] User: "It's a steamer that can be used in the microwave."

[0514] 4. Final product proposal

[0515] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0516] Device: Show suggested content to the user.

[0517] User: Selects a product and proceeds with the purchase.

[0518] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[0519] The processing flow will be explained below.

[0520] Specific processing flow of the program

[0521] Step 1:

[0522] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[0523] Step 2:

[0524] The device sends the user's input to the server.

[0525] Step 3:

[0526] The server receives an ambiguous request from a user.

[0527] Step 4:

[0528] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[0529] Step 5:

[0530] The server generates appropriate questions for the user (e.g., "What is the name of that information program?") based on the extracted related keywords.

[0531] Step 6:

[0532] The server generates a question and sends it to the user's device.

[0533] Step 7:

[0534] The device displays the questions received from the server on the screen and prompts the user to interact.

[0535] Step 8:

[0536] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[0537] Step 9:

[0538] The server receives the user's response and analyzes it again using the generative AI model.

[0539] Step 10:

[0540] The server generates a more specific question (e.g., "Please tell me the specific uses and features of that cookware") and sends it to the terminal.

[0541] Step 11:

[0542] The device asks the user additional questions, and the user enters a specific answer (e.g., "It's a microwaveable steamer"), which the device then sends to the server.

[0543] Step 12:

[0544] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[0545] Step 13:

[0546] The server identifies the best product candidates (e.g., "The microwave steamer featured on yesterday's Good Morning") and generates content to suggest them to the user.

[0547] Step 14:

[0548] The server sends the generated suggested content to the user's terminal.

[0549] Step 15:

[0550] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[0551] Step 16:

[0552] The user selects a product and proceeds with the purchase.

[0553] In this way, the process of identifying specific product candidates from vague requests and proposing them to the user is completed.

[0554] Example 1

[0555] 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."

[0556] On conventional shopping sites, it is difficult for users to find suitable products unless they enter specific keywords. In addition, there is a lack of efficient means to suggest related products to users with vague requirements. This causes users to feel stressed and waste time when searching for products. Therefore, a system is needed that can efficiently and appropriately suggest products even when users enter vague requirements.

[0557] 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.

[0558] In this invention, the server includes a means for analyzing a user's vague request using a generative AI model and extracting related keywords, a means for generating and presenting questions to the user based on the related keywords, and a means for reanalyzing the user's answers to identify specific product candidates, thereby enabling efficient and appropriate product suggestions even from a user's vague request.

[0559] "User" means an individual or corporation that uses this system to search for and purchase products.

[0560] "Vague requests" are vaguely expressed wishes or requests that do not include specific product names or detailed information.

[0561] A "generative AI model" is an artificial intelligence model that learns from large amounts of data, analyzes ambiguous requests, and extracts relevant keywords.

[0562] "Related keywords" are important words and phrases related to product search and suggestions that are extracted by analyzing a user's vague requirements.

[0563] "Question generation and presentation means" refers to the function or device that creates and presents questions to users based on the extracted related keywords.

[0564] "Reanalysis" refers to the process of reanalyzing user responses to identify more specific product candidates.

[0565] "Product Candidates" refers to a list or set of products that may be of interest to the user, identified from the user's vague requests and responses.

[0566] A "database" is a collection of information that systematically stores and manages user requests, responses, product information, etc., and is referenced when analyzing and making proposals.

[0567] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This system allows the user to have a less stressful search experience. The following describes in detail the embodiments of the present invention.

[0568] System Configuration

[0569] The system includes the following major hardware and software components:

[0570] User Interface (UI): The interface through which a user inputs requests and interacts with a system. Examples include a web browser or a mobile application.

[0571] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server. An internet connection is mainly used.

[0572] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers. It also contains the computing resources to run the generative AI model.

[0573] Program processing

[0574] The program of this system executes a series of processes from user request input to product proposal in the following order.

[0575] User request input

[0576] A user accesses a shopping site and inputs a vague request such as "I want this and that thing I saw on yesterday's news program." The device sends this input to the server. The device can be a PC or a smartphone.

[0577] Parsing the request

[0578] The server uses a generative AI model to analyze ambiguous requests received from users. The generative AI model has been trained with a large amount of ambiguous data in advance. This analysis method extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request.

[0579] Question Generation

[0580] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated and sent to the terminal. The terminal then displays the received question to the user.

[0581] User interaction

[0582] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "What are the specific uses and features of that cookware?", and collect information through dialogue with the user.

[0583] Product candidate suggestions

[0584] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server then sends the identified product candidates to the device and suggests them to the user.

[0585] User Choices and Purchases

[0586] The user selects the product of interest from the suggested product candidates, checks the detailed information, and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server, and the server stores the purchase history in a database.

[0587] Specific examples

[0588] 1. User Input

[0589] User: "I want this thing I saw on yesterday's TV show."

[0590] Terminal: Send this input to the server.

[0591] 2. Server-based analysis and query generation

[0592] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[0593] 3. User interaction

[0594] Terminal: Display the question to the user.

[0595] User: "It's 'Good Morning' from yesterday."

[0596] Server: Generate the next question: "What is the specific use of that cookware?"

[0597] User: "It's a steamer that can be used in the microwave."

[0598] 4. Final product proposal

[0599] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0600] Device: Show suggested content to the user.

[0601] User: Selects a product and proceeds with the purchase.

[0602] Prompt Sentence Examples

[0603] "I want this thing I saw on yesterday's news program. How do I search for it?"

[0604] "The name of this information program is 'Good Morning.' I would like to find the product that was featured on this program."

[0605] Please tell me about a steamer that can be used in a microwave.

[0606] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Program processing flow

[0609] Step 1: User Request Input

[0610] The user accesses a shopping site and inputs a vague request. For example, a request such as "I want this and that thing I saw on yesterday's news program." The terminal sends this input to the server. In this step, the input is the user's vague request, and the output is the request data sent to the server.

[0611] Step 2: Parsing the request

[0612] The server uses a generative AI model to analyze the received ambiguous request. The generative AI model has been trained with a large amount of ambiguous expression data in advance. The server extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request. In this step, the input is the ambiguous request data, and the output is the related keywords.

[0613] Step 3: Generate questions

[0614] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated. The server sends the generated question to the terminal. In this step, the input is the related keywords, and the output is the generated question.

[0615] Step 4: Present the question to the user

[0616] The terminal displays the received question to the user, and allows the user to enter an answer to the question. In this step, input: generated question, output: question presented to the user.

[0617] Step 5: User answers

[0618] The user answers the question displayed on the terminal. For example, the user might answer, "The name of the information program is 'Good Morning.'" The terminal then sends this answer to the server. In this step, the input is the user's answer, and the output is the answer data sent to the server.

[0619] Step 6: Reanalyze the answers

[0620] The server reanalyzes the received answer and generates a more specific question if necessary. For example, it generates an additional question such as, "Please tell me the specific uses and features of the cookware." The server then sends the generated additional question to the terminal. In this step, the input is the user's answer data, and the output is the generated additional question.

[0621] Step 7: Ask questions again and collect answers

[0622] The process from step 4 to step 6 is repeated until enough information is gathered. The device asks the user another question and sends the user's answer to the server again. This cycle is: Input: additional question and answer; Output: identified information.

[0623] Step 8: Identify product candidates

[0624] The server uses a generative AI model to identify the most suitable product candidate based on all the information obtained from the user. For example, "The microwave steamer featured on yesterday's Good Morning" is identified. The server sends the identified product candidate and its details to the terminal. In this step, the input is the user's specific request information, and the output is the identified product candidate.

[0625] Step 9: Propose the product to the user

[0626] The terminal displays the received product candidates to the user. The user selects the product of interest from the suggested product candidates and checks the detailed information. In this step, input: identified product candidates, output: products presented to the user.

[0627] Step 10: User selection and checkout

[0628] The user checks the detailed information from the suggested product candidates and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server. The server stores the purchase history in a database and uses it as reference data for future operations. In this step, input: user's purchase selection, output: purchase history stored on the server.

[0629] (Application example 1)

[0630] 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."

[0631] In modern content distribution services, users often have difficulty finding the appropriate content when the title or content of the video or movie they want to watch is unclear. Users often spend a lot of time and effort trying to identify content that meets their needs from the vast amount of content available. Furthermore, traditional search functions are unable to fully respond to ambiguous requests, resulting in a decline in user satisfaction.

[0632] 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.

[0633] In this invention, the server includes a means for inputting a user's ambiguous request, a means for analyzing the ambiguous request and extracting related keywords, and a means for generating and presenting questions to the user based on the related keywords. This makes it possible to effectively analyze the user's ambiguous request and suggest appropriate content. Furthermore, by utilizing a generative AI model, the server can specify the request through dialogue with the user and identify content candidates by learning the latest trends and information, thereby improving user satisfaction.

[0634] An "ambiguous request" refers to a request where the specific details are unclear and the user's intentions and wishes are partially unclear.

[0635] "Analysis" refers to the process of extracting meaning and relationships based on input data and information.

[0636] "Related keywords" refer to important, highly relevant words and phrases that are obtained as a result of analyzing a user's request.

[0637] "Means for generating and presenting questions" refers to the function for creating appropriate questions for the user based on the analysis results and displaying them to the user.

[0638] "Means for receiving responses" refers to the functionality for receiving replies or responses from users.

[0639] "Specific content suggestions" refers to a list of content that the user is likely to want, identified after specifying the user's request.

[0640] "Means for presenting content candidates" refers to functionality for displaying identified content candidates to a user.

[0641] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate questions or content based on user input or requests.

[0642] "Dialogue" refers to the process in which a user and a system exchange questions and answers with each other.

[0643] "Means of learning trends and information" refers to a function that collects the latest trends and information as data and uses that data to make appropriate suggestions to users.

[0644] As an embodiment of the present invention, we will explain a system that analyzes vague requests entered by a user and efficiently suggests appropriate content. This system utilizes a generative AI model to concretize the user's vague requests and provide optimal content.

[0645] Overall system overview

[0646] A user uses a smartphone to input a vague request into the search box of a content delivery service. This request is sent to a server, which uses a generative AI model to analyze the request. Based on the analysis results, the server generates questions for the user, and while receiving the user's answers, identifies and suggests appropriate content candidates to the user.

[0647] System configuration for implementation

[0648] The system includes the following major components:

[0649] User Interface (UI): The interface through which users input requests and interact with the system.

[0650] Communication means: A communication means for sending user requests and answers to the server and receiving questions and content suggestions from the server.

[0651] Server: A central device that analyzes user requests, generates appropriate questions, and identifies content suggestions based on the user's answers.

[0652] Generative AI model: A model that analyzes vague user requests, gathers specific information through dialogue, and suggests optimal content.

[0653] Examples and prompts

[0654] User Input:

[0655] User: "I want to watch a drama like the movie I saw on streaming last week."

[0656] Terminal: Send this input to the server.

[0657] The server uses a generative AI model to analyze the vague requests received from users. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "last week's broadcasts," "movies," and "dramas" are identified.

[0658] The server generates a question for the user based on the extracted related keywords, for example, "Who was the main character in that movie?", and sends it to the user's device.

[0659] The user answers a question displayed on the device. For example, they might say, "Maybe it's a famous actor." The device then sends this answer to the server. The server then re-analyzes the answer and generates a more specific question if necessary. For example, it might generate a follow-up question like, "What genre is that movie?", and collect information from the user through dialogue.

[0660] Below is an example of a prompt sentence to input to the generative AI model.

[0661] A user makes a request like: "I want to watch a drama like the movie I saw on streaming last week."

[0662] What questions should I ask next?

[0663] Finally, the server uses a generative AI model to identify the most suitable content candidates based on all the information obtained from the user. For example, it might identify "dramas starring famous actors that were featured in last week's stream." The identified content candidates are sent to the user's device and suggested to the user.

[0664] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0665] Step 1:

[0666] A user uses a smartphone's user interface (UI) to input a vague request, such as, "I want to watch a TV show like the movie I saw streaming last week."

[0667] Input: User's vague request

[0668] Output: Sends the request data to the server

[0669] Specific operation: When the user enters a request in the text box and taps the "Search" button, the device will send this request to the server.

[0670] Step 2:

[0671] The server uses a generative AI model to analyze the ambiguous request it receives. The analysis extracts relevant keywords from the user's request. For example, keywords such as "last week's streams," "movies," and "dramas" are identified.

[0672] Input: Request data, Generative AI model

[0673] Output: Related keywords

[0674] Specific operation: The server passes the request data to the generative AI model, which then extracts relevant keywords.

[0675] Step 3:

[0676] The server generates questions for the user based on the extracted related keywords, such as "Who was the main character in that movie?"

[0677] Input: Related keywords

[0678] Output: Question text

[0679] Specific operation: Based on relevant keywords, the server uses a generative AI model to construct an appropriate question and sends this question to the user.

[0680] Step 4:

[0681] The device displays the generated question text to the user, who then enters an answer to the question, for example, "Maybe he's a famous actor."

[0682] Input: Question text

[0683] Output: User's answer

[0684] Specific operation: The device receives the user's answer to the displayed question and sends it to the server.

[0685] Step 5:

[0686] The server re-analyzes the user's answers and, if necessary, generates more specific questions to present to the user, such as "What genre is that movie?"

[0687] Input: User's answer

[0688] Output: Next question text

[0689] Specific operation: The server uses the generative AI model based on the user's answers to generate the next question to obtain additional information and sends it to the device.

[0690] Step 6:

[0691] The terminal displays the following question text to the user, who then enters a more specific answer, and this interactive process is repeated as necessary.

[0692] Input: Next question text

[0693] Output: Additional user answers

[0694] Specific operation: Each time a user answers a question, the answer is sent to the server.

[0695] Step 7:

[0696] The server then re-analyzes all the collected information and uses a generative AI model to identify the best content candidates, for example, "dramas starring famous actors featured in last week's streams."

[0697] Input: All user responses

[0698] Output: Best content candidates

[0699] How it works: The server uses collected data and generative AI models to identify content candidates and generate suggestions for the user.

[0700] Step 8:

[0701] The device presents the identified content candidates to the user, who can then review and select the suggested content.

[0702] Input: Best content suggestions

[0703] Output: Content suggestions presented to the user

[0704] Specific operation: The device displays content suggestions received from the server, and the user selects and watches the content of interest.

[0705] 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.

[0706] This invention combines a system that analyzes a user's vague requests and proposes specific product candidates with an emotion engine that recognizes the user's emotions and optimizes the content of questions and product proposals based on those emotions. By taking the user's emotions into consideration, it is possible to provide an optimal shopping experience with even less stress for the user.

[0707] Overall system overview

[0708] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which uses a generative AI model and an emotion engine to analyze the request and generate and present appropriate questions. As the server receives the user's responses, it adjusts the content of the questions and product candidates in response to changes in emotion, suggesting the most suitable products.

[0709] System configuration for implementation

[0710] The system includes the following major components:

[0711] User Interface (UI): The interface through which users input requests and interact with the system.

[0712] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[0713] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0714] Emotion engine: An engine for recognizing user emotions and reflecting them in analysis.

[0715] Program processing

[0716] The program of this system proceeds in the following order:

[0717] User request input

[0718] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[0719] Parsing the request

[0720] The server uses a generative AI model to analyze vague requests received from users and extract related keywords (e.g., "information program," "yesterday," "cooking equipment"), while an emotion engine recognizes the user's emotions and incorporates them into the analysis.

[0721] Question Generation

[0722] The server generates a question for the user (e.g., "What is the name of that information program?") based on the extracted related keywords and the recognition results of the emotion engine. The question is adjusted according to the user's emotions.

[0723] User interaction

[0724] The user answers a question displayed on the device (e.g., "The name of the information program is 'Good Morning'"). The device then sends this answer to the server. The server then re-analyzes the received answer and re-evaluates the user's emotions using the emotion engine. If necessary, when generating a more specific question (e.g., "What are the specific uses and features of that cookware?"), the content is adjusted taking the user's emotions into account.

[0725] Product candidate suggestions

[0726] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the emotion engine's evaluation. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server optimizes the presentation order of the identified product candidates based on the user's emotions and sends them to the device.

[0727] User Choices and Purchases

[0728] The device displays suggested products to the user, who can then review the details, select the products they are interested in, and finally complete the purchase process.

[0729] Specific examples

[0730] 1. User Input

[0731] User: "I want this thing I saw on yesterday's TV show."

[0732] Terminal: Send this input to the server.

[0733] 2. Server-based analysis and query generation

[0734] Server: Generates "What is the name of that information program?" and then the emotion engine recognizes the user's emotion.

[0735] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer, such as "Please don't hesitate to tell me, what is the name of that information program?"

[0736] 3. User interaction

[0737] Terminal: Display the question to the user.

[0738] User: "Good morning," and reevaluate the emotion engine's recognition results.

[0739] Server: Re-analyzes the answer and takes into account the sentiment engine's evaluation when generating the next question.

[0740] 4. Final product proposal

[0741] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0742] Server: Optimize the product presentation order based on user sentiment.

[0743] Device: Show suggested content to the user.

[0744] User: Selects a product and proceeds with the purchase.

[0745] In this way, the system efficiently embodies the user's vague requests and further proposes optimal products taking into account their emotions.

[0746] The processing flow will be explained below.

[0747] Specific processing flow of the program

[0748] Step 1:

[0749] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[0750] Step 2:

[0751] The device sends the user's input to the server.

[0752] Step 3:

[0753] The server receives an ambiguous request from a user.

[0754] Step 4:

[0755] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[0756] Step 5:

[0757] The server generates appropriate questions for the user based on the extracted related keywords.

[0758] Step 6:

[0759] The server generates a question and sends it to the user's device.

[0760] Step 7:

[0761] The device displays the questions received from the server on the screen and prompts the user to interact.

[0762] Step 8:

[0763] The emotion engine analyzes the user's emotions and evaluates their current emotional state. For example, if it recognizes that the user looks anxious, it will adjust the tone of the question to something like, "Please relax and answer freely. What is the name of that news program?"

[0764] Step 9:

[0765] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[0766] Step 10:

[0767] The server receives the user's response and analyzes it again using the generative AI model.

[0768] Step 11:

[0769] The emotion engine reevaluates the user's emotional state at the time of answering and generates more appropriate questions, with the server adapting the questions accordingly (e.g., "Please tell me the specific uses and features of that cookware").

[0770] Step 12:

[0771] The server sends additional questions to the terminal, which displays the questions to the user.

[0772] Step 13:

[0773] The user enters a specific answer (e.g., "It's a steamer that can be used in a microwave"), and the device sends the answer to the server.

[0774] Step 14:

[0775] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[0776] Step 15:

[0777] The server identifies appropriate product candidates based on the evaluation results of the emotion engine and optimizes the order of presentation, making friendly suggestions based on the user's emotions, such as "Here's a microwave steamer that everyone has highly rated."

[0778] Step 16:

[0779] The server sends the generated suggested content to the user's terminal.

[0780] Step 17:

[0781] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[0782] Step 18:

[0783] As users select products and proceed with the purchase process, the emotion engine monitors their emotions and provides support to ensure a stress-free experience.

[0784] This series of steps will realize a system that takes emotions into account, efficiently clarifies the user's vague requests, and suggests optimal product candidates.

[0785] Example 2

[0786] 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."

[0787] Conventional shopping systems have difficulty identifying appropriate products based on vague user input. Furthermore, questions and suggestions are often made without considering the user's feelings, resulting in a poor user experience. As a result, it takes a lot of time and effort for users to find the product they are looking for, which increases their stress.

[0788] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's vague request and extracting related information, means for generating and presenting appropriate questions based on the related information and the user's emotions, means for reanalyzing the user's answers and emotions to identify product candidates, means for presenting the product candidates in an optimal order based on the user's emotions, means for specifying the request through dialogue with the user using a generative AI model and an emotion recognition engine, and means for learning the latest market trends and information and using them to identify product candidates and present them in accordance with the user's emotions. This makes it possible to quickly and appropriately suggest products while taking emotions into consideration, even based on a user's vague request.

[0789] "Ambiguous user requests" are requests that express vague needs or desires without clear specific product names or details.

[0790] "Related information" refers to keywords and concepts extracted from a user's vague request that are useful for making the request more specific.

[0791] An "emotion recognition engine" is a program or software that analyzes and recognizes a user's emotional state (e.g., anxiety, excitement, satisfaction, etc.) from their input or dialogue.

[0792] A "generative AI model" is an artificial intelligence model that generates questions and responses in natural language from input data.

[0793] "Question generation and presentation" is the process of creating appropriate questions based on user requests and presenting them to the user.

[0794] "Product Candidate" means a specific product or service that is recommended based on the user's request and analysis results.

[0795] "Latest market trends" refers to information related to current market trends and user interests.

[0796] "Presenting in the appropriate order" means taking into consideration the user's emotions and interests and displaying information and product candidates in the order that will attract the most attention.

[0797] "User interface (UI)" refers to an interface such as a screen or input means that allows a user to interact with a system.

[0798] This system analyzes the user's vague requests and proposes optimal questions and products based on the user's emotions, thereby providing the user with a stress-free shopping experience.

[0799] Overall system overview

[0800] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which analyzes the request using a generative AI model and an emotion recognition engine to generate and present an appropriate question. As the server receives the user's response, it adjusts the question content and product candidates in response to changes in emotion, suggesting the most suitable product.

[0801] System configuration for implementation

[0802] The system includes the following major components:

[0803] User Interface (UI): The interface through which the user enters requests and interacts with the system.

[0804] Communication method: This is the communication method used to send user requests and answers to the server and receive questions and product suggestions from the server. Specifically, HTTPS is used.

[0805] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0806] Emotion recognition engine: An engine that recognizes user emotions and reflects them in analysis. An example is IBM Watson Tone Analyzer.

[0807] Generative AI model: A model that performs natural language processing and generates appropriate questions and product suggestions based on user requests and answers. An example is OpenAI GPT-4.

[0808] Specific examples

[0809] 1. User Input

[0810] User: "I want this thing I saw on yesterday's TV show."

[0811] Terminal: Send this input to the server.

[0812] 2. Server-based analysis and query generation

[0813] Server: Generates "What is the name of that information program?" and then the emotion recognition engine recognizes the user's emotion.

[0814] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer like, "Please don't hesitate to tell me, what is the name of that information program?"

[0815] 3. User interaction

[0816] Terminal: Display the question to the user.

[0817] User: "Good morning," and the device sends this response to the server.

[0818] Server: Re-analyzes the answer and takes into account the emotion recognition engine's evaluation when generating the next question.

[0819] 4. Final product proposal

[0820] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0821] Server: Optimize the product presentation order based on user sentiment.

[0822] Device: Display suggested content to the user.

[0823] User: Selects a product and proceeds with the purchase.

[0824] Prompt Sentence Examples

[0825] "Please provide a prompt for the system that uses a corresponding emotion recognition engine and generative AI model to parse a user's vague request and identify specific product candidates."

[0826] As described above, the present invention provides a system that efficiently embodies the vague needs of a user and further proposes optimal products taking emotions into consideration.

[0827] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0828] Step 1: User Request Input

[0829] A user visits a shopping site and enters a vague request into the search box (e.g., "I want this and that thing I saw on yesterday's news program"). As input, vague natural language text is obtained. The device receives this input and sends it to the server. As output, data containing the user's request is sent to the server.

[0830] Step 2: Submitting the request

[0831] The terminal sends an ambiguous request entered by the user to the server using the HTTPS protocol. It receives the user's text data as input and sends an HTTPS request to the server as output.

[0832] Step 3: Parsing the request

[0833] The server inputs the text data into a generative AI model (e.g., OpenAI GPT-4) to analyze the received user request. The user's request text is passed to the model as input, and data processing involves extracting related keywords and specifying the information. The text is also passed to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The output is related keywords and the user's emotional information.

[0834] Step 4: Generate and submit your question

[0835] The server generates an appropriate question based on the extracted related keywords and the results of emotion recognition. For example, it generates a question such as, "What is the name of that information program?" It receives related keywords and emotion information as input and generates a specific question through data calculations using a generative AI model. If the user feels uneasy, it adjusts the question to, "Please feel free to tell me, what is the name of that information program?" The generated question is sent to the device as output.

[0836] Step 5: Receiving and sending user responses

[0837] The terminal displays the generated question on the user's screen. It receives the generated question as input and presents it to the user. The user enters an answer (e.g., "The name of the information program is 'Good Morning'"), and the terminal sends this answer to the server. As output, the user's answer data is sent to the server.

[0838] Step 6: Reanalyze the answers

[0839] The server re-analyzes the received user response. The response text is input into the generative AI model, relevant information is extracted again, and the user's emotions are re-evaluated through the emotion recognition engine. The server receives the user's response text as input, and processes it to extract information and evaluate emotions. The re-analyzed information and emotion evaluation are obtained as output.

[0840] Step 7: Product candidate proposals

[0841] The server uses a generative AI model to identify suitable product candidates based on the reanalyzed information and emotional evaluation. It receives the reanalyzed information and emotional evaluation as input and performs data calculations to identify the best product candidates from the product database. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." As output, it generates a presentation order based on detailed product information and emotional evaluation, and sends it to the device.

[0842] Step 8: User Selection and Purchase

[0843] The terminal displays the suggested product candidates to the user. As input, it receives product candidate information and displays it to the user. The user checks the details and selects the product they are interested in. Finally, the terminal receives the user's selection and proceeds with the purchase. As output, the server is notified of the user's selection information and the completion of the purchase process.

[0844] Through the above processing steps, the system converts the user's vague requests into specific product suggestions, providing an optimal shopping experience that takes emotions into consideration.

[0845] (Application example 2)

[0846] 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."

[0847] Conventional shopping systems have difficulty analyzing users' vague requests, which means it takes a long time to accurately find the product they are looking for. Furthermore, because they do not take users' emotions into consideration, the experience is often stressful for users.

[0848] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's vague request, means for analyzing the vague request and extracting related keywords, means for generating and presenting a question to the user based on the related keywords, means for receiving an answer from the user and further analyzing the received answer to identify specific product candidates, means for presenting specific product candidates to the user, and means for recognizing the user's emotions and optimizing the question content and product candidates based on the emotions. This makes it possible to efficiently specify the user's vague request and provide an optimal shopping experience that takes emotions into consideration.

[0849] "Vague user requests" are vague requests or wishes that do not include specific product names or specific information, but indicate what the user is looking for.

[0850] "Related keywords" are important words and phrases that are extracted in the process of analyzing a user's vague request and that make the request more specific.

[0851] "Means for generating and presenting" refers to the means for automatically creating questions based on related keywords and showing them to users.

[0852] "User response" refers to the information entered by the user in response to a question posed by the system.

[0853] "Specific Product Candidates" are specific products that a user may be looking for, identified based on the user's request and related keywords.

[0854] "User emotions" refers to the psychological state and reactions exhibited by users during the shopping process.

[0855] "Means for recognizing and analyzing emotions" refers to technologies and systems that identify and analyze emotions from user input and behavior.

[0856] "Means for optimizing question content and product suggestions" refers to means for adjusting the content and order of questions and the way product suggestions are presented based on recognized user sentiment, in order to improve the user experience.

[0857] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to concretize a user's vague requests and generate appropriate questions and suggestions.

[0858] System configuration

[0859] This invention is a shopping system that analyzes a user's vague requests and proposes specific product candidates based on them. The system consists of a user interface (UI), communication means, a server, an emotion recognition engine, and a generative AI model.

[0860] Hardware and software used

[0861] User Interface: Smartphone application

[0862] Communication method: 4G / 5G network, Wi-Fi

[0863] Server: Cloud server (AWS, Google Cloud, etc.)

[0864] Emotion recognition engine: EmotionRecognition library

[0865] Generative AI model: OpenAI's GPT-3

[0866] What the program does

[0867] User request input

[0868] The user inputs a vague request using a smartphone application, such as "I want this and that thing I saw on yesterday's news program." The device then transmits this input to the server via a communication means.

[0869] Parsing the request

[0870] The server uses a generative AI model to analyze ambiguous requests received from users and extract related keywords. It also uses an emotion recognition engine to recognize the user's emotions and incorporates that information into the analysis. For example, related keywords such as "information program," "yesterday," and "cooking equipment" are extracted.

[0871] Question Generation

[0872] The server generates questions for the user based on the extracted related keywords and the results of the emotion recognition engine. The generated questions are adjusted according to the user's emotions. For example, if the user is feeling anxious, the question is softened to say, "Please don't hesitate to tell me, what is the name of that information program?"

[0873] User interaction

[0874] The user answers questions displayed on the device. For example, "What is the name of that news program?", the device receives a response such as "Good Morning." The device then sends this response to the server, which then re-analyzes the response. At the same time, the emotion recognition engine re-evaluates the user's emotions and adjusts the content of the generated questions to take their emotions into account.

[0875] Product candidate suggestions

[0876] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the evaluation by the emotion recognition engine. For example, it identifies "the microwave steamer featured on yesterday's Good Morning," optimizes the presentation order of the product candidates based on the user's emotions, and sends them to the device.

[0877] User Choices and Purchases

[0878] The device displays suggested products to the user, and the user can check the details and select the product they are interested in. Finally, the purchase process is completed. For example, the device may suggest, "This is the microwave steamer that was featured on 'Good Morning' yesterday," and the user can select the product and proceed to the purchase process.

[0879] Prompt Sentence Examples

[0880] "User's vague request: I want this and that thing I saw on yesterday's news program.

[0881] Emotion: I want to be introduced

[0882] Generate specific questions."

[0883] In this way, it is possible to efficiently materialize the user's vague requests and propose optimal products taking their emotions into consideration.

[0884] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0885] Step 1:

[0886] A user uses a smartphone application to input a vague request, such as "I want this and that thing I saw on yesterday's news program." Once the input is complete, the device sends this data to the server.

[0887] Step 2:

[0888] The server inputs the received ambiguous request into a generative AI model (OpenAI GPT-3) to extract related keywords, providing the following prompt sentence to the generative AI model:

[0889] Vague user requests: I want this and that thing I saw on yesterday's news program.

[0890] Extract specific keywords.

[0891] The generative AI model outputs related keywords such as "information program," "yesterday," and "cooking utensils."

[0892] Step 3:

[0893] The server uses the extracted related keywords to generate questions for the user. It also uses an emotion recognition engine to analyze the user's emotions and reflects the results in the questions. For example, if the emotion recognition engine detects "anxiety" in the user's text, the generated question will be softer-phrased, such as "Please feel free to tell me, what is the name of that information program?"

[0894] Step 4:

[0895] The device displays the generated question to the user, who then answers the question. For example, in response to the question "What is the name of that information program?", the user answers "It's 'Good Morning.'"

[0896] Step 5:

[0897] The device sends the user's answer to the server. The server receives the answer and again uses the generative AI model to analyze it and extract relevant information. At the same time, it re-evaluates the user's emotions with an emotion recognition engine. The following prompt sentence is used to generate a new question:

[0898] User Answer: "Good morning"

[0899] Please extract specific relevant information.

[0900] The generative AI model outputs related information such as "information programs," "good morning," and "cooking utensils."

[0901] Step 6:

[0902] The server identifies the best product candidates for the user based on the re-evaluated emotion data and newly extracted information, and uses the generative AI model again to list the product candidates. It also optimizes the product presentation order taking into account the results of the emotion recognition engine. For example, it identifies "the microwave steamer that was featured on 'Good Morning' yesterday" and uses the following prompt sentence:

[0903] Keywords: Good Morning, microwave, steamer

[0904] Please suggest the best product options.

[0905] The generative AI model outputs relevant product candidates.

[0906] Step 7:

[0907] The terminal displays the product suggestions sent from the server to the user. The user checks the detailed information and selects the product to purchase. For example, the user selects a suggested product such as "This is the microwave steamer that was featured on yesterday's Good Morning," and proceeds with the purchase process.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] [Third embodiment]

[0912] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0913] 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.

[0914] 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).

[0915] 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.

[0916] 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.

[0917] 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).

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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."

[0924] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This allows the user to have a less stressful search experience. The following describes in detail the embodiments of the invention.

[0925] Overall system overview

[0926] A user uses a device to input a vague request into the search box of a shopping site. This request is sent to a server, which uses a generative AI model to analyze the request. Then, based on the analysis results, the server generates questions for the user and identifies and suggests suitable products to the user while receiving the user's answers.

[0927] System configuration for implementation

[0928] The system includes the following major components:

[0929] User Interface (UI): The interface through which users input requests and interact with the system.

[0930] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[0931] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[0932] Program processing

[0933] The program of this system proceeds in the following order:

[0934] User request input

[0935] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[0936] Parsing the request

[0937] The server uses the generative AI model to analyze the vague request received from the user. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "information program," "yesterday," and "cooking equipment" are identified.

[0938] Question Generation

[0939] The server generates a question for the user based on the extracted related keywords, for example, "What is the name of that information program?", and sends it to the user's device.

[0940] User interaction

[0941] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "Please tell me the specific uses and features of that cookware," and collect information from the user through dialogue.

[0942] Product candidate suggestions

[0943] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The identified product candidates are sent to the user's device and suggested to the user.

[0944] User Choices and Purchases

[0945] Users can select products of interest from the suggested options, check out the details, and finally complete the purchase process.

[0946] Specific examples

[0947] 1. User Input

[0948] User: "I want this thing I saw on yesterday's TV show."

[0949] Terminal: Send this input to the server.

[0950] 2. Server-based analysis and query generation

[0951] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[0952] 3. User interaction

[0953] Terminal: Display the question to the user.

[0954] User: "It's 'Good Morning' from yesterday."

[0955] Server: Generate the next question: "What is the specific use of that cookware?"

[0956] User: "It's a steamer that can be used in the microwave."

[0957] 4. Final product proposal

[0958] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[0959] Device: Show suggested content to the user.

[0960] User: Selects a product and proceeds with the purchase.

[0961] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[0962] The processing flow will be explained below.

[0963] Specific processing flow of the program

[0964] Step 1:

[0965] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[0966] Step 2:

[0967] The device sends the user's input to the server.

[0968] Step 3:

[0969] The server receives an ambiguous request from a user.

[0970] Step 4:

[0971] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[0972] Step 5:

[0973] The server generates appropriate questions for the user (e.g., "What is the name of that information program?") based on the extracted related keywords.

[0974] Step 6:

[0975] The server generates a question and sends it to the user's device.

[0976] Step 7:

[0977] The device displays the questions received from the server on the screen and prompts the user to interact.

[0978] Step 8:

[0979] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[0980] Step 9:

[0981] The server receives the user's response and analyzes it again using the generative AI model.

[0982] Step 10:

[0983] The server generates a more specific question (e.g., "Please tell me the specific uses and features of that cookware") and sends it to the terminal.

[0984] Step 11:

[0985] The device asks the user additional questions, and the user enters a specific answer (e.g., "It's a microwaveable steamer"), which the device then sends to the server.

[0986] Step 12:

[0987] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[0988] Step 13:

[0989] The server identifies the best product candidates (e.g., "The microwave steamer featured on yesterday's Good Morning") and generates content to suggest them to the user.

[0990] Step 14:

[0991] The server sends the generated suggested content to the user's terminal.

[0992] Step 15:

[0993] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[0994] Step 16:

[0995] The user selects a product and proceeds with the purchase.

[0996] In this way, the process of identifying specific product candidates from vague requests and proposing them to the user is completed.

[0997] Example 1

[0998] 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."

[0999] On conventional shopping sites, it is difficult for users to find suitable products unless they enter specific keywords. In addition, there is a lack of efficient means to suggest related products to users with vague requirements. This causes users to feel stressed and waste time when searching for products. Therefore, a system is needed that can efficiently and appropriately suggest products even when users enter vague requirements.

[1000] 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.

[1001] In this invention, the server includes a means for analyzing a user's vague request using a generative AI model and extracting related keywords, a means for generating and presenting questions to the user based on the related keywords, and a means for reanalyzing the user's answers to identify specific product candidates, thereby enabling efficient and appropriate product suggestions even from a user's vague request.

[1002] "User" means an individual or corporation that uses this system to search for and purchase products.

[1003] "Vague requests" are vaguely expressed wishes or requests that do not include specific product names or detailed information.

[1004] A "generative AI model" is an artificial intelligence model that learns from large amounts of data, analyzes ambiguous requests, and extracts relevant keywords.

[1005] "Related keywords" are important words and phrases related to product search and suggestions that are extracted by analyzing a user's vague requirements.

[1006] "Question generation and presentation means" refers to the function or device that creates and presents questions to users based on the extracted related keywords.

[1007] "Reanalysis" refers to the process of reanalyzing user responses to identify more specific product candidates.

[1008] "Product Candidates" refers to a list or set of products that may be of interest to the user, identified from the user's vague requests and responses.

[1009] A "database" is a collection of information that systematically stores and manages user requests, responses, product information, etc., and is referenced when analyzing and making proposals.

[1010] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This system allows the user to have a less stressful search experience. The following describes in detail the embodiments of the present invention.

[1011] System Configuration

[1012] The system includes the following major hardware and software components:

[1013] User Interface (UI): The interface through which a user inputs requests and interacts with a system. Examples include a web browser or a mobile application.

[1014] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server. An internet connection is mainly used.

[1015] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers. It also contains the computing resources to run the generative AI model.

[1016] Program processing

[1017] The program of this system executes a series of processes from user request input to product proposal in the following order.

[1018] User request input

[1019] A user accesses a shopping site and inputs a vague request such as "I want this and that thing I saw on yesterday's news program." The device sends this input to the server. The device can be a PC or a smartphone.

[1020] Parsing the request

[1021] The server uses a generative AI model to analyze ambiguous requests received from users. The generative AI model has been trained with a large amount of ambiguous data in advance. This analysis method extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request.

[1022] Question Generation

[1023] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated and sent to the terminal. The terminal then displays the received question to the user.

[1024] User interaction

[1025] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "What are the specific uses and features of that cookware?", and collect information through dialogue with the user.

[1026] Product candidate suggestions

[1027] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server then sends the identified product candidates to the device and suggests them to the user.

[1028] User Choices and Purchases

[1029] The user selects the product of interest from the suggested product candidates, checks the detailed information, and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server, and the server stores the purchase history in a database.

[1030] Specific examples

[1031] 1. User Input

[1032] User: "I want this thing I saw on yesterday's TV show."

[1033] Terminal: Send this input to the server.

[1034] 2. Server-based analysis and query generation

[1035] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[1036] 3. User interaction

[1037] Terminal: Display the question to the user.

[1038] User: "It's 'Good Morning' from yesterday."

[1039] Server: Generate the next question: "What is the specific use of that cookware?"

[1040] User: "It's a steamer that can be used in the microwave."

[1041] 4. Final product proposal

[1042] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1043] Device: Show suggested content to the user.

[1044] User: Selects a product and proceeds with the purchase.

[1045] Prompt Sentence Examples

[1046] "I want this thing I saw on yesterday's news program. How do I search for it?"

[1047] "The name of this information program is 'Good Morning.' I would like to find the product that was featured on this program."

[1048] Please tell me about a steamer that can be used in a microwave.

[1049] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[1050] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1051] Program processing flow

[1052] Step 1: User Request Input

[1053] The user accesses a shopping site and inputs a vague request. For example, a request such as "I want this and that thing I saw on yesterday's news program." The terminal sends this input to the server. In this step, the input is the user's vague request, and the output is the request data sent to the server.

[1054] Step 2: Parsing the request

[1055] The server uses a generative AI model to analyze the received ambiguous request. The generative AI model has been trained with a large amount of ambiguous expression data in advance. The server extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request. In this step, the input is the ambiguous request data, and the output is the related keywords.

[1056] Step 3: Generate questions

[1057] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated. The server sends the generated question to the terminal. In this step, the input is the related keywords, and the output is the generated question.

[1058] Step 4: Present the question to the user

[1059] The terminal displays the received question to the user, and allows the user to enter an answer to the question. In this step, input: generated question, output: question presented to the user.

[1060] Step 5: User answers

[1061] The user answers the question displayed on the terminal. For example, the user might answer, "The name of the information program is 'Good Morning.'" The terminal then sends this answer to the server. In this step, the input is the user's answer, and the output is the answer data sent to the server.

[1062] Step 6: Reanalyze the answers

[1063] The server reanalyzes the received answer and generates a more specific question if necessary. For example, it generates an additional question such as, "Please tell me the specific uses and features of the cookware." The server then sends the generated additional question to the terminal. In this step, the input is the user's answer data, and the output is the generated additional question.

[1064] Step 7: Ask questions again and collect answers

[1065] The process from step 4 to step 6 is repeated until enough information is gathered. The device asks the user another question and sends the user's answer to the server again. This cycle is: Input: additional question and answer; Output: identified information.

[1066] Step 8: Identify product candidates

[1067] The server uses a generative AI model to identify the most suitable product candidate based on all the information obtained from the user. For example, "The microwave steamer featured on yesterday's Good Morning" is identified. The server sends the identified product candidate and its details to the terminal. In this step, the input is the user's specific request information, and the output is the identified product candidate.

[1068] Step 9: Propose the product to the user

[1069] The terminal displays the received product candidates to the user. The user selects the product of interest from the suggested product candidates and checks the detailed information. In this step, input: identified product candidates, output: products presented to the user.

[1070] Step 10: User selection and checkout

[1071] The user checks the detailed information from the suggested product candidates and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server. The server stores the purchase history in a database and uses it as reference data for future operations. In this step, input: user's purchase selection, output: purchase history stored on the server.

[1072] (Application example 1)

[1073] 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."

[1074] In modern content distribution services, users often have difficulty finding the appropriate content when the title or content of the video or movie they want to watch is unclear. Users often spend a lot of time and effort trying to identify content that meets their needs from the vast amount of content available. Furthermore, traditional search functions are unable to fully respond to ambiguous requests, resulting in a decline in user satisfaction.

[1075] 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.

[1076] In this invention, the server includes a means for inputting a user's ambiguous request, a means for analyzing the ambiguous request and extracting related keywords, and a means for generating and presenting questions to the user based on the related keywords. This makes it possible to effectively analyze the user's ambiguous request and suggest appropriate content. Furthermore, by utilizing a generative AI model, the server can specify the request through dialogue with the user and identify content candidates by learning the latest trends and information, thereby improving user satisfaction.

[1077] An "ambiguous request" refers to a request where the specific details are unclear and the user's intentions and wishes are partially unclear.

[1078] "Analysis" refers to the process of extracting meaning and relationships based on input data and information.

[1079] "Related keywords" refer to important, highly relevant words and phrases that are obtained as a result of analyzing a user's request.

[1080] "Means for generating and presenting questions" refers to the function for creating appropriate questions for the user based on the analysis results and displaying them to the user.

[1081] "Means for receiving responses" refers to the functionality for receiving replies or responses from users.

[1082] "Specific content suggestions" refers to a list of content that the user is likely to want, identified after specifying the user's request.

[1083] "Means for presenting content candidates" refers to functionality for displaying identified content candidates to a user.

[1084] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate questions or content based on user input or requests.

[1085] "Dialogue" refers to the process in which a user and a system exchange questions and answers with each other.

[1086] "Means of learning trends and information" refers to a function that collects the latest trends and information as data and uses that data to make appropriate suggestions to users.

[1087] As an embodiment of the present invention, we will explain a system that analyzes vague requests entered by a user and efficiently suggests appropriate content. This system utilizes a generative AI model to concretize the user's vague requests and provide optimal content.

[1088] Overall system overview

[1089] A user uses a smartphone to input a vague request into the search box of a content delivery service. This request is sent to a server, which uses a generative AI model to analyze the request. Based on the analysis results, the server generates questions for the user, and while receiving the user's answers, identifies and suggests appropriate content candidates to the user.

[1090] System configuration for implementation

[1091] The system includes the following major components:

[1092] User Interface (UI): The interface through which users input requests and interact with the system.

[1093] Communication means: A communication means for sending user requests and answers to the server and receiving questions and content suggestions from the server.

[1094] Server: A central device that analyzes user requests, generates appropriate questions, and identifies content suggestions based on the user's answers.

[1095] Generative AI model: A model that analyzes vague user requests, gathers specific information through dialogue, and suggests optimal content.

[1096] Examples and prompts

[1097] User Input:

[1098] User: "I want to watch a drama like the movie I saw on streaming last week."

[1099] Terminal: Send this input to the server.

[1100] The server uses a generative AI model to analyze the vague requests received from users. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "last week's broadcasts," "movies," and "dramas" are identified.

[1101] The server generates a question for the user based on the extracted related keywords, for example, "Who was the main character in that movie?", and sends it to the user's device.

[1102] The user answers a question displayed on the device. For example, they might say, "Maybe it's a famous actor." The device then sends this answer to the server. The server then re-analyzes the answer and generates a more specific question if necessary. For example, it might generate a follow-up question like, "What genre is that movie?", and collect information from the user through dialogue.

[1103] Below is an example of a prompt sentence to input to the generative AI model.

[1104] A user makes a request like: "I want to watch a drama like the movie I saw on streaming last week."

[1105] What questions should I ask next?

[1106] Finally, the server uses a generative AI model to identify the most suitable content candidates based on all the information obtained from the user. For example, it might identify "dramas starring famous actors that were featured in last week's stream." The identified content candidates are sent to the user's device and suggested to the user.

[1107] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1108] Step 1:

[1109] A user uses a smartphone's user interface (UI) to input a vague request, such as, "I want to watch a TV show like the movie I saw streaming last week."

[1110] Input: User's vague request

[1111] Output: Sends the request data to the server

[1112] Specific operation: When the user enters a request in the text box and taps the "Search" button, the device will send this request to the server.

[1113] Step 2:

[1114] The server uses a generative AI model to analyze the ambiguous request it receives. The analysis extracts relevant keywords from the user's request. For example, keywords such as "last week's streams," "movies," and "dramas" are identified.

[1115] Input: Request data, Generative AI model

[1116] Output: Related keywords

[1117] Specific operation: The server passes the request data to the generative AI model, which then extracts relevant keywords.

[1118] Step 3:

[1119] The server generates questions for the user based on the extracted related keywords, such as "Who was the main character in that movie?"

[1120] Input: Related keywords

[1121] Output: Question text

[1122] Specific operation: Based on relevant keywords, the server uses a generative AI model to construct an appropriate question and sends this question to the user.

[1123] Step 4:

[1124] The device displays the generated question text to the user, who then enters an answer to the question, for example, "Maybe he's a famous actor."

[1125] Input: Question text

[1126] Output: User's answer

[1127] Specific operation: The device receives the user's answer to the displayed question and sends it to the server.

[1128] Step 5:

[1129] The server re-analyzes the user's answers and, if necessary, generates more specific questions to present to the user, such as "What genre is that movie?"

[1130] Input: User's answer

[1131] Output: Next question text

[1132] Specific operation: The server uses the generative AI model based on the user's answers to generate the next question to obtain additional information and sends it to the device.

[1133] Step 6:

[1134] The terminal displays the following question text to the user, who then enters a more specific answer, and this interactive process is repeated as necessary.

[1135] Input: Next question text

[1136] Output: Additional user answers

[1137] Specific operation: Each time a user answers a question, the answer is sent to the server.

[1138] Step 7:

[1139] The server then re-analyzes all the collected information and uses a generative AI model to identify the best content candidates, for example, "dramas starring famous actors featured in last week's streams."

[1140] Input: All user responses

[1141] Output: Best content candidates

[1142] How it works: The server uses collected data and generative AI models to identify content candidates and generate suggestions for the user.

[1143] Step 8:

[1144] The device presents the identified content candidates to the user, who can then review and select the suggested content.

[1145] Input: Best content suggestions

[1146] Output: Content suggestions presented to the user

[1147] Specific operation: The device displays content suggestions received from the server, and the user selects and watches the content of interest.

[1148] 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.

[1149] This invention combines a system that analyzes a user's vague requests and proposes specific product candidates with an emotion engine that recognizes the user's emotions and optimizes the content of questions and product proposals based on those emotions. By taking the user's emotions into consideration, it is possible to provide an optimal shopping experience with even less stress for the user.

[1150] Overall system overview

[1151] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which uses a generative AI model and an emotion engine to analyze the request and generate and present appropriate questions. As the server receives the user's responses, it adjusts the content of the questions and product candidates in response to changes in emotion, suggesting the most suitable products.

[1152] System configuration for implementation

[1153] The system includes the following major components:

[1154] User Interface (UI): The interface through which users input requests and interact with the system.

[1155] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[1156] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[1157] Emotion engine: An engine for recognizing user emotions and reflecting them in analysis.

[1158] Program processing

[1159] The program of this system proceeds in the following order:

[1160] User request input

[1161] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[1162] Parsing the request

[1163] The server uses a generative AI model to analyze vague requests received from users and extract related keywords (e.g., "information program," "yesterday," "cooking equipment"), while an emotion engine recognizes the user's emotions and incorporates them into the analysis.

[1164] Question Generation

[1165] The server generates a question for the user (e.g., "What is the name of that information program?") based on the extracted related keywords and the recognition results of the emotion engine. The question is adjusted according to the user's emotions.

[1166] User interaction

[1167] The user answers a question displayed on the device (e.g., "The name of the information program is 'Good Morning'"). The device then sends this answer to the server. The server then re-analyzes the received answer and re-evaluates the user's emotions using the emotion engine. If necessary, when generating a more specific question (e.g., "What are the specific uses and features of that cookware?"), the content is adjusted taking the user's emotions into account.

[1168] Product candidate suggestions

[1169] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the emotion engine's evaluation. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server optimizes the presentation order of the identified product candidates based on the user's emotions and sends them to the device.

[1170] User Choices and Purchases

[1171] The device displays suggested products to the user, who can then review the details, select the products they are interested in, and finally complete the purchase process.

[1172] Specific examples

[1173] 1. User Input

[1174] User: "I want this thing I saw on yesterday's TV show."

[1175] Terminal: Send this input to the server.

[1176] 2. Server-based analysis and query generation

[1177] Server: Generates "What is the name of that information program?" and then the emotion engine recognizes the user's emotion.

[1178] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer, such as "Please don't hesitate to tell me, what is the name of that information program?"

[1179] 3. User interaction

[1180] Terminal: Display the question to the user.

[1181] User: "Good morning," and reevaluate the emotion engine's recognition results.

[1182] Server: Re-analyzes the answer and takes into account the sentiment engine's evaluation when generating the next question.

[1183] 4. Final product proposal

[1184] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1185] Server: Optimize the product presentation order based on user sentiment.

[1186] Device: Show suggested content to the user.

[1187] User: Selects a product and proceeds with the purchase.

[1188] In this way, the system efficiently embodies the user's vague requests and further proposes optimal products taking into account their emotions.

[1189] The processing flow will be explained below.

[1190] Specific processing flow of the program

[1191] Step 1:

[1192] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[1193] Step 2:

[1194] The device sends the user's input to the server.

[1195] Step 3:

[1196] The server receives an ambiguous request from a user.

[1197] Step 4:

[1198] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[1199] Step 5:

[1200] The server generates appropriate questions for the user based on the extracted related keywords.

[1201] Step 6:

[1202] The server generates a question and sends it to the user's device.

[1203] Step 7:

[1204] The device displays the questions received from the server on the screen and prompts the user to interact.

[1205] Step 8:

[1206] The emotion engine analyzes the user's emotions and evaluates their current emotional state. For example, if it recognizes that the user looks anxious, it will adjust the tone of the question to something like, "Please relax and answer freely. What is the name of that news program?"

[1207] Step 9:

[1208] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[1209] Step 10:

[1210] The server receives the user's response and analyzes it again using the generative AI model.

[1211] Step 11:

[1212] The emotion engine reevaluates the user's emotional state at the time of answering and generates more appropriate questions, with the server adapting the questions accordingly (e.g., "Please tell me the specific uses and features of that cookware").

[1213] Step 12:

[1214] The server sends additional questions to the terminal, which displays the questions to the user.

[1215] Step 13:

[1216] The user enters a specific answer (e.g., "It's a steamer that can be used in a microwave"), and the device sends the answer to the server.

[1217] Step 14:

[1218] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[1219] Step 15:

[1220] The server identifies appropriate product candidates based on the evaluation results of the emotion engine and optimizes the order of presentation, making friendly suggestions based on the user's emotions, such as "Here's a microwave steamer that everyone has highly rated."

[1221] Step 16:

[1222] The server sends the generated suggested content to the user's terminal.

[1223] Step 17:

[1224] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[1225] Step 18:

[1226] As users select products and proceed with the purchase process, the emotion engine monitors their emotions and provides support to ensure a stress-free experience.

[1227] This series of steps will realize a system that takes emotions into account, efficiently clarifies the user's vague requests, and suggests optimal product candidates.

[1228] Example 2

[1229] 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."

[1230] Conventional shopping systems have difficulty identifying appropriate products based on vague user input. Furthermore, questions and suggestions are often made without considering the user's feelings, resulting in a poor user experience. As a result, it takes a lot of time and effort for users to find the product they are looking for, which increases their stress.

[1231] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's vague request and extracting related information, means for generating and presenting appropriate questions based on the related information and the user's emotions, means for reanalyzing the user's answers and emotions to identify product candidates, means for presenting the product candidates in an optimal order based on the user's emotions, means for specifying the request through dialogue with the user using a generative AI model and an emotion recognition engine, and means for learning the latest market trends and information and using them to identify product candidates and present them in accordance with the user's emotions. This makes it possible to quickly and appropriately suggest products while taking emotions into consideration, even based on a user's vague request.

[1232] "Ambiguous user requests" are requests that express vague needs or desires without clear specific product names or details.

[1233] "Related information" refers to keywords and concepts extracted from a user's vague request that are useful for making the request more specific.

[1234] An "emotion recognition engine" is a program or software that analyzes and recognizes a user's emotional state (e.g., anxiety, excitement, satisfaction, etc.) from their input or dialogue.

[1235] A "generative AI model" is an artificial intelligence model that generates questions and responses in natural language from input data.

[1236] "Question generation and presentation" is the process of creating appropriate questions based on user requests and presenting them to the user.

[1237] "Product Candidate" means a specific product or service that is recommended based on the user's request and analysis results.

[1238] "Latest market trends" refers to information related to current market trends and user interests.

[1239] "Presenting in the appropriate order" means taking into consideration the user's emotions and interests and displaying information and product candidates in the order that will attract the most attention.

[1240] "User interface (UI)" refers to an interface such as a screen or input means that allows a user to interact with a system.

[1241] This system analyzes the user's vague requests and proposes optimal questions and products based on the user's emotions, thereby providing the user with a stress-free shopping experience.

[1242] Overall system overview

[1243] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which analyzes the request using a generative AI model and an emotion recognition engine to generate and present an appropriate question. As the server receives the user's response, it adjusts the question content and product candidates in response to changes in emotion, suggesting the most suitable product.

[1244] System configuration for implementation

[1245] The system includes the following major components:

[1246] User Interface (UI): The interface through which the user enters requests and interacts with the system.

[1247] Communication method: This is the communication method used to send user requests and answers to the server and receive questions and product suggestions from the server. Specifically, HTTPS is used.

[1248] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[1249] Emotion recognition engine: An engine that recognizes user emotions and reflects them in analysis. An example is IBM Watson Tone Analyzer.

[1250] Generative AI model: A model that performs natural language processing and generates appropriate questions and product suggestions based on user requests and answers. An example is OpenAI GPT-4.

[1251] Specific examples

[1252] 1. User Input

[1253] User: "I want this thing I saw on yesterday's TV show."

[1254] Terminal: Send this input to the server.

[1255] 2. Server-based analysis and query generation

[1256] Server: Generates "What is the name of that information program?" and then the emotion recognition engine recognizes the user's emotion.

[1257] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer like, "Please don't hesitate to tell me, what is the name of that information program?"

[1258] 3. User interaction

[1259] Terminal: Display the question to the user.

[1260] User: "Good morning," and the device sends this response to the server.

[1261] Server: Re-analyzes the answer and takes into account the emotion recognition engine's evaluation when generating the next question.

[1262] 4. Final product proposal

[1263] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1264] Server: Optimize the product presentation order based on user sentiment.

[1265] Device: Display suggested content to the user.

[1266] User: Selects a product and proceeds with the purchase.

[1267] Prompt Sentence Examples

[1268] "Please provide a prompt for the system that uses a corresponding emotion recognition engine and generative AI model to parse a user's vague request and identify specific product candidates."

[1269] As described above, the present invention provides a system that efficiently embodies the vague needs of a user and further proposes optimal products taking emotions into consideration.

[1270] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1271] Step 1: User Request Input

[1272] A user visits a shopping site and enters a vague request into the search box (e.g., "I want this and that thing I saw on yesterday's news program"). As input, vague natural language text is obtained. The device receives this input and sends it to the server. As output, data containing the user's request is sent to the server.

[1273] Step 2: Submitting the request

[1274] The terminal sends an ambiguous request entered by the user to the server using the HTTPS protocol. It receives the user's text data as input and sends an HTTPS request to the server as output.

[1275] Step 3: Parsing the request

[1276] The server inputs the text data into a generative AI model (e.g., OpenAI GPT-4) to analyze the received user request. The user's request text is passed to the model as input, and data processing involves extracting related keywords and specifying the information. The text is also passed to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The output is related keywords and the user's emotional information.

[1277] Step 4: Generate and submit your question

[1278] The server generates an appropriate question based on the extracted related keywords and the results of emotion recognition. For example, it generates a question such as, "What is the name of that information program?" It receives related keywords and emotion information as input and generates a specific question through data calculations using a generative AI model. If the user feels uneasy, it adjusts the question to, "Please feel free to tell me, what is the name of that information program?" The generated question is sent to the device as output.

[1279] Step 5: Receiving and sending user responses

[1280] The terminal displays the generated question on the user's screen. It receives the generated question as input and presents it to the user. The user enters an answer (e.g., "The name of the information program is 'Good Morning'"), and the terminal sends this answer to the server. As output, the user's answer data is sent to the server.

[1281] Step 6: Reanalyze the answers

[1282] The server re-analyzes the received user response. The response text is input into the generative AI model, relevant information is extracted again, and the user's emotions are re-evaluated through the emotion recognition engine. The server receives the user's response text as input, and processes it to extract information and evaluate emotions. The re-analyzed information and emotion evaluation are obtained as output.

[1283] Step 7: Product candidate proposals

[1284] The server uses a generative AI model to identify suitable product candidates based on the reanalyzed information and emotional evaluation. It receives the reanalyzed information and emotional evaluation as input and performs data calculations to identify the best product candidates from the product database. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." As output, it generates a presentation order based on detailed product information and emotional evaluation, and sends it to the device.

[1285] Step 8: User Selection and Purchase

[1286] The terminal displays the suggested product candidates to the user. As input, it receives product candidate information and displays it to the user. The user checks the details and selects the product they are interested in. Finally, the terminal receives the user's selection and proceeds with the purchase. As output, the server is notified of the user's selection information and the completion of the purchase process.

[1287] Through the above processing steps, the system converts the user's vague requests into specific product suggestions, providing an optimal shopping experience that takes emotions into consideration.

[1288] (Application example 2)

[1289] 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."

[1290] Conventional shopping systems have difficulty analyzing users' vague requests, which means it takes a long time to accurately find the product they are looking for. Furthermore, because they do not take users' emotions into consideration, the experience is often stressful for users.

[1291] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's vague request, means for analyzing the vague request and extracting related keywords, means for generating and presenting a question to the user based on the related keywords, means for receiving an answer from the user and further analyzing the received answer to identify specific product candidates, means for presenting specific product candidates to the user, and means for recognizing the user's emotions and optimizing the question content and product candidates based on the emotions. This makes it possible to efficiently specify the user's vague request and provide an optimal shopping experience that takes emotions into consideration.

[1292] "Vague user requests" are vague requests or wishes that do not include specific product names or specific information, but indicate what the user is looking for.

[1293] "Related keywords" are important words and phrases that are extracted in the process of analyzing a user's vague request and that make the request more specific.

[1294] "Means for generating and presenting" refers to the means for automatically creating questions based on related keywords and showing them to users.

[1295] "User response" refers to the information entered by the user in response to a question posed by the system.

[1296] "Specific Product Candidates" are specific products that a user may be looking for, identified based on the user's request and related keywords.

[1297] "User emotions" refers to the psychological state and reactions exhibited by users during the shopping process.

[1298] "Means for recognizing and analyzing emotions" refers to technologies and systems that identify and analyze emotions from user input and behavior.

[1299] "Means for optimizing question content and product suggestions" refers to means for adjusting the content and order of questions and the way product suggestions are presented based on recognized user sentiment, in order to improve the user experience.

[1300] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to concretize a user's vague requests and generate appropriate questions and suggestions.

[1301] System configuration

[1302] This invention is a shopping system that analyzes a user's vague requests and proposes specific product candidates based on them. The system consists of a user interface (UI), communication means, a server, an emotion recognition engine, and a generative AI model.

[1303] Hardware and software used

[1304] User Interface: Smartphone application

[1305] Communication method: 4G / 5G network, Wi-Fi

[1306] Server: Cloud server (AWS, Google Cloud, etc.)

[1307] Emotion recognition engine: EmotionRecognition library

[1308] Generative AI model: OpenAI's GPT-3

[1309] What the program does

[1310] User request input

[1311] The user inputs a vague request using a smartphone application, such as "I want this and that thing I saw on yesterday's news program." The device then transmits this input to the server via a communication means.

[1312] Parsing the request

[1313] The server uses a generative AI model to analyze ambiguous requests received from users and extract related keywords. It also uses an emotion recognition engine to recognize the user's emotions and incorporates that information into the analysis. For example, related keywords such as "information program," "yesterday," and "cooking equipment" are extracted.

[1314] Question Generation

[1315] The server generates questions for the user based on the extracted related keywords and the results of the emotion recognition engine. The generated questions are adjusted according to the user's emotions. For example, if the user is feeling anxious, the question is softened to say, "Please don't hesitate to tell me, what is the name of that information program?"

[1316] User interaction

[1317] The user answers questions displayed on the device. For example, "What is the name of that news program?", the device receives a response such as "Good Morning." The device then sends this response to the server, which then re-analyzes the response. At the same time, the emotion recognition engine re-evaluates the user's emotions and adjusts the content of the generated questions to take their emotions into account.

[1318] Product candidate suggestions

[1319] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the evaluation by the emotion recognition engine. For example, it identifies "the microwave steamer featured on yesterday's Good Morning," optimizes the presentation order of the product candidates based on the user's emotions, and sends them to the device.

[1320] User Choices and Purchases

[1321] The device displays suggested products to the user, and the user can check the details and select the product they are interested in. Finally, the purchase process is completed. For example, the device may suggest, "This is the microwave steamer that was featured on 'Good Morning' yesterday," and the user can select the product and proceed to the purchase process.

[1322] Prompt Sentence Examples

[1323] "User's vague request: I want this and that thing I saw on yesterday's news program.

[1324] Emotion: I want to be introduced

[1325] Generate specific questions."

[1326] In this way, it is possible to efficiently materialize the user's vague requests and propose optimal products taking their emotions into consideration.

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] A user uses a smartphone application to input a vague request, such as "I want this and that thing I saw on yesterday's news program." Once the input is complete, the device sends this data to the server.

[1330] Step 2:

[1331] The server inputs the received ambiguous request into a generative AI model (OpenAI GPT-3) to extract related keywords, providing the following prompt sentence to the generative AI model:

[1332] Vague user requests: I want this and that thing I saw on yesterday's news program.

[1333] Extract specific keywords.

[1334] The generative AI model outputs related keywords such as "information program," "yesterday," and "cooking utensils."

[1335] Step 3:

[1336] The server uses the extracted related keywords to generate questions for the user. It also uses an emotion recognition engine to analyze the user's emotions and reflects the results in the questions. For example, if the emotion recognition engine detects "anxiety" in the user's text, the generated question will be softer-phrased, such as "Please feel free to tell me, what is the name of that information program?"

[1337] Step 4:

[1338] The device displays the generated question to the user, who then answers the question. For example, in response to the question "What is the name of that information program?", the user answers "It's 'Good Morning.'"

[1339] Step 5:

[1340] The device sends the user's answer to the server. The server receives the answer and again uses the generative AI model to analyze it and extract relevant information. At the same time, it re-evaluates the user's emotions with an emotion recognition engine. The following prompt sentence is used to generate a new question:

[1341] User Answer: "Good morning"

[1342] Please extract specific relevant information.

[1343] The generative AI model outputs related information such as "information programs," "good morning," and "cooking utensils."

[1344] Step 6:

[1345] The server identifies the best product candidates for the user based on the re-evaluated emotion data and newly extracted information, and uses the generative AI model again to list the product candidates. It also optimizes the product presentation order taking into account the results of the emotion recognition engine. For example, it identifies "the microwave steamer that was featured on 'Good Morning' yesterday" and uses the following prompt sentence:

[1346] Keywords: Good Morning, microwave, steamer

[1347] Please suggest the best product options.

[1348] The generative AI model outputs relevant product candidates.

[1349] Step 7:

[1350] The terminal displays the product suggestions sent from the server to the user. The user checks the detailed information and selects the product to purchase. For example, the user selects a suggested product such as "This is the microwave steamer that was featured on yesterday's Good Morning," and proceeds with the purchase process.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] [Fourth embodiment]

[1355] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1356] 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.

[1357] 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).

[1358] 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.

[1359] 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.

[1360] 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).

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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."

[1368] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This allows the user to have a less stressful search experience. The following describes in detail the embodiments of the invention.

[1369] Overall system overview

[1370] A user uses a device to input a vague request into the search box of a shopping site. This request is sent to a server, which uses a generative AI model to analyze the request. Then, based on the analysis results, the server generates questions for the user and identifies and suggests suitable products to the user while receiving the user's answers.

[1371] System configuration for implementation

[1372] The system includes the following major components:

[1373] User Interface (UI): The interface through which users input requests and interact with the system.

[1374] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[1375] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[1376] Program processing

[1377] The program of this system proceeds in the following order:

[1378] User request input

[1379] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[1380] Parsing the request

[1381] The server uses the generative AI model to analyze the vague request received from the user. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "information program," "yesterday," and "cooking equipment" are identified.

[1382] Question Generation

[1383] The server generates a question for the user based on the extracted related keywords, for example, "What is the name of that information program?", and sends it to the user's device.

[1384] User interaction

[1385] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "Please tell me the specific uses and features of that cookware," and collect information from the user through dialogue.

[1386] Product candidate suggestions

[1387] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The identified product candidates are sent to the user's device and suggested to the user.

[1388] User Choices and Purchases

[1389] Users can select products of interest from the suggested options, check out the details, and finally complete the purchase process.

[1390] Specific examples

[1391] 1. User Input

[1392] User: "I want this thing I saw on yesterday's TV show."

[1393] Terminal: Send this input to the server.

[1394] 2. Server-based analysis and query generation

[1395] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[1396] 3. User interaction

[1397] Terminal: Display the question to the user.

[1398] User: "It's 'Good Morning' from yesterday."

[1399] Server: Generate the next question: "What is the specific use of that cookware?"

[1400] User: "It's a steamer that can be used in the microwave."

[1401] 4. Final product proposal

[1402] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1403] Device: Show suggested content to the user.

[1404] User: Selects a product and proceeds with the purchase.

[1405] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[1406] The processing flow will be explained below.

[1407] Specific processing flow of the program

[1408] Step 1:

[1409] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[1410] Step 2:

[1411] The device sends the user's input to the server.

[1412] Step 3:

[1413] The server receives an ambiguous request from a user.

[1414] Step 4:

[1415] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[1416] Step 5:

[1417] The server generates appropriate questions for the user (e.g., "What is the name of that information program?") based on the extracted related keywords.

[1418] Step 6:

[1419] The server generates a question and sends it to the user's device.

[1420] Step 7:

[1421] The device displays the questions received from the server on the screen and prompts the user to interact.

[1422] Step 8:

[1423] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[1424] Step 9:

[1425] The server receives the user's response and analyzes it again using the generative AI model.

[1426] Step 10:

[1427] The server generates a more specific question (e.g., "Please tell me the specific uses and features of that cookware") and sends it to the terminal.

[1428] Step 11:

[1429] The device asks the user additional questions, and the user enters a specific answer (e.g., "It's a microwaveable steamer"), which the device then sends to the server.

[1430] Step 12:

[1431] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[1432] Step 13:

[1433] The server identifies the best product candidates (e.g., "The microwave steamer featured on yesterday's Good Morning") and generates content to suggest them to the user.

[1434] Step 14:

[1435] The server sends the generated suggested content to the user's terminal.

[1436] Step 15:

[1437] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[1438] Step 16:

[1439] The user selects a product and proceeds with the purchase.

[1440] In this way, the process of identifying specific product candidates from vague requests and proposing them to the user is completed.

[1441] Example 1

[1442] 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."

[1443] On conventional shopping sites, it is difficult for users to find suitable products unless they enter specific keywords. In addition, there is a lack of efficient means to suggest related products to users with vague requirements. This causes users to feel stressed and waste time when searching for products. Therefore, a system is needed that can efficiently and appropriately suggest products even when users enter vague requirements.

[1444] 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.

[1445] In this invention, the server includes a means for analyzing a user's vague request using a generative AI model and extracting related keywords, a means for generating and presenting questions to the user based on the related keywords, and a means for reanalyzing the user's answers to identify specific product candidates, thereby enabling efficient and appropriate product suggestions even from a user's vague request.

[1446] "User" means an individual or corporation that uses this system to search for and purchase products.

[1447] "Vague requests" are vaguely expressed wishes or requests that do not include specific product names or detailed information.

[1448] A "generative AI model" is an artificial intelligence model that learns from large amounts of data, analyzes ambiguous requests, and extracts relevant keywords.

[1449] "Related keywords" are important words and phrases related to product search and suggestions that are extracted by analyzing a user's vague requirements.

[1450] "Question generation and presentation means" refers to the function or device that creates and presents questions to users based on the extracted related keywords.

[1451] "Reanalysis" refers to the process of reanalyzing user responses to identify more specific product candidates.

[1452] "Product Candidates" refers to a list or set of products that may be of interest to the user, identified from the user's vague requests and responses.

[1453] A "database" is a collection of information that systematically stores and manages user requests, responses, product information, etc., and is referenced when analyzing and making proposals.

[1454] This invention is a system that analyzes a user's vague request and efficiently suggests appropriate products when the user inputs the request. This system allows the user to have a less stressful search experience. The following describes in detail the embodiments of the present invention.

[1455] System Configuration

[1456] The system includes the following major hardware and software components:

[1457] User Interface (UI): The interface through which a user inputs requests and interacts with a system. Examples include a web browser or a mobile application.

[1458] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server. An internet connection is mainly used.

[1459] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers. It also contains the computing resources to run the generative AI model.

[1460] Program processing

[1461] The program of this system executes a series of processes from user request input to product proposal in the following order.

[1462] User request input

[1463] A user accesses a shopping site and inputs a vague request such as "I want this and that thing I saw on yesterday's news program." The device sends this input to the server. The device can be a PC or a smartphone.

[1464] Parsing the request

[1465] The server uses a generative AI model to analyze ambiguous requests received from users. The generative AI model has been trained with a large amount of ambiguous data in advance. This analysis method extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request.

[1466] Question Generation

[1467] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated and sent to the terminal. The terminal then displays the received question to the user.

[1468] User interaction

[1469] The user answers the question displayed on the device. For example, they might say, "The name of the information program is 'Good Morning.'" The device then sends this answer to the server. The server then reanalyzes the received answer and generates a more specific question if necessary. For example, it might generate an additional question such as, "What are the specific uses and features of that cookware?", and collect information through dialogue with the user.

[1470] Product candidate suggestions

[1471] The server uses a generative AI model to identify the most suitable product candidates based on all the information obtained from the user. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server then sends the identified product candidates to the device and suggests them to the user.

[1472] User Choices and Purchases

[1473] The user selects the product of interest from the suggested product candidates, checks the detailed information, and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server, and the server stores the purchase history in a database.

[1474] Specific examples

[1475] 1. User Input

[1476] User: "I want this thing I saw on yesterday's TV show."

[1477] Terminal: Send this input to the server.

[1478] 2. Server-based analysis and query generation

[1479] Server: Generates "What is the name of that information program?" and sends it to the terminal.

[1480] 3. User interaction

[1481] Terminal: Display the question to the user.

[1482] User: "It's 'Good Morning' from yesterday."

[1483] Server: Generate the next question: "What is the specific use of that cookware?"

[1484] User: "It's a steamer that can be used in the microwave."

[1485] 4. Final product proposal

[1486] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1487] Device: Show suggested content to the user.

[1488] User: Selects a product and proceeds with the purchase.

[1489] Prompt Sentence Examples

[1490] "I want this thing I saw on yesterday's news program. How do I search for it?"

[1491] "The name of this information program is 'Good Morning.' I would like to find the product that was featured on this program."

[1492] Please tell me about a steamer that can be used in a microwave.

[1493] In this way, the system can efficiently materialize the user's vague requests and propose the most suitable products.

[1494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1495] Program processing flow

[1496] Step 1: User Request Input

[1497] The user accesses a shopping site and inputs a vague request. For example, a request such as "I want this and that thing I saw on yesterday's news program." The terminal sends this input to the server. In this step, the input is the user's vague request, and the output is the request data sent to the server.

[1498] Step 2: Parsing the request

[1499] The server uses a generative AI model to analyze the received ambiguous request. The generative AI model has been trained with a large amount of ambiguous expression data in advance. The server extracts related keywords (e.g., "information program," "yesterday," "cooking equipment") from the user's request. In this step, the input is the ambiguous request data, and the output is the related keywords.

[1500] Step 3: Generate questions

[1501] The server generates a question for the user based on the extracted related keywords. For example, a question such as "What is the name of that information program?" is generated. The server sends the generated question to the terminal. In this step, the input is the related keywords, and the output is the generated question.

[1502] Step 4: Present the question to the user

[1503] The terminal displays the received question to the user, and allows the user to enter an answer to the question. In this step, input: generated question, output: question presented to the user.

[1504] Step 5: User answers

[1505] The user answers the question displayed on the terminal. For example, the user might answer, "The name of the information program is 'Good Morning.'" The terminal then sends this answer to the server. In this step, the input is the user's answer, and the output is the answer data sent to the server.

[1506] Step 6: Reanalyze the answers

[1507] The server reanalyzes the received answer and generates a more specific question if necessary. For example, it generates an additional question such as, "Please tell me the specific uses and features of the cookware." The server then sends the generated additional question to the terminal. In this step, the input is the user's answer data, and the output is the generated additional question.

[1508] Step 7: Ask questions again and collect answers

[1509] The process from step 4 to step 6 is repeated until enough information is gathered. The device asks the user another question and sends the user's answer to the server again. This cycle is: Input: additional question and answer; Output: identified information.

[1510] Step 8: Identify product candidates

[1511] The server uses a generative AI model to identify the most suitable product candidate based on all the information obtained from the user. For example, "The microwave steamer featured on yesterday's Good Morning" is identified. The server sends the identified product candidate and its details to the terminal. In this step, the input is the user's specific request information, and the output is the identified product candidate.

[1512] Step 9: Propose the product to the user

[1513] The terminal displays the received product candidates to the user. The user selects the product of interest from the suggested product candidates and checks the detailed information. In this step, input: identified product candidates, output: products presented to the user.

[1514] Step 10: User selection and checkout

[1515] The user checks the detailed information from the suggested product candidates and finally completes the purchase procedure. The terminal returns the purchase procedure information to the server. The server stores the purchase history in a database and uses it as reference data for future operations. In this step, input: user's purchase selection, output: purchase history stored on the server.

[1516] (Application example 1)

[1517] 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."

[1518] In modern content distribution services, users often have difficulty finding the appropriate content when the title or content of the video or movie they want to watch is unclear. Users often spend a lot of time and effort trying to identify content that meets their needs from the vast amount of content available. Furthermore, traditional search functions are unable to fully respond to ambiguous requests, resulting in a decline in user satisfaction.

[1519] 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.

[1520] In this invention, the server includes a means for inputting a user's ambiguous request, a means for analyzing the ambiguous request and extracting related keywords, and a means for generating and presenting questions to the user based on the related keywords. This makes it possible to effectively analyze the user's ambiguous request and suggest appropriate content. Furthermore, by utilizing a generative AI model, the server can specify the request through dialogue with the user and identify content candidates by learning the latest trends and information, thereby improving user satisfaction.

[1521] An "ambiguous request" refers to a request where the specific details are unclear and the user's intentions and wishes are partially unclear.

[1522] "Analysis" refers to the process of extracting meaning and relationships based on input data and information.

[1523] "Related keywords" refer to important, highly relevant words and phrases that are obtained as a result of analyzing a user's request.

[1524] "Means for generating and presenting questions" refers to the function for creating appropriate questions for the user based on the analysis results and displaying them to the user.

[1525] "Means for receiving responses" refers to the functionality for receiving replies or responses from users.

[1526] "Specific content suggestions" refers to a list of content that the user is likely to want, identified after specifying the user's request.

[1527] "Means for presenting content candidates" refers to functionality for displaying identified content candidates to a user.

[1528] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate appropriate questions or content based on user input or requests.

[1529] "Dialogue" refers to the process in which a user and a system exchange questions and answers with each other.

[1530] "Means of learning trends and information" refers to a function that collects the latest trends and information as data and uses that data to make appropriate suggestions to users.

[1531] As an embodiment of the present invention, we will explain a system that analyzes vague requests entered by a user and efficiently suggests appropriate content. This system utilizes a generative AI model to concretize the user's vague requests and provide optimal content.

[1532] Overall system overview

[1533] A user uses a smartphone to input a vague request into the search box of a content delivery service. This request is sent to a server, which uses a generative AI model to analyze the request. Based on the analysis results, the server generates questions for the user, and while receiving the user's answers, identifies and suggests appropriate content candidates to the user.

[1534] System configuration for implementation

[1535] The system includes the following major components:

[1536] User Interface (UI): The interface through which users input requests and interact with the system.

[1537] Communication means: A communication means for sending user requests and answers to the server and receiving questions and content suggestions from the server.

[1538] Server: A central device that analyzes user requests, generates appropriate questions, and identifies content suggestions based on the user's answers.

[1539] Generative AI model: A model that analyzes vague user requests, gathers specific information through dialogue, and suggests optimal content.

[1540] Examples and prompts

[1541] User Input:

[1542] User: "I want to watch a drama like the movie I saw on streaming last week."

[1543] Terminal: Send this input to the server.

[1544] The server uses a generative AI model to analyze the vague requests received from users. This analysis method extracts relevant keywords from the user's request. For example, keywords such as "last week's broadcasts," "movies," and "dramas" are identified.

[1545] The server generates a question for the user based on the extracted related keywords, for example, "Who was the main character in that movie?", and sends it to the user's device.

[1546] The user answers a question displayed on the device. For example, they might say, "Maybe it's a famous actor." The device then sends this answer to the server. The server then re-analyzes the answer and generates a more specific question if necessary. For example, it might generate a follow-up question like, "What genre is that movie?", and collect information from the user through dialogue.

[1547] Below is an example of a prompt sentence to input to the generative AI model.

[1548] A user makes a request like: "I want to watch a drama like the movie I saw on streaming last week."

[1549] What questions should I ask next?

[1550] Finally, the server uses a generative AI model to identify the most suitable content candidates based on all the information obtained from the user. For example, it might identify "dramas starring famous actors that were featured in last week's stream." The identified content candidates are sent to the user's device and suggested to the user.

[1551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1552] Step 1:

[1553] A user uses a smartphone's user interface (UI) to input a vague request, such as, "I want to watch a TV show like the movie I saw streaming last week."

[1554] Input: User's vague request

[1555] Output: Sends the request data to the server

[1556] Specific operation: When the user enters a request in the text box and taps the "Search" button, the device will send this request to the server.

[1557] Step 2:

[1558] The server uses a generative AI model to analyze the ambiguous request it receives. The analysis extracts relevant keywords from the user's request. For example, keywords such as "last week's streams," "movies," and "dramas" are identified.

[1559] Input: Request data, Generative AI model

[1560] Output: Related keywords

[1561] Specific operation: The server passes the request data to the generative AI model, which then extracts relevant keywords.

[1562] Step 3:

[1563] The server generates questions for the user based on the extracted related keywords, such as "Who was the main character in that movie?"

[1564] Input: Related keywords

[1565] Output: Question text

[1566] Specific operation: Based on relevant keywords, the server uses a generative AI model to construct an appropriate question and sends this question to the user.

[1567] Step 4:

[1568] The device displays the generated question text to the user, who then enters an answer to the question, for example, "Maybe he's a famous actor."

[1569] Input: Question text

[1570] Output: User's answer

[1571] Specific operation: The device receives the user's answer to the displayed question and sends it to the server.

[1572] Step 5:

[1573] The server re-analyzes the user's answers and, if necessary, generates more specific questions to present to the user, such as "What genre is that movie?"

[1574] Input: User's answer

[1575] Output: Next question text

[1576] Specific operation: The server uses the generative AI model based on the user's answers to generate the next question to obtain additional information and sends it to the device.

[1577] Step 6:

[1578] The terminal displays the following question text to the user, who then enters a more specific answer, and this interactive process is repeated as necessary.

[1579] Input: Next question text

[1580] Output: Additional user answers

[1581] Specific operation: Each time a user answers a question, the answer is sent to the server.

[1582] Step 7:

[1583] The server then re-analyzes all the collected information and uses a generative AI model to identify the best content candidates, for example, "dramas starring famous actors featured in last week's streams."

[1584] Input: All user responses

[1585] Output: Best content candidates

[1586] How it works: The server uses collected data and generative AI models to identify content candidates and generate suggestions for the user.

[1587] Step 8:

[1588] The device presents the identified content candidates to the user, who can then review and select the suggested content.

[1589] Input: Best content suggestions

[1590] Output: Content suggestions presented to the user

[1591] Specific operation: The device displays content suggestions received from the server, and the user selects and watches the content of interest.

[1592] 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.

[1593] This invention combines a system that analyzes a user's vague requests and proposes specific product candidates with an emotion engine that recognizes the user's emotions and optimizes the content of questions and product proposals based on those emotions. By taking the user's emotions into consideration, it is possible to provide an optimal shopping experience with even less stress for the user.

[1594] Overall system overview

[1595] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which uses a generative AI model and an emotion engine to analyze the request and generate and present appropriate questions. As the server receives the user's responses, it adjusts the content of the questions and product candidates in response to changes in emotion, suggesting the most suitable products.

[1596] System configuration for implementation

[1597] The system includes the following major components:

[1598] User Interface (UI): The interface through which users input requests and interact with the system.

[1599] Communication means: A communication means for sending user requests and answers to the server and receiving questions and product suggestions from the server.

[1600] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[1601] Emotion engine: An engine for recognizing user emotions and reflecting them in analysis.

[1602] Program processing

[1603] The program of this system proceeds in the following order:

[1604] User request input

[1605] A user accesses a shopping site and inputs a vague request such as, "I want this and that thing I saw on yesterday's news program." The device then sends this input to the server.

[1606] Parsing the request

[1607] The server uses a generative AI model to analyze vague requests received from users and extract related keywords (e.g., "information program," "yesterday," "cooking equipment"), while an emotion engine recognizes the user's emotions and incorporates them into the analysis.

[1608] Question Generation

[1609] The server generates a question for the user (e.g., "What is the name of that information program?") based on the extracted related keywords and the recognition results of the emotion engine. The question is adjusted according to the user's emotions.

[1610] User interaction

[1611] The user answers a question displayed on the device (e.g., "The name of the information program is 'Good Morning'"). The device then sends this answer to the server. The server then re-analyzes the received answer and re-evaluates the user's emotions using the emotion engine. If necessary, when generating a more specific question (e.g., "What are the specific uses and features of that cookware?"), the content is adjusted taking the user's emotions into account.

[1612] Product candidate suggestions

[1613] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the emotion engine's evaluation. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." The server optimizes the presentation order of the identified product candidates based on the user's emotions and sends them to the device.

[1614] User Choices and Purchases

[1615] The device displays suggested products to the user, who can then review the details, select the products they are interested in, and finally complete the purchase process.

[1616] Specific examples

[1617] 1. User Input

[1618] User: "I want this thing I saw on yesterday's TV show."

[1619] Terminal: Send this input to the server.

[1620] 2. Server-based analysis and query generation

[1621] Server: Generates "What is the name of that information program?" and then the emotion engine recognizes the user's emotion.

[1622] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer, such as "Please don't hesitate to tell me, what is the name of that information program?"

[1623] 3. User interaction

[1624] Terminal: Display the question to the user.

[1625] User: "Good morning," and reevaluate the emotion engine's recognition results.

[1626] Server: Re-analyzes the answer and takes into account the sentiment engine's evaluation when generating the next question.

[1627] 4. Final product proposal

[1628] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1629] Server: Optimize the product presentation order based on user sentiment.

[1630] Device: Show suggested content to the user.

[1631] User: Selects a product and proceeds with the purchase.

[1632] In this way, the system efficiently embodies the user's vague requests and further proposes optimal products taking into account their emotions.

[1633] The processing flow will be explained below.

[1634] Specific processing flow of the program

[1635] Step 1:

[1636] A user accesses a shopping site and inputs a vague request (e.g., "I want this and that thing I saw on yesterday's news program.") The device receives this input.

[1637] Step 2:

[1638] The device sends the user's input to the server.

[1639] Step 3:

[1640] The server receives an ambiguous request from a user.

[1641] Step 4:

[1642] The server's generative AI model analyzes vague requests and extracts relevant keywords (e.g., "information program," "yesterday," "cooking equipment").

[1643] Step 5:

[1644] The server generates appropriate questions for the user based on the extracted related keywords.

[1645] Step 6:

[1646] The server generates a question and sends it to the user's device.

[1647] Step 7:

[1648] The device displays the questions received from the server on the screen and prompts the user to interact.

[1649] Step 8:

[1650] The emotion engine analyzes the user's emotions and evaluates their current emotional state. For example, if it recognizes that the user looks anxious, it will adjust the tone of the question to something like, "Please relax and answer freely. What is the name of that news program?"

[1651] Step 9:

[1652] The user answers the displayed question (e.g., "The name of the information program is 'Good Morning'"), and the device sends the answer to the server.

[1653] Step 10:

[1654] The server receives the user's response and analyzes it again using the generative AI model.

[1655] Step 11:

[1656] The emotion engine reevaluates the user's emotional state at the time of answering and generates more appropriate questions, with the server adapting the questions accordingly (e.g., "Please tell me the specific uses and features of that cookware").

[1657] Step 12:

[1658] The server sends additional questions to the terminal, which displays the questions to the user.

[1659] Step 13:

[1660] The user enters a specific answer (e.g., "It's a steamer that can be used in a microwave"), and the device sends the answer to the server.

[1661] Step 14:

[1662] The server analyzes the user's responses again and identifies product candidates based on the information obtained.

[1663] Step 15:

[1664] The server identifies appropriate product candidates based on the evaluation results of the emotion engine and optimizes the order of presentation, making friendly suggestions based on the user's emotions, such as "Here's a microwave steamer that everyone has highly rated."

[1665] Step 16:

[1666] The server sends the generated suggested content to the user's terminal.

[1667] Step 17:

[1668] The device displays suggested product candidates to the user, who then checks the details and selects the product of interest.

[1669] Step 18:

[1670] As users select products and proceed with the purchase process, the emotion engine monitors their emotions and provides support to ensure a stress-free experience.

[1671] This series of steps will realize a system that takes emotions into account, efficiently clarifies the user's vague requests, and suggests optimal product candidates.

[1672] Example 2

[1673] 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."

[1674] Conventional shopping systems have difficulty identifying appropriate products based on vague user input. Furthermore, questions and suggestions are often made without considering the user's feelings, resulting in a poor user experience. As a result, it takes a lot of time and effort for users to find the product they are looking for, which increases their stress.

[1675] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing a user's vague request and extracting related information, means for generating and presenting appropriate questions based on the related information and the user's emotions, means for reanalyzing the user's answers and emotions to identify product candidates, means for presenting the product candidates in an optimal order based on the user's emotions, means for specifying the request through dialogue with the user using a generative AI model and an emotion recognition engine, and means for learning the latest market trends and information and using them to identify product candidates and present them in accordance with the user's emotions. This makes it possible to quickly and appropriately suggest products while taking emotions into consideration, even based on a user's vague request.

[1676] "Ambiguous user requests" are requests that express vague needs or desires without clear specific product names or details.

[1677] "Related information" refers to keywords and concepts extracted from a user's vague request that are useful for making the request more specific.

[1678] An "emotion recognition engine" is a program or software that analyzes and recognizes a user's emotional state (e.g., anxiety, excitement, satisfaction, etc.) from their input or dialogue.

[1679] A "generative AI model" is an artificial intelligence model that generates questions and responses in natural language from input data.

[1680] "Question generation and presentation" is the process of creating appropriate questions based on user requests and presenting them to the user.

[1681] "Product Candidate" means a specific product or service that is recommended based on the user's request and analysis results.

[1682] "Latest market trends" refers to information related to current market trends and user interests.

[1683] "Presenting in the appropriate order" means taking into consideration the user's emotions and interests and displaying information and product candidates in the order that will attract the most attention.

[1684] "User interface (UI)" refers to an interface such as a screen or input means that allows a user to interact with a system.

[1685] This system analyzes the user's vague requests and proposes optimal questions and products based on the user's emotions, thereby providing the user with a stress-free shopping experience.

[1686] Overall system overview

[1687] A user uses a device to enter a vague request into the search box of a shopping site. This request is sent to the server, which analyzes the request using a generative AI model and an emotion recognition engine to generate and present an appropriate question. As the server receives the user's response, it adjusts the question content and product candidates in response to changes in emotion, suggesting the most suitable product.

[1688] System configuration for implementation

[1689] The system includes the following major components:

[1690] User Interface (UI): The interface through which the user enters requests and interacts with the system.

[1691] Communication method: This is the communication method used to send user requests and answers to the server and receive questions and product suggestions from the server. Specifically, HTTPS is used.

[1692] Server: A central device that analyzes user requests, generates appropriate questions, and identifies product candidates based on the user's answers.

[1693] Emotion recognition engine: An engine that recognizes user emotions and reflects them in analysis. An example is IBM Watson Tone Analyzer.

[1694] Generative AI model: A model that performs natural language processing and generates appropriate questions and product suggestions based on user requests and answers. An example is OpenAI GPT-4.

[1695] Specific examples

[1696] 1. User Input

[1697] User: "I want this thing I saw on yesterday's TV show."

[1698] Terminal: Send this input to the server.

[1699] 2. Server-based analysis and query generation

[1700] Server: Generates "What is the name of that information program?" and then the emotion recognition engine recognizes the user's emotion.

[1701] Server: Adjust the wording of the question depending on the user's emotions. For example, if the user is feeling anxious, change the wording to something softer like, "Please don't hesitate to tell me, what is the name of that information program?"

[1702] 3. User interaction

[1703] Terminal: Display the question to the user.

[1704] User: "Good morning," and the device sends this response to the server.

[1705] Server: Re-analyzes the answer and takes into account the emotion recognition engine's evaluation when generating the next question.

[1706] 4. Final product proposal

[1707] Server: Identifies related products and generates suggested content such as, "This is the microwave steamer that was featured on Good Morning yesterday."

[1708] Server: Optimize the product presentation order based on user sentiment.

[1709] Device: Display suggested content to the user.

[1710] User: Selects a product and proceeds with the purchase.

[1711] Prompt Sentence Examples

[1712] "Please provide a prompt for the system that uses a corresponding emotion recognition engine and generative AI model to parse a user's vague request and identify specific product candidates."

[1713] As described above, the present invention provides a system that efficiently embodies the vague needs of a user and further proposes optimal products taking emotions into consideration.

[1714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1715] Step 1: User Request Input

[1716] A user visits a shopping site and enters a vague request into the search box (e.g., "I want this and that thing I saw on yesterday's news program"). As input, vague natural language text is obtained. The device receives this input and sends it to the server. As output, data containing the user's request is sent to the server.

[1717] Step 2: Submitting the request

[1718] The terminal sends an ambiguous request entered by the user to the server using the HTTPS protocol. It receives the user's text data as input and sends an HTTPS request to the server as output.

[1719] Step 3: Parsing the request

[1720] The server inputs the text data into a generative AI model (e.g., OpenAI GPT-4) to analyze the received user request. The user's request text is passed to the model as input, and data processing involves extracting related keywords and specifying the information. The text is also passed to an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions. The output is related keywords and the user's emotional information.

[1721] Step 4: Generate and submit your question

[1722] The server generates an appropriate question based on the extracted related keywords and the results of emotion recognition. For example, it generates a question such as, "What is the name of that information program?" It receives related keywords and emotion information as input and generates a specific question through data calculations using a generative AI model. If the user feels uneasy, it adjusts the question to, "Please feel free to tell me, what is the name of that information program?" The generated question is sent to the device as output.

[1723] Step 5: Receiving and sending user responses

[1724] The terminal displays the generated question on the user's screen. It receives the generated question as input and presents it to the user. The user enters an answer (e.g., "The name of the information program is 'Good Morning'"), and the terminal sends this answer to the server. As output, the user's answer data is sent to the server.

[1725] Step 6: Reanalyze the answers

[1726] The server re-analyzes the received user response. The response text is input into the generative AI model, relevant information is extracted again, and the user's emotions are re-evaluated through the emotion recognition engine. The server receives the user's response text as input, and processes it to extract information and evaluate emotions. The re-analyzed information and emotion evaluation are obtained as output.

[1727] Step 7: Product candidate proposals

[1728] The server uses a generative AI model to identify suitable product candidates based on the reanalyzed information and emotional evaluation. It receives the reanalyzed information and emotional evaluation as input and performs data calculations to identify the best product candidates from the product database. For example, it identifies "the microwave steamer featured on yesterday's Good Morning." As output, it generates a presentation order based on detailed product information and emotional evaluation, and sends it to the device.

[1729] Step 8: User Selection and Purchase

[1730] The terminal displays the suggested product candidates to the user. As input, it receives product candidate information and displays it to the user. The user checks the details and selects the product they are interested in. Finally, the terminal receives the user's selection and proceeds with the purchase. As output, the server is notified of the user's selection information and the completion of the purchase process.

[1731] Through the above processing steps, the system converts the user's vague requests into specific product suggestions, providing an optimal shopping experience that takes emotions into consideration.

[1732] (Application example 2)

[1733] 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."

[1734] Conventional shopping systems have difficulty analyzing users' vague requests, which means it takes a long time to accurately find the product they are looking for. Furthermore, because they do not take users' emotions into consideration, the experience is often stressful for users.

[1735] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting a user's vague request, means for analyzing the vague request and extracting related keywords, means for generating and presenting a question to the user based on the related keywords, means for receiving an answer from the user and further analyzing the received answer to identify specific product candidates, means for presenting specific product candidates to the user, and means for recognizing the user's emotions and optimizing the question content and product candidates based on the emotions. This makes it possible to efficiently specify the user's vague request and provide an optimal shopping experience that takes emotions into consideration.

[1736] "Vague user requests" are vague requests or wishes that do not include specific product names or specific information, but indicate what the user is looking for.

[1737] "Related keywords" are important words and phrases that are extracted in the process of analyzing a user's vague request and that make the request more specific.

[1738] "Means for generating and presenting" refers to the means for automatically creating questions based on related keywords and showing them to users.

[1739] "User response" refers to the information entered by the user in response to a question posed by the system.

[1740] "Specific Product Candidates" are specific products that a user may be looking for, identified based on the user's request and related keywords.

[1741] "User emotions" refers to the psychological state and reactions exhibited by users during the shopping process.

[1742] "Means for recognizing and analyzing emotions" refers to technologies and systems that identify and analyze emotions from user input and behavior.

[1743] "Means for optimizing question content and product suggestions" refers to means for adjusting the content and order of questions and the way product suggestions are presented based on recognized user sentiment, in order to improve the user experience.

[1744] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to concretize a user's vague requests and generate appropriate questions and suggestions.

[1745] System configuration

[1746] This invention is a shopping system that analyzes a user's vague requests and proposes specific product candidates based on them. The system consists of a user interface (UI), communication means, a server, an emotion recognition engine, and a generative AI model.

[1747] Hardware and software used

[1748] User Interface: Smartphone application

[1749] Communication method: 4G / 5G network, Wi-Fi

[1750] Server: Cloud server (AWS, Google Cloud, etc.)

[1751] Emotion recognition engine: EmotionRecognition library

[1752] Generative AI model: OpenAI's GPT-3

[1753] What the program does

[1754] User request input

[1755] The user inputs a vague request using a smartphone application, such as "I want this and that thing I saw on yesterday's news program." The device then transmits this input to the server via a communication means.

[1756] Parsing the request

[1757] The server uses a generative AI model to analyze ambiguous requests received from users and extract related keywords. It also uses an emotion recognition engine to recognize the user's emotions and incorporates that information into the analysis. For example, related keywords such as "information program," "yesterday," and "cooking equipment" are extracted.

[1758] Question Generation

[1759] The server generates questions for the user based on the extracted related keywords and the results of the emotion recognition engine. The generated questions are adjusted according to the user's emotions. For example, if the user is feeling anxious, the question is softened to say, "Please don't hesitate to tell me, what is the name of that information program?"

[1760] User interaction

[1761] The user answers questions displayed on the device. For example, "What is the name of that news program?", the device receives a response such as "Good Morning." The device then sends this response to the server, which then re-analyzes the response. At the same time, the emotion recognition engine re-evaluates the user's emotions and adjusts the content of the generated questions to take their emotions into account.

[1762] Product candidate suggestions

[1763] The server uses a generative AI model to identify the most suitable product candidates based on all information obtained from the user and the evaluation by the emotion recognition engine. For example, it identifies "the microwave steamer featured on yesterday's Good Morning," optimizes the presentation order of the product candidates based on the user's emotions, and sends them to the device.

[1764] User Choices and Purchases

[1765] The device displays suggested products to the user, and the user can check the details and select the product they are interested in. Finally, the purchase process is completed. For example, the device may suggest, "This is the microwave steamer that was featured on 'Good Morning' yesterday," and the user can select the product and proceed to the purchase process.

[1766] Prompt Sentence Examples

[1767] "User's vague request: I want this and that thing I saw on yesterday's news program.

[1768] Emotion: I want to be introduced

[1769] Generate specific questions."

[1770] In this way, it is possible to efficiently materialize the user's vague requests and propose optimal products taking their emotions into consideration.

[1771] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1772] Step 1:

[1773] A user uses a smartphone application to input a vague request, such as "I want this and that thing I saw on yesterday's news program." Once the input is complete, the device sends this data to the server.

[1774] Step 2:

[1775] The server inputs the received ambiguous request into a generative AI model (OpenAI GPT-3) to extract related keywords, providing the following prompt sentence to the generative AI model:

[1776] Vague user requests: I want this and that thing I saw on yesterday's news program.

[1777] Extract specific keywords.

[1778] The generative AI model outputs related keywords such as "information program," "yesterday," and "cooking utensils."

[1779] Step 3:

[1780] The server uses the extracted related keywords to generate questions for the user. It also uses an emotion recognition engine to analyze the user's emotions and reflects the results in the questions. For example, if the emotion recognition engine detects "anxiety" in the user's text, the generated question will be softer-phrased, such as "Please feel free to tell me, what is the name of that information program?"

[1781] Step 4:

[1782] The device displays the generated question to the user, who then answers the question. For example, in response to the question "What is the name of that information program?", the user answers "It's 'Good Morning.'"

[1783] Step 5:

[1784] The device sends the user's answer to the server. The server receives the answer and again uses the generative AI model to analyze it and extract relevant information. At the same time, it re-evaluates the user's emotions with an emotion recognition engine. The following prompt sentence is used to generate a new question:

[1785] User Answer: "Good morning"

[1786] Please extract specific relevant information.

[1787] The generative AI model outputs related information such as "information programs," "good morning," and "cooking utensils."

[1788] Step 6:

[1789] The server identifies the best product candidates for the user based on the re-evaluated emotion data and newly extracted information, and uses the generative AI model again to list the product candidates. It also optimizes the product presentation order taking into account the results of the emotion recognition engine. For example, it identifies "the microwave steamer that was featured on 'Good Morning' yesterday" and uses the following prompt sentence:

[1790] Keywords: Good Morning, microwave, steamer

[1791] Please suggest the best product options.

[1792] The generative AI model outputs relevant product candidates.

[1793] Step 7:

[1794] The terminal displays the product suggestions sent from the server to the user. The user checks the detailed information and selects the product to purchase. For example, the user selects a suggested product such as "This is the microwave steamer that was featured on yesterday's Good Morning," and proceeds with the purchase process.

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] 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.

[1800] 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.

[1801] 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).

[1802] 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.

[1803] 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."

[1804] 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.

[1805] 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).

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] The following is further disclosed regarding the above embodiment.

[1817] (Claim 1)

[1818] a means for inputting a user's vague request;

[1819] means for analyzing the ambiguous request and extracting related keywords;

[1820] A means for generating and presenting questions to the user based on the related keywords;

[1821] a means for receiving responses from users and further analyzing the received responses to identify specific product candidates;

[1822] The system includes a means for presenting the specific product candidates to the user.

[1823] (Claim 2)

[1824] 10. The system of claim 1, including a generative AI model for fleshing out requirements through interaction with a user.

[1825] (Claim 3)

[1826] 10. The system of claim 1, further comprising means for learning current trends and information and utilizing them in identifying potential products.

[1827] "Example 1"

[1828] (Claim 1)

[1829] a means for inputting a user's vague request;

[1830] A means for analyzing the ambiguous request using a generative AI model and extracting related keywords;

[1831] A means for generating and presenting questions to the user based on the related keywords;

[1832] a means for receiving responses from users and reanalyzing the received responses to identify specific product candidates;

[1833] A means for presenting the specific product candidates to the user;

[1834] a means for storing user requests and responses in a database;

[1835] The system includes means for using the database to improve the accuracy of analysis and product candidate identification.

[1836] (Claim 2)

[1837] 10. The system of claim 1, further comprising means for utilizing the generative AI model to instantiate the request through interaction with a user.

[1838] (Claim 3)

[1839] 10. The system of claim 1, further comprising means for learning the latest trends and information from a database and utilizing the information to identify potential products.

[1840] "Application Example 1"

[1841] (Claim 1)

[1842] a means for inputting a user's vague request;

[1843] means for analyzing the ambiguous request and extracting related keywords;

[1844] A means for generating and presenting questions to the user based on the related keywords;

[1845] means for receiving responses from users and further analyzing the received responses to identify specific content candidates;

[1846] The system includes means for presenting the specific content candidates to a user.

[1847] (Claim 2)

[1848] 10. The system of claim 1, including a generative AI model for fleshing out requirements through interaction with a user.

[1849] (Claim 3)

[1850] 10. The system of claim 1, further comprising means for learning current trends and information and utilizing them in identifying content candidates.

[1851] "Example 2: Combining Emotion Engines"

[1852] (Claim 1)

[1853] a means for inputting a user's vague request;

[1854] means for analyzing the ambiguous request to extract relevant information;

[1855] A means for generating and presenting appropriate questions based on the relevant information and the user's emotions;

[1856] a means for receiving responses from users and reanalyzing the received responses and the user's sentiments to identify product candidates;

[1857] The system includes a means for presenting the product candidates in an optimal order based on the user's emotions.

[1858] (Claim 2)

[1859] 10. The system of claim 1, further comprising means for fleshing out the request through interaction with the user using a generative AI model and an emotion recognition engine.

[1860] (Claim 3)

[1861] 2. The system according to claim 1, further comprising means for learning the latest market trends and information and using the information to identify potential products and present them in accordance with the user's emotions.

[1862] "Application example 2 when combining emotion engines"

[1863] (Claim 1)

[1864] a means for inputting a user's vague request;

[1865] means for analyzing the ambiguous request and extracting related keywords;

[1866] A means for generating and presenting questions to the user based on the related keywords;

[1867] a means for receiving responses from users and further analyzing the received responses to identify specific product candidates;

[1868] A means for presenting the specific product candidates to the user;

[1869] A system that includes a means of recognizing user emotions and optimizing questions and product suggestions based on these emotions.

[1870] (Claim 2)

[1871] The system of claim 1, further comprising means for utilizing a generative AI model to flesh out a user's request and generate questions taking into account emotion recognition results.

[1872] (Claim 3)

[1873] 2. The system according to claim 1, further comprising means for optimizing the product presentation order based on the emotion recognition result to provide a less stressful shopping experience for the user. [Explanation of symbols]

[1874] 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. a means for inputting a user's vague request; means for analyzing the ambiguous request and extracting related keywords; A means for generating and presenting a question to a user based on the related keywords; a means for receiving responses from users and further analyzing the received responses to identify specific product candidates; The system includes a means for presenting the specific product candidates to the user.

2. 10. The system of claim 1, including a generative AI model for fleshing out requirements through interaction with a user.

3. 10. The system of claim 1, further comprising means for learning current trends and information and utilizing them in identifying potential products.

Images