System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a question input by a user; means for analyzing the question and extracting key words and phrases; means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question; means for collecting and evaluating responses from the selected users; and means for generating a multilateral recommendation list based on the evaluation and transmitting the list to the users.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When people search for information in areas they are unfamiliar with, they often do not know which information is reliable or where to get it, making it difficult to find appropriate information. To solve this problem, there is a need for a system that uses recommendations from multiple people with different perspectives and backgrounds to provide users with reliable and useful information. [Means for solving the problem]

[0005] The present invention includes a means for receiving a question entered by a user, analyzing the question, and extracting key keywords and phrases. It also includes a means for selecting a group of users with different perspectives and sending them a recommendation request based on the question. It also includes a means for collecting and evaluating responses from the selected users, and a means for generating a multifaceted recommendation list based on the evaluations and sending it to the user. This allows the user to obtain reliable information from multiple perspectives.

[0006] "User" refers to an individual who utilizes the system to enter questions and obtain information.

[0007] "Question" refers to a text input that a user enters through the system to request information or knowledge.

[0008] The term "means" refers to a functional component for executing a specific function or process in a system.

[0009] "Analysis" refers to the process by which the system receives a question, structures its content, and extracts keywords and important elements.

[0010] "Keywords" refer to important words extracted from questions that serve as criteria for information search and recommendations.

[0011] A "user group" refers to a set of multiple users with different perspectives and backgrounds who are selected for the system to ask for question-based recommendations.

[0012] "Recommendation Request" means a request sent by the System to a selected group of Users for opinions or recommendations based on a question.

[0013] A "response" refers to an opinion or recommendation entered by a user who receives a recommendation request and sent to the system.

[0014] "Evaluation" refers to the process by which the system determines the usefulness and redundancy of the responses it collects.

[0015] "Natural language processing technology" refers to the technology used by systems to understand, analyze, and generate human language.

[0016] A "multifaceted recommendation list" refers to a list of information provided to a user that is generated based on opinions and recommendations evaluated from different perspectives.

[0017] "Transmit" refers to the process of sending system-generated information or requests as data to other systems or devices. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments of the system of the present invention will be described below.

[0040] First, the user inputs a question using the terminal. For example, the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, which sends the question to the server.

[0041] The server uses a natural language processing (NLP) engine to analyze the received question. The server analyzes the question and extracts key keywords and phrases. In this case, "mystery," "easy to read," and "book" are extracted. The analysis results are temporarily stored in storage.

[0042] Next, the server selects a group of users with different perspectives, including people who read less books, people who read more books, editors, etc. The server generates and sends recommendation requests based on the analysis results to the selected users.

[0043] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, "Keigo Higashino's works are easy to read." When the target user sends the recommendation to the server, the server receives it.

[0044] The server then evaluates the collected opinions and recommendations, using natural language processing technology and evaluation algorithms to determine the usefulness and redundancy of each opinion, and stores the evaluation results in a database.

[0045] After the evaluation is complete, the server generates a multifaceted recommendation list based on the evaluation results. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the device. The user can view this recommendation list on their device. For example, the list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0046] In this way, the system of the present invention uses recommendations from different perspectives to provide information from multiple angles in areas that the user is unfamiliar with, allowing the user to efficiently obtain reliable and useful information.

[0047] For example, if a user asks, "Tell me some easy-to-read mystery books," someone who doesn't read much might recommend "Works by Keigo Higashino," someone who reads a lot might recommend "Works by Agatha Christie," and an editor might recommend "Mystery novels for beginners recommended by a famous editor." By integrating this recommendation information and providing it to the user, the system allows users to obtain information from multiple perspectives.

[0048] The above is a description of the mode for carrying out the invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, thereby providing users with the information they desire.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user uses the terminal to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button.

[0052] Step 2:

[0053] The user's question is sent from the terminal to the server.

[0054] Step 3:

[0055] The server receives the user's query.

[0056] Step 4:

[0057] The server uses a natural language processing engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[0058] Step 5:

[0059] The server stores the analysis results in temporary storage.

[0060] Step 6:

[0061] The server selects a group of users with different perspectives, including casual readers, frequent readers, editors, etc.

[0062] Step 7:

[0063] The server generates recommendation requests based on the questions for a selected set of users.

[0064] Step 8:

[0065] The server sends recommendation requests to a selected set of users.

[0066] Step 9:

[0067] Selected users with terminals receive recommendation requests.

[0068] Step 10:

[0069] The selected user enters a recommendation from their own perspective. For example, they can write, "Higashino Keigo's works are easy to read," and then press the submit button.

[0070] Step 11:

[0071] The recommendation opinion is transmitted from the selected user terminal to the server.

[0072] Step 12:

[0073] The server receives the recommendations.

[0074] Step 13:

[0075] The server evaluates each recommendation received using natural language processing technology and evaluation algorithms to determine usefulness and redundancy.

[0076] Step 14:

[0077] The server stores the evaluation results in a database.

[0078] Step 15:

[0079] The server generates a multifaceted recommendation list based on the evaluated opinions.

[0080] Step 16:

[0081] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[0082] Step 17:

[0083] The server sends the formatted recommendation list to the user's terminal.

[0084] Step 18:

[0085] The terminal receives the recommendation list from the server.

[0086] Step 19:

[0087] The user uses the device to view the received recommendation list, which may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[0088] The above are the processing steps of the program.

[0089] Example 1

[0090] 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."

[0091] Conventional information recommendation systems lack the means to efficiently provide multifaceted information on areas that users are unfamiliar with. This makes it difficult to obtain highly reliable and useful information. The purpose of this invention is to solve these problems and provide multifaceted information from different perspectives.

[0092] 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.

[0093] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and concepts, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, and means for providing the generated recommendation list in a format that the user can view. This enables the user to efficiently obtain reliable and useful information.

[0094] The "means for receiving a question input by a user" refers to a function that enables the server to receive a question input by a user via a terminal.

[0095] "Means for analyzing questions and extracting key keywords and concepts" refers to a function that uses natural language processing technology to analyze received questions and extract key keywords and concepts from them.

[0096] "Means for selecting a group of users with different perspectives and sending recommendation requests based on questions" refers to a function for selecting a target group of users from a database based on user profiles and sending recommendation requests based on the analysis results to that group of users.

[0097] "Means for collecting and evaluating responses from selected users" refers to a function by which the server collects recommendation opinions sent by target users and evaluates the usefulness and overlap of those opinions using natural language processing technology and evaluation algorithms.

[0098] "Means for generating a multifaceted recommendation list based on the evaluation and sending it to the user" refers to a function for creating a recommendation list from various perspectives based on the evaluation results and providing that list to the user.

[0099] "Means for providing the generated recommendation list in a format that can be viewed by the user" refers to a function for adjusting the display format and data format so that the generated recommendation list can be easily viewed by the user on a terminal.

[0100] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments for implementing the present invention will be described in detail below.

[0101] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, the question is sent to the server. At this time, the terminal sends the question data to the specified URL on the server as an HTTP POST request.

[0102] The server uses a natural language processing (NLP) engine to analyze the received question. Specific software such as Google® NLP API or SpaCy can be used here. The server analyzes the question and extracts key keywords and concepts. In this case, "mystery," "easy to read," and "book" are extracted. The analyzed data is temporarily stored in the server's storage.

[0103] Next, the server selects a user group with different perspectives. This user group may include occasional readers, frequent readers, editors, etc. The server retrieves user profile data from a database (e.g., MySQL®) and selects a target user group based on the analysis results. Next, the server generates a recommendation request and sends it to the selected user group. The request can be sent via email or in-app notification.

[0104] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, they may say, "Keigo Higashino's works are easy to read." When the target user sends the recommendation from their device to the server, the server receives it and stores it in a database.

[0105] The server evaluates the received opinions and recommendations using natural language processing techniques (e.g., BERT or GPT-3 (registered trademark)) and evaluation algorithms. The evaluation results are stored in a database, which determines the usefulness and redundancy of each opinion.

[0106] After the evaluation is complete, the server generates a multifaceted recommendation list based on these evaluation results. The generated recommendation list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors." The server then formats this recommendation list into a user-viewable format and sends it to the device in JSON format, for example. The user can view this recommendation list on their device and obtain the information they need.

[0107] For example, if a user asks, "Tell me some easy-to-read mystery books," people who don't read much may recommend "Works by Keigo Higashino," people who read a lot may recommend "Works by Agatha Christie," and editors may recommend "Mystery novels for beginners recommended by famous editors." These recommendations are then combined and provided to the user as a final recommendation list.

[0108] Example prompt sentence:

[0109] "Tell me some easy-to-read mystery books."

[0110] "What are some easy-to-read mystery novels for beginners?"

[0111] "I'd like to know some recommendations for contemporary Japanese mystery writers."

[0112] "What are some classic mystery novels?"

[0113] The above is an embodiment of the present invention. By using this system, users can efficiently obtain highly reliable information from various perspectives.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] The user enters a question

[0117] A user uses a terminal to input a question, for example, "Tell me some good mystery books to read."

[0118] Input: The question typed by the user.

[0119] Output: The question is sent from the terminal to the server.

[0120] Specific behavior:

[0121] The user enters a question into the interface of their smartphone or PC and presses the send button.

[0122] At this time, the device sends the question data as an HTTP POST request to the specified URL on the server.

[0123] Step 2:

[0124] The server receives and parses the query

[0125] The server receives a question sent by a user.

[0126] Input: The question received from the user.

[0127] Output: Data with key keywords and concepts extracted.

[0128] Specific behavior:

[0129] The server receives the HTTP request and extracts the question data.

[0130] Next, a natural language processing engine (e.g., Google NLP API or SpaCy) is launched to analyze the question.

[0131] Key keywords such as "mystery," "easy to read," and "book" are extracted from the question and temporarily stored.

[0132] Step 3:

[0133] The server selects the target user group

[0134] The server selects a group of users with different perspectives.

[0135] Input: Question analysis results and user profile data.

[0136] Output: A list of target users and a recommendation request.

[0137] Specific behavior:

[0138] The server retrieves user profile data (reading frequency, occupation, etc.) from a database (e.g. MySQL).

[0139] Based on this profile data, target user groups are selected, such as people who don't read many books, people who read a lot of books, and editors.

[0140] After the selection, a recommendation request for "easy-to-read mystery books" is generated based on the analysis results and sent via email or in-app notification.

[0141] Step 4:

[0142] Target users provide recommendations

[0143] The target user receives the recommendation request and enters their opinion or recommendation from their own perspective.

[0144] Input: Recommendation request and target user's opinion.

[0145] Output: The recommendation is sent to the server.

[0146] Specific behavior:

[0147] In response to the recommendation request received by the target user, the user inputs their opinion, such as "Higashino Keigo's works are easy to read," into their own device.

[0148] The input recommendation is sent again as an HTTP POST request to the specified URL on the server.

[0149] Step 5:

[0150] The server evaluates opinions and recommendations

[0151] The server evaluates the collected opinions and recommendations using natural language processing techniques and evaluation algorithms.

[0152] Input: Collected testimonials.

[0153] Output: Evaluation of each opinion's usefulness and overlap.

[0154] Specific behavior:

[0155] The server stores the received recommendation opinion data in a database.

[0156] We use natural language processing models (e.g., BERT and GPT-3) and evaluation algorithms to evaluate the reliability and overlap of each opinion.

[0157] The evaluation results are stored in a database.

[0158] Step 6:

[0159] The server generates a recommendation list and provides it to the user.

[0160] The server generates a multifaceted recommendation list based on the evaluation results and sends it to the terminal.

[0161] Input: Evaluation result data.

[0162] Output: The recommendation list will be available on your device.

[0163] Specific behavior:

[0164] The server uses the evaluation results to generate a multifaceted recommendation list, such as "Works by Higashino Keigo," "Works by Agatha Christie," or "Mystery novels for beginners recommended by famous editors."

[0165] The recommendation list is sent to the device in JSON format.

[0166] The user can view this recommendation list on the terminal and obtain the information they need.

[0167] The above are the specific processing steps of the program of this system.

[0168] (Application example 1)

[0169] 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."

[0170] When it comes to electronic payment services, it is difficult for users to efficiently search for low-cost, secure remittance methods and payment methods that meet their specific needs, and there is a lack of accurate and reliable information from various perspectives.

[0171] 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.

[0172] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, means for analyzing questions about electronic payment services and providing recommendations from various perspectives, and means for visualizing and providing the recommendation list to the user, thereby enabling the user to efficiently obtain recommendation information from multiple perspectives.

[0173] A "user" is an individual or organization that utilizes the system to enter questions and obtain information.

[0174] A "question" is a query that seeks information for a user to enter into the system.

[0175] "Keywords" are the main nouns, verbs, adjectives, and other important words contained in the query.

[0176] A "phrase" is a sub-clause that has a specific meaning and is made up of a group of words contained in a question.

[0177] A "user group" is a group consisting of multiple users with different perspectives.

[0178] A "recommendation request" is a request for information sent to a group of users based on detected keywords or phrases.

[0179] A "response" is an opinion or recommendation provided by a group of users in response to a recommendation request.

[0180] "Evaluation" is the process of determining the usefulness and redundancy of responses using natural language processing techniques and evaluation algorithms.

[0181] A "multifaceted recommendation list" is a list of recommendation information generated based on evaluation results from different perspectives.

[0182] "Server" means a computer system that receives and analyzes questions, sends recommendation requests to a group of users, collects and evaluates responses, and generates a recommendation list.

[0183] A "natural language processing engine" is software that analyzes text data and extracts keywords and phrases.

[0184] An "evaluation algorithm" is a program that automatically evaluates the usefulness and redundancy of responses.

[0185] An "electronic payment service" is an online platform or application that enables users to conduct financial transactions.

[0186] "Visualization" is the process of presenting information to a user in an easy-to-view format.

[0187] The system of the present invention provides information from multiple perspectives in response to questions about electronic payment services entered by users. The following describes specific embodiments of the invention. The system is operated using the following hardware and software.

[0188] Hardware:

[0189] Smartphone: A device where users can enter questions and receive and view results.

[0190] Server: A computer system that analyzes questions, sends recommendation requests, collects and evaluates responses, and generates recommendation lists.

[0191] software:

[0192] Natural language processing engine (Spacy): Analyzes questions and extracts key keywords and phrases

[0193] Evaluation algorithm: Evaluating the usefulness and redundancy of responses using natural language processing techniques

[0194] REST API: A communication method for collecting and sending recommendation information

[0195] Data processing and calculation:

[0196] 1. Receiving questions from users

[0197] A user uses a smartphone to type in a question such as "Please tell me a low-cost and safe way to send money overseas" and submit it.

[0198] 2. Question Analysis

[0199] The server analyzes the received question using a natural language processing engine (Spacy) and extracts key keywords (e.g., "low cost," "safety," "overseas remittance").

[0200] 3. Selecting a group of users with different perspectives

[0201] The server selects a plurality of user groups with different viewpoints, such as emphasis on cost, emphasis on safety, emphasis on frequency of use, etc.

[0202] 4. Generate and send a recommendation request

[0203] The server generates and transmits recommendation requests based on the extracted keywords to each selected user group.

[0204] 5. Collecting responses

[0205] Collect responses from each user group (e.g., "cost-conscious users would like a low-cost remittance method," "safety-conscious users would like the most secure remittance method," etc.).

[0206] 6. Evaluating Responses

[0207] The server uses a rating algorithm to assess the usefulness and duplication of the responses and stores the results in a database.

[0208] 7. Creating and providing a multifaceted recommendation list

[0209] Based on the evaluation results, the server generates a multifaceted recommendation list (e.g., "low-cost overseas remittance methods," "safety-oriented overseas remittance methods," etc.) and sends it to the user's smartphone. The user can visualize and view these recommendation lists on their smartphone.

[0210] Examples:

[0211] For example, if a user asks, "What is a low-cost and safe way to send money overseas?", the system extracts keywords such as "low-cost," "safe," and "overseas remittance." It then sends recommendation requests to groups of users with different perspectives, such as those prioritizing cost, safety, or frequency of use. Once the responses are collected, the server evaluates them using natural language processing technology and evaluation algorithms to create a multifaceted recommendation list. Finally, this recommendation list is sent to the user's smartphone, where the user can visualize and review it.

[0212] Example prompt sentence:

[0213] Please tell me a low-cost and safe way to send money overseas.

[0214] In this way, the system of the present invention helps users to efficiently obtain information about electronic payment services.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The user inputs a question using a smartphone. For example, they input a prompt such as "Please tell me a low-cost and safe way to send money overseas" and press the send button. The input question is sent to the server.

[0218] Step 2:

[0219] The server analyzes the received question using a natural language processing engine (Spacy). Specifically, it analyzes the question (input) and extracts key keywords (such as "low cost," "safety," and "overseas remittance") (data processing). The extracted keywords are used as input for the next processing step.

[0220] Step 3:

[0221] The server selects a user group with different perspectives, such as cost priority, safety priority, or frequency of use priority, from the database. The result of this user group selection becomes the input for generating a recommendation request.

[0222] Step 4:

[0223] The server generates and sends a recommendation request based on the question to each selected user group. Specifically, it creates a recommendation request in the form of a question appropriate for each user group based on the extracted keywords, and sends it via a communication method (such as a REST API). The output of this step is the generated recommendation request.

[0224] Step 5:

[0225] The selected users respond to the recommendation request. As a response, they send recommendation information (e.g., "low-cost remittance methods," "secure remittance methods," etc.) to the server. The response is received by the server.

[0226] Step 6:

[0227] The server analyzes the received responses using an evaluation algorithm. Specifically, it evaluates the usefulness and redundancy of each response using natural language processing technology, and stores the evaluation results in a database. These results serve as input for generating the next recommendation list.

[0228] Step 7:

[0229] The server generates a multifaceted recommendation list based on the evaluation results. Based on the output of the evaluation algorithm, it integrates and organizes the optimal recommendation information from each perspective and presents it in a format that is easy for the user to understand. This recommendation list is the final output to the user.

[0230] Step 8:

[0231] The server sends the generated recommendation list to the user's smartphone, where the user can visualize and view the recommendation list. For example, the list contains recommendations from various perspectives, such as "low-cost remittance methods" and "safe remittance methods."

[0232] In this way, a system is realized that allows users to input questions about electronic payment services and efficiently obtain useful information from multiple perspectives.

[0233] 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.

[0234] The present invention provides a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to enable the user to efficiently search for information in areas in which the user is unfamiliar. Specific embodiments of the system of the present invention will be described below.

[0235] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" and presses the send button, the question is sent to the server. At this point, the emotion engine recognizes the emotion of the user when they input their question. For example, if the user is excited when inputting their question, that emotion information is also sent to the server.

[0236] The server receives the user's question and emotional information. The server analyzes the question and emotional information using a natural language processing (NLP) engine and an emotional engine. In this case, the server extracts key keywords such as "mystery," "easy to read," and "book," as well as the user's emotional state (e.g., excitement, confusion, etc.). The analysis results are temporarily stored in storage.

[0237] The server then selects user groups with different perspectives based on the user's emotional state. For example, if the emotion engine determines that the user is confused, it will select a user group with a perspective suitable for solving the problem. The user groups include people who don't read books often, people who read books often, editors, etc.

[0238] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their opinions and recommendations from their own perspectives. For example, "Keigo Higashino's works are easy to read."

[0239] When a response from a target user is sent to the server, the server receives the recommendation opinion and evaluates the response using natural language processing technology and evaluation algorithms. The evaluation is based on usefulness, redundancy, and emotional state. For example, recommendations that provide solutions to a confused user are prioritized.

[0240] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the terminal. The user can view this recommendation list on the terminal. For example, it may contain information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0241] For example, if a user asks, "Recommend some easy-to-read mystery books," and the emotion engine recognizes that the user is excited, the server will incorporate many recommendations that have elements that will entertain the user. For someone who doesn't read many books, "Works by Higashino Keigo" might be recommended, for a person who reads a lot of books, "Works by Agatha Christie" might be recommended, and for an editor, "Mystery novels for beginners recommended by a famous editor" might be recommended. By integrating these recommendations and providing them to the user, the system can obtain information that is multifaceted and takes emotions into consideration.

[0242] This concludes the description of the embodiments of the present invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, and further analyzes user emotions to more appropriately provide users with the information they desire.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user uses the device to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button. The device simultaneously captures the user's emotions.

[0246] Step 2:

[0247] The user's question and emotion data are transmitted from the terminal to the server.

[0248] Step 3:

[0249] A server receives the user's question and emotion data.

[0250] Step 4:

[0251] The server uses a natural language processing (NLP) engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[0252] Step 5:

[0253] The server uses an emotion engine to analyze the emotion data and identify the user's emotional state, such as "excited" or "confused."

[0254] Step 6:

[0255] The server stores the analysis results and emotion data in temporary storage.

[0256] Step 7:

[0257] The server selects a group of users with different perspectives based on the emotional state of the users. For example, for a confused user, it preferentially selects a user who is good at providing solutions.

[0258] Step 8:

[0259] The server generates recommendation requests based on the analysis results for a selected group of users, adjusting the tone and content of the requests depending on their emotional state.

[0260] Step 9:

[0261] The server sends recommendation requests to a selected set of users.

[0262] Step 10:

[0263] The selected target user receives the recommendation request at the terminal.

[0264] Step 11:

[0265] The target user inputs a recommendation from their own perspective. For example, they might type, "Keigo Higashino's works are easy to read," and then press the send button.

[0266] Step 12:

[0267] The recommendation opinions are transmitted from the target user terminal to the server.

[0268] Step 13:

[0269] The server receives the recommendations.

[0270] Step 14:

[0271] The server evaluates each recommendation received using natural language processing technology and an evaluation algorithm, taking into account not only usefulness and redundancy but also emotional state.

[0272] Step 15:

[0273] The server stores the evaluation results in a database.

[0274] Step 16:

[0275] The server generates a multifaceted recommendation list based on the evaluated opinions, and the content is arranged and emphasized according to the user's emotional state.

[0276] Step 17:

[0277] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[0278] Step 18:

[0279] The server sends the formatted recommendation list to the user's terminal.

[0280] Step 19:

[0281] The terminal receives the recommendation list from the server.

[0282] Step 20:

[0283] The user reviews the recommendation list received on their device and obtains multifaceted, emotion-based information, such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[0284] The above are the detailed processing steps of the system that combines the emotion engine.

[0285] Example 2

[0286] 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."

[0287] Conventional information recommendation systems are limited to providing general recommendations in response to questions entered by users, and it is difficult to provide multifaceted information that takes into account the user's emotions and circumstances. As a result, there are many cases where users' needs cannot be fully met. Specifically, the problem is that the information provided is inappropriate because the emotional state and background information of the user when entering a question are not taken into account.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0289] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for recognizing and receiving user emotional information, means for selecting a group of users with different perspectives based on the emotional information and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, and means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user. This enables multifaceted and advanced information recommendations that take into account the user's emotions and background information.

[0290] A "user" is an individual or group who uses the system to enter questions and receive information.

[0291] A "terminal" is an electronic device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[0292] A "server" is a central processing unit that receives a user's query, analyzes it, processes it, and provides appropriate information.

[0293] A "question" is text or voice data entered by a user about which information he or she wishes to obtain.

[0294] "Emotional information" is data related to the emotional state (e.g., excitement, confusion, etc.) expressed by the user when entering a question.

[0295] A "natural language processing engine" is a software technology that analyzes user questions and extracts key keywords and phrases.

[0296] An "emotion engine" is a software technology that analyzes a user's emotional state.

[0297] A "recommendation request" is a request for information that the server generates and transmits to a group of users with different viewpoints.

[0298] A "user group" is a group of users selected by the server who have different perspectives and knowledge.

[0299] A "response" is an opinion or piece of information that a group of users provides in response to a recommendation request.

[0300] The "rating means" is the process by which the server evaluates the usefulness and redundancy of responses using natural language processing techniques and rating algorithms.

[0301] A "recommendation list" is a list of information generated by the server based on the evaluation results, and provides the user with optimal recommendations from multiple perspectives.

[0302] The present invention is a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to efficiently search for information in areas in which the user is unfamiliar.

[0303] System configuration

[0304] Hardware

[0305] 1. Device: PC, smartphone, tablet, etc.

[0306] 2. Server: Central processing unit.

[0307] software

[0308] 1. Natural Language Processing Engine (NLP): Analyzes the question and extracts key keywords and phrases.

[0309] 2. Emotion engine: Recognize and analyze the user's emotional information.

[0310] Data processing and calculation

[0311] 1. Receiving user questions:

[0312] The terminal receives the user's question and sends it to the server.

[0313] 2. Recognition of emotional information:

[0314] The device's built-in emotion engine recognizes the emotion the user is feeling when entering a question and transmits it to the server.

[0315] 3. Question and emotion analysis:

[0316] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases.

[0317] At the same time, the emotion engine analyzes emotional information to understand the user's emotional state.

[0318] 4. User Group Selection:

[0319] The server selects a group of users with different perspectives based on the analysis results. Selection criteria include emotional information and past recommendation history.

[0320] 5. Generate and send a recommendation request:

[0321] The server generates and sends recommendation requests to a selected group of users, including key keywords and user emotion information.

[0322] 6. Collect and evaluate responses from target users:

[0323] The server collects responses from the target users and rates the responses using natural language processing techniques and rating algorithms.

[0324] 7. Generating and serving recommendation lists:

[0325] The server generates a multifaceted recommendation list based on the evaluation results and transmits it to the terminal for provision to the user.

[0326] Specific examples

[0327] The user uses a device to enter a question such as "Tell me about an easy-to-read mystery book" and presses the send button. The device's built-in emotion engine recognizes the user's excited state and sends this information along with the question to the server. The server receives and analyzes the question and emotion information, extracting key keywords such as "mystery," "easy to read," and "book" as well as the emotion information of "excitement."

[0328] The server then selects a group of users with appropriate perspectives, generates a recommendation request, and sends it. For example, responses are collected from people who don't read many books with perspectives suitable for problem solving, people who read a lot of books, editors, and others, and evaluated. For example, responses such as "Keigo Higashino's works are easy to read" are collected.

[0329] The server evaluates the responses and generates a multifaceted recommendation list, which is then formatted and sent to the device in a user-friendly format.The user can then browse on their device "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," and more.

[0330] Prompt Sentence Examples

[0331] "User is looking for a mystery, easy-to-read book. Their emotional state is excitement. What are your recommendations?"

[0332] Generative AI Models

[0333] The system uses a generative AI model to generate prompts for recommendation requests and collect responses from an appropriate set of users.

[0334] By using the above method, the present invention realizes multifaceted and sophisticated information recommendation that takes into account the user's emotions and background information.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1:

[0337] The user inputs a question using the terminal. For example, they input "Tell me about an easy-to-read mystery book" and press the send button. (Input) User's question (Output) Question data sent from the terminal to the server

[0338] Step 2:

[0339] The device uses an emotion engine to recognize the user's emotions. Specifically, emotions are analyzed using a facial recognition camera and voice input. (Input) User's facial expressions and voice. (Output) User's emotional information (e.g., excitement).

[0340] Step 3:

[0341] The device sends question data and emotion information to the server. (Input) Question data, emotion information (Output) Data transmission to the server

[0342] Step 4:

[0343] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases. (Input) Question data (Output) Key keywords (e.g., "mystery," "easy to read," "book")

[0344] Step 5:

[0345] The server analyzes the emotional information using an emotion engine and grasps the user's emotional state. (Input) Emotional information (Output) Analyzed emotional state (e.g., excitement)

[0346] Step 6:

[0347] The server selects a group of users with different perspectives based on key keywords and emotional information. Selection criteria include past recommendation history and expertise. (Input) Key keywords, emotional information (Output) Selected user group (e.g., frequent readers, editors)

[0348] Step 7:

[0349] The server generates and sends a recommendation request to a group of selected users. The recommendation request includes key keywords and emotion information. (Input) Key keywords, emotion information (Output) Send recommendation request

[0350] Step 8:

[0351] The target user inputs their opinion or recommendation based on the recommendation request and sends it to the server. For example, they send an opinion such as "Keigo Higashino's works are easy to read." (Input) Recommendation request (Output) Response from the target user

[0352] Step 9:

[0353] The server receives the response from the target user and evaluates the response content using natural language processing technology and evaluation algorithms. Evaluation criteria include usefulness, redundancy, emotional state, etc. (Input) Response from the target user (Output) Evaluation result (e.g., opinion with high usefulness)

[0354] Step 10:

[0355] The server generates a multifaceted recommendation list based on the evaluation results. The recommendation list contains information to meet the user's needs. (Input) Evaluation results (Output) Recommendation list

[0356] Step 11:

[0357] The server formats the generated recommendation list into a format that is easy for the user to provide, and sends it to the terminal. (Input) Recommendation list (Output) Sending the formatted recommendation list

[0358] Step 12:

[0359] The user browses the recommendation list on the device and makes a selection from the provided recommendation information. For example, they browse "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," etc. (Input) Formatted recommendation list (Output) User's selection and browsing

[0360] (Application example 2)

[0361] 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."

[0362] The problem is that there is a lack of methods to provide recommendation information from multiple perspectives, especially considering the user's emotional state, when collecting information about a product category that the user is not familiar with. Conventional systems have had difficulty making appropriate recommendations that take into account not only the content of the user's question but also the user's emotional state.

[0363] 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 receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for detecting the user's emotional state using an emotion detection engine, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question and emotional information, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluations and transmitting it to the user, and means for displaying the recommendation list on the user terminal. This makes it possible to provide appropriate recommendation information that takes into account the user's emotional state from a multifaceted perspective for product categories in which the user is not familiar.

[0364] The term "user" refers to a person who uses an information system, and in particular, a person who inputs a question to the system of the present invention and receives a reply.

[0365] The "means for receiving a question" is a function or device that allows the system to obtain a question input from a user.

[0366] "Means for analyzing questions and extracting key keywords and phrases" refers to a function or device that uses natural language processing technology to understand the content of a user's question and extract important words and phrases.

[0367] An "emotion detection engine" is a software or hardware device that analyzes and determines the emotional state of a user at the time of input.

[0368] The "means for selecting a group of users with different viewpoints" is a function or device for selecting other users with various backgrounds and knowledge based on the user's emotional state and question content.

[0369] The "means for sending a recommendation request" is a function or device for sending a request based on the question content and emotional information of a user to a selected group of users.

[0370] The "means for collecting and evaluating responses" is a function or device for collecting responses from other users who have received a recommendation request and evaluating the content of the responses.

[0371] The "means for generating and transmitting a multifaceted recommendation list" is a function or device for compiling recommendation information that takes into account various perspectives based on collected responses into a list format and providing this to the user.

[0372] A "user terminal" is a device that a user uses to interact with the system and to display a recommendation list from the system of the present invention.

[0373] The present invention is a system that efficiently searches for information on products in areas that the user is unfamiliar with, and provides recommendation information from multiple perspectives that take into account the user's emotional state. Here, a product recommendation system in a virtual store will be described as a specific embodiment.

[0374] First, a user inputs a question using a smartphone. For example, if the user types "Tell me about drones for beginners" and presses the send button, the question is sent to the server. Here, an emotion detection engine (e.g., Microsoft® Azure® Face API) is used to detect the emotional state of the user at the time of input. For example, if the user is detected to be excited, that emotional information is also sent to the server along with the question.

[0375] The server receives the question and emotion information and analyzes the question using a generative AI model (e.g., OpenAI® GPT-3). During this analysis, key keywords and phrases are extracted, resulting in important keywords such as "for beginners" and "drone." The analysis results and emotion information are temporarily stored in storage.

[0376] Next, the server selects user groups with different perspectives. If the emotion detection engine determines that the user is excited, it selects user groups that can make recommendations from a perspective that has an entertaining element. For example, it includes users who do not read books often, users who frequently use products, and experts.

[0377] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their own recommendations. For example, they can receive specific recommendations such as "easy-to-use drones for beginners."

[0378] When the target user's response is sent to the server, the server receives the recommendation and evaluates the response using natural language processing techniques and evaluation algorithms. The evaluation includes checking usefulness and redundancy, and also evaluates the response based on emotional state. For example, an excited user will be given priority over recommendations that are likely to be interesting.

[0379] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server then formats the recommendation list in a format that is easy for the user to provide and sends it to the user's smartphone. The user can view the recommendation list on their smartphone and check the details. For example, the list may include information such as "easy-to-use drones for beginners," "popular drones for beginners," and "drones recommended by experts."

[0380] As a concrete example, the following is an example of a prompt sentence when a user asks, "Tell me about drones for beginners," and the emotion engine recognizes that the user is excited.

[0381] Prompt: "Tell me about drones for beginners. I'm excited."

[0382] This allows the user to obtain recommendation information from multiple perspectives that take into account their emotional state, enabling them to select appropriate products.

[0383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0384] Step 1:

[0385] A user inputs a question using a smartphone terminal. For example, they input "Tell me about drones for beginners." At this point, the input data is the user's question. The input question is sent from the terminal to the server.

[0386] Step 2:

[0387] The server receives the question and analyzes the user's emotional state using an emotion detection engine (e.g., Microsoft Azure Face API). This analysis yields emotional information such as excitement, confusion, apprehension, and interest. The acquired emotional information is stored on the server along with the question content.

[0388] Step 3:

[0389] The server analyzes the question using a generative AI model (e.g., OpenAI GPT-3). By analyzing the question, key keywords and phrases are extracted. For example, keywords such as "for beginners" and "drone" are obtained. The analysis results are temporarily stored in storage.

[0390] Step 4:

[0391] The server selects a group of users with different perspectives based on their emotional state and the analysis results. If the emotion engine determines that the user is excited, it extracts users who can make recommendations with entertaining elements. In this case, it selects users from the database who are suitable for the user's excited state (e.g., experienced users, experts, etc.).

[0392] Step 5:

[0393] The server generates and sends recommendation requests based on the question content and emotion information to the selected group of users. The requests include the analyzed keywords and emotion information. The selected target users receive the recommendation requests and input their opinions and recommendations from their own perspectives.

[0394] Step 6:

[0395] When a response from a target user is sent to the server, the server receives a recommendation opinion. The server evaluates the response using natural language processing technology and an evaluation algorithm. The evaluation includes the usefulness, redundancy, and priority based on the emotional state of the response. The evaluation results are stored in a database.

[0396] Step 7:

[0397] The server generates a multifaceted recommendation list based on the evaluated opinions. For example, it may generate lists such as "Easy-to-use drones for beginners," "Popular drones for beginners," and "Drones recommended by experts." This recommendation list is formatted to be easily provided to users.

[0398] Step 8:

[0399] The server then sends the generated recommendation list to the user's smartphone. The user can then receive the recommendation list on their smartphone and check the details. This allows the user to obtain appropriate recommendation information that takes into account their emotional state.

[0400] This allows the user to obtain appropriate recommendation information from multiple perspectives that take into account the user's emotional state, even for product categories that the user is not familiar with.

[0401] 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.

[0402] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0403] 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.

[0404] [Second embodiment]

[0405] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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."

[0417] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments of the system of the present invention will be described below.

[0418] First, the user inputs a question using the terminal. For example, the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, which sends the question to the server.

[0419] The server uses a natural language processing (NLP) engine to analyze the received question. The server analyzes the question and extracts key keywords and phrases. In this case, "mystery," "easy to read," and "book" are extracted. The analysis results are temporarily stored in storage.

[0420] Next, the server selects a group of users with different perspectives, including people who read less books, people who read more books, editors, etc. The server generates and sends recommendation requests based on the analysis results to the selected users.

[0421] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, "Keigo Higashino's works are easy to read." When the target user sends the recommendation to the server, the server receives it.

[0422] The server then evaluates the collected opinions and recommendations, using natural language processing technology and evaluation algorithms to determine the usefulness and redundancy of each opinion, and stores the evaluation results in a database.

[0423] After the evaluation is complete, the server generates a multifaceted recommendation list based on the evaluation results. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the device. The user can view this recommendation list on their device. For example, the list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0424] In this way, the system of the present invention uses recommendations from different perspectives to provide information from multiple angles in areas that the user is unfamiliar with, allowing the user to efficiently obtain reliable and useful information.

[0425] For example, if a user asks, "Tell me some easy-to-read mystery books," someone who doesn't read much might recommend "Works by Keigo Higashino," someone who reads a lot might recommend "Works by Agatha Christie," and an editor might recommend "Mystery novels for beginners recommended by a famous editor." By integrating this recommendation information and providing it to the user, the system allows users to obtain information from multiple perspectives.

[0426] The above is a description of the mode for carrying out the invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, thereby providing users with the information they desire.

[0427] The processing flow will be explained below.

[0428] Step 1:

[0429] The user uses the terminal to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button.

[0430] Step 2:

[0431] The user's question is sent from the terminal to the server.

[0432] Step 3:

[0433] The server receives the user's query.

[0434] Step 4:

[0435] The server uses a natural language processing engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[0436] Step 5:

[0437] The server stores the analysis results in temporary storage.

[0438] Step 6:

[0439] The server selects a group of users with different perspectives, including casual readers, frequent readers, editors, etc.

[0440] Step 7:

[0441] The server generates recommendation requests based on the questions for a selected set of users.

[0442] Step 8:

[0443] The server sends recommendation requests to a selected set of users.

[0444] Step 9:

[0445] Selected users with terminals receive recommendation requests.

[0446] Step 10:

[0447] The selected user enters a recommendation from their own perspective. For example, they can write, "Higashino Keigo's works are easy to read," and then press the submit button.

[0448] Step 11:

[0449] The recommendation opinion is transmitted from the selected user terminal to the server.

[0450] Step 12:

[0451] The server receives the recommendations.

[0452] Step 13:

[0453] The server evaluates each recommendation received using natural language processing technology and evaluation algorithms to determine usefulness and redundancy.

[0454] Step 14:

[0455] The server stores the evaluation results in a database.

[0456] Step 15:

[0457] The server generates a multifaceted recommendation list based on the evaluated opinions.

[0458] Step 16:

[0459] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[0460] Step 17:

[0461] The server sends the formatted recommendation list to the user's terminal.

[0462] Step 18:

[0463] The terminal receives the recommendation list from the server.

[0464] Step 19:

[0465] The user uses the device to view the received recommendation list, which may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[0466] The above are the processing steps of the program.

[0467] Example 1

[0468] 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."

[0469] Conventional information recommendation systems lack the means to efficiently provide multifaceted information on areas that users are unfamiliar with. This makes it difficult to obtain highly reliable and useful information. The purpose of this invention is to solve these problems and provide multifaceted information from different perspectives.

[0470] 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.

[0471] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and concepts, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, and means for providing the generated recommendation list in a format that the user can view. This enables the user to efficiently obtain reliable and useful information.

[0472] The "means for receiving a question input by a user" refers to a function that enables the server to receive a question input by a user via a terminal.

[0473] "Means for analyzing questions and extracting key keywords and concepts" refers to a function that uses natural language processing technology to analyze received questions and extract key keywords and concepts from them.

[0474] "Means for selecting a group of users with different perspectives and sending recommendation requests based on questions" refers to a function for selecting a target group of users from a database based on user profiles and sending recommendation requests based on the analysis results to that group of users.

[0475] "Means for collecting and evaluating responses from selected users" refers to a function by which the server collects recommendation opinions sent by target users and evaluates the usefulness and overlap of those opinions using natural language processing technology and evaluation algorithms.

[0476] "Means for generating a multifaceted recommendation list based on the evaluation and sending it to the user" refers to a function for creating a recommendation list from various perspectives based on the evaluation results and providing that list to the user.

[0477] "Means for providing the generated recommendation list in a format that can be viewed by the user" refers to a function for adjusting the display format and data format so that the generated recommendation list can be easily viewed by the user on a terminal.

[0478] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments for implementing the present invention will be described in detail below.

[0479] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, the question is sent to the server. At this time, the terminal sends the question data to the specified URL on the server as an HTTP POST request.

[0480] The server uses a natural language processing (NLP) engine to analyze the received question. Specific software such as Google NLP API or SpaCy can be used here. The server analyzes the question and extracts key keywords and concepts. In this case, "mystery," "easy to read," and "book" are extracted. The analyzed data is temporarily stored in the server's storage.

[0481] Next, the server selects user groups with different perspectives. These user groups include casual readers, frequent readers, editors, etc. The server retrieves user profile data from a database (e.g., MySQL) and selects target user groups based on the analysis results. The server then generates recommendation requests and sends them to the selected user groups via email or in-app notifications.

[0482] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, they may say, "Keigo Higashino's works are easy to read." When the target user sends the recommendation from their device to the server, the server receives it and stores it in a database.

[0483] The server evaluates the received opinions and recommendations using natural language processing techniques (e.g., BERT or GPT-3) and evaluation algorithms. The evaluation results are stored in a database, which determines the usefulness and redundancy of each opinion.

[0484] After the evaluation is complete, the server generates a multifaceted recommendation list based on these evaluation results. The generated recommendation list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors." The server then formats this recommendation list into a user-viewable format and sends it to the device in JSON format, for example. The user can view this recommendation list on their device and obtain the information they need.

[0485] For example, if a user asks, "Tell me some easy-to-read mystery books," people who don't read much may recommend "Works by Keigo Higashino," people who read a lot may recommend "Works by Agatha Christie," and editors may recommend "Mystery novels for beginners recommended by famous editors." These recommendations are then combined and provided to the user as a final recommendation list.

[0486] Example prompt sentence:

[0487] "Tell me some easy-to-read mystery books."

[0488] "What are some easy-to-read mystery novels for beginners?"

[0489] "I'd like to know some recommendations for contemporary Japanese mystery writers."

[0490] "What are some classic mystery novels?"

[0491] The above is an embodiment of the present invention. By using this system, users can efficiently obtain highly reliable information from various perspectives.

[0492] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0493] Step 1:

[0494] The user enters a question

[0495] A user uses a terminal to input a question, for example, "Tell me some good mystery books to read."

[0496] Input: The question typed by the user.

[0497] Output: The question is sent from the terminal to the server.

[0498] Specific behavior:

[0499] The user enters a question into the interface of their smartphone or PC and presses the send button.

[0500] At this time, the device sends the question data as an HTTP POST request to the specified URL on the server.

[0501] Step 2:

[0502] The server receives and parses the query

[0503] The server receives a question sent by a user.

[0504] Input: The question received from the user.

[0505] Output: Data with key keywords and concepts extracted.

[0506] Specific behavior:

[0507] The server receives the HTTP request and extracts the question data.

[0508] Next, a natural language processing engine (e.g., Google NLP API or SpaCy) is launched to analyze the question.

[0509] Key keywords such as "mystery," "easy to read," and "book" are extracted from the question and temporarily stored.

[0510] Step 3:

[0511] The server selects the target user group

[0512] The server selects a group of users with different perspectives.

[0513] Input: Question analysis results and user profile data.

[0514] Output: A list of target users and a recommendation request.

[0515] Specific behavior:

[0516] The server retrieves user profile data (reading frequency, occupation, etc.) from a database (e.g. MySQL).

[0517] Based on this profile data, target user groups are selected, such as people who don't read many books, people who read a lot of books, and editors.

[0518] After the selection, a recommendation request for "easy-to-read mystery books" is generated based on the analysis results and sent via email or in-app notification.

[0519] Step 4:

[0520] Target users provide recommendations

[0521] The target user receives the recommendation request and enters their opinion or recommendation from their own perspective.

[0522] Input: Recommendation request and target user's opinion.

[0523] Output: The recommendation is sent to the server.

[0524] Specific behavior:

[0525] In response to the recommendation request received by the target user, the user inputs their opinion, such as "Higashino Keigo's works are easy to read," into their own device.

[0526] The input recommendation is sent again as an HTTP POST request to the specified URL on the server.

[0527] Step 5:

[0528] The server evaluates opinions and recommendations

[0529] The server evaluates the collected opinions and recommendations using natural language processing techniques and evaluation algorithms.

[0530] Input: Collected testimonials.

[0531] Output: Evaluation of each opinion's usefulness and overlap.

[0532] Specific behavior:

[0533] The server stores the received recommendation opinion data in a database.

[0534] We use natural language processing models (e.g., BERT and GPT-3) and evaluation algorithms to evaluate the reliability and overlap of each opinion.

[0535] The evaluation results are stored in a database.

[0536] Step 6:

[0537] The server generates a recommendation list and provides it to the user.

[0538] The server generates a multifaceted recommendation list based on the evaluation results and sends it to the terminal.

[0539] Input: Evaluation result data.

[0540] Output: The recommendation list will be available on your device.

[0541] Specific behavior:

[0542] The server uses the evaluation results to generate a multifaceted recommendation list, such as "Works by Higashino Keigo," "Works by Agatha Christie," or "Mystery novels for beginners recommended by famous editors."

[0543] The recommendation list is sent to the device in JSON format.

[0544] The user can view this recommendation list on the terminal and obtain the information they need.

[0545] The above are the specific processing steps of the program of this system.

[0546] (Application example 1)

[0547] 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."

[0548] When it comes to electronic payment services, it is difficult for users to efficiently search for low-cost, secure remittance methods and payment methods that meet their specific needs, and there is a lack of accurate and reliable information from various perspectives.

[0549] 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.

[0550] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, means for analyzing questions about electronic payment services and providing recommendations from various perspectives, and means for visualizing and providing the recommendation list to the user, thereby enabling the user to efficiently obtain recommendation information from multiple perspectives.

[0551] A "user" is an individual or organization that utilizes the system to enter questions and obtain information.

[0552] A "question" is a query that seeks information for a user to enter into the system.

[0553] "Keywords" are the main nouns, verbs, adjectives, and other important words contained in the query.

[0554] A "phrase" is a sub-clause that has a specific meaning and is made up of a group of words contained in a question.

[0555] A "user group" is a group consisting of multiple users with different perspectives.

[0556] A "recommendation request" is a request for information sent to a group of users based on detected keywords or phrases.

[0557] A "response" is an opinion or recommendation provided by a group of users in response to a recommendation request.

[0558] "Evaluation" is the process of determining the usefulness and redundancy of responses using natural language processing techniques and evaluation algorithms.

[0559] A "multifaceted recommendation list" is a list of recommendation information generated based on evaluation results from different perspectives.

[0560] "Server" means a computer system that receives and analyzes questions, sends recommendation requests to a group of users, collects and evaluates responses, and generates a recommendation list.

[0561] A "natural language processing engine" is software that analyzes text data and extracts keywords and phrases.

[0562] An "evaluation algorithm" is a program that automatically evaluates the usefulness and redundancy of responses.

[0563] An "electronic payment service" is an online platform or application that enables users to conduct financial transactions.

[0564] "Visualization" is the process of presenting information to a user in an easy-to-view format.

[0565] The system of the present invention provides information from multiple perspectives in response to questions about electronic payment services entered by users. The following describes specific embodiments of the invention. The system is operated using the following hardware and software.

[0566] Hardware:

[0567] Smartphone: A device where users can enter questions and receive and view results.

[0568] Server: A computer system that analyzes questions, sends recommendation requests, collects and evaluates responses, and generates recommendation lists.

[0569] software:

[0570] Natural language processing engine (Spacy): Analyzes questions and extracts key keywords and phrases

[0571] Evaluation algorithm: Evaluating the usefulness and redundancy of responses using natural language processing techniques

[0572] REST API: A communication method for collecting and sending recommendation information

[0573] Data processing and calculation:

[0574] 1. Receiving questions from users

[0575] A user uses a smartphone to type in a question such as "Please tell me a low-cost and safe way to send money overseas" and submit it.

[0576] 2. Question Analysis

[0577] The server analyzes the received question using a natural language processing engine (Spacy) and extracts key keywords (e.g., "low cost," "safety," "overseas remittance").

[0578] 3. Selecting a group of users with different perspectives

[0579] The server selects a plurality of user groups with different viewpoints, such as emphasis on cost, emphasis on safety, emphasis on frequency of use, etc.

[0580] 4. Generate and send a recommendation request

[0581] The server generates and transmits recommendation requests based on the extracted keywords to each selected user group.

[0582] 5. Collecting responses

[0583] Collect responses from each user group (e.g., "cost-conscious users would like a low-cost remittance method," "safety-conscious users would like the most secure remittance method," etc.).

[0584] 6. Evaluating Responses

[0585] The server uses a rating algorithm to assess the usefulness and duplication of the responses and stores the results in a database.

[0586] 7. Creating and providing a multifaceted recommendation list

[0587] Based on the evaluation results, the server generates a multifaceted recommendation list (e.g., "low-cost overseas remittance methods," "safety-oriented overseas remittance methods," etc.) and sends it to the user's smartphone. The user can visualize and view these recommendation lists on their smartphone.

[0588] Examples:

[0589] For example, if a user asks, "What is a low-cost and safe way to send money overseas?", the system extracts keywords such as "low-cost," "safe," and "overseas remittance." It then sends recommendation requests to groups of users with different perspectives, such as those prioritizing cost, safety, or frequency of use. Once the responses are collected, the server evaluates them using natural language processing technology and evaluation algorithms to create a multifaceted recommendation list. Finally, this recommendation list is sent to the user's smartphone, where the user can visualize and review it.

[0590] Example prompt sentence:

[0591] Please tell me a low-cost and safe way to send money overseas.

[0592] In this way, the system of the present invention helps users to efficiently obtain information about electronic payment services.

[0593] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0594] Step 1:

[0595] The user inputs a question using a smartphone. For example, they input a prompt such as "Please tell me a low-cost and safe way to send money overseas" and press the send button. The input question is sent to the server.

[0596] Step 2:

[0597] The server analyzes the received question using a natural language processing engine (Spacy). Specifically, it analyzes the question (input) and extracts key keywords (such as "low cost," "safety," and "overseas remittance") (data processing). The extracted keywords are used as input for the next processing step.

[0598] Step 3:

[0599] The server selects a user group with different perspectives, such as cost priority, safety priority, or frequency of use priority, from the database. The result of this user group selection becomes the input for generating a recommendation request.

[0600] Step 4:

[0601] The server generates and sends a recommendation request based on the question to each selected user group. Specifically, it creates a recommendation request in the form of a question appropriate for each user group based on the extracted keywords, and sends it via a communication method (such as a REST API). The output of this step is the generated recommendation request.

[0602] Step 5:

[0603] The selected users respond to the recommendation request. As a response, they send recommendation information (e.g., "low-cost remittance methods," "secure remittance methods," etc.) to the server. The response is received by the server.

[0604] Step 6:

[0605] The server analyzes the received responses using an evaluation algorithm. Specifically, it evaluates the usefulness and redundancy of each response using natural language processing technology, and stores the evaluation results in a database. These results serve as input for generating the next recommendation list.

[0606] Step 7:

[0607] The server generates a multifaceted recommendation list based on the evaluation results. Based on the output of the evaluation algorithm, it integrates and organizes the optimal recommendation information from each perspective and presents it in a format that is easy for the user to understand. This recommendation list is the final output to the user.

[0608] Step 8:

[0609] The server sends the generated recommendation list to the user's smartphone, where the user can visualize and view the recommendation list. For example, the list contains recommendations from various perspectives, such as "low-cost remittance methods" and "safe remittance methods."

[0610] In this way, a system is realized that allows users to input questions about electronic payment services and efficiently obtain useful information from multiple perspectives.

[0611] 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.

[0612] The present invention provides a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to enable the user to efficiently search for information in areas in which the user is unfamiliar. Specific embodiments of the system of the present invention will be described below.

[0613] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" and presses the send button, the question is sent to the server. At this point, the emotion engine recognizes the emotion of the user when they input their question. For example, if the user is excited when inputting their question, that emotion information is also sent to the server.

[0614] The server receives the user's question and emotional information. The server analyzes the question and emotional information using a natural language processing (NLP) engine and an emotional engine. In this case, the server extracts key keywords such as "mystery," "easy to read," and "book," as well as the user's emotional state (e.g., excitement, confusion, etc.). The analysis results are temporarily stored in storage.

[0615] The server then selects user groups with different perspectives based on the user's emotional state. For example, if the emotion engine determines that the user is confused, it will select a user group with a perspective suitable for solving the problem. The user groups include people who don't read books often, people who read books often, editors, etc.

[0616] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their opinions and recommendations from their own perspectives. For example, "Keigo Higashino's works are easy to read."

[0617] When a response from a target user is sent to the server, the server receives the recommendation opinion and evaluates the response using natural language processing technology and evaluation algorithms. The evaluation is based on usefulness, redundancy, and emotional state. For example, recommendations that provide solutions to a confused user are prioritized.

[0618] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the terminal. The user can view this recommendation list on the terminal. For example, it may contain information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0619] For example, if a user asks, "Recommend some easy-to-read mystery books," and the emotion engine recognizes that the user is excited, the server will incorporate many recommendations that have elements that will entertain the user. For someone who doesn't read many books, "Works by Higashino Keigo" might be recommended, for a person who reads a lot of books, "Works by Agatha Christie" might be recommended, and for an editor, "Mystery novels for beginners recommended by a famous editor" might be recommended. By integrating these recommendations and providing them to the user, the system can obtain information that is multifaceted and takes emotions into consideration.

[0620] This concludes the description of the embodiments of the present invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, and further analyzes user emotions to more appropriately provide users with the information they desire.

[0621] The processing flow will be explained below.

[0622] Step 1:

[0623] The user uses the device to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button. The device simultaneously captures the user's emotions.

[0624] Step 2:

[0625] The user's question and emotion data are transmitted from the terminal to the server.

[0626] Step 3:

[0627] A server receives the user's question and emotion data.

[0628] Step 4:

[0629] The server uses a natural language processing (NLP) engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[0630] Step 5:

[0631] The server uses an emotion engine to analyze the emotion data and identify the user's emotional state, such as "excited" or "confused."

[0632] Step 6:

[0633] The server stores the analysis results and emotion data in temporary storage.

[0634] Step 7:

[0635] The server selects a group of users with different perspectives based on the emotional state of the users. For example, for a confused user, it preferentially selects a user who is good at providing solutions.

[0636] Step 8:

[0637] The server generates recommendation requests based on the analysis results for a selected group of users, adjusting the tone and content of the requests depending on their emotional state.

[0638] Step 9:

[0639] The server sends recommendation requests to a selected set of users.

[0640] Step 10:

[0641] The selected target user receives the recommendation request at the terminal.

[0642] Step 11:

[0643] The target user inputs a recommendation from their own perspective. For example, they might type, "Keigo Higashino's works are easy to read," and then press the send button.

[0644] Step 12:

[0645] The recommendation opinions are transmitted from the target user terminal to the server.

[0646] Step 13:

[0647] The server receives the recommendations.

[0648] Step 14:

[0649] The server evaluates each recommendation received using natural language processing technology and an evaluation algorithm, taking into account not only usefulness and redundancy but also emotional state.

[0650] Step 15:

[0651] The server stores the evaluation results in a database.

[0652] Step 16:

[0653] The server generates a multifaceted recommendation list based on the evaluated opinions, and the content is arranged and emphasized according to the user's emotional state.

[0654] Step 17:

[0655] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[0656] Step 18:

[0657] The server sends the formatted recommendation list to the user's terminal.

[0658] Step 19:

[0659] The terminal receives the recommendation list from the server.

[0660] Step 20:

[0661] The user reviews the recommendation list received on their device and obtains multifaceted, emotion-based information, such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[0662] The above are the detailed processing steps of the system that combines the emotion engine.

[0663] Example 2

[0664] 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."

[0665] Conventional information recommendation systems are limited to providing general recommendations in response to questions entered by users, and it is difficult to provide multifaceted information that takes into account the user's emotions and circumstances. As a result, there are many cases where users' needs cannot be fully met. Specifically, the problem is that the information provided is inappropriate because the emotional state and background information of the user when entering a question are not taken into account.

[0666] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0667] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for recognizing and receiving user emotional information, means for selecting a group of users with different perspectives based on the emotional information and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, and means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user. This enables multifaceted and advanced information recommendations that take into account the user's emotions and background information.

[0668] A "user" is an individual or group who uses the system to enter questions and receive information.

[0669] A "terminal" is an electronic device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[0670] A "server" is a central processing unit that receives a user's query, analyzes it, processes it, and provides appropriate information.

[0671] A "question" is text or voice data entered by a user about which information he or she wishes to obtain.

[0672] "Emotional information" is data related to the emotional state (e.g., excitement, confusion, etc.) expressed by the user when entering a question.

[0673] A "natural language processing engine" is a software technology that analyzes user questions and extracts key keywords and phrases.

[0674] An "emotion engine" is a software technology that analyzes a user's emotional state.

[0675] A "recommendation request" is a request for information that the server generates and transmits to a group of users with different viewpoints.

[0676] A "user group" is a group of users selected by the server who have different perspectives and knowledge.

[0677] A "response" is an opinion or piece of information that a group of users provides in response to a recommendation request.

[0678] The "rating means" is the process by which the server evaluates the usefulness and redundancy of responses using natural language processing techniques and rating algorithms.

[0679] A "recommendation list" is a list of information generated by the server based on the evaluation results, and provides the user with optimal recommendations from multiple perspectives.

[0680] The present invention is a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to efficiently search for information in areas in which the user is unfamiliar.

[0681] System configuration

[0682] Hardware

[0683] 1. Device: PC, smartphone, tablet, etc.

[0684] 2. Server: Central processing unit.

[0685] software

[0686] 1. Natural Language Processing Engine (NLP): Analyzes the question and extracts key keywords and phrases.

[0687] 2. Emotion engine: Recognize and analyze the user's emotional information.

[0688] Data processing and calculation

[0689] 1. Receiving user questions:

[0690] The terminal receives the user's question and sends it to the server.

[0691] 2. Recognition of emotional information:

[0692] The device's built-in emotion engine recognizes the emotion the user is feeling when entering a question and transmits it to the server.

[0693] 3. Question and emotion analysis:

[0694] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases.

[0695] At the same time, the emotion engine analyzes emotional information to understand the user's emotional state.

[0696] 4. User Group Selection:

[0697] The server selects a group of users with different perspectives based on the analysis results. Selection criteria include emotional information and past recommendation history.

[0698] 5. Generate and send a recommendation request:

[0699] The server generates and sends recommendation requests to a selected group of users, including key keywords and user emotion information.

[0700] 6. Collect and evaluate responses from target users:

[0701] The server collects responses from the target users and rates the responses using natural language processing techniques and rating algorithms.

[0702] 7. Generating and serving recommendation lists:

[0703] The server generates a multifaceted recommendation list based on the evaluation results and transmits it to the terminal for provision to the user.

[0704] Specific examples

[0705] The user uses a device to enter a question such as "Tell me about an easy-to-read mystery book" and presses the send button. The device's built-in emotion engine recognizes the user's excited state and sends this information along with the question to the server. The server receives and analyzes the question and emotion information, extracting key keywords such as "mystery," "easy to read," and "book" as well as the emotion information of "excitement."

[0706] The server then selects a group of users with appropriate perspectives, generates a recommendation request, and sends it. For example, responses are collected from people who don't read many books with perspectives suitable for problem solving, people who read a lot of books, editors, and others, and evaluated. For example, responses such as "Keigo Higashino's works are easy to read" are collected.

[0707] The server evaluates the responses and generates a multifaceted recommendation list, which is then formatted and sent to the device in a user-friendly format.The user can then browse on their device "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," and more.

[0708] Prompt Sentence Examples

[0709] "User is looking for a mystery, easy-to-read book. Their emotional state is excitement. What are your recommendations?"

[0710] Generative AI Models

[0711] The system uses a generative AI model to generate prompts for recommendation requests and collect responses from an appropriate set of users.

[0712] By using the above method, the present invention realizes multifaceted and sophisticated information recommendation that takes into account the user's emotions and background information.

[0713] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0714] Step 1:

[0715] The user inputs a question using the terminal. For example, they input "Tell me about an easy-to-read mystery book" and press the send button. (Input) User's question (Output) Question data sent from the terminal to the server

[0716] Step 2:

[0717] The device uses an emotion engine to recognize the user's emotions. Specifically, emotions are analyzed using a facial recognition camera and voice input. (Input) User's facial expressions and voice. (Output) User's emotional information (e.g., excitement).

[0718] Step 3:

[0719] The device sends question data and emotion information to the server. (Input) Question data, emotion information (Output) Data transmission to the server

[0720] Step 4:

[0721] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases. (Input) Question data (Output) Key keywords (e.g., "mystery," "easy to read," "book")

[0722] Step 5:

[0723] The server analyzes the emotional information using an emotion engine and grasps the user's emotional state. (Input) Emotional information (Output) Analyzed emotional state (e.g., excitement)

[0724] Step 6:

[0725] The server selects a group of users with different perspectives based on key keywords and emotional information. Selection criteria include past recommendation history and expertise. (Input) Key keywords, emotional information (Output) Selected user group (e.g., frequent readers, editors)

[0726] Step 7:

[0727] The server generates and sends a recommendation request to a group of selected users. The recommendation request includes key keywords and emotion information. (Input) Key keywords, emotion information (Output) Send recommendation request

[0728] Step 8:

[0729] The target user inputs their opinion or recommendation based on the recommendation request and sends it to the server. For example, they send an opinion such as "Keigo Higashino's works are easy to read." (Input) Recommendation request (Output) Response from the target user

[0730] Step 9:

[0731] The server receives the response from the target user and evaluates the response content using natural language processing technology and evaluation algorithms. Evaluation criteria include usefulness, redundancy, emotional state, etc. (Input) Response from the target user (Output) Evaluation result (e.g., opinion with high usefulness)

[0732] Step 10:

[0733] The server generates a multifaceted recommendation list based on the evaluation results. The recommendation list contains information to meet the user's needs. (Input) Evaluation results (Output) Recommendation list

[0734] Step 11:

[0735] The server formats the generated recommendation list into a format that is easy for the user to provide, and sends it to the terminal. (Input) Recommendation list (Output) Sending the formatted recommendation list

[0736] Step 12:

[0737] The user browses the recommendation list on the device and makes a selection from the provided recommendation information. For example, they browse "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," etc. (Input) Formatted recommendation list (Output) User's selection and browsing

[0738] (Application example 2)

[0739] 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."

[0740] The problem is that there is a lack of methods to provide recommendation information from multiple perspectives, especially considering the user's emotional state, when collecting information about a product category that the user is not familiar with. Conventional systems have had difficulty making appropriate recommendations that take into account not only the content of the user's question but also the user's emotional state.

[0741] 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 receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for detecting the user's emotional state using an emotion detection engine, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question and emotional information, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluations and transmitting it to the user, and means for displaying the recommendation list on the user terminal. This makes it possible to provide appropriate recommendation information that takes into account the user's emotional state from a multifaceted perspective for product categories in which the user is not familiar.

[0742] The term "user" refers to a person who uses an information system, and in particular, a person who inputs a question to the system of the present invention and receives a reply.

[0743] The "means for receiving a question" is a function or device that allows the system to obtain a question input from a user.

[0744] "Means for analyzing questions and extracting key keywords and phrases" refers to a function or device that uses natural language processing technology to understand the content of a user's question and extract important words and phrases.

[0745] An "emotion detection engine" is a software or hardware device that analyzes and determines the emotional state of a user at the time of input.

[0746] The "means for selecting a group of users with different viewpoints" is a function or device for selecting other users with various backgrounds and knowledge based on the user's emotional state and question content.

[0747] The "means for sending a recommendation request" is a function or device for sending a request based on the question content and emotional information of a user to a selected group of users.

[0748] The "means for collecting and evaluating responses" is a function or device for collecting responses from other users who have received a recommendation request and evaluating the content of the responses.

[0749] The "means for generating and transmitting a multifaceted recommendation list" is a function or device for compiling recommendation information that takes into account various perspectives based on collected responses into a list format and providing this to the user.

[0750] A "user terminal" is a device that a user uses to interact with the system and to display a recommendation list from the system of the present invention.

[0751] The present invention is a system that efficiently searches for information on products in areas that the user is unfamiliar with, and provides recommendation information from multiple perspectives that take into account the user's emotional state. Here, a product recommendation system in a virtual store will be described as a specific embodiment.

[0752] First, a user inputs a question using a smartphone. For example, by typing "Tell me about drones for beginners" and pressing the send button, the question is sent to the server. Here, an emotion detection engine (e.g., Microsoft Azure Face API) is used to detect the emotional state of the user at the time of input. For example, if the user is detected to be excited, that emotional information is also sent to the server along with the question.

[0753] The server receives the question and emotion information and analyzes the question using a generative AI model (e.g., OpenAI GPT-3). During this analysis, key keywords and phrases are extracted, resulting in important keywords such as "for beginners" and "drone." The analysis results and emotion information are temporarily stored in storage.

[0754] Next, the server selects user groups with different perspectives. If the emotion detection engine determines that the user is excited, it selects user groups that can make recommendations from a perspective that has an entertaining element. For example, it includes users who do not read books often, users who frequently use products, and experts.

[0755] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their own recommendations. For example, they can receive specific recommendations such as "easy-to-use drones for beginners."

[0756] When the target user's response is sent to the server, the server receives the recommendation and evaluates the response using natural language processing techniques and evaluation algorithms. The evaluation includes checking usefulness and redundancy, and also evaluates the response based on emotional state. For example, an excited user will be given priority over recommendations that are likely to be interesting.

[0757] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server then formats the recommendation list in a format that is easy for the user to provide and sends it to the user's smartphone. The user can view the recommendation list on their smartphone and check the details. For example, the list may include information such as "easy-to-use drones for beginners," "popular drones for beginners," and "drones recommended by experts."

[0758] As a concrete example, the following is an example of a prompt sentence when a user asks, "Tell me about drones for beginners," and the emotion engine recognizes that the user is excited.

[0759] Prompt: "Tell me about drones for beginners. I'm excited."

[0760] This allows the user to obtain recommendation information from multiple perspectives that take into account their emotional state, enabling them to select appropriate products.

[0761] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0762] Step 1:

[0763] A user inputs a question using a smartphone terminal. For example, they input "Tell me about drones for beginners." At this point, the input data is the user's question. The input question is sent from the terminal to the server.

[0764] Step 2:

[0765] The server receives the question and analyzes the user's emotional state using an emotion detection engine (e.g., Microsoft Azure Face API). This analysis yields emotional information such as excitement, confusion, apprehension, and interest. The acquired emotional information is stored on the server along with the question content.

[0766] Step 3:

[0767] The server analyzes the question using a generative AI model (e.g., OpenAI GPT-3). By analyzing the question, key keywords and phrases are extracted. For example, keywords such as "for beginners" and "drone" are obtained. The analysis results are temporarily stored in storage.

[0768] Step 4:

[0769] The server selects a group of users with different perspectives based on their emotional state and the analysis results. If the emotion engine determines that the user is excited, it extracts users who can make recommendations with entertaining elements. In this case, it selects users from the database who are suitable for the user's excited state (e.g., experienced users, experts, etc.).

[0770] Step 5:

[0771] The server generates and sends recommendation requests based on the question content and emotion information to the selected group of users. The requests include the analyzed keywords and emotion information. The selected target users receive the recommendation requests and input their opinions and recommendations from their own perspectives.

[0772] Step 6:

[0773] When a response from a target user is sent to the server, the server receives a recommendation opinion. The server evaluates the response using natural language processing technology and an evaluation algorithm. The evaluation includes the usefulness, redundancy, and priority based on the emotional state of the response. The evaluation results are stored in a database.

[0774] Step 7:

[0775] The server generates a multifaceted recommendation list based on the evaluated opinions. For example, it may generate lists such as "Easy-to-use drones for beginners," "Popular drones for beginners," and "Drones recommended by experts." This recommendation list is formatted to be easily provided to users.

[0776] Step 8:

[0777] The server then sends the generated recommendation list to the user's smartphone. The user can then receive the recommendation list on their smartphone and check the details. This allows the user to obtain appropriate recommendation information that takes into account their emotional state.

[0778] This allows the user to obtain appropriate recommendation information from multiple perspectives that take into account the user's emotional state, even for product categories that the user is not familiar with.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] [Third embodiment]

[0783] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0784] 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.

[0785] 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).

[0786] 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.

[0787] 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.

[0788] 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).

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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."

[0795] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments of the system of the present invention will be described below.

[0796] First, the user inputs a question using the terminal. For example, the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, which sends the question to the server.

[0797] The server uses a natural language processing (NLP) engine to analyze the received question. The server analyzes the question and extracts key keywords and phrases. In this case, "mystery," "easy to read," and "book" are extracted. The analysis results are temporarily stored in storage.

[0798] Next, the server selects a group of users with different perspectives, including people who read less books, people who read more books, editors, etc. The server generates and sends recommendation requests based on the analysis results to the selected users.

[0799] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, "Keigo Higashino's works are easy to read." When the target user sends the recommendation to the server, the server receives it.

[0800] The server then evaluates the collected opinions and recommendations, using natural language processing technology and evaluation algorithms to determine the usefulness and redundancy of each opinion, and stores the evaluation results in a database.

[0801] After the evaluation is complete, the server generates a multifaceted recommendation list based on the evaluation results. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the device. The user can view this recommendation list on their device. For example, the list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0802] In this way, the system of the present invention uses recommendations from different perspectives to provide information from multiple angles in areas that the user is unfamiliar with, allowing the user to efficiently obtain reliable and useful information.

[0803] For example, if a user asks, "Tell me some easy-to-read mystery books," someone who doesn't read much might recommend "Works by Keigo Higashino," someone who reads a lot might recommend "Works by Agatha Christie," and an editor might recommend "Mystery novels for beginners recommended by a famous editor." By integrating this recommendation information and providing it to the user, the system allows users to obtain information from multiple perspectives.

[0804] The above is a description of the mode for carrying out the invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, thereby providing users with the information they desire.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] The user uses the terminal to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button.

[0808] Step 2:

[0809] The user's question is sent from the terminal to the server.

[0810] Step 3:

[0811] The server receives the user's query.

[0812] Step 4:

[0813] The server uses a natural language processing engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[0814] Step 5:

[0815] The server stores the analysis results in temporary storage.

[0816] Step 6:

[0817] The server selects a group of users with different perspectives, including casual readers, frequent readers, editors, etc.

[0818] Step 7:

[0819] The server generates recommendation requests based on the questions for a selected set of users.

[0820] Step 8:

[0821] The server sends recommendation requests to a selected set of users.

[0822] Step 9:

[0823] Selected users with terminals receive recommendation requests.

[0824] Step 10:

[0825] The selected user enters a recommendation from their own perspective. For example, they can write, "Higashino Keigo's works are easy to read," and then press the submit button.

[0826] Step 11:

[0827] The recommendation opinion is transmitted from the selected user terminal to the server.

[0828] Step 12:

[0829] The server receives the recommendations.

[0830] Step 13:

[0831] The server evaluates each recommendation received using natural language processing technology and evaluation algorithms to determine usefulness and redundancy.

[0832] Step 14:

[0833] The server stores the evaluation results in a database.

[0834] Step 15:

[0835] The server generates a multifaceted recommendation list based on the evaluated opinions.

[0836] Step 16:

[0837] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[0838] Step 17:

[0839] The server sends the formatted recommendation list to the user's terminal.

[0840] Step 18:

[0841] The terminal receives the recommendation list from the server.

[0842] Step 19:

[0843] The user uses the device to view the received recommendation list, which may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[0844] The above are the processing steps of the program.

[0845] Example 1

[0846] 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."

[0847] Conventional information recommendation systems lack the means to efficiently provide multifaceted information on areas that users are unfamiliar with. This makes it difficult to obtain highly reliable and useful information. The purpose of this invention is to solve these problems and provide multifaceted information from different perspectives.

[0848] 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.

[0849] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and concepts, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, and means for providing the generated recommendation list in a format that the user can view. This enables the user to efficiently obtain reliable and useful information.

[0850] The "means for receiving a question input by a user" refers to a function that enables the server to receive a question input by a user via a terminal.

[0851] "Means for analyzing questions and extracting key keywords and concepts" refers to a function that uses natural language processing technology to analyze received questions and extract key keywords and concepts from them.

[0852] "Means for selecting a group of users with different perspectives and sending recommendation requests based on questions" refers to a function for selecting a target group of users from a database based on user profiles and sending recommendation requests based on the analysis results to that group of users.

[0853] "Means for collecting and evaluating responses from selected users" refers to a function by which the server collects recommendation opinions sent by target users and evaluates the usefulness and overlap of those opinions using natural language processing technology and evaluation algorithms.

[0854] "Means for generating a multifaceted recommendation list based on the evaluation and sending it to the user" refers to a function for creating a recommendation list from various perspectives based on the evaluation results and providing that list to the user.

[0855] "Means for providing the generated recommendation list in a format that can be viewed by the user" refers to a function for adjusting the display format and data format so that the generated recommendation list can be easily viewed by the user on a terminal.

[0856] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments for implementing the present invention will be described in detail below.

[0857] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, the question is sent to the server. At this time, the terminal sends the question data to the specified URL on the server as an HTTP POST request.

[0858] The server uses a natural language processing (NLP) engine to analyze the received question. Specific software such as Google NLP API or SpaCy can be used here. The server analyzes the question and extracts key keywords and concepts. In this case, "mystery," "easy to read," and "book" are extracted. The analyzed data is temporarily stored in the server's storage.

[0859] Next, the server selects user groups with different perspectives. These user groups include casual readers, frequent readers, editors, etc. The server retrieves user profile data from a database (e.g., MySQL) and selects target user groups based on the analysis results. The server then generates recommendation requests and sends them to the selected user groups via email or in-app notifications.

[0860] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, they may say, "Keigo Higashino's works are easy to read." When the target user sends the recommendation from their device to the server, the server receives it and stores it in a database.

[0861] The server evaluates the received opinions and recommendations using natural language processing techniques (e.g., BERT or GPT-3) and evaluation algorithms. The evaluation results are stored in a database, which determines the usefulness and redundancy of each opinion.

[0862] After the evaluation is complete, the server generates a multifaceted recommendation list based on these evaluation results. The generated recommendation list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors." The server then formats this recommendation list into a user-viewable format and sends it to the device in JSON format, for example. The user can view this recommendation list on their device and obtain the information they need.

[0863] For example, if a user asks, "Tell me some easy-to-read mystery books," people who don't read much may recommend "Works by Keigo Higashino," people who read a lot may recommend "Works by Agatha Christie," and editors may recommend "Mystery novels for beginners recommended by famous editors." These recommendations are then combined and provided to the user as a final recommendation list.

[0864] Example prompt sentence:

[0865] "Tell me some easy-to-read mystery books."

[0866] "What are some easy-to-read mystery novels for beginners?"

[0867] "I'd like to know some recommendations for contemporary Japanese mystery writers."

[0868] "What are some classic mystery novels?"

[0869] The above is an embodiment of the present invention. By using this system, users can efficiently obtain highly reliable information from various perspectives.

[0870] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0871] Step 1:

[0872] The user enters a question

[0873] A user uses a terminal to input a question, for example, "Tell me some good mystery books to read."

[0874] Input: The question typed by the user.

[0875] Output: The question is sent from the terminal to the server.

[0876] Specific behavior:

[0877] The user enters a question into the interface of their smartphone or PC and presses the send button.

[0878] At this time, the device sends the question data as an HTTP POST request to the specified URL on the server.

[0879] Step 2:

[0880] The server receives and parses the query

[0881] The server receives a question sent by a user.

[0882] Input: The question received from the user.

[0883] Output: Data with key keywords and concepts extracted.

[0884] Specific behavior:

[0885] The server receives the HTTP request and extracts the question data.

[0886] Next, a natural language processing engine (e.g., Google NLP API or SpaCy) is launched to analyze the question.

[0887] Key keywords such as "mystery," "easy to read," and "book" are extracted from the question and temporarily stored.

[0888] Step 3:

[0889] The server selects the target user group

[0890] The server selects a group of users with different perspectives.

[0891] Input: Question analysis results and user profile data.

[0892] Output: A list of target users and a recommendation request.

[0893] Specific behavior:

[0894] The server retrieves user profile data (reading frequency, occupation, etc.) from a database (e.g. MySQL).

[0895] Based on this profile data, target user groups are selected, such as people who don't read many books, people who read a lot of books, and editors.

[0896] After the selection, a recommendation request for "easy-to-read mystery books" is generated based on the analysis results and sent via email or in-app notification.

[0897] Step 4:

[0898] Target users provide recommendations

[0899] The target user receives the recommendation request and enters their opinion or recommendation from their own perspective.

[0900] Input: Recommendation request and target user's opinion.

[0901] Output: The recommendation is sent to the server.

[0902] Specific behavior:

[0903] In response to the recommendation request received by the target user, the user inputs their opinion, such as "Higashino Keigo's works are easy to read," into their own device.

[0904] The input recommendation is sent again as an HTTP POST request to the specified URL on the server.

[0905] Step 5:

[0906] The server evaluates opinions and recommendations

[0907] The server evaluates the collected opinions and recommendations using natural language processing techniques and evaluation algorithms.

[0908] Input: Collected testimonials.

[0909] Output: Evaluation of each opinion's usefulness and overlap.

[0910] Specific behavior:

[0911] The server stores the received recommendation opinion data in a database.

[0912] We use natural language processing models (e.g., BERT and GPT-3) and evaluation algorithms to evaluate the reliability and overlap of each opinion.

[0913] The evaluation results are stored in a database.

[0914] Step 6:

[0915] The server generates a recommendation list and provides it to the user.

[0916] The server generates a multifaceted recommendation list based on the evaluation results and sends it to the terminal.

[0917] Input: Evaluation result data.

[0918] Output: The recommendation list will be available on your device.

[0919] Specific behavior:

[0920] The server uses the evaluation results to generate a multifaceted recommendation list, such as "Works by Higashino Keigo," "Works by Agatha Christie," or "Mystery novels for beginners recommended by famous editors."

[0921] The recommendation list is sent to the device in JSON format.

[0922] The user can view this recommendation list on the terminal and obtain the information they need.

[0923] The above are the specific processing steps of the program of this system.

[0924] (Application example 1)

[0925] 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."

[0926] When it comes to electronic payment services, it is difficult for users to efficiently search for low-cost, secure remittance methods and payment methods that meet their specific needs, and there is a lack of accurate and reliable information from various perspectives.

[0927] 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.

[0928] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, means for analyzing questions about electronic payment services and providing recommendations from various perspectives, and means for visualizing and providing the recommendation list to the user, thereby enabling the user to efficiently obtain recommendation information from multiple perspectives.

[0929] A "user" is an individual or organization that utilizes the system to enter questions and obtain information.

[0930] A "question" is a query that seeks information for a user to enter into the system.

[0931] "Keywords" are the main nouns, verbs, adjectives, and other important words contained in the query.

[0932] A "phrase" is a sub-clause that has a specific meaning and is made up of a group of words contained in a question.

[0933] A "user group" is a group consisting of multiple users with different perspectives.

[0934] A "recommendation request" is a request for information sent to a group of users based on detected keywords or phrases.

[0935] A "response" is an opinion or recommendation provided by a group of users in response to a recommendation request.

[0936] "Evaluation" is the process of determining the usefulness and redundancy of responses using natural language processing techniques and evaluation algorithms.

[0937] A "multifaceted recommendation list" is a list of recommendation information generated based on evaluation results from different perspectives.

[0938] "Server" means a computer system that receives and analyzes questions, sends recommendation requests to a group of users, collects and evaluates responses, and generates a recommendation list.

[0939] A "natural language processing engine" is software that analyzes text data and extracts keywords and phrases.

[0940] An "evaluation algorithm" is a program that automatically evaluates the usefulness and redundancy of responses.

[0941] An "electronic payment service" is an online platform or application that enables users to conduct financial transactions.

[0942] "Visualization" is the process of presenting information to a user in an easy-to-view format.

[0943] The system of the present invention provides information from multiple perspectives in response to questions about electronic payment services entered by users. The following describes specific embodiments of the invention. The system is operated using the following hardware and software.

[0944] Hardware:

[0945] Smartphone: A device where users can enter questions and receive and view results.

[0946] Server: A computer system that analyzes questions, sends recommendation requests, collects and evaluates responses, and generates recommendation lists.

[0947] software:

[0948] Natural language processing engine (Spacy): Analyzes questions and extracts key keywords and phrases

[0949] Evaluation algorithm: Evaluating the usefulness and redundancy of responses using natural language processing techniques

[0950] REST API: A communication method for collecting and sending recommendation information

[0951] Data processing and calculation:

[0952] 1. Receiving questions from users

[0953] A user uses a smartphone to type in a question such as "Please tell me a low-cost and safe way to send money overseas" and submit it.

[0954] 2. Question Analysis

[0955] The server analyzes the received question using a natural language processing engine (Spacy) and extracts key keywords (e.g., "low cost," "safety," "overseas remittance").

[0956] 3. Selecting a group of users with different perspectives

[0957] The server selects a plurality of user groups with different viewpoints, such as emphasis on cost, emphasis on safety, emphasis on frequency of use, etc.

[0958] 4. Generate and send a recommendation request

[0959] The server generates and transmits recommendation requests based on the extracted keywords to each selected user group.

[0960] 5. Collecting responses

[0961] Collect responses from each user group (e.g., "cost-conscious users would like a low-cost remittance method," "safety-conscious users would like the most secure remittance method," etc.).

[0962] 6. Evaluating Responses

[0963] The server uses a rating algorithm to assess the usefulness and duplication of the responses and stores the results in a database.

[0964] 7. Creating and providing a multifaceted recommendation list

[0965] Based on the evaluation results, the server generates a multifaceted recommendation list (e.g., "low-cost overseas remittance methods," "safety-oriented overseas remittance methods," etc.) and sends it to the user's smartphone. The user can visualize and view these recommendation lists on their smartphone.

[0966] Examples:

[0967] For example, if a user asks, "What is a low-cost and safe way to send money overseas?", the system extracts keywords such as "low-cost," "safe," and "overseas remittance." It then sends recommendation requests to groups of users with different perspectives, such as those prioritizing cost, safety, or frequency of use. Once the responses are collected, the server evaluates them using natural language processing technology and evaluation algorithms to create a multifaceted recommendation list. Finally, this recommendation list is sent to the user's smartphone, where the user can visualize and review it.

[0968] Example prompt sentence:

[0969] Please tell me a low-cost and safe way to send money overseas.

[0970] In this way, the system of the present invention helps users to efficiently obtain information about electronic payment services.

[0971] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0972] Step 1:

[0973] The user inputs a question using a smartphone. For example, they input a prompt such as "Please tell me a low-cost and safe way to send money overseas" and press the send button. The input question is sent to the server.

[0974] Step 2:

[0975] The server analyzes the received question using a natural language processing engine (Spacy). Specifically, it analyzes the question (input) and extracts key keywords (such as "low cost," "safety," and "overseas remittance") (data processing). The extracted keywords are used as input for the next processing step.

[0976] Step 3:

[0977] The server selects a user group with different perspectives, such as cost priority, safety priority, or frequency of use priority, from the database. The result of this user group selection becomes the input for generating a recommendation request.

[0978] Step 4:

[0979] The server generates and sends a recommendation request based on the question to each selected user group. Specifically, it creates a recommendation request in the form of a question appropriate for each user group based on the extracted keywords, and sends it via a communication method (such as a REST API). The output of this step is the generated recommendation request.

[0980] Step 5:

[0981] The selected users respond to the recommendation request. As a response, they send recommendation information (e.g., "low-cost remittance methods," "secure remittance methods," etc.) to the server. The response is received by the server.

[0982] Step 6:

[0983] The server analyzes the received responses using an evaluation algorithm. Specifically, it evaluates the usefulness and redundancy of each response using natural language processing technology, and stores the evaluation results in a database. These results serve as input for generating the next recommendation list.

[0984] Step 7:

[0985] The server generates a multifaceted recommendation list based on the evaluation results. Based on the output of the evaluation algorithm, it integrates and organizes the optimal recommendation information from each perspective and presents it in a format that is easy for the user to understand. This recommendation list is the final output to the user.

[0986] Step 8:

[0987] The server sends the generated recommendation list to the user's smartphone, where the user can visualize and view the recommendation list. For example, the list contains recommendations from various perspectives, such as "low-cost remittance methods" and "safe remittance methods."

[0988] In this way, a system is realized that allows users to input questions about electronic payment services and efficiently obtain useful information from multiple perspectives.

[0989] 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.

[0990] The present invention provides a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to enable the user to efficiently search for information in areas in which the user is unfamiliar. Specific embodiments of the system of the present invention will be described below.

[0991] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" and presses the send button, the question is sent to the server. At this point, the emotion engine recognizes the emotion of the user when they input their question. For example, if the user is excited when inputting their question, that emotion information is also sent to the server.

[0992] The server receives the user's question and emotional information. The server analyzes the question and emotional information using a natural language processing (NLP) engine and an emotional engine. In this case, the server extracts key keywords such as "mystery," "easy to read," and "book," as well as the user's emotional state (e.g., excitement, confusion, etc.). The analysis results are temporarily stored in storage.

[0993] The server then selects user groups with different perspectives based on the user's emotional state. For example, if the emotion engine determines that the user is confused, it will select a user group with a perspective suitable for solving the problem. The user groups include people who don't read books often, people who read books often, editors, etc.

[0994] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their opinions and recommendations from their own perspectives. For example, "Keigo Higashino's works are easy to read."

[0995] When a response from a target user is sent to the server, the server receives the recommendation opinion and evaluates the response using natural language processing technology and evaluation algorithms. The evaluation is based on usefulness, redundancy, and emotional state. For example, recommendations that provide solutions to a confused user are prioritized.

[0996] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the terminal. The user can view this recommendation list on the terminal. For example, it may contain information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[0997] For example, if a user asks, "Recommend some easy-to-read mystery books," and the emotion engine recognizes that the user is excited, the server will incorporate many recommendations that have elements that will entertain the user. For someone who doesn't read many books, "Works by Higashino Keigo" might be recommended, for a person who reads a lot of books, "Works by Agatha Christie" might be recommended, and for an editor, "Mystery novels for beginners recommended by a famous editor" might be recommended. By integrating these recommendations and providing them to the user, the system can obtain information that is multifaceted and takes emotions into consideration.

[0998] This concludes the description of the embodiments of the present invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, and further analyzes user emotions to more appropriately provide users with the information they desire.

[0999] The processing flow will be explained below.

[1000] Step 1:

[1001] The user uses the device to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button. The device simultaneously captures the user's emotions.

[1002] Step 2:

[1003] The user's question and emotion data are transmitted from the terminal to the server.

[1004] Step 3:

[1005] A server receives the user's question and emotion data.

[1006] Step 4:

[1007] The server uses a natural language processing (NLP) engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[1008] Step 5:

[1009] The server uses an emotion engine to analyze the emotion data and identify the user's emotional state, such as "excited" or "confused."

[1010] Step 6:

[1011] The server stores the analysis results and emotion data in temporary storage.

[1012] Step 7:

[1013] The server selects a group of users with different perspectives based on the emotional state of the users. For example, for a confused user, it preferentially selects a user who is good at providing solutions.

[1014] Step 8:

[1015] The server generates recommendation requests based on the analysis results for a selected group of users, adjusting the tone and content of the requests depending on their emotional state.

[1016] Step 9:

[1017] The server sends recommendation requests to a selected set of users.

[1018] Step 10:

[1019] The selected target user receives the recommendation request at the terminal.

[1020] Step 11:

[1021] The target user inputs a recommendation from their own perspective. For example, they might type, "Keigo Higashino's works are easy to read," and then press the send button.

[1022] Step 12:

[1023] The recommendation opinions are transmitted from the target user terminal to the server.

[1024] Step 13:

[1025] The server receives the recommendations.

[1026] Step 14:

[1027] The server evaluates each recommendation received using natural language processing technology and an evaluation algorithm, taking into account not only usefulness and redundancy but also emotional state.

[1028] Step 15:

[1029] The server stores the evaluation results in a database.

[1030] Step 16:

[1031] The server generates a multifaceted recommendation list based on the evaluated opinions, and the content is arranged and emphasized according to the user's emotional state.

[1032] Step 17:

[1033] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[1034] Step 18:

[1035] The server sends the formatted recommendation list to the user's terminal.

[1036] Step 19:

[1037] The terminal receives the recommendation list from the server.

[1038] Step 20:

[1039] The user reviews the recommendation list received on their device and obtains multifaceted, emotion-based information, such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[1040] The above are the detailed processing steps of the system that combines the emotion engine.

[1041] Example 2

[1042] 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."

[1043] Conventional information recommendation systems are limited to providing general recommendations in response to questions entered by users, and it is difficult to provide multifaceted information that takes into account the user's emotions and circumstances. As a result, there are many cases where users' needs cannot be fully met. Specifically, the problem is that the information provided is inappropriate because the emotional state and background information of the user when entering a question are not taken into account.

[1044] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1045] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for recognizing and receiving user emotional information, means for selecting a group of users with different perspectives based on the emotional information and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, and means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user. This enables multifaceted and advanced information recommendations that take into account the user's emotions and background information.

[1046] A "user" is an individual or group who uses the system to enter questions and receive information.

[1047] A "terminal" is an electronic device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[1048] A "server" is a central processing unit that receives a user's query, analyzes it, processes it, and provides appropriate information.

[1049] A "question" is text or voice data entered by a user about which information he or she wishes to obtain.

[1050] "Emotional information" is data related to the emotional state (e.g., excitement, confusion, etc.) expressed by the user when entering a question.

[1051] A "natural language processing engine" is a software technology that analyzes user questions and extracts key keywords and phrases.

[1052] An "emotion engine" is a software technology that analyzes a user's emotional state.

[1053] A "recommendation request" is a request for information that the server generates and transmits to a group of users with different viewpoints.

[1054] A "user group" is a group of users selected by the server who have different perspectives and knowledge.

[1055] A "response" is an opinion or piece of information that a group of users provides in response to a recommendation request.

[1056] The "rating means" is the process by which the server evaluates the usefulness and redundancy of responses using natural language processing techniques and rating algorithms.

[1057] A "recommendation list" is a list of information generated by the server based on the evaluation results, and provides the user with optimal recommendations from multiple perspectives.

[1058] The present invention is a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to efficiently search for information in areas in which the user is unfamiliar.

[1059] System configuration

[1060] Hardware

[1061] 1. Device: PC, smartphone, tablet, etc.

[1062] 2. Server: Central processing unit.

[1063] software

[1064] 1. Natural Language Processing Engine (NLP): Analyzes the question and extracts key keywords and phrases.

[1065] 2. Emotion engine: Recognize and analyze the user's emotional information.

[1066] Data processing and calculation

[1067] 1. Receiving user questions:

[1068] The terminal receives the user's question and sends it to the server.

[1069] 2. Recognition of emotional information:

[1070] The device's built-in emotion engine recognizes the emotion the user is feeling when entering a question and transmits it to the server.

[1071] 3. Question and emotion analysis:

[1072] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases.

[1073] At the same time, the emotion engine analyzes emotional information to understand the user's emotional state.

[1074] 4. User Group Selection:

[1075] The server selects a group of users with different perspectives based on the analysis results. Selection criteria include emotional information and past recommendation history.

[1076] 5. Generate and send a recommendation request:

[1077] The server generates and sends recommendation requests to a selected group of users, including key keywords and user emotion information.

[1078] 6. Collect and evaluate responses from target users:

[1079] The server collects responses from the target users and rates the responses using natural language processing techniques and rating algorithms.

[1080] 7. Generating and serving recommendation lists:

[1081] The server generates a multifaceted recommendation list based on the evaluation results and transmits it to the terminal for provision to the user.

[1082] Specific examples

[1083] The user uses a device to enter a question such as "Tell me about an easy-to-read mystery book" and presses the send button. The device's built-in emotion engine recognizes the user's excited state and sends this information along with the question to the server. The server receives and analyzes the question and emotion information, extracting key keywords such as "mystery," "easy to read," and "book" as well as the emotion information of "excitement."

[1084] The server then selects a group of users with appropriate perspectives, generates a recommendation request, and sends it. For example, responses are collected from people who don't read many books with perspectives suitable for problem solving, people who read a lot of books, editors, and others, and evaluated. For example, responses such as "Keigo Higashino's works are easy to read" are collected.

[1085] The server evaluates the responses and generates a multifaceted recommendation list, which is then formatted and sent to the device in a user-friendly format.The user can then browse on their device "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," and more.

[1086] Prompt Sentence Examples

[1087] "User is looking for a mystery, easy-to-read book. Their emotional state is excitement. What are your recommendations?"

[1088] Generative AI Models

[1089] The system uses a generative AI model to generate prompts for recommendation requests and collect responses from an appropriate set of users.

[1090] By using the above method, the present invention realizes multifaceted and sophisticated information recommendation that takes into account the user's emotions and background information.

[1091] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] The user inputs a question using the terminal. For example, they input "Tell me about an easy-to-read mystery book" and press the send button. (Input) User's question (Output) Question data sent from the terminal to the server

[1094] Step 2:

[1095] The device uses an emotion engine to recognize the user's emotions. Specifically, emotions are analyzed using a facial recognition camera and voice input. (Input) User's facial expressions and voice. (Output) User's emotional information (e.g., excitement).

[1096] Step 3:

[1097] The device sends question data and emotion information to the server. (Input) Question data, emotion information (Output) Data transmission to the server

[1098] Step 4:

[1099] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases. (Input) Question data (Output) Key keywords (e.g., "mystery," "easy to read," "book")

[1100] Step 5:

[1101] The server analyzes the emotional information using an emotion engine and grasps the user's emotional state. (Input) Emotional information (Output) Analyzed emotional state (e.g., excitement)

[1102] Step 6:

[1103] The server selects a group of users with different perspectives based on key keywords and emotional information. Selection criteria include past recommendation history and expertise. (Input) Key keywords, emotional information (Output) Selected user group (e.g., frequent readers, editors)

[1104] Step 7:

[1105] The server generates and sends a recommendation request to a group of selected users. The recommendation request includes key keywords and emotion information. (Input) Key keywords, emotion information (Output) Send recommendation request

[1106] Step 8:

[1107] The target user inputs their opinion or recommendation based on the recommendation request and sends it to the server. For example, they send an opinion such as "Keigo Higashino's works are easy to read." (Input) Recommendation request (Output) Response from the target user

[1108] Step 9:

[1109] The server receives the response from the target user and evaluates the response content using natural language processing technology and evaluation algorithms. Evaluation criteria include usefulness, redundancy, emotional state, etc. (Input) Response from the target user (Output) Evaluation result (e.g., opinion with high usefulness)

[1110] Step 10:

[1111] The server generates a multifaceted recommendation list based on the evaluation results. The recommendation list contains information to meet the user's needs. (Input) Evaluation results (Output) Recommendation list

[1112] Step 11:

[1113] The server formats the generated recommendation list into a format that is easy for the user to provide, and sends it to the terminal. (Input) Recommendation list (Output) Sending the formatted recommendation list

[1114] Step 12:

[1115] The user browses the recommendation list on the device and makes a selection from the provided recommendation information. For example, they browse "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," etc. (Input) Formatted recommendation list (Output) User's selection and browsing

[1116] (Application example 2)

[1117] 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."

[1118] The problem is that there is a lack of methods to provide recommendation information from multiple perspectives, especially considering the user's emotional state, when collecting information about a product category that the user is not familiar with. Conventional systems have had difficulty making appropriate recommendations that take into account not only the content of the user's question but also the user's emotional state.

[1119] 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 receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for detecting the user's emotional state using an emotion detection engine, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question and emotional information, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluations and transmitting it to the user, and means for displaying the recommendation list on the user terminal. This makes it possible to provide appropriate recommendation information that takes into account the user's emotional state from a multifaceted perspective for product categories in which the user is not familiar.

[1120] The term "user" refers to a person who uses an information system, and in particular, a person who inputs a question to the system of the present invention and receives a reply.

[1121] The "means for receiving a question" is a function or device that allows the system to obtain a question input from a user.

[1122] "Means for analyzing questions and extracting key keywords and phrases" refers to a function or device that uses natural language processing technology to understand the content of a user's question and extract important words and phrases.

[1123] An "emotion detection engine" is a software or hardware device that analyzes and determines the emotional state of a user at the time of input.

[1124] The "means for selecting a group of users with different viewpoints" is a function or device for selecting other users with various backgrounds and knowledge based on the user's emotional state and question content.

[1125] The "means for sending a recommendation request" is a function or device for sending a request based on the question content and emotional information of a user to a selected group of users.

[1126] The "means for collecting and evaluating responses" is a function or device for collecting responses from other users who have received a recommendation request and evaluating the content of the responses.

[1127] The "means for generating and transmitting a multifaceted recommendation list" is a function or device for compiling recommendation information that takes into account various perspectives based on collected responses into a list format and providing this to the user.

[1128] A "user terminal" is a device that a user uses to interact with the system and to display a recommendation list from the system of the present invention.

[1129] The present invention is a system that efficiently searches for information on products in areas that the user is unfamiliar with, and provides recommendation information from multiple perspectives that take into account the user's emotional state. Here, a product recommendation system in a virtual store will be described as a specific embodiment.

[1130] First, a user inputs a question using a smartphone. For example, by typing "Tell me about drones for beginners" and pressing the send button, the question is sent to the server. Here, an emotion detection engine (e.g., Microsoft Azure Face API) is used to detect the emotional state of the user at the time of input. For example, if the user is detected to be excited, that emotional information is also sent to the server along with the question.

[1131] The server receives the question and emotion information and analyzes the question using a generative AI model (e.g., OpenAI GPT-3). During this analysis, key keywords and phrases are extracted, resulting in important keywords such as "for beginners" and "drone." The analysis results and emotion information are temporarily stored in storage.

[1132] Next, the server selects user groups with different perspectives. If the emotion detection engine determines that the user is excited, it selects user groups that can make recommendations from a perspective that has an entertaining element. For example, it includes users who do not read books often, users who frequently use products, and experts.

[1133] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their own recommendations. For example, they can receive specific recommendations such as "easy-to-use drones for beginners."

[1134] When the target user's response is sent to the server, the server receives the recommendation and evaluates the response using natural language processing techniques and evaluation algorithms. The evaluation includes checking usefulness and redundancy, and also evaluates the response based on emotional state. For example, an excited user will be given priority over recommendations that are likely to be interesting.

[1135] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server then formats the recommendation list in a format that is easy for the user to provide and sends it to the user's smartphone. The user can view the recommendation list on their smartphone and check the details. For example, the list may include information such as "easy-to-use drones for beginners," "popular drones for beginners," and "drones recommended by experts."

[1136] As a concrete example, the following is an example of a prompt sentence when a user asks, "Tell me about drones for beginners," and the emotion engine recognizes that the user is excited.

[1137] Prompt: "Tell me about drones for beginners. I'm excited."

[1138] This allows the user to obtain recommendation information from multiple perspectives that take into account their emotional state, enabling them to select appropriate products.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] A user inputs a question using a smartphone terminal. For example, they input "Tell me about drones for beginners." At this point, the input data is the user's question. The input question is sent from the terminal to the server.

[1142] Step 2:

[1143] The server receives the question and analyzes the user's emotional state using an emotion detection engine (e.g., Microsoft Azure Face API). This analysis yields emotional information such as excitement, confusion, apprehension, and interest. The acquired emotional information is stored on the server along with the question content.

[1144] Step 3:

[1145] The server analyzes the question using a generative AI model (e.g., OpenAI GPT-3). By analyzing the question, key keywords and phrases are extracted. For example, keywords such as "for beginners" and "drone" are obtained. The analysis results are temporarily stored in storage.

[1146] Step 4:

[1147] The server selects a group of users with different perspectives based on their emotional state and the analysis results. If the emotion engine determines that the user is excited, it extracts users who can make recommendations with entertaining elements. In this case, it selects users from the database who are suitable for the user's excited state (e.g., experienced users, experts, etc.).

[1148] Step 5:

[1149] The server generates and sends recommendation requests based on the question content and emotion information to the selected group of users. The requests include the analyzed keywords and emotion information. The selected target users receive the recommendation requests and input their opinions and recommendations from their own perspectives.

[1150] Step 6:

[1151] When a response from a target user is sent to the server, the server receives a recommendation opinion. The server evaluates the response using natural language processing technology and an evaluation algorithm. The evaluation includes the usefulness, redundancy, and priority based on the emotional state of the response. The evaluation results are stored in a database.

[1152] Step 7:

[1153] The server generates a multifaceted recommendation list based on the evaluated opinions. For example, it may generate lists such as "Easy-to-use drones for beginners," "Popular drones for beginners," and "Drones recommended by experts." This recommendation list is formatted to be easily provided to users.

[1154] Step 8:

[1155] The server then sends the generated recommendation list to the user's smartphone. The user can then receive the recommendation list on their smartphone and check the details. This allows the user to obtain appropriate recommendation information that takes into account their emotional state.

[1156] This allows the user to obtain appropriate recommendation information from multiple perspectives that take into account the user's emotional state, even for product categories that the user is not familiar with.

[1157] 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.

[1158] 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.

[1159] 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.

[1160] [Fourth embodiment]

[1161] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1162] 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.

[1163] 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).

[1164] 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.

[1165] 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.

[1166] 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).

[1167] 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.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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."

[1174] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments of the system of the present invention will be described below.

[1175] First, the user inputs a question using the terminal. For example, the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, which sends the question to the server.

[1176] The server uses a natural language processing (NLP) engine to analyze the received question. The server analyzes the question and extracts key keywords and phrases. In this case, "mystery," "easy to read," and "book" are extracted. The analysis results are temporarily stored in storage.

[1177] Next, the server selects a group of users with different perspectives, including people who read less books, people who read more books, editors, etc. The server generates and sends recommendation requests based on the analysis results to the selected users.

[1178] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, "Keigo Higashino's works are easy to read." When the target user sends the recommendation to the server, the server receives it.

[1179] The server then evaluates the collected opinions and recommendations, using natural language processing technology and evaluation algorithms to determine the usefulness and redundancy of each opinion, and stores the evaluation results in a database.

[1180] After the evaluation is complete, the server generates a multifaceted recommendation list based on the evaluation results. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the device. The user can view this recommendation list on their device. For example, the list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[1181] In this way, the system of the present invention uses recommendations from different perspectives to provide information from multiple angles in areas that the user is unfamiliar with, allowing the user to efficiently obtain reliable and useful information.

[1182] For example, if a user asks, "Tell me some easy-to-read mystery books," someone who doesn't read much might recommend "Works by Keigo Higashino," someone who reads a lot might recommend "Works by Agatha Christie," and an editor might recommend "Mystery novels for beginners recommended by a famous editor." By integrating this recommendation information and providing it to the user, the system allows users to obtain information from multiple perspectives.

[1183] The above is a description of the mode for carrying out the invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, thereby providing users with the information they desire.

[1184] The processing flow will be explained below.

[1185] Step 1:

[1186] The user uses the terminal to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button.

[1187] Step 2:

[1188] The user's question is sent from the terminal to the server.

[1189] Step 3:

[1190] The server receives the user's query.

[1191] Step 4:

[1192] The server uses a natural language processing engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[1193] Step 5:

[1194] The server stores the analysis results in temporary storage.

[1195] Step 6:

[1196] The server selects a group of users with different perspectives, including casual readers, frequent readers, editors, etc.

[1197] Step 7:

[1198] The server generates recommendation requests based on the questions for a selected set of users.

[1199] Step 8:

[1200] The server sends recommendation requests to a selected set of users.

[1201] Step 9:

[1202] Selected users with terminals receive recommendation requests.

[1203] Step 10:

[1204] The selected user enters a recommendation from their own perspective. For example, they can write, "Higashino Keigo's works are easy to read," and then press the submit button.

[1205] Step 11:

[1206] The recommendation opinion is transmitted from the selected user terminal to the server.

[1207] Step 12:

[1208] The server receives the recommendations.

[1209] Step 13:

[1210] The server evaluates each recommendation received using natural language processing technology and evaluation algorithms to determine usefulness and redundancy.

[1211] Step 14:

[1212] The server stores the evaluation results in a database.

[1213] Step 15:

[1214] The server generates a multifaceted recommendation list based on the evaluated opinions.

[1215] Step 16:

[1216] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[1217] Step 17:

[1218] The server sends the formatted recommendation list to the user's terminal.

[1219] Step 18:

[1220] The terminal receives the recommendation list from the server.

[1221] Step 19:

[1222] The user uses the device to view the received recommendation list, which may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[1223] The above are the processing steps of the program.

[1224] Example 1

[1225] 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."

[1226] Conventional information recommendation systems lack the means to efficiently provide multifaceted information on areas that users are unfamiliar with. This makes it difficult to obtain highly reliable and useful information. The purpose of this invention is to solve these problems and provide multifaceted information from different perspectives.

[1227] 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.

[1228] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and concepts, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, and means for providing the generated recommendation list in a format that the user can view. This enables the user to efficiently obtain reliable and useful information.

[1229] The "means for receiving a question input by a user" refers to a function that enables the server to receive a question input by a user via a terminal.

[1230] "Means for analyzing questions and extracting key keywords and concepts" refers to a function that uses natural language processing technology to analyze received questions and extract key keywords and concepts from them.

[1231] "Means for selecting a group of users with different perspectives and sending recommendation requests based on questions" refers to a function for selecting a target group of users from a database based on user profiles and sending recommendation requests based on the analysis results to that group of users.

[1232] "Means for collecting and evaluating responses from selected users" refers to a function by which the server collects recommendation opinions sent by target users and evaluates the usefulness and overlap of those opinions using natural language processing technology and evaluation algorithms.

[1233] "Means for generating a multifaceted recommendation list based on the evaluation and sending it to the user" refers to a function for creating a recommendation list from various perspectives based on the evaluation results and providing that list to the user.

[1234] "Means for providing the generated recommendation list in a format that can be viewed by the user" refers to a function for adjusting the display format and data format so that the generated recommendation list can be easily viewed by the user on a terminal.

[1235] The system of the present invention provides multifaceted information using recommendations from various perspectives so that a user can efficiently search for information in areas in which they are not familiar. Specific embodiments for implementing the present invention will be described in detail below.

[1236] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" into the terminal and presses the send button, the question is sent to the server. At this time, the terminal sends the question data to the specified URL on the server as an HTTP POST request.

[1237] The server uses a natural language processing (NLP) engine to analyze the received question. Specific software such as Google NLP API or SpaCy can be used here. The server analyzes the question and extracts key keywords and concepts. In this case, "mystery," "easy to read," and "book" are extracted. The analyzed data is temporarily stored in the server's storage.

[1238] Next, the server selects user groups with different perspectives. These user groups include casual readers, frequent readers, editors, etc. The server retrieves user profile data from a database (e.g., MySQL) and selects target user groups based on the analysis results. The server then generates recommendation requests and sends them to the selected user groups via email or in-app notifications.

[1239] The target user receives the recommendation request and inputs their opinion or recommendation from their own perspective. For example, they may say, "Keigo Higashino's works are easy to read." When the target user sends the recommendation from their device to the server, the server receives it and stores it in a database.

[1240] The server evaluates the received opinions and recommendations using natural language processing techniques (e.g., BERT or GPT-3) and evaluation algorithms. The evaluation results are stored in a database, which determines the usefulness and redundancy of each opinion.

[1241] After the evaluation is complete, the server generates a multifaceted recommendation list based on these evaluation results. The generated recommendation list may include information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors." The server then formats this recommendation list into a user-viewable format and sends it to the device in JSON format, for example. The user can view this recommendation list on their device and obtain the information they need.

[1242] For example, if a user asks, "Tell me some easy-to-read mystery books," people who don't read much may recommend "Works by Keigo Higashino," people who read a lot may recommend "Works by Agatha Christie," and editors may recommend "Mystery novels for beginners recommended by famous editors." These recommendations are then combined and provided to the user as a final recommendation list.

[1243] Example prompt sentence:

[1244] "Tell me some easy-to-read mystery books."

[1245] "What are some easy-to-read mystery novels for beginners?"

[1246] "I'd like to know some recommendations for contemporary Japanese mystery writers."

[1247] "What are some classic mystery novels?"

[1248] The above is an embodiment of the present invention. By using this system, users can efficiently obtain highly reliable information from various perspectives.

[1249] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1250] Step 1:

[1251] The user enters a question

[1252] A user uses a terminal to input a question, for example, "Tell me some good mystery books to read."

[1253] Input: The question typed by the user.

[1254] Output: The question is sent from the terminal to the server.

[1255] Specific behavior:

[1256] The user enters a question into the interface of their smartphone or PC and presses the send button.

[1257] At this time, the device sends the question data as an HTTP POST request to the specified URL on the server.

[1258] Step 2:

[1259] The server receives and parses the query

[1260] The server receives a question sent by a user.

[1261] Input: The question received from the user.

[1262] Output: Data with key keywords and concepts extracted.

[1263] Specific behavior:

[1264] The server receives the HTTP request and extracts the question data.

[1265] Next, a natural language processing engine (e.g., Google NLP API or SpaCy) is launched to analyze the question.

[1266] Key keywords such as "mystery," "easy to read," and "book" are extracted from the question and temporarily stored.

[1267] Step 3:

[1268] The server selects the target user group

[1269] The server selects a group of users with different perspectives.

[1270] Input: Question analysis results and user profile data.

[1271] Output: A list of target users and a recommendation request.

[1272] Specific behavior:

[1273] The server retrieves user profile data (reading frequency, occupation, etc.) from a database (e.g. MySQL).

[1274] Based on this profile data, target user groups are selected, such as people who don't read many books, people who read a lot of books, and editors.

[1275] After the selection, a recommendation request for "easy-to-read mystery books" is generated based on the analysis results and sent via email or in-app notification.

[1276] Step 4:

[1277] Target users provide recommendations

[1278] The target user receives the recommendation request and enters their opinion or recommendation from their own perspective.

[1279] Input: Recommendation request and target user's opinion.

[1280] Output: The recommendation is sent to the server.

[1281] Specific behavior:

[1282] In response to the recommendation request received by the target user, the user inputs their opinion, such as "Higashino Keigo's works are easy to read," into their own device.

[1283] The input recommendation is sent again as an HTTP POST request to the specified URL on the server.

[1284] Step 5:

[1285] The server evaluates opinions and recommendations

[1286] The server evaluates the collected opinions and recommendations using natural language processing techniques and evaluation algorithms.

[1287] Input: Collected testimonials.

[1288] Output: Evaluation of each opinion's usefulness and overlap.

[1289] Specific behavior:

[1290] The server stores the received recommendation opinion data in a database.

[1291] We use natural language processing models (e.g., BERT and GPT-3) and evaluation algorithms to evaluate the reliability and overlap of each opinion.

[1292] The evaluation results are stored in a database.

[1293] Step 6:

[1294] The server generates a recommendation list and provides it to the user.

[1295] The server generates a multifaceted recommendation list based on the evaluation results and sends it to the terminal.

[1296] Input: Evaluation result data.

[1297] Output: The recommendation list will be available on your device.

[1298] Specific behavior:

[1299] The server uses the evaluation results to generate a multifaceted recommendation list, such as "Works by Higashino Keigo," "Works by Agatha Christie," or "Mystery novels for beginners recommended by famous editors."

[1300] The recommendation list is sent to the device in JSON format.

[1301] The user can view this recommendation list on the terminal and obtain the information they need.

[1302] The above are the specific processing steps of the program of this system.

[1303] (Application example 1)

[1304] 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."

[1305] When it comes to electronic payment services, it is difficult for users to efficiently search for low-cost, secure remittance methods and payment methods that meet their specific needs, and there is a lack of accurate and reliable information from various perspectives.

[1306] 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.

[1307] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user, means for analyzing questions about electronic payment services and providing recommendations from various perspectives, and means for visualizing and providing the recommendation list to the user, thereby enabling the user to efficiently obtain recommendation information from multiple perspectives.

[1308] A "user" is an individual or organization that utilizes the system to enter questions and obtain information.

[1309] A "question" is a query that seeks information for a user to enter into the system.

[1310] "Keywords" are the main nouns, verbs, adjectives, and other important words contained in the query.

[1311] A "phrase" is a sub-clause that has a specific meaning and is made up of a group of words contained in a question.

[1312] A "user group" is a group consisting of multiple users with different perspectives.

[1313] A "recommendation request" is a request for information sent to a group of users based on detected keywords or phrases.

[1314] A "response" is an opinion or recommendation provided by a group of users in response to a recommendation request.

[1315] "Evaluation" is the process of determining the usefulness and redundancy of responses using natural language processing techniques and evaluation algorithms.

[1316] A "multifaceted recommendation list" is a list of recommendation information generated based on evaluation results from different perspectives.

[1317] "Server" means a computer system that receives and analyzes questions, sends recommendation requests to a group of users, collects and evaluates responses, and generates a recommendation list.

[1318] A "natural language processing engine" is software that analyzes text data and extracts keywords and phrases.

[1319] An "evaluation algorithm" is a program that automatically evaluates the usefulness and redundancy of responses.

[1320] An "electronic payment service" is an online platform or application that enables users to conduct financial transactions.

[1321] "Visualization" is the process of presenting information to a user in an easy-to-view format.

[1322] The system of the present invention provides information from multiple perspectives in response to questions about electronic payment services entered by users. The following describes specific embodiments of the invention. The system is operated using the following hardware and software.

[1323] Hardware:

[1324] Smartphone: A device where users can enter questions and receive and view results.

[1325] Server: A computer system that analyzes questions, sends recommendation requests, collects and evaluates responses, and generates recommendation lists.

[1326] software:

[1327] Natural language processing engine (Spacy): Analyzes questions and extracts key keywords and phrases

[1328] Evaluation algorithm: Evaluating the usefulness and redundancy of responses using natural language processing techniques

[1329] REST API: A communication method for collecting and sending recommendation information

[1330] Data processing and calculation:

[1331] 1. Receiving questions from users

[1332] A user uses a smartphone to type in a question such as "Please tell me a low-cost and safe way to send money overseas" and submit it.

[1333] 2. Question Analysis

[1334] The server analyzes the received question using a natural language processing engine (Spacy) and extracts key keywords (e.g., "low cost," "safety," "overseas remittance").

[1335] 3. Selecting a group of users with different perspectives

[1336] The server selects a plurality of user groups with different viewpoints, such as emphasis on cost, emphasis on safety, emphasis on frequency of use, etc.

[1337] 4. Generate and send a recommendation request

[1338] The server generates and transmits recommendation requests based on the extracted keywords to each selected user group.

[1339] 5. Collecting responses

[1340] Collect responses from each user group (e.g., "cost-conscious users would like a low-cost remittance method," "safety-conscious users would like the most secure remittance method," etc.).

[1341] 6. Evaluating Responses

[1342] The server uses a rating algorithm to assess the usefulness and duplication of the responses and stores the results in a database.

[1343] 7. Creating and providing a multifaceted recommendation list

[1344] Based on the evaluation results, the server generates a multifaceted recommendation list (e.g., "low-cost overseas remittance methods," "safety-oriented overseas remittance methods," etc.) and sends it to the user's smartphone. The user can visualize and view these recommendation lists on their smartphone.

[1345] Examples:

[1346] For example, if a user asks, "What is a low-cost and safe way to send money overseas?", the system extracts keywords such as "low-cost," "safe," and "overseas remittance." It then sends recommendation requests to groups of users with different perspectives, such as those prioritizing cost, safety, or frequency of use. Once the responses are collected, the server evaluates them using natural language processing technology and evaluation algorithms to create a multifaceted recommendation list. Finally, this recommendation list is sent to the user's smartphone, where the user can visualize and review it.

[1347] Example prompt sentence:

[1348] Please tell me a low-cost and safe way to send money overseas.

[1349] In this way, the system of the present invention helps users to efficiently obtain information about electronic payment services.

[1350] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1351] Step 1:

[1352] The user inputs a question using a smartphone. For example, they input a prompt such as "Please tell me a low-cost and safe way to send money overseas" and press the send button. The input question is sent to the server.

[1353] Step 2:

[1354] The server analyzes the received question using a natural language processing engine (Spacy). Specifically, it analyzes the question (input) and extracts key keywords (such as "low cost," "safety," and "overseas remittance") (data processing). The extracted keywords are used as input for the next processing step.

[1355] Step 3:

[1356] The server selects a user group with different perspectives, such as cost priority, safety priority, or frequency of use priority, from the database. The result of this user group selection becomes the input for generating a recommendation request.

[1357] Step 4:

[1358] The server generates and sends a recommendation request based on the question to each selected user group. Specifically, it creates a recommendation request in the form of a question appropriate for each user group based on the extracted keywords, and sends it via a communication method (such as a REST API). The output of this step is the generated recommendation request.

[1359] Step 5:

[1360] The selected users respond to the recommendation request. As a response, they send recommendation information (e.g., "low-cost remittance methods," "secure remittance methods," etc.) to the server. The response is received by the server.

[1361] Step 6:

[1362] The server analyzes the received responses using an evaluation algorithm. Specifically, it evaluates the usefulness and redundancy of each response using natural language processing technology, and stores the evaluation results in a database. These results serve as input for generating the next recommendation list.

[1363] Step 7:

[1364] The server generates a multifaceted recommendation list based on the evaluation results. Based on the output of the evaluation algorithm, it integrates and organizes the optimal recommendation information from each perspective and presents it in a format that is easy for the user to understand. This recommendation list is the final output to the user.

[1365] Step 8:

[1366] The server sends the generated recommendation list to the user's smartphone, where the user can visualize and view the recommendation list. For example, the list contains recommendations from various perspectives, such as "low-cost remittance methods" and "safe remittance methods."

[1367] In this way, a system is realized that allows users to input questions about electronic payment services and efficiently obtain useful information from multiple perspectives.

[1368] 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.

[1369] The present invention provides a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to enable the user to efficiently search for information in areas in which the user is unfamiliar. Specific embodiments of the system of the present invention will be described below.

[1370] First, the user inputs a question using the terminal. For example, if the user inputs "Tell me about some easy-to-read mystery books" and presses the send button, the question is sent to the server. At this point, the emotion engine recognizes the emotion of the user when they input their question. For example, if the user is excited when inputting their question, that emotion information is also sent to the server.

[1371] The server receives the user's question and emotional information. The server analyzes the question and emotional information using a natural language processing (NLP) engine and an emotional engine. In this case, the server extracts key keywords such as "mystery," "easy to read," and "book," as well as the user's emotional state (e.g., excitement, confusion, etc.). The analysis results are temporarily stored in storage.

[1372] The server then selects user groups with different perspectives based on the user's emotional state. For example, if the emotion engine determines that the user is confused, it will select a user group with a perspective suitable for solving the problem. The user groups include people who don't read books often, people who read books often, editors, etc.

[1373] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their opinions and recommendations from their own perspectives. For example, "Keigo Higashino's works are easy to read."

[1374] When a response from a target user is sent to the server, the server receives the recommendation opinion and evaluates the response using natural language processing technology and evaluation algorithms. The evaluation is based on usefulness, redundancy, and emotional state. For example, recommendations that provide solutions to a confused user are prioritized.

[1375] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server formats the recommendation list in a format that is easy for the user to provide and sends it to the terminal. The user can view this recommendation list on the terminal. For example, it may contain information such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by famous editors."

[1376] For example, if a user asks, "Recommend some easy-to-read mystery books," and the emotion engine recognizes that the user is excited, the server will incorporate many recommendations that have elements that will entertain the user. For someone who doesn't read many books, "Works by Higashino Keigo" might be recommended, for a person who reads a lot of books, "Works by Agatha Christie" might be recommended, and for an editor, "Mystery novels for beginners recommended by a famous editor" might be recommended. By integrating these recommendations and providing them to the user, the system can obtain information that is multifaceted and takes emotions into consideration.

[1377] This concludes the description of the embodiments of the present invention. The system of the present invention efficiently and effectively collects and evaluates recommendation information from users with diverse perspectives, and further analyzes user emotions to more appropriately provide users with the information they desire.

[1378] The processing flow will be explained below.

[1379] Step 1:

[1380] The user uses the device to input a question, such as "Tell me about some easy-to-read mystery books," and presses the send button. The device simultaneously captures the user's emotions.

[1381] Step 2:

[1382] The user's question and emotion data are transmitted from the terminal to the server.

[1383] Step 3:

[1384] A server receives the user's question and emotion data.

[1385] Step 4:

[1386] The server uses a natural language processing (NLP) engine to analyze the question, extracting keywords such as "mystery," "easy to read," and "book."

[1387] Step 5:

[1388] The server uses an emotion engine to analyze the emotion data and identify the user's emotional state, such as "excited" or "confused."

[1389] Step 6:

[1390] The server stores the analysis results and emotion data in temporary storage.

[1391] Step 7:

[1392] The server selects a group of users with different perspectives based on the emotional state of the users. For example, for a confused user, it preferentially selects a user who is good at providing solutions.

[1393] Step 8:

[1394] The server generates recommendation requests based on the analysis results for a selected group of users, adjusting the tone and content of the requests depending on their emotional state.

[1395] Step 9:

[1396] The server sends recommendation requests to a selected set of users.

[1397] Step 10:

[1398] The selected target user receives the recommendation request at the terminal.

[1399] Step 11:

[1400] The target user inputs a recommendation from their own perspective. For example, they might type, "Keigo Higashino's works are easy to read," and then press the send button.

[1401] Step 12:

[1402] The recommendation opinions are transmitted from the target user terminal to the server.

[1403] Step 13:

[1404] The server receives the recommendations.

[1405] Step 14:

[1406] The server evaluates each recommendation received using natural language processing technology and an evaluation algorithm, taking into account not only usefulness and redundancy but also emotional state.

[1407] Step 15:

[1408] The server stores the evaluation results in a database.

[1409] Step 16:

[1410] The server generates a multifaceted recommendation list based on the evaluated opinions, and the content is arranged and emphasized according to the user's emotional state.

[1411] Step 17:

[1412] The recommendation list generated by the server is formatted into a format that is easy to provide to the user.

[1413] Step 18:

[1414] The server sends the formatted recommendation list to the user's terminal.

[1415] Step 19:

[1416] The terminal receives the recommendation list from the server.

[1417] Step 20:

[1418] The user reviews the recommendation list received on their device and obtains multifaceted, emotion-based information, such as "Works by Keigo Higashino," "Works by Agatha Christie," and "Mystery novels for beginners recommended by a well-known editor."

[1419] The above are the detailed processing steps of the system that combines the emotion engine.

[1420] Example 2

[1421] 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."

[1422] Conventional information recommendation systems are limited to providing general recommendations in response to questions entered by users, and it is difficult to provide multifaceted information that takes into account the user's emotions and circumstances. As a result, there are many cases where users' needs cannot be fully met. Specifically, the problem is that the information provided is inappropriate because the emotional state and background information of the user when entering a question are not taken into account.

[1423] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1424] In this invention, the server includes means for receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for recognizing and receiving user emotional information, means for selecting a group of users with different perspectives based on the emotional information and transmitting a recommendation request based on the question, means for collecting and evaluating responses from the selected users, and means for generating a multifaceted recommendation list based on the evaluation and transmitting it to the user. This enables multifaceted and advanced information recommendations that take into account the user's emotions and background information.

[1425] A "user" is an individual or group who uses the system to enter questions and receive information.

[1426] A "terminal" is an electronic device, such as a computer, smartphone, or tablet, that a user uses to enter a question.

[1427] A "server" is a central processing unit that receives a user's query, analyzes it, processes it, and provides appropriate information.

[1428] A "question" is text or voice data entered by a user about which information he or she wishes to obtain.

[1429] "Emotional information" is data related to the emotional state (e.g., excitement, confusion, etc.) expressed by the user when entering a question.

[1430] A "natural language processing engine" is a software technology that analyzes user questions and extracts key keywords and phrases.

[1431] An "emotion engine" is a software technology that analyzes a user's emotional state.

[1432] A "recommendation request" is a request for information that the server generates and transmits to a group of users with different viewpoints.

[1433] A "user group" is a group of users selected by the server who have different perspectives and knowledge.

[1434] A "response" is an opinion or piece of information that a group of users provides in response to a recommendation request.

[1435] The "rating means" is the process by which the server evaluates the usefulness and redundancy of responses using natural language processing techniques and rating algorithms.

[1436] A "recommendation list" is a list of information generated by the server based on the evaluation results, and provides the user with optimal recommendations from multiple perspectives.

[1437] The present invention is a system that provides multifaceted information by combining recommendations from various perspectives with the user's emotions, in order to efficiently search for information in areas in which the user is unfamiliar.

[1438] System configuration

[1439] Hardware

[1440] 1. Device: PC, smartphone, tablet, etc.

[1441] 2. Server: Central processing unit.

[1442] software

[1443] 1. Natural Language Processing Engine (NLP): Analyzes the question and extracts key keywords and phrases.

[1444] 2. Emotion engine: Recognize and analyze the user's emotional information.

[1445] Data processing and calculation

[1446] 1. Receiving user questions:

[1447] The terminal receives the user's question and sends it to the server.

[1448] 2. Recognition of emotional information:

[1449] The device's built-in emotion engine recognizes the emotion the user is feeling when entering a question and transmits it to the server.

[1450] 3. Question and emotion analysis:

[1451] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases.

[1452] At the same time, the emotion engine analyzes emotional information to understand the user's emotional state.

[1453] 4. User Group Selection:

[1454] The server selects a group of users with different perspectives based on the analysis results. Selection criteria include emotional information and past recommendation history.

[1455] 5. Generate and send a recommendation request:

[1456] The server generates and sends recommendation requests to a selected group of users, including key keywords and user emotion information.

[1457] 6. Collect and evaluate responses from target users:

[1458] The server collects responses from the target users and rates the responses using natural language processing techniques and rating algorithms.

[1459] 7. Generating and serving recommendation lists:

[1460] The server generates a multifaceted recommendation list based on the evaluation results and transmits it to the terminal for provision to the user.

[1461] Specific examples

[1462] The user uses a device to enter a question such as "Tell me about an easy-to-read mystery book" and presses the send button. The device's built-in emotion engine recognizes the user's excited state and sends this information along with the question to the server. The server receives and analyzes the question and emotion information, extracting key keywords such as "mystery," "easy to read," and "book" as well as the emotion information of "excitement."

[1463] The server then selects a group of users with appropriate perspectives, generates a recommendation request, and sends it. For example, responses are collected from people who don't read many books with perspectives suitable for problem solving, people who read a lot of books, editors, and others, and evaluated. For example, responses such as "Keigo Higashino's works are easy to read" are collected.

[1464] The server evaluates the responses and generates a multifaceted recommendation list, which is then formatted and sent to the device in a user-friendly format.The user can then browse on their device "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," and more.

[1465] Prompt Sentence Examples

[1466] "User is looking for a mystery, easy-to-read book. Their emotional state is excitement. What are your recommendations?"

[1467] Generative AI Models

[1468] The system uses a generative AI model to generate prompts for recommendation requests and collect responses from an appropriate set of users.

[1469] By using the above method, the present invention realizes multifaceted and sophisticated information recommendation that takes into account the user's emotions and background information.

[1470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1471] Step 1:

[1472] The user inputs a question using the terminal. For example, they input "Tell me about an easy-to-read mystery book" and press the send button. (Input) User's question (Output) Question data sent from the terminal to the server

[1473] Step 2:

[1474] The device uses an emotion engine to recognize the user's emotions. Specifically, emotions are analyzed using a facial recognition camera and voice input. (Input) User's facial expressions and voice. (Output) User's emotional information (e.g., excitement).

[1475] Step 3:

[1476] The device sends question data and emotion information to the server. (Input) Question data, emotion information (Output) Data transmission to the server

[1477] Step 4:

[1478] The server uses a natural language processing engine to analyze the question and extract key keywords and phrases. (Input) Question data (Output) Key keywords (e.g., "mystery," "easy to read," "book")

[1479] Step 5:

[1480] The server analyzes the emotional information using an emotion engine and grasps the user's emotional state. (Input) Emotional information (Output) Analyzed emotional state (e.g., excitement)

[1481] Step 6:

[1482] The server selects a group of users with different perspectives based on key keywords and emotional information. Selection criteria include past recommendation history and expertise. (Input) Key keywords, emotional information (Output) Selected user group (e.g., frequent readers, editors)

[1483] Step 7:

[1484] The server generates and sends a recommendation request to a group of selected users. The recommendation request includes key keywords and emotion information. (Input) Key keywords, emotion information (Output) Send recommendation request

[1485] Step 8:

[1486] The target user inputs their opinion or recommendation based on the recommendation request and sends it to the server. For example, they send an opinion such as "Keigo Higashino's works are easy to read." (Input) Recommendation request (Output) Response from the target user

[1487] Step 9:

[1488] The server receives the response from the target user and evaluates the response content using natural language processing technology and evaluation algorithms. Evaluation criteria include usefulness, redundancy, emotional state, etc. (Input) Response from the target user (Output) Evaluation result (e.g., opinion with high usefulness)

[1489] Step 10:

[1490] The server generates a multifaceted recommendation list based on the evaluation results. The recommendation list contains information to meet the user's needs. (Input) Evaluation results (Output) Recommendation list

[1491] Step 11:

[1492] The server formats the generated recommendation list into a format that is easy for the user to provide, and sends it to the terminal. (Input) Recommendation list (Output) Sending the formatted recommendation list

[1493] Step 12:

[1494] The user browses the recommendation list on the device and makes a selection from the provided recommendation information. For example, they browse "Works by Keigo Higashino," "Works by Agatha Christie," "Mystery novels for beginners recommended by famous editors," etc. (Input) Formatted recommendation list (Output) User's selection and browsing

[1495] (Application example 2)

[1496] 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."

[1497] The problem is that there is a lack of methods to provide recommendation information from multiple perspectives, especially considering the user's emotional state, when collecting information about a product category that the user is not familiar with. Conventional systems have had difficulty making appropriate recommendations that take into account not only the content of the user's question but also the user's emotional state.

[1498] 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 receiving a question entered by a user, means for analyzing the question and extracting key keywords and phrases, means for detecting the user's emotional state using an emotion detection engine, means for selecting a group of users with different perspectives and transmitting a recommendation request based on the question and emotional information, means for collecting and evaluating responses from the selected users, means for generating a multifaceted recommendation list based on the evaluations and transmitting it to the user, and means for displaying the recommendation list on the user terminal. This makes it possible to provide appropriate recommendation information that takes into account the user's emotional state from a multifaceted perspective for product categories in which the user is not familiar.

[1499] The term "user" refers to a person who uses an information system, and in particular, a person who inputs a question to the system of the present invention and receives a reply.

[1500] The "means for receiving a question" is a function or device that allows the system to obtain a question input from a user.

[1501] "Means for analyzing questions and extracting key keywords and phrases" refers to a function or device that uses natural language processing technology to understand the content of a user's question and extract important words and phrases.

[1502] An "emotion detection engine" is a software or hardware device that analyzes and determines the emotional state of a user at the time of input.

[1503] The "means for selecting a group of users with different viewpoints" is a function or device for selecting other users with various backgrounds and knowledge based on the user's emotional state and question content.

[1504] The "means for sending a recommendation request" is a function or device for sending a request based on the question content and emotional information of a user to a selected group of users.

[1505] The "means for collecting and evaluating responses" is a function or device for collecting responses from other users who have received a recommendation request and evaluating the content of the responses.

[1506] The "means for generating and transmitting a multifaceted recommendation list" is a function or device for compiling recommendation information that takes into account various perspectives based on collected responses into a list format and providing this to the user.

[1507] A "user terminal" is a device that a user uses to interact with the system and to display a recommendation list from the system of the present invention.

[1508] The present invention is a system that efficiently searches for information on products in areas that the user is unfamiliar with, and provides recommendation information from multiple perspectives that take into account the user's emotional state. Here, a product recommendation system in a virtual store will be described as a specific embodiment.

[1509] First, a user inputs a question using a smartphone. For example, by typing "Tell me about drones for beginners" and pressing the send button, the question is sent to the server. Here, an emotion detection engine (e.g., Microsoft Azure Face API) is used to detect the emotional state of the user at the time of input. For example, if the user is detected to be excited, that emotional information is also sent to the server along with the question.

[1510] The server receives the question and emotion information and analyzes the question using a generative AI model (e.g., OpenAI GPT-3). During this analysis, key keywords and phrases are extracted, resulting in important keywords such as "for beginners" and "drone." The analysis results and emotion information are temporarily stored in storage.

[1511] Next, the server selects user groups with different perspectives. If the emotion detection engine determines that the user is excited, it selects user groups that can make recommendations from a perspective that has an entertaining element. For example, it includes users who do not read books often, users who frequently use products, and experts.

[1512] The server generates and sends recommendation requests based on the analysis results and emotional information to the selected group of users. The target users receive the recommendation requests and input their own recommendations. For example, they can receive specific recommendations such as "easy-to-use drones for beginners."

[1513] When the target user's response is sent to the server, the server receives the recommendation and evaluates the response using natural language processing techniques and evaluation algorithms. The evaluation includes checking usefulness and redundancy, and also evaluates the response based on emotional state. For example, an excited user will be given priority over recommendations that are likely to be interesting.

[1514] The evaluation results are stored in a database, and the server generates a multifaceted recommendation list based on the evaluated opinions. The server then formats the recommendation list in a format that is easy for the user to provide and sends it to the user's smartphone. The user can view the recommendation list on their smartphone and check the details. For example, the list may include information such as "easy-to-use drones for beginners," "popular drones for beginners," and "drones recommended by experts."

[1515] As a concrete example, the following is an example of a prompt sentence when a user asks, "Tell me about drones for beginners," and the emotion engine recognizes that the user is excited.

[1516] Prompt: "Tell me about drones for beginners. I'm excited."

[1517] This allows the user to obtain recommendation information from multiple perspectives that take into account their emotional state, enabling them to select appropriate products.

[1518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1519] Step 1:

[1520] A user inputs a question using a smartphone terminal. For example, they input "Tell me about drones for beginners." At this point, the input data is the user's question. The input question is sent from the terminal to the server.

[1521] Step 2:

[1522] The server receives the question and analyzes the user's emotional state using an emotion detection engine (e.g., Microsoft Azure Face API). This analysis yields emotional information such as excitement, confusion, apprehension, and interest. The acquired emotional information is stored on the server along with the question content.

[1523] Step 3:

[1524] The server analyzes the question using a generative AI model (e.g., OpenAI GPT-3). By analyzing the question, key keywords and phrases are extracted. For example, keywords such as "for beginners" and "drone" are obtained. The analysis results are temporarily stored in storage.

[1525] Step 4:

[1526] The server selects a group of users with different perspectives based on their emotional state and the analysis results. If the emotion engine determines that the user is excited, it extracts users who can make recommendations with entertaining elements. In this case, it selects users from the database who are suitable for the user's excited state (e.g., experienced users, experts, etc.).

[1527] Step 5:

[1528] The server generates and sends recommendation requests based on the question content and emotion information to the selected group of users. The requests include the analyzed keywords and emotion information. The selected target users receive the recommendation requests and input their opinions and recommendations from their own perspectives.

[1529] Step 6:

[1530] When a response from a target user is sent to the server, the server receives a recommendation opinion. The server evaluates the response using natural language processing technology and an evaluation algorithm. The evaluation includes the usefulness, redundancy, and priority based on the emotional state of the response. The evaluation results are stored in a database.

[1531] Step 7:

[1532] The server generates a multifaceted recommendation list based on the evaluated opinions. For example, it may generate lists such as "Easy-to-use drones for beginners," "Popular drones for beginners," and "Drones recommended by experts." This recommendation list is formatted to be easily provided to users.

[1533] Step 8:

[1534] The server then sends the generated recommendation list to the user's smartphone. The user can then receive the recommendation list on their smartphone and check the details. This allows the user to obtain appropriate recommendation information that takes into account their emotional state.

[1535] This allows the user to obtain appropriate recommendation information from multiple perspectives that take into account the user's emotional state, even for product categories that the user is not familiar with.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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).

[1543] 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.

[1544] 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."

[1545] 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.

[1546] 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).

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] The following is further disclosed regarding the above embodiment.

[1558] (Claim 1)

[1559] means for receiving a user-entered question;

[1560] means for analyzing the question and extracting key keywords and phrases;

[1561] a means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question;

[1562] means for collecting and evaluating responses from selected users;

[1563] The system includes means for generating a multifaceted recommendation list based on the ratings and transmitting the recommendation list to the user.

[1564] (Claim 2)

[1565] 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

[1566] (Claim 3)

[1567] 2. The system according to claim 1, wherein the question analyzing means analyzes the question sentence using a natural language processing engine.

[1568] "Example 1"

[1569] (Claim 1)

[1570] means for receiving a user-entered question;

[1571] means for analyzing the question and extracting key keywords and concepts;

[1572] a means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question;

[1573] means for collecting and evaluating responses from selected users;

[1574] means for generating a multifaceted recommendation list based on the evaluation and transmitting the list to the user;

[1575] The system includes means for providing the generated recommendation list in a format that can be viewed by the user.

[1576] (Claim 2)

[1577] 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

[1578] (Claim 3)

[1579] 2. The system according to claim 1, wherein the question analyzing means analyzes the question sentence using a natural language processing engine.

[1580] "Application Example 1"

[1581] (Claim 1)

[1582] means for receiving a user-entered question;

[1583] means for analyzing the question and extracting key keywords and phrases;

[1584] a means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question;

[1585] means for collecting and evaluating responses from selected users;

[1586] means for generating a multifaceted recommendation list based on the evaluation and transmitting the list to the user;

[1587] A means for analyzing questions about electronic payment services and providing recommendations from various perspectives;

[1588] The system includes means for providing a visualization of the recommendation list to a user.

[1589] (Claim 2)

[1590] 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

[1591] (Claim 3)

[1592] 2. The system according to claim 1, wherein the question analysis means analyzes the question sentence using a natural language processing engine and extracts specific keywords related to the electronic payment service.

[1593] "Example 2: Combining Emotion Engines"

[1594] (Claim 1)

[1595] means for receiving a user-entered question;

[1596] means for analyzing the question and extracting key keywords and phrases;

[1597] means for recognizing and receiving user emotion information;

[1598] a means for selecting a group of users having different viewpoints based on the emotion information and transmitting a recommendation request based on the question;

[1599] means for collecting and evaluating responses from selected users;

[1600] The system includes means for generating a multifaceted recommendation list based on the ratings and transmitting the recommendation list to the user.

[1601] (Claim 2)

[1602] 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

[1603] (Claim 3)

[1604] 2. The system according to claim 1, wherein the question analyzing means analyzes the question sentence using a natural language processing engine.

[1605] "Application example 2 when combining emotion engines"

[1606] (Claim 1)

[1607] means for receiving a user-entered question;

[1608] means for analyzing the question and extracting key keywords and phrases;

[1609] means for detecting an emotional state of a user using an emotion detection engine;

[1610] a means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question and emotion information;

[1611] means for collecting and evaluating responses from selected users;

[1612] means for generating a multifaceted recommendation list based on the evaluation and transmitting the list to the user;

[1613] The system includes means for displaying the recommendation list at a user terminal.

[1614] (Claim 2)

[1615] 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

[1616] (Claim 3)

[1617] 2. The system according to claim 1, wherein the question analysis means analyzes the question sentence using a generative AI model. [Explanation of symbols]

[1618] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a user-entered question; means for analyzing the question and extracting key keywords and phrases; a means for selecting a group of users having different viewpoints and transmitting a recommendation request based on the question; means for collecting and evaluating responses from selected users; The system includes means for generating a multifaceted recommendation list based on the ratings and transmitting the recommendation list to the user.

2. 2. The system of claim 1, wherein the evaluation means evaluates the usefulness and redundancy of the replies using natural language processing techniques and evaluation algorithms.

3. 2. The system according to claim 1, wherein the question analyzing means analyzes the question sentence using a natural language processing engine.

Images