System

Abstract

A system is provided.SOLUTION: Means for a user to input a question, set a price, and transmit the question; means for a server to compare the received question with a database of similar questions by AI and search for the similar question; A system comprising: means for storing as a new question if there is none; means for adding a new question to a list of answers desired; means for a respondent to select a question and provide a solution; means for sending and storing an answer to a server when the answer is provided; means for a user to confirm and evaluate the answer and send the evaluation to the server; means for the server to update a usefulness score of the answer based on the evaluation result; and means for paying the respondent a reward each time the answer is displayed.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] In conventional knowledge sharing systems, the process of users posting questions and receiving answers is inefficient. Specifically, the same or similar questions are posted repeatedly, resulting in numerous duplicate answers, which consumes time and effort from respondents, while making it difficult for users to quickly obtain high-quality answers. Furthermore, reward systems for respondents are often inadequate, making it difficult to maintain motivation. This hinders effective knowledge sharing and results in a lack of an improved user experience. [Means for solving the problem]

[0005] The present invention is a system including a means for a user to input a question, set a price, and submit it, a means for a server to search by comparing the received question with a database of similar questions using AI, a means for the server to provide an answer to the similar question if one is found, and to save the answer as a new question if one is not found, a means for adding the new question to a list of desired answers, a means for a respondent to select a question and provide a solution, a means for transmitting and saving the answer to the server when an answer is provided, a means for the user to check the answer, rate it, and send the rating to the server, a means for the server to update the answer's usefulness score based on the rating results, a means for adding highly useful answers to a list of frequently displayed questions, and a means for paying a reward to the respondent each time an answer is displayed. This allows users to obtain high-quality answers quickly, and respondents receive rewards to maintain their motivation while promoting the sharing of knowledge.

[0006] "User" means any person or entity that uses the System to post questions and receive answers.

[0007] "Questions" are problems or questions posted by users through the system.

[0008] "Price" is the amount of reward that a user sets for a question.

[0009] A "terminal" is a device (such as a computer, smartphone, or tablet) that a user or respondent uses to access the system.

[0010] A "server" is a central computer that manages the entire system and processes, searches, and stores data.

[0011] "AI" is an algorithm that uses artificial intelligence technology to determine the similarity of questions and search for appropriate answers.

[0012] A "database" is a collection of information that stores past questions and answers saved within the system.

[0013] "Similar questions" are past questions that AI has determined to be similar in content to the current question.

[0014] An "answer" is a solution or explanation provided by a respondent to a user's question.

[0015] The "answer request list" is a list that respondents can view and select questions to answer.

[0016] A "Respondent" is a person or organization that provides solutions or explanations to users' questions.

[0017] "Transmission" is the process of moving or transmitting data from one system to another.

[0018] "Storage" is the process of recording received data in a database.

[0019] "Rating" is the act of a user expressing the helpfulness of a provided answer using a number or stars.

[0020] The "usefulness score" is an index that indicates the effectiveness and value of an answer, calculated based on the evaluation of the answer.

[0021] "Show frequency" refers to how often an answer is shown in the system.

[0022] "Reward" refers to compensation such as money or points paid to respondents for their answers. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] The present invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. This system has the following means to solve conventional problems:

[0045] System Overview

[0046] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[0047] This sends the question to the server.

[0048] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[0049] If the server finds a similar question, it provides the answer to the user.

[0050] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[0051] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[0052] The answers provided by the respondent are sent to the server and stored in a database.

[0053] Users review the answers provided and rate whether they are helpful.

[0054] The user's ratings are sent to the server via the device.

[0055] The server updates the helpfulness score of the answer based on the evaluation results, so that answers with higher helpfulness are displayed more frequently.

[0056] Answers that are more useful will be displayed preferentially when other users ask the same question.

[0057] Each time an answer is displayed, the server pays the answerer a reward.

[0058] Rewards are calculated based on the number of times an answer is viewed and its rating.

[0059] Example system operation

[0060] The process from posting a question to providing an answer

[0061] For example, user A enters the question "How to implement asynchronous processing in JavaScript," sets the price as 200 yen, and submits it. At this time, user A's device sends this data to the server.

[0062] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions.

[0063] Since no similar questions were found, the question is saved in the database as a new question and added to the list of questions to be answered.

[0064] Respondent B selects this question from the list of preferred answers and answers as follows:

[0065] "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[0066] This answer is sent from respondent B's terminal to the server and stored in the database.

[0067] If User A checks the answer and finds it useful, he or she rates it 4 stars. This rating is sent from User A's device to the server.

[0068] The server receives this rating and updates the helpfulness score of the answer.

[0069] Because of its usefulness, the next time someone searches for a question on "JavaScript asynchronous processing," this answer will be prioritized.

[0070] Furthermore, the server pays a reward to respondent B each time an answer is displayed.

[0071] Rewards are calculated based on the number of times an answer is viewed and user ratings.

[0072] In this way, the system of the present invention allows users to quickly obtain high-quality answers, and respondents receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[0076] Step 2:

[0077] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[0078] Step 3:

[0079] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[0080] Step 4:

[0081] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[0082] Step 5:

[0083] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[0084] Step 6:

[0085] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[0086] Step 7:

[0087] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[0088] Step 8:

[0089] The server stores the received answers in a database, where the answers are linked to the related questions.

[0090] Step 9:

[0091] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[0092] Step 10:

[0093] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[0094] Step 11:

[0095] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and stored in the database.

[0096] Step 12:

[0097] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[0098] Step 13:

[0099] The server pays the answerer a reward each time their answer is viewed. The reward is calculated based on the rating and number of views, and recorded in the answerer's account.

[0100] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[0101] Example 1

[0102] 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."

[0103] Previously, the exchange of questions and answers for users to obtain specialized knowledge was inefficient, with problems in the quality and speed of answers. Furthermore, respondents were not sufficiently motivated, making it difficult to obtain high-quality answers. This resulted in a decrease in the efficiency of knowledge sharing and dissatisfaction for both users and respondents.

[0104] 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.

[0105] In this invention, the server includes means for a user to input an inquiry, set a price, and send it, means for comparing the inquiry received by the server with a database of similar inquiries using artificial intelligence to search, means for the server to provide an answer to the user if a similar inquiry is found, or to save it as a new inquiry if no similar inquiry is found, means for adding the new inquiry to a list of desired solutions, means for a respondent to select an inquiry and input a solution, means for sending the answer to the server and saving it in the database when an answer is provided, means for the user to check the answer, rate it, and send the rating results to the server, means for the server to update the usefulness score of the answer based on the rating results, means for adding highly useful answers to a list of frequently displayed inquiries, and means for paying a reward to the respondent each time an answer is displayed. This allows users to quickly obtain high-quality answers, motivates responders by receiving appropriate rewards, and enables effective knowledge sharing.

[0106] "User" means any person or entity that uses this system to enter an inquiry and obtain a solution.

[0107] "Device" refers to electronic devices such as computers, smartphones, tablets, etc. used by users or respondents.

[0108] "Server" refers to the central computer system that receives and processes data submitted by users or respondents.

[0109] "Artificial intelligence" refers to the AI ​​technology used by the server to analyze queries and search for similar queries.

[0110] A "databank" refers to a database system in which past inquiries and their responses are recorded and stored.

[0111] "Similar inquiries" refer to past inquiries that are similar in content to the inquiry entered by the user.

[0112] The "List of Requests for Resolution" refers to a list that lists newly submitted inquiries from users and displays them so that respondents can select from them.

[0113] "Respondent" refers to an individual or corporation that selects an inquiry from the list of solutions desired and provides the solution.

[0114] "Evaluation" refers to the feedback that a user sends to the server based on whether the provided answer is useful or not.

[0115] "Usefulness score" refers to an index that the server uses to quantify the usefulness of an answer based on the evaluation results.

[0116] "Display frequency" refers to how often the server displays your answer to other users based on its helpfulness score.

[0117] "Reward" refers to the amount paid by the server each time an answer provided by an answerer is displayed.

[0118] The present invention relates to a knowledge sharing system in which users input and submit inquiries and respondents provide solutions, resulting in mutual benefits. This system provides a means for promoting the effective sharing and utilization of knowledge by allowing users to quickly obtain high-quality answers and by providing appropriate compensation to respondents.

[0119] Specifically, the system allows users to input inquiries using a terminal, set a price, and submit the inquiry. The user-inputted inquiry is then sent to a server. When the server receives the inquiry, it analyzes it using a generative AI model (e.g., OpenAI GPT-3) to extract keywords. It then compares the inquiry with past inquiries in a database to search for similar inquiries.

[0120] If a similar query is found, the server provides the answer to the user. If no similar query is found, the server saves it as a new query in the database and adds it to a list of queries to be resolved. This list can be accessed by the respondent using their terminal, and the respondent can select queries of interest from it.

[0121] After the respondent selects a question, they enter a solution and send it to the server. For example, they provide an answer such as "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." This answer is sent to the server and stored in the database at the same time.

[0122] The user reviews the provided answer and rates it if it is useful. The user sends the rating to the server using their device. The server receives the rating result and updates the helpfulness score of the answer. Based on the updated helpfulness score, answers with high helpfulness are displayed preferentially in the search results for subsequent queries.

[0123] Furthermore, the server pays the answerer a reward each time their answer is displayed, based on the frequency of display and the rating results, which motivates the answerer to continue providing high-quality answers.

[0124] As a specific example, if User A enters "How to implement asynchronous processing in JavaScript" as a question, sets the price to 200 yen, and submits it, the server will extract keywords such as "JavaScript asynchronous processing" and search its past database using a generative AI model. If no similar inquiries are found, the inquiry will be saved as a new inquiry and displayed in the list of desired solutions. If Respondent B selects this inquiry and answers with specific methods for asynchronous processing, the answer will be provided to User A via the server. If User A rates the answer as useful (e.g., 4 stars), the rating result will be sent to the server, and the answer's usefulness score will be updated.

[0125] An example of a prompt is as follows:

[0126] "Please tell me how to implement asynchronous processing in JavaScript. Please include examples of using Promises and async / await."

[0127] As described above, the present invention improves the efficiency and effectiveness of knowledge sharing systems and provides a beneficial environment for both users and respondents.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] User enters inquiry, sets price and submits.

[0131] Input: The user uses a terminal to enter an inquiry and price.

[0132] Data processing: The terminal converts the input data into a data format that can be sent to the server.

[0133] Output: The terminal sends the query and price data to the server.

[0134] Step 2:

[0135] The server receives the query.

[0136] Input: Enquiry and pricing data sent from the device.

[0137] Data processing: The server analyzes the received data and extracts keywords such as "JavaScript asynchronous processing."

[0138] Output: Extracted keywords.

[0139] Step 3:

[0140] The server searches the database using the extracted keywords.

[0141] Input: Extracted keywords.

[0142] Data processing: Using a generative AI model (e.g., GPT-3), search for similar queries by comparing them with past queries in a database.

[0143] Output: Search results for similar queries.

[0144] Step 4:

[0145] The server serves similar queries or stores the new query.

[0146] Input: Search results for similar queries.

[0147] Data processing: If a similar query is found, provide the answer to the user. If not, save it as a new query.

[0148] Output: Answers to similar queries or new queries are stored in the databank.

[0149] Step 5:

[0150] Add new inquiries to the list of issues to be resolved.

[0151] Input: New inquiry data.

[0152] Data processing: The server registers the inquiry details in a list of requests for resolution.

[0153] Output: Updated resolution list.

[0154] Step 6:

[0155] The respondent selects the query and provides a solution.

[0156] Input: List of desired solutions.

[0157] Data processing: The respondent uses a terminal to select an inquiry from a list and enter a solution.

[0158] Output: The input solution data.

[0159] Step 7:

[0160] The server receives and stores the solution.

[0161] Input: Solution data.

[0162] Data processing: The server stores the received solutions in a databank.

[0163] Output: Saved solution data.

[0164] Step 8:

[0165] The user reviews the solution and rates it.

[0166] Input: Saved solution data.

[0167] Data processing: The user uses a device to view the solution and evaluate whether it is useful.

[0168] Output: User rating data.

[0169] Step 9:

[0170] The server updates the helpfulness score of the answer based on the evaluation results.

[0171] Input: User rating data.

[0172] Data processing: The server receives the evaluation results and calculates and updates the usefulness score.

[0173] Output: Updated usefulness score.

[0174] Step 10:

[0175] The server adds the most useful answers to a list of frequently asked questions.

[0176] Input: Updated usefulness score.

[0177] Data processing: The server prioritizes answers in future search results based on their usefulness score.

[0178] Output: The updated query list.

[0179] Step 11:

[0180] Respondents are paid a reward each time their answer is viewed.

[0181] Input: Answer display data and user rating data.

[0182] Data processing: The server calculates rewards based on the number of impressions and ratings.

[0183] Output: Respondent payment data.

[0184] (Application example 1)

[0185] 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."

[0186] Current knowledge sharing systems face challenges such as the inability to obtain useful answers quickly and limited opportunities for respondents to receive appropriate rewards. In particular, content distribution services lack mechanisms that enable users to quickly obtain information of interest. Existing systems also face challenges in the accuracy of searching for similar questions and the transparency of reward distribution. By resolving these challenges, it is hoped that we can improve user convenience and provide incentives to respondents.

[0187] 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.

[0188] In this invention, the server includes a means for a user to input a question, set a price, and send it, a means for comparing the question received by the server with a database of similar questions using a generative AI model, and a means for the server to provide an answer to the similar question if there is one, or to save the answer as a new question if there is not. This allows the user to quickly input and send a question, and enables the AI ​​model to provide an answer based on highly accurate search results.

[0189] "User" refers to a general user who asks questions, answers, gives ratings, etc.

[0190] "Price" refers to the monetary value a user places on a question.

[0191] "Server" refers to the computer system used to store and process questions, answers, and ratings data.

[0192] A "generative AI model" refers to an artificial intelligence algorithm that analyzes data on past questions and answers to search for similar questions and generate optimal answers.

[0193] A "database of similar questions" refers to data storage that stores previously entered questions and their answers.

[0194] The "list of desired answers" refers to a list in which newly added questions are displayed in list form and are viewable by respondents.

[0195] "Solution" refers to the specific answer or solution provided by the respondent to the question.

[0196] "Usefulness score" refers to an indicator that quantifies the usefulness of an answer based on user ratings.

[0197] The "list of frequently displayed questions" refers to a group of items that lists questions and their answers that are displayed preferentially based on their usefulness scores.

[0198] "Reward" refers to monetary compensation received when a respondent provides a useful solution and their answer is viewed and evaluated.

[0199] "Smartphone application" refers to software for mobile devices that allows users and respondents to enter, check, and evaluate questions and answers.

[0200] "Prompt sentence" refers to the input data that a generative AI model uses to optimize questions and answers.

[0201] This invention is a knowledge sharing system that starts when a user inputs a question, sets a price, and submits it. The system is implemented using a server and a smartphone application. The server can use a cloud platform such as Microsoft Azure or Amazon Web Services, and the smartphone application is developed as an application that runs on iOS or Android.

[0202] System configuration

[0203] 1. User inputs and submits question

[0204] Users can submit their questions and set the price for each question through a smartphone application, and the question data is then sent to the server.

[0205] 2. Server parsing and searching the query

[0206] The server analyzes the received question using a generative AI model and compares it with a database of similar questions to perform a search. For example, the AI ​​model can be built using Python machine learning libraries such as TensorFlow and PyTorch.

[0207] 3. Suggesting similar questions and saving new questions

[0208] If the server finds a similar question, it provides the answer to the user, and if there is no similar question, it saves it in the database as a new question.

[0209] 4. Update the list of questions you would like answered

[0210] When a new question is saved to the database, it is automatically added to the list of questions you want answered, which is displayed for other respondents to see.

[0211] 5. Respondents provide answers

[0212] The respondent selects a question from a list of desired answers and provides a solution, which is sent to the server and stored in a database.

[0213] 6. User Rating of Answers

[0214] Users review the answers provided and rate their usefulness, and the rating data is sent to the server.

[0215] 7. Server Update of Usefulness Score

[0216] The server updates the usefulness score of the answer based on the evaluation result and adds the highly useful answers to the list of frequently displayed questions.

[0217] 8. Reward Distribution

[0218] Each time an answer is displayed, the server automatically pays the answerer a reward, a process that can also be achieved using smart contract technology.

[0219] Specific examples

[0220] For example, a user might use the application to set up and submit a question such as "I want to know the latest movie trends" for 500 yen. The server analyzes the question and uses a generative AI model to search a database of similar questions. If there are no similar questions, the question is saved in the database as a new question and added to the list of desired answers.

[0221] If a respondent selects this question and provides an answer such as "Current movie trends are...", the answer is stored on the server and notified to the user. If the user rates this answer as useful and the rating is sent to the server, the server updates the answer's usefulness score. If the answer is deemed useful, it will be displayed preferentially the next time a similar question is searched.

[0222] Prompt Sentence Examples

[0223] Below are some examples of prompts that generative AI models use to optimize questions and answers:

[0224] "What are the latest movie trends?"

[0225] In this way, the system of the present invention allows users to quickly obtain high-quality answers and respondents to receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[0226] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0227] Step 1:

[0228] A user uses a smartphone application to input a question and the price for that question, and then submits it. The inputs include the user name, question, set price, and current time. This data is sent to the server in JSON format.

[0229] Step 2:

[0230] The server receives the received question data and passes it to a generative AI model to analyze similarities. The question content and a database of past questions are given to the generative AI model as input. Data processing involves extracting keywords from the question content using natural language processing technology. The generative AI model compares the question with past questions and evaluates whether there are any similar questions. The output is a list of similar questions or a result indicating that there are no similar questions.

[0231] Step 3:

[0232] The server generates a list of similar questions, and if there are any similar questions, it provides the results to the user. If there are no similar questions, it saves the new question in the database. The input is the data of the new question (user name, question content, price, time), and the output is a confirmation message indicating that the new question has been saved.

[0233] Step 4:

[0234] The server adds a new question to the list of desired answers. The server receives the new question's ID, question content, price, and time as input. The data is processed by adding the new question's data to the database of the list of desired answers. The output is the updated list of desired answers.

[0235] Step 5:

[0236] The respondent uses a smartphone application to select a question from a list of desired answers and provide a solution. The respondent enters the selected question ID and answer content as input into the application and sends them to the server. The output is the answer data sent to the server.

[0237] Step 6:

[0238] The server stores the received response data in a database. The server receives the response content, respondent name, question ID, and time as input. The data is processed by saving the response data in the database. The output is a confirmation message indicating that the response has been saved.

[0239] Step 7:

[0240] The user reviews the provided answers and submits their rating using a smartphone application. As input, the rating score and question ID are entered into the application and sent to the server. The output is a confirmation message indicating that the rating score has arrived at the server.

[0241] Step 8:

[0242] The server updates the usefulness score of the answer based on the evaluation results. The evaluation score and question ID are given as input, and the cumulative score of the answer is calculated as a data operation. The output is the updated usefulness score.

[0243] Step 9:

[0244] The server adds useful answers to a list of frequently asked questions. As input, answers with high evaluation scores and their question IDs are given. In data processing, the server sorts the list of questions based on their usefulness scores, placing useful answers at the top. The output is the updated list of questions.

[0245] Step 10:

[0246] Each time an answer is displayed, the server pays a reward to the respondent. The server receives the number of impressions, rating score, and respondent ID as input. This information is combined to calculate the reward amount as a data calculation. The output is the reward amount paid to the respondent.

[0247] 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.

[0248] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits. This system provides a means to further improve existing problems by incorporating an emotion engine that recognizes users' emotions.

[0249] System Overview

[0250] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[0251] This sends the question and the user's emotional data to the server.

[0252] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[0253] The server then uses an emotion engine to analyze the user's emotions when entering a question.

[0254] If the server finds a similar question, it provides the answer to the user.

[0255] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[0256] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[0257] When the respondent enters and submits their answer, the emotion engine also collects emotional data from the user when rating the answer.

[0258] Users review the answers provided and rate whether they are helpful.

[0259] The user's ratings are sent to the server via the device.

[0260] The server then again uses the emotion engine to analyze the user's emotions at the time of rating.

[0261] The server updates the helpfulness score of the answer based on the evaluation results.

[0262] The usefulness score is adjusted based on the emotional data provided by the emotion engine.

[0263] Answers that are highly useful will be displayed preferentially when other users ask the same question.

[0264] Each time an answer is displayed, the server pays the answerer a reward.

[0265] Rewards are calculated based on the number of times an answer is viewed and its rating.

[0266] Emotional data is also taken into account in reward calculations.

[0267] Example system operation

[0268] The process from posting a question to providing an answer

[0269] For example, user A enters a question such as "How to implement asynchronous processing in JavaScript," sets the price to 200 yen, and submits the question. At the time of question submission, the emotion engine analyzes user A's emotions (e.g., troubled, anxious).

[0270] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions, while also recording emotional data.

[0271] Since no similar questions were found, the question is saved as a new question in the database and added to the list of desired answers. Respondent B selects this question from the list of desired answers and answers as follows: "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[0272] This answer is sent from respondent B's terminal to the server and stored in the database.

[0273] User A reviews the answer and, if he finds it useful, he rates it with 4 stars. During this rating process, the emotion engine again analyzes User A's emotions (satisfied, happy).

[0274] The server receives this rating and sentiment data and updates the helpfulness score of the answer.

[0275] Because of its high usefulness, the next time another user searches for a question on "JavaScript asynchronous processing," this answer will be displayed preferentially. Furthermore, each time the answer is displayed, the server pays a reward to Answerer B. The reward is calculated taking into account the number of views, user ratings, and emotional data.

[0276] In this way, the system of the present invention takes into account the user's emotions to provide high-quality answers more quickly, increase the motivation of respondents, and maximize the effectiveness of knowledge sharing.

[0277] The processing flow will be explained below.

[0278] Step 1:

[0279] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[0280] Step 2:

[0281] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[0282] Step 3:

[0283] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[0284] Step 4:

[0285] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[0286] Step 5:

[0287] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[0288] Step 6:

[0289] The emotion engine analyzes the user's emotions during the question submission process, for example, by analyzing the user's facial expressions and typing speed to determine whether the user is confused or anxious.

[0290] Step 7:

[0291] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[0292] Step 8:

[0293] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[0294] Step 9:

[0295] The server stores the received answers in a database, where the answers are linked to the related questions.

[0296] Step 10:

[0297] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[0298] Step 11:

[0299] The emotion engine analyzes the user's emotions during the user rating process, for example, whether they are satisfied or happy.

[0300] Step 12:

[0301] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[0302] Step 13:

[0303] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and sentiment data and stored in the database.

[0304] Step 14:

[0305] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[0306] Step 15:

[0307] The server pays the respondent a reward each time their answer is displayed. The reward is calculated based on the rating, number of views, and emotional data, and recorded in the respondent's account.

[0308] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[0309] Example 2

[0310] 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."

[0311] Conventional knowledge sharing systems have difficulty in quickly providing appropriate answers to questions entered by users. Furthermore, they have had problems with low user satisfaction because they judge the usefulness of answers solely on quantitative evaluations without considering the user's feelings. Furthermore, the compensation paid to respondents was uniform, which lacked motivation to improve the quality of answers.

[0312] 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.

[0313] In this invention, the server includes means for a user to input a question, set a price, and send it, means for comparing the received question with a database of similar questions using AI to search, means for the server to provide an answer to the similar question if one is found and saving it as a new question if one is not found, means for analyzing the user's emotions when the question is input, means for receiving the user's emotion data, means for adding a new question to a list of desired answers, means for a respondent to select a question and provide a solution, means for sending and saving the answer to the server when an answer is provided, means for the user to check the answer, rate it, and send the rating to the server, means for collecting the user's emotion at the time of rating, means for the server to update the answer's usefulness score based on the rating result, means for correcting the answer's usefulness score based on the emotion data, means for adding highly useful answers to a list of frequently displayed questions, means for paying a reward to the respondent each time an answer is displayed, and means for calculating the reward to the respondent taking the emotion data into consideration. This makes it possible to provide quick and appropriate answers that take the user's emotions into consideration and to realize a reward system that increases the motivation of respondents.

[0314] A "user" is an entity that enters a question and receives an answer in a knowledge sharing system.

[0315] A "question" is information that a user enters and sends to a server to obtain a solution.

[0316] "Price" is the amount of reward that a user sets for a question.

[0317] A "server" is a central control device that receives, processes, searches, stores, and provides answers to questions.

[0318] "AI" is an artificial intelligence technology that analyzes questions, compares them with past questions, and searches for similar questions.

[0319] A "similar question" is a question whose content is similar to that of a newly entered question in the past question database.

[0320] A "database" is a collection of information that stores questions and answers that have been entered in the past.

[0321] A "new question" is a newly entered question for which no similar questions exist in the database.

[0322] An "emotion engine" is a software engine for analyzing a user's emotional state when entering a question or rating.

[0323] "Emotion data" is information about the user's emotional state analyzed by the emotion engine.

[0324] A "wanted answer list" is a list of questions that a respondent can select to provide a solution after a new question has been added.

[0325] A "respondent" is an entity that selects a question from a list of desired answers and provides a solution.

[0326] A "solution" is the content of the answer or advice provided by the respondent to a question.

[0327] A "rating" is feedback that a user gives to indicate the usefulness or satisfaction of a provided answer.

[0328] The "usefulness score" is an index that indicates the usefulness of an answer, calculated based on the user's evaluation results and emotional data.

[0329] The "list of frequently displayed questions" is a list in which questions containing highly useful answers are displayed with priority.

[0330] "Reward" refers to monetary compensation paid to respondents based on user ratings, number of views, and emotional data.

[0331] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. Specifically, this system incorporates an emotion engine to consider the user's emotions and provide high-quality answers.

[0332] Overall system overview

[0333] The user uses the terminal to enter a question, set a price, and submit.

[0334] The user uses a device such as a smartphone or PC to enter the question and reward amount, then presses the send button. This sends the question and the user's emotional data to the server. For example, a user might enter, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await," and set a reward of 200 yen. At this time, the emotion engine analyzes the user's emotions (e.g., troubled, anxious).

[0335] The server receives the question and the user's emotion data.

[0336] The server receives the user's emotion data collected using an emotion engine (e.g., Emotion API) along with the user's submitted question data. The received data is stored in a database.

[0337] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[0338] The server analyzes the received question data using AI (e.g., generative AI models such as BERT or GPT) to understand the content of the question. At the same time, an emotion engine analyzes the user's emotions when they entered the question. The results of this analysis are used for subsequent processing.

[0339] The server compares the question with previous questions in a database to find similar questions.

[0340] The server extracts keywords from the question (e.g., "JavaScript asynchronous processing") and compares them with a database of past questions to search for similar questions. It also uses AI to deeply understand the intent of the question and checks whether similar questions exist in the database.

[0341] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[0342] If a similar question is found, the answer is immediately provided to the user. For example, if a similar question such as "JavaScript asynchronous processing" has previously been answered with the answer "Implement it using Promise or async / await," the answer will be displayed to the user. If no similar question is found, the question is saved in the database as a new question and added to the list of desired answers.

[0343] Respondents use a terminal to select questions and provide solutions.

[0344] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution to that question, and submit it. For example, a respondent might enter a solution such as "Asynchronous processing in JavaScript is implemented using Promise or async / await. A concrete example would be as follows." and submit it.

[0345] Users review the answers provided and rate whether they are helpful.

[0346] The user checks the provided answer on their device and, if they find it useful, rates it with four stars. By pressing the rating button, the rating data is sent to the server. At this time, the emotion engine again analyzes the user's emotions (e.g., satisfied, happy).

[0347] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[0348] The server analyzes the received rating along with the sentiment data (e.g., satisfied) and updates the answer's helpfulness score, which determines whether the answer will be prioritized the next time the same question is asked.

[0349] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[0350] The server calculates and pays rewards to respondents based on the number of times the answer has been viewed, user ratings, and even emotional data. If the answer provided by the respondent is useful to many users and receives a high rating, the respondent will receive a corresponding reward. Reward calculations use payment services (e.g., PayPal or bank transfer).

[0351] Specific examples

[0352] For example, user A sets a question with a reward of 200 yen, saying, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await." The server receives this question, and the emotion engine analyzes user A's emotion as "troubled." The AI ​​then searches the database of past questions to confirm that no similar questions exist, and adds the question as a new question.

[0353] Respondent B selects this new question and provides the following solution: "Asynchronous processing is implemented using Promise or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." User A checks this answer and sends the emotion data "Satisfied" along with a four-star rating to the server. The server updates the usefulness score based on this and pays a reward to Respondent B. In this way, a system is built that provides high-quality answers quickly and increases respondent motivation.

[0354] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0355] Step 1:

[0356] The user inputs and sends a question using a terminal.

[0357] A user uses a smartphone or computer to enter the question and the desired reward amount, then presses the send button. At this time, the following input data is sent from the device to the server: the question, reward amount, user ID, and the user's emotion at the time of input (e.g., text input "How do I implement asynchronous processing in JavaScript?" and reward amount 200 yen). Based on this input, the server receives the question data and the user's emotion data.

[0358] Step 2:

[0359] The server receives the question and the user's emotion data.

[0360] The server receives the question data sent by the user and simultaneously analyzes the user's emotional data using an emotion engine (e.g., EmotionAPI). The input is the text data and emotional data sent by the user, and the output is the question data and emotional data containing the analysis results. These data are stored in a database.

[0361] Step 3:

[0362] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[0363] The server analyzes the received question data using an AI model (e.g., BERT or GPT) to understand the content of the question. This AI model converts the input question text into data in a more understandable format. At the same time, the emotion engine re-analyzes the user's emotions. The input to this process is the question text and emotion data submitted by the user, and the output is the question labeling and emotion analysis results.

[0364] Step 4:

[0365] The server compares the question with previous questions in a database to find similar questions.

[0366] The server extracts keywords from the question analyzed by the AI ​​model (e.g., "JavaScript asynchronous processing") and uses those keywords to compare it with a database of past questions. The input is the question keywords and the database of past questions, and the output is a list of similar questions. The server searches the database for similar questions and generates a list of the results.

[0367] Step 5:

[0368] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[0369] The server displays a list of similar questions to the user, along with the answers to those questions. If no similar questions are found, the question is saved as a new question in the database and added to the list of desired answers. The input to this process is a list of similar questions and their answers, and the output is either displaying the answers to the user or saving the new question.

[0370] Step 6:

[0371] Respondents use a terminal to select questions and provide solutions.

[0372] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution for that question, and submit it. The input includes the solution text, respondent ID, and the selected question ID. The output is the submission of the answer and its storage in a database. For example, a solution such as "Asynchronous processing is implemented using Promises or async / await" may be entered.

[0373] Step 7:

[0374] The user reviews the answers provided and rates whether they are helpful.

[0375] The user checks the provided answer, enters a rating for it, and sends it to the server. At this time, the user's emotions at the time of rating are also analyzed using the emotion engine. The input includes the rating score, user ID, answer ID, and emotion data at the time of rating. The output is the transmission of the rating data and the emotion analysis results. For example, a four-star rating and the emotion "Satisfied" are sent.

[0376] Step 8:

[0377] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[0378] The server analyzes the received rating data and user emotion data and updates the helpfulness score of the answer. This score serves as the basis for prioritizing the answer the next time the same question is asked. The input is the rating data, emotion data, and existing score data, and the output is the updated helpfulness score.

[0379] Step 9:

[0380] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[0381] The server calculates the reward based on the number of times the answer has been viewed, the results of user ratings, and emotional data, and pays it to the respondent. The input is the number of views, rating data, emotional data, and the respondent's ID, and the output is the calculated reward amount and payment. Payment is made using a payment service (e.g., PayPal or bank transfer).

[0382] In this way, based on the detailed processing steps and their specific operations, the system of the present invention provides answers efficiently and in consideration of the user's feelings.

[0383] (Application example 2)

[0384] 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."

[0385] Conventional knowledge sharing systems have the problem that the quality of answers given to users is uniform, making it difficult to respond appropriately to the user's emotions and situation. Furthermore, in brick-and-mortar stores, sales staff are unable to respond appropriately to customers' questions, resulting in a decline in customer satisfaction. A particular issue is the lack of a means to analyze customers' emotions and provide the most appropriate answer for each situation. Furthermore, a method to improve the accuracy of evaluating the usefulness of answers was also needed.

[0386] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0387] In this invention, the server includes: means for a user to input a question, set a price, and send it; means for comparing the received question with a database of similar questions using AI to search; means for the server to provide an answer to the user if a similar question is found, or to save the answer as a new question if one is not found; means for adding the new question to a list of desired answers; means for a respondent to select a question and provide a solution; means for transmitting and saving the provided answer to the server; means for the user to review the answer and rate it, and send the rating to the server; means for the server to update the usefulness score of the answer based on the rating result; means for adding highly useful answers to a list of frequently displayed questions; means for paying a reward to the respondent each time an answer is displayed; means for acquiring questions using voice recognition using smart glasses; means for analyzing emotions at the time of asking the question using an emotion analysis engine; means for the server to provide an optimal answer based on the emotion data; and means for collecting emotion data at the time of rating and improving the quality of customer service. This makes it possible to analyze users' emotions, provide answers adapted to the situation, and improve the quality of customer service in physical stores.

[0388] A "user" is an individual or organization that uses the system to enter questions and receive answers.

[0389] A "Question" is text or audio data about a question or problem that a user wants solved.

[0390] "Price" is the amount of compensation set by the user for providing an answer to a question.

[0391] A "server" is a computer system that processes the data it receives, communicates with the database, and performs analysis.

[0392] "AI" refers to programs or algorithms that use artificial intelligence technology to analyze and process data.

[0393] A "database" is a collection of data that stores questions and their answers and manages them in a searchable format.

[0394] "Similar questions" are past questions that are similar in content to the question entered by the user.

[0395] A "new question" is a question that is newly added because there is no similar question in the database.

[0396] The "answer preference list" is a list of unanswered questions that the respondent can select.

[0397] A "respondent" is an individual or organization that provides solutions or answers to users' questions.

[0398] An "answer" is a solution or information to a user's question provided by a respondent.

[0399] A "rating" is an act by a user indicating the usefulness or satisfaction of a provided answer.

[0400] The "usefulness score" is an evaluation value that indicates the usefulness of an answer.

[0401] "Smart glasses" are wearable devices equipped with information display and voice recognition functions.

[0402] "Speech recognition" is a technology that converts voice data into text data.

[0403] A "sentiment analysis engine" is an algorithm or program that analyzes a user's emotions and outputs the results.

[0404] "Emotion data" is data that indicates the emotional state of the user.

[0405] The present invention is a system that applies a knowledge sharing system using an emotion engine to customer service in a brick-and-mortar store. Specific embodiments of the invention will be described in detail below.

[0406] System configuration

[0407] The system consists of the following main components:

[0408] 1. User Device

[0409] Users input their questions using the smart glasses, which are equipped with voice recognition software that captures the user's questions in real time.

[0410] 2. Server

[0411] The server uses artificial intelligence (AI) to compare the received question with a database of similar questions, and the sentiment at the time of the question is analyzed by a sentiment analysis engine.

[0412] 3. Sentiment Analysis Engine

[0413] The sentiment analysis engine includes algorithms that interpret emotions from user speech and voice data, which is then used by the server to provide and rate answers.

[0414] 4. Database

[0415] A database that stores questions and their answers, searches for similar questions, saves new questions, and updates answer helpfulness scores based on ratings.

[0416] 5. Respondent Device

[0417] Respondents use devices such as smartphones or tablets to select questions from a list of desired answers and enter solutions.

[0418] System Operation

[0419] 1. Questions

[0420] The user uses the smart glasses to voice their inquiry, set a price, and submit. Speech recognition software (e.g., SpeechRecognition) converts this voice data into text data.

[0421] 2. Question analysis and sentiment analysis

[0422] The server analyzes the received question and uses AI to search for similar questions in the database, while a sentiment analysis engine analyzes the user's emotional data.

[0423] 3. Providing answers

[0424] If the server finds an answer to a similar question, it will provide it to the user. If not, it will save it as a new question in the database and add it to the list of desired answers.

[0425] 4. Enter and evaluate your answers

[0426] Respondents select questions from a list of desired answers and provide solutions. At this time, the answers are sent from the respondent's device to the server and stored in a database. Users review the answers provided and rate them. Emotional data is also collected during the rating process.

[0427] 5. Update usefulness score

[0428] The server updates the helpfulness score of answers based on user ratings and sentiment data, and highly rated answers are prioritized when other users ask similar questions.

[0429] 6. Payment of Rewards

[0430] Each time an answer is viewed, the server pays the respondent a reward, which is calculated based on the number of views, ratings, and sentiment data.

[0431] Hardware and software used

[0432] Smart glasses (e.g. Google Glass)

[0433] Voice recognition software (e.g., SpeechRecognition)

[0434] Sentiment analysis engine (Virtual Library: Futabado)

[0435] Database (e.g. MongoDB)

[0436] AI models (e.g., neural networks for natural language processing)

[0437] Specific examples

[0438] For example, a user can use smart glasses to voice-input a question such as "Please tell me how to use this product." The sentiment analysis engine then analyzes the user's sentiment as "confused." The server then searches a database for similar questions and provides an appropriate answer. When a customer rates the answer as "satisfied," the answer's usefulness score is updated. This process ensures that other users can receive a prompt and appropriate answer when they ask a similar question.

[0439] Example prompt for generative AI model:

[0440] Q: How do I use this product?

[0441] Emotion: Confused

[0442] Generate the appropriate answer.

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] The user uses the smart glasses to input a question by voice. This voice data is converted into text data by the smart glasses' voice recognition software (e.g., SpeechRecognition). The input is voice data, and the output is text data. The specific operation at this point is that the voice recognition software converts the voice signal into text.

[0446] Step 2:

[0447] The server analyzes the received question text and uses AI to search for similar questions in a database. The input is the user's question text, and the output is similar questions and their answers. Specifically, it uses natural language processing (NLP) technology to break down the question text into keywords and compare them with previous questions in the database.

[0448] Step 3:

[0449] The server uses a sentiment analysis engine to analyze the user's emotions. The input is the user's question text and voice data, and the output is the analyzed emotion data. The specific operation is to determine the user's emotional state based on the voice tone, speaking rate, text content, etc. extracted from the voice data.

[0450] Step 4:

[0451] If the server finds an answer to a similar question, it provides that answer to the user. If not found, it saves it as a new question in the database and adds it to the list of desired answers. The input is the question text and emotion data, and the output is saving the answer or a new question in the database. Specifically, if a similar question is found, the answer is sent to the user's device; if not, it is saved as a new question in the database.

[0452] Step 5:

[0453] The respondent selects a question from the list of desired answers and provides a solution. The input is the question from the list of desired answers, and the output is the provided answer. The specific operation is that the respondent selects a question using their own terminal, enters the solution, and submits it.

[0454] Step 6:

[0455] The user reviews the provided answer and rates it. This rating is sent to the server, and emotion data is collected at the same time. The input is the user's rating and emotion data, and the output is the saved rating data. The specific operation is that the user enters a star rating or text comment for the answer, and sends the emotion data to the server.

[0456] Step 7:

[0457] The server updates the helpfulness score of an answer based on the user's rating and sentiment data. The input is the rating data and sentiment data, and the output is the updated helpfulness score. The specific operation is to analyze the rating data and sentiment data and adjust / update the helpfulness score of an answer based on it.

[0458] Step 8:

[0459] Each time an answer is viewed, the server pays the answerer a reward. The input is the number of views of the answer and the rating data, and the output is the calculated reward. The specific operation is to calculate the reward based on the number of views and the rating data, and notify the answerer of the result.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] [Second embodiment]

[0464] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] 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.

[0475] 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."

[0476] The present invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. This system has the following means to solve conventional problems:

[0477] System Overview

[0478] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[0479] This sends the question to the server.

[0480] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[0481] If the server finds a similar question, it provides the answer to the user.

[0482] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[0483] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[0484] The answers provided by the respondent are sent to the server and stored in a database.

[0485] Users review the answers provided and rate whether they are helpful.

[0486] The user's ratings are sent to the server via the device.

[0487] The server updates the helpfulness score of the answer based on the evaluation results, so that answers with higher helpfulness are displayed more frequently.

[0488] Answers that are more useful will be displayed preferentially when other users ask the same question.

[0489] Each time an answer is displayed, the server pays the answerer a reward.

[0490] Rewards are calculated based on the number of times an answer is viewed and its rating.

[0491] Example system operation

[0492] The process from posting a question to providing an answer

[0493] For example, user A enters the question "How to implement asynchronous processing in JavaScript," sets the price as 200 yen, and submits it. At this time, user A's device sends this data to the server.

[0494] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions.

[0495] Since no similar questions were found, the question is saved in the database as a new question and added to the list of questions to be answered.

[0496] Respondent B selects this question from the list of preferred answers and answers as follows:

[0497] "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[0498] This answer is sent from respondent B's terminal to the server and stored in the database.

[0499] If User A checks the answer and finds it useful, he or she rates it 4 stars. This rating is sent from User A's device to the server.

[0500] The server receives this rating and updates the helpfulness score of the answer.

[0501] Because of its usefulness, the next time someone searches for a question on "JavaScript asynchronous processing," this answer will be prioritized.

[0502] Furthermore, the server pays a reward to respondent B each time an answer is displayed.

[0503] Rewards are calculated based on the number of times an answer is viewed and user ratings.

[0504] In this way, the system of the present invention allows users to quickly obtain high-quality answers, and respondents receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[0505] The processing flow will be explained below.

[0506] Step 1:

[0507] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[0508] Step 2:

[0509] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[0510] Step 3:

[0511] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[0512] Step 4:

[0513] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[0514] Step 5:

[0515] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[0516] Step 6:

[0517] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[0518] Step 7:

[0519] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[0520] Step 8:

[0521] The server stores the received answers in a database, where the answers are linked to the related questions.

[0522] Step 9:

[0523] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[0524] Step 10:

[0525] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[0526] Step 11:

[0527] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and stored in the database.

[0528] Step 12:

[0529] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[0530] Step 13:

[0531] The server pays the answerer a reward each time their answer is viewed. The reward is calculated based on the rating and number of views, and recorded in the answerer's account.

[0532] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[0533] Example 1

[0534] 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."

[0535] Previously, the exchange of questions and answers for users to obtain specialized knowledge was inefficient, with problems in the quality and speed of answers. Furthermore, respondents were not sufficiently motivated, making it difficult to obtain high-quality answers. This resulted in a decrease in the efficiency of knowledge sharing and dissatisfaction for both users and respondents.

[0536] 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.

[0537] In this invention, the server includes means for a user to input an inquiry, set a price, and send it, means for comparing the inquiry received by the server with a database of similar inquiries using artificial intelligence to search, means for the server to provide an answer to the user if a similar inquiry is found, or to save it as a new inquiry if no similar inquiry is found, means for adding the new inquiry to a list of desired solutions, means for a respondent to select an inquiry and input a solution, means for sending the answer to the server and saving it in the database when an answer is provided, means for the user to check the answer, rate it, and send the rating results to the server, means for the server to update the usefulness score of the answer based on the rating results, means for adding highly useful answers to a list of frequently displayed inquiries, and means for paying a reward to the respondent each time an answer is displayed. This allows users to quickly obtain high-quality answers, motivates responders by receiving appropriate rewards, and enables effective knowledge sharing.

[0538] "User" means any person or entity that uses this system to enter an inquiry and obtain a solution.

[0539] "Device" refers to electronic devices such as computers, smartphones, tablets, etc. used by users or respondents.

[0540] "Server" refers to the central computer system that receives and processes data submitted by users or respondents.

[0541] "Artificial intelligence" refers to the AI ​​technology used by the server to analyze queries and search for similar queries.

[0542] A "databank" refers to a database system in which past inquiries and their responses are recorded and stored.

[0543] "Similar inquiries" refer to past inquiries that are similar in content to the inquiry entered by the user.

[0544] The "List of Requests for Resolution" refers to a list that lists newly submitted inquiries from users and displays them so that respondents can select from them.

[0545] "Respondent" refers to an individual or corporation that selects an inquiry from the list of solutions desired and provides the solution.

[0546] "Evaluation" refers to the feedback that a user sends to the server based on whether the provided answer is useful or not.

[0547] "Usefulness score" refers to an index that the server uses to quantify the usefulness of an answer based on the evaluation results.

[0548] "Display frequency" refers to how often the server displays your answer to other users based on its helpfulness score.

[0549] "Reward" refers to the amount paid by the server each time an answer provided by an answerer is displayed.

[0550] The present invention relates to a knowledge sharing system in which users input and submit inquiries and respondents provide solutions, resulting in mutual benefits. This system provides a means for promoting the effective sharing and utilization of knowledge by allowing users to quickly obtain high-quality answers and by providing appropriate compensation to respondents.

[0551] Specifically, the system allows users to input inquiries using a terminal, set a price, and submit the inquiry. The user-inputted inquiry is then sent to a server. When the server receives the inquiry, it analyzes it using a generative AI model (e.g., OpenAI GPT-3) to extract keywords. It then compares the inquiry with past inquiries in a database to search for similar inquiries.

[0552] If a similar query is found, the server provides the answer to the user. If no similar query is found, the server saves it as a new query in the database and adds it to a list of queries to be resolved. This list can be accessed by the respondent using their terminal, and the respondent can select queries of interest from it.

[0553] After the respondent selects a question, they enter a solution and send it to the server. For example, they provide an answer such as "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." This answer is sent to the server and stored in the database at the same time.

[0554] The user reviews the provided answer and rates it if it is useful. The user sends the rating to the server using their device. The server receives the rating result and updates the helpfulness score of the answer. Based on the updated helpfulness score, answers with high helpfulness are displayed preferentially in the search results for subsequent queries.

[0555] Furthermore, the server pays the answerer a reward each time their answer is displayed, based on the frequency of display and the rating results, which motivates the answerer to continue providing high-quality answers.

[0556] As a specific example, if User A enters "How to implement asynchronous processing in JavaScript" as a question, sets the price to 200 yen, and submits it, the server will extract keywords such as "JavaScript asynchronous processing" and search its past database using a generative AI model. If no similar inquiries are found, the inquiry will be saved as a new inquiry and displayed in the list of desired solutions. If Respondent B selects this inquiry and answers with specific methods for asynchronous processing, the answer will be provided to User A via the server. If User A rates the answer as useful (e.g., 4 stars), the rating result will be sent to the server, and the answer's usefulness score will be updated.

[0557] An example of a prompt is as follows:

[0558] "Please tell me how to implement asynchronous processing in JavaScript. Please include examples of using Promises and async / await."

[0559] As described above, the present invention improves the efficiency and effectiveness of knowledge sharing systems and provides a beneficial environment for both users and respondents.

[0560] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0561] Step 1:

[0562] User enters inquiry, sets price and submits.

[0563] Input: The user uses a terminal to enter an inquiry and price.

[0564] Data processing: The terminal converts the input data into a data format that can be sent to the server.

[0565] Output: The terminal sends the query and price data to the server.

[0566] Step 2:

[0567] The server receives the query.

[0568] Input: Enquiry and pricing data sent from the device.

[0569] Data processing: The server analyzes the received data and extracts keywords such as "JavaScript asynchronous processing."

[0570] Output: Extracted keywords.

[0571] Step 3:

[0572] The server searches the database using the extracted keywords.

[0573] Input: Extracted keywords.

[0574] Data processing: Using a generative AI model (e.g., GPT-3), search for similar queries by comparing them with past queries in a database.

[0575] Output: Search results for similar queries.

[0576] Step 4:

[0577] The server serves similar queries or stores the new query.

[0578] Input: Search results for similar queries.

[0579] Data processing: If a similar query is found, provide the answer to the user. If not, save it as a new query.

[0580] Output: Answers to similar queries or new queries are stored in the databank.

[0581] Step 5:

[0582] Add new inquiries to the list of issues to be resolved.

[0583] Input: New inquiry data.

[0584] Data processing: The server registers the inquiry details in a list of requests for resolution.

[0585] Output: Updated resolution list.

[0586] Step 6:

[0587] The respondent selects the query and provides a solution.

[0588] Input: List of desired solutions.

[0589] Data processing: The respondent uses a terminal to select an inquiry from a list and enter a solution.

[0590] Output: The input solution data.

[0591] Step 7:

[0592] The server receives and stores the solution.

[0593] Input: Solution data.

[0594] Data processing: The server stores the received solutions in a databank.

[0595] Output: Saved solution data.

[0596] Step 8:

[0597] The user reviews the solution and rates it.

[0598] Input: Saved solution data.

[0599] Data processing: The user uses a device to view the solution and evaluate whether it is useful.

[0600] Output: User rating data.

[0601] Step 9:

[0602] The server updates the helpfulness score of the answer based on the evaluation results.

[0603] Input: User rating data.

[0604] Data processing: The server receives the evaluation results and calculates and updates the usefulness score.

[0605] Output: Updated usefulness score.

[0606] Step 10:

[0607] The server adds the most useful answers to a list of frequently asked questions.

[0608] Input: Updated usefulness score.

[0609] Data processing: The server prioritizes answers in future search results based on their usefulness score.

[0610] Output: The updated query list.

[0611] Step 11:

[0612] Respondents are paid a reward each time their answer is viewed.

[0613] Input: Answer display data and user rating data.

[0614] Data processing: The server calculates rewards based on the number of impressions and ratings.

[0615] Output: Respondent payment data.

[0616] (Application example 1)

[0617] 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."

[0618] Current knowledge sharing systems face challenges such as the inability to obtain useful answers quickly and limited opportunities for respondents to receive appropriate rewards. In particular, content distribution services lack mechanisms that enable users to quickly obtain information of interest. Existing systems also face challenges in the accuracy of searching for similar questions and the transparency of reward distribution. By resolving these challenges, it is hoped that we can improve user convenience and provide incentives to respondents.

[0619] 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.

[0620] In this invention, the server includes a means for a user to input a question, set a price, and send it, a means for comparing the question received by the server with a database of similar questions using a generative AI model, and a means for the server to provide an answer to the similar question if there is one, or to save the answer as a new question if there is not. This allows the user to quickly input and send a question, and enables the AI ​​model to provide an answer based on highly accurate search results.

[0621] "User" refers to a general user who asks questions, answers, gives ratings, etc.

[0622] "Price" refers to the monetary value a user places on a question.

[0623] "Server" refers to the computer system used to store and process questions, answers, and ratings data.

[0624] A "generative AI model" refers to an artificial intelligence algorithm that analyzes data on past questions and answers to search for similar questions and generate optimal answers.

[0625] A "database of similar questions" refers to data storage that stores previously entered questions and their answers.

[0626] The "list of desired answers" refers to a list in which newly added questions are displayed in list form and are viewable by respondents.

[0627] "Solution" refers to the specific answer or solution provided by the respondent to the question.

[0628] "Usefulness score" refers to an indicator that quantifies the usefulness of an answer based on user ratings.

[0629] The "list of frequently displayed questions" refers to a group of items that lists questions and their answers that are displayed preferentially based on their usefulness scores.

[0630] "Reward" refers to monetary compensation received when a respondent provides a useful solution and their answer is viewed and evaluated.

[0631] "Smartphone application" refers to software for mobile devices that allows users and respondents to enter, check, and evaluate questions and answers.

[0632] "Prompt sentence" refers to the input data that a generative AI model uses to optimize questions and answers.

[0633] This invention is a knowledge sharing system that starts when a user inputs a question, sets a price, and submits it. The system is implemented using a server and a smartphone application. The server can use a cloud platform such as Microsoft Azure or Amazon Web Services, and the smartphone application is developed as an application that runs on iOS or Android.

[0634] System configuration

[0635] 1. User inputs and submits question

[0636] Users can submit their questions and set the price for each question through a smartphone application, and the question data is then sent to the server.

[0637] 2. Server parsing and searching the query

[0638] The server analyzes the received question using a generative AI model and compares it with a database of similar questions to perform a search. For example, the AI ​​model can be built using Python machine learning libraries such as TensorFlow and PyTorch.

[0639] 3. Suggesting similar questions and saving new questions

[0640] If the server finds a similar question, it provides the answer to the user, and if there is no similar question, it saves it in the database as a new question.

[0641] 4. Update the list of questions you would like answered

[0642] When a new question is saved to the database, it is automatically added to the list of questions you want answered, which is displayed for other respondents to see.

[0643] 5. Respondents provide answers

[0644] The respondent selects a question from a list of desired answers and provides a solution, which is sent to the server and stored in a database.

[0645] 6. User Rating of Answers

[0646] Users review the answers provided and rate their usefulness, and the rating data is sent to the server.

[0647] 7. Server Update of Usefulness Score

[0648] The server updates the usefulness score of the answer based on the evaluation result and adds the highly useful answers to the list of frequently displayed questions.

[0649] 8. Reward Distribution

[0650] Each time an answer is displayed, the server automatically pays the answerer a reward, a process that can also be achieved using smart contract technology.

[0651] Specific examples

[0652] For example, a user might use the application to set up and submit a question such as "I want to know the latest movie trends" for 500 yen. The server analyzes the question and uses a generative AI model to search a database of similar questions. If there are no similar questions, the question is saved in the database as a new question and added to the list of desired answers.

[0653] If a respondent selects this question and provides an answer such as "Current movie trends are...", the answer is stored on the server and notified to the user. If the user rates this answer as useful and the rating is sent to the server, the server updates the answer's usefulness score. If the answer is deemed useful, it will be displayed preferentially the next time a similar question is searched.

[0654] Prompt Sentence Examples

[0655] Below are some examples of prompts that generative AI models use to optimize questions and answers:

[0656] "What are the latest movie trends?"

[0657] In this way, the system of the present invention allows users to quickly obtain high-quality answers and respondents to receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[0658] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0659] Step 1:

[0660] A user uses a smartphone application to input a question and the price for that question, and then submits it. The inputs include the user name, question, set price, and current time. This data is sent to the server in JSON format.

[0661] Step 2:

[0662] The server receives the received question data and passes it to a generative AI model to analyze similarities. The question content and a database of past questions are given to the generative AI model as input. Data processing involves extracting keywords from the question content using natural language processing technology. The generative AI model compares the question with past questions and evaluates whether there are any similar questions. The output is a list of similar questions or a result indicating that there are no similar questions.

[0663] Step 3:

[0664] The server generates a list of similar questions, and if there are any similar questions, it provides the results to the user. If there are no similar questions, it saves the new question in the database. The input is the data of the new question (user name, question content, price, time), and the output is a confirmation message indicating that the new question has been saved.

[0665] Step 4:

[0666] The server adds a new question to the list of desired answers. The server receives the new question's ID, question content, price, and time as input. The data is processed by adding the new question's data to the database of the list of desired answers. The output is the updated list of desired answers.

[0667] Step 5:

[0668] The respondent uses a smartphone application to select a question from a list of desired answers and provide a solution. The respondent enters the selected question ID and answer content as input into the application and sends them to the server. The output is the answer data sent to the server.

[0669] Step 6:

[0670] The server stores the received response data in a database. The server receives the response content, respondent name, question ID, and time as input. The data is processed by saving the response data in the database. The output is a confirmation message indicating that the response has been saved.

[0671] Step 7:

[0672] The user reviews the provided answers and submits their rating using a smartphone application. As input, the rating score and question ID are entered into the application and sent to the server. The output is a confirmation message indicating that the rating score has arrived at the server.

[0673] Step 8:

[0674] The server updates the usefulness score of the answer based on the evaluation results. The evaluation score and question ID are given as input, and the cumulative score of the answer is calculated as a data operation. The output is the updated usefulness score.

[0675] Step 9:

[0676] The server adds useful answers to a list of frequently asked questions. As input, answers with high evaluation scores and their question IDs are given. In data processing, the server sorts the list of questions based on their usefulness scores, placing useful answers at the top. The output is the updated list of questions.

[0677] Step 10:

[0678] Each time an answer is displayed, the server pays a reward to the respondent. The server receives the number of impressions, rating score, and respondent ID as input. This information is combined to calculate the reward amount as a data calculation. The output is the reward amount paid to the respondent.

[0679] 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.

[0680] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits. This system provides a means to further improve existing problems by incorporating an emotion engine that recognizes users' emotions.

[0681] System Overview

[0682] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[0683] This sends the question and the user's emotional data to the server.

[0684] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[0685] The server then uses an emotion engine to analyze the user's emotions when entering a question.

[0686] If the server finds a similar question, it provides the answer to the user.

[0687] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[0688] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[0689] When the respondent enters and submits their answer, the emotion engine also collects emotional data from the user when rating the answer.

[0690] Users review the answers provided and rate whether they are helpful.

[0691] The user's ratings are sent to the server via the device.

[0692] The server then again uses the emotion engine to analyze the user's emotions at the time of rating.

[0693] The server updates the helpfulness score of the answer based on the evaluation results.

[0694] The usefulness score is adjusted based on the emotional data provided by the emotion engine.

[0695] Answers that are highly useful will be displayed preferentially when other users ask the same question.

[0696] Each time an answer is displayed, the server pays the answerer a reward.

[0697] Rewards are calculated based on the number of times an answer is viewed and its rating.

[0698] Emotional data is also taken into account in reward calculations.

[0699] Example system operation

[0700] The process from posting a question to providing an answer

[0701] For example, user A enters a question such as "How to implement asynchronous processing in JavaScript," sets the price to 200 yen, and submits the question. At the time of question submission, the emotion engine analyzes user A's emotions (e.g., troubled, anxious).

[0702] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions, while also recording emotional data.

[0703] Since no similar questions were found, the question is saved as a new question in the database and added to the list of desired answers. Respondent B selects this question from the list of desired answers and answers as follows: "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[0704] This answer is sent from respondent B's terminal to the server and stored in the database.

[0705] User A reviews the answer and, if he finds it useful, he rates it with 4 stars. During this rating process, the emotion engine again analyzes User A's emotions (satisfied, happy).

[0706] The server receives this rating and sentiment data and updates the helpfulness score of the answer.

[0707] Because of its high usefulness, the next time another user searches for a question on "JavaScript asynchronous processing," this answer will be displayed preferentially. Furthermore, each time the answer is displayed, the server pays a reward to Answerer B. The reward is calculated taking into account the number of views, user ratings, and emotional data.

[0708] In this way, the system of the present invention takes into account the user's emotions to provide high-quality answers more quickly, increase the motivation of respondents, and maximize the effectiveness of knowledge sharing.

[0709] The processing flow will be explained below.

[0710] Step 1:

[0711] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[0712] Step 2:

[0713] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[0714] Step 3:

[0715] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[0716] Step 4:

[0717] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[0718] Step 5:

[0719] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[0720] Step 6:

[0721] The emotion engine analyzes the user's emotions during the question submission process, for example, by analyzing the user's facial expressions and typing speed to determine whether the user is confused or anxious.

[0722] Step 7:

[0723] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[0724] Step 8:

[0725] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[0726] Step 9:

[0727] The server stores the received answers in a database, where the answers are linked to the related questions.

[0728] Step 10:

[0729] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[0730] Step 11:

[0731] The emotion engine analyzes the user's emotions during the user rating process, for example, whether they are satisfied or happy.

[0732] Step 12:

[0733] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[0734] Step 13:

[0735] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and sentiment data and stored in the database.

[0736] Step 14:

[0737] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[0738] Step 15:

[0739] The server pays the respondent a reward each time their answer is displayed. The reward is calculated based on the rating, number of views, and emotional data, and recorded in the respondent's account.

[0740] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[0741] Example 2

[0742] 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."

[0743] Conventional knowledge sharing systems have difficulty in quickly providing appropriate answers to questions entered by users. Furthermore, they have had problems with low user satisfaction because they judge the usefulness of answers solely on quantitative evaluations without considering the user's feelings. Furthermore, the compensation paid to respondents was uniform, which lacked motivation to improve the quality of answers.

[0744] 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.

[0745] In this invention, the server includes means for a user to input a question, set a price, and send it, means for comparing the received question with a database of similar questions using AI to search, means for the server to provide an answer to the similar question if one is found and saving it as a new question if one is not found, means for analyzing the user's emotions when the question is input, means for receiving the user's emotion data, means for adding a new question to a list of desired answers, means for a respondent to select a question and provide a solution, means for sending and saving the answer to the server when an answer is provided, means for the user to check the answer, rate it, and send the rating to the server, means for collecting the user's emotion at the time of rating, means for the server to update the answer's usefulness score based on the rating result, means for correcting the answer's usefulness score based on the emotion data, means for adding highly useful answers to a list of frequently displayed questions, means for paying a reward to the respondent each time an answer is displayed, and means for calculating the reward to the respondent taking the emotion data into consideration. This makes it possible to provide quick and appropriate answers that take the user's emotions into consideration and to realize a reward system that increases the motivation of respondents.

[0746] A "user" is an entity that enters a question and receives an answer in a knowledge sharing system.

[0747] A "question" is information that a user enters and sends to a server to obtain a solution.

[0748] "Price" is the amount of reward that a user sets for a question.

[0749] A "server" is a central control device that receives, processes, searches, stores, and provides answers to questions.

[0750] "AI" is an artificial intelligence technology that analyzes questions, compares them with past questions, and searches for similar questions.

[0751] A "similar question" is a question whose content is similar to that of a newly entered question in the past question database.

[0752] A "database" is a collection of information that stores questions and answers that have been entered in the past.

[0753] A "new question" is a newly entered question for which no similar questions exist in the database.

[0754] An "emotion engine" is a software engine for analyzing a user's emotional state when entering a question or rating.

[0755] "Emotion data" is information about the user's emotional state analyzed by the emotion engine.

[0756] A "wanted answer list" is a list of questions that a respondent can select to provide a solution after a new question has been added.

[0757] A "respondent" is an entity that selects a question from a list of desired answers and provides a solution.

[0758] A "solution" is the content of the answer or advice provided by the respondent to a question.

[0759] A "rating" is feedback that a user gives to indicate the usefulness or satisfaction of a provided answer.

[0760] The "usefulness score" is an index that indicates the usefulness of an answer, calculated based on the user's evaluation results and emotional data.

[0761] The "list of frequently displayed questions" is a list in which questions containing highly useful answers are displayed with priority.

[0762] "Reward" refers to monetary compensation paid to respondents based on user ratings, number of views, and emotional data.

[0763] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. Specifically, this system incorporates an emotion engine to consider the user's emotions and provide high-quality answers.

[0764] Overall system overview

[0765] The user uses the terminal to enter a question, set a price, and submit.

[0766] The user uses a device such as a smartphone or PC to enter the question and reward amount, then presses the send button. This sends the question and the user's emotional data to the server. For example, a user might enter, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await," and set a reward of 200 yen. At this time, the emotion engine analyzes the user's emotions (e.g., troubled, anxious).

[0767] The server receives the question and the user's emotion data.

[0768] The server receives the user's emotion data collected using an emotion engine (e.g., Emotion API) along with the user's submitted question data. The received data is stored in a database.

[0769] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[0770] The server analyzes the received question data using AI (e.g., generative AI models such as BERT or GPT) to understand the content of the question. At the same time, an emotion engine analyzes the user's emotions when they entered the question. The results of this analysis are used for subsequent processing.

[0771] The server compares the question with previous questions in a database to find similar questions.

[0772] The server extracts keywords from the question (e.g., "JavaScript asynchronous processing") and compares them with a database of past questions to search for similar questions. It also uses AI to deeply understand the intent of the question and checks whether similar questions exist in the database.

[0773] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[0774] If a similar question is found, the answer is immediately provided to the user. For example, if a similar question such as "JavaScript asynchronous processing" has previously been answered with the answer "Implement it using Promise or async / await," the answer will be displayed to the user. If no similar question is found, the question is saved in the database as a new question and added to the list of desired answers.

[0775] Respondents use a terminal to select questions and provide solutions.

[0776] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution to that question, and submit it. For example, a respondent might enter a solution such as "Asynchronous processing in JavaScript is implemented using Promise or async / await. A concrete example would be as follows." and submit it.

[0777] Users review the answers provided and rate whether they are helpful.

[0778] The user checks the provided answer on their device and, if they find it useful, rates it with four stars. By pressing the rating button, the rating data is sent to the server. At this time, the emotion engine again analyzes the user's emotions (e.g., satisfied, happy).

[0779] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[0780] The server analyzes the received rating along with the sentiment data (e.g., satisfied) and updates the answer's helpfulness score, which determines whether the answer will be prioritized the next time the same question is asked.

[0781] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[0782] The server calculates and pays rewards to respondents based on the number of times the answer has been viewed, user ratings, and even emotional data. If the answer provided by the respondent is useful to many users and receives a high rating, the respondent will receive a corresponding reward. Reward calculations use payment services (e.g., PayPal or bank transfer).

[0783] Specific examples

[0784] For example, user A sets a question with a reward of 200 yen, saying, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await." The server receives this question, and the emotion engine analyzes user A's emotion as "troubled." The AI ​​then searches the database of past questions to confirm that no similar questions exist, and adds the question as a new question.

[0785] Respondent B selects this new question and provides the following solution: "Asynchronous processing is implemented using Promise or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." User A checks this answer and sends the emotion data "Satisfied" along with a four-star rating to the server. The server updates the usefulness score based on this and pays a reward to Respondent B. In this way, a system is built that provides high-quality answers quickly and increases respondent motivation.

[0786] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0787] Step 1:

[0788] The user inputs and sends a question using a terminal.

[0789] A user uses a smartphone or computer to enter the question and the desired reward amount, then presses the send button. At this time, the following input data is sent from the device to the server: the question, reward amount, user ID, and the user's emotion at the time of input (e.g., text input "How do I implement asynchronous processing in JavaScript?" and reward amount 200 yen). Based on this input, the server receives the question data and the user's emotion data.

[0790] Step 2:

[0791] The server receives the question and the user's emotion data.

[0792] The server receives the question data sent by the user and simultaneously analyzes the user's emotional data using an emotion engine (e.g., EmotionAPI). The input is the text data and emotional data sent by the user, and the output is the question data and emotional data containing the analysis results. These data are stored in a database.

[0793] Step 3:

[0794] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[0795] The server analyzes the received question data using an AI model (e.g., BERT or GPT) to understand the content of the question. This AI model converts the input question text into data in a more understandable format. At the same time, the emotion engine re-analyzes the user's emotions. The input to this process is the question text and emotion data submitted by the user, and the output is the question labeling and emotion analysis results.

[0796] Step 4:

[0797] The server compares the question with previous questions in a database to find similar questions.

[0798] The server extracts keywords from the question analyzed by the AI ​​model (e.g., "JavaScript asynchronous processing") and uses those keywords to compare it with a database of past questions. The input is the question keywords and the database of past questions, and the output is a list of similar questions. The server searches the database for similar questions and generates a list of the results.

[0799] Step 5:

[0800] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[0801] The server displays a list of similar questions to the user, along with the answers to those questions. If no similar questions are found, the question is saved as a new question in the database and added to the list of desired answers. The input to this process is a list of similar questions and their answers, and the output is either displaying the answers to the user or saving the new question.

[0802] Step 6:

[0803] Respondents use a terminal to select questions and provide solutions.

[0804] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution for that question, and submit it. The input includes the solution text, respondent ID, and the selected question ID. The output is the submission of the answer and its storage in a database. For example, a solution such as "Asynchronous processing is implemented using Promises or async / await" may be entered.

[0805] Step 7:

[0806] The user reviews the answers provided and rates whether they are helpful.

[0807] The user checks the provided answer, enters a rating for it, and sends it to the server. At this time, the user's emotions at the time of rating are also analyzed using the emotion engine. The input includes the rating score, user ID, answer ID, and emotion data at the time of rating. The output is the transmission of the rating data and the emotion analysis results. For example, a four-star rating and the emotion "Satisfied" are sent.

[0808] Step 8:

[0809] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[0810] The server analyzes the received rating data and user emotion data and updates the helpfulness score of the answer. This score serves as the basis for prioritizing the answer the next time the same question is asked. The input is the rating data, emotion data, and existing score data, and the output is the updated helpfulness score.

[0811] Step 9:

[0812] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[0813] The server calculates the reward based on the number of times the answer has been viewed, the results of user ratings, and emotional data, and pays it to the respondent. The input is the number of views, rating data, emotional data, and the respondent's ID, and the output is the calculated reward amount and payment. Payment is made using a payment service (e.g., PayPal or bank transfer).

[0814] In this way, based on the detailed processing steps and their specific operations, the system of the present invention provides answers efficiently and in consideration of the user's feelings.

[0815] (Application example 2)

[0816] 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."

[0817] Conventional knowledge sharing systems have the problem that the quality of answers given to users is uniform, making it difficult to respond appropriately to the user's emotions and situation. Furthermore, in brick-and-mortar stores, sales staff are unable to respond appropriately to customers' questions, resulting in a decline in customer satisfaction. A particular issue is the lack of a means to analyze customers' emotions and provide the most appropriate answer for each situation. Furthermore, a method to improve the accuracy of evaluating the usefulness of answers was also needed.

[0818] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0819] In this invention, the server includes: means for a user to input a question, set a price, and send it; means for comparing the received question with a database of similar questions using AI to search; means for the server to provide an answer to the user if a similar question is found, or to save the answer as a new question if one is not found; means for adding the new question to a list of desired answers; means for a respondent to select a question and provide a solution; means for transmitting and saving the provided answer to the server; means for the user to review the answer and rate it, and send the rating to the server; means for the server to update the usefulness score of the answer based on the rating result; means for adding highly useful answers to a list of frequently displayed questions; means for paying a reward to the respondent each time an answer is displayed; means for acquiring questions using voice recognition using smart glasses; means for analyzing emotions at the time of asking the question using an emotion analysis engine; means for the server to provide an optimal answer based on the emotion data; and means for collecting emotion data at the time of rating and improving the quality of customer service. This makes it possible to analyze users' emotions, provide answers adapted to the situation, and improve the quality of customer service in physical stores.

[0820] A "user" is an individual or organization that uses the system to enter questions and receive answers.

[0821] A "Question" is text or audio data about a question or problem that a user wants solved.

[0822] "Price" is the amount of compensation set by the user for providing an answer to a question.

[0823] A "server" is a computer system that processes the data it receives, communicates with the database, and performs analysis.

[0824] "AI" refers to programs or algorithms that use artificial intelligence technology to analyze and process data.

[0825] A "database" is a collection of data that stores questions and their answers and manages them in a searchable format.

[0826] "Similar questions" are past questions that are similar in content to the question entered by the user.

[0827] A "new question" is a question that is newly added because there is no similar question in the database.

[0828] The "answer preference list" is a list of unanswered questions that the respondent can select.

[0829] A "respondent" is an individual or organization that provides solutions or answers to users' questions.

[0830] An "answer" is a solution or information to a user's question provided by a respondent.

[0831] A "rating" is an act by a user indicating the usefulness or satisfaction of a provided answer.

[0832] The "usefulness score" is an evaluation value that indicates the usefulness of an answer.

[0833] "Smart glasses" are wearable devices equipped with information display and voice recognition functions.

[0834] "Speech recognition" is a technology that converts voice data into text data.

[0835] A "sentiment analysis engine" is an algorithm or program that analyzes a user's emotions and outputs the results.

[0836] "Emotion data" is data that indicates the emotional state of the user.

[0837] The present invention is a system that applies a knowledge sharing system using an emotion engine to customer service in a brick-and-mortar store. Specific embodiments of the invention will be described in detail below.

[0838] System configuration

[0839] The system consists of the following main components:

[0840] 1. User Device

[0841] Users input their questions using the smart glasses, which are equipped with voice recognition software that captures the user's questions in real time.

[0842] 2. Server

[0843] The server uses artificial intelligence (AI) to compare the received question with a database of similar questions, and the sentiment at the time of the question is analyzed by a sentiment analysis engine.

[0844] 3. Sentiment Analysis Engine

[0845] The sentiment analysis engine includes algorithms that interpret emotions from user speech and voice data, which is then used by the server to provide and rate answers.

[0846] 4. Database

[0847] A database that stores questions and their answers, searches for similar questions, saves new questions, and updates answer helpfulness scores based on ratings.

[0848] 5. Respondent Device

[0849] Respondents use devices such as smartphones or tablets to select questions from a list of desired answers and enter solutions.

[0850] System Operation

[0851] 1. Questions

[0852] The user uses the smart glasses to voice their inquiry, set a price, and submit. Speech recognition software (e.g., SpeechRecognition) converts this voice data into text data.

[0853] 2. Question analysis and sentiment analysis

[0854] The server analyzes the received question and uses AI to search for similar questions in the database, while a sentiment analysis engine analyzes the user's emotional data.

[0855] 3. Providing answers

[0856] If the server finds an answer to a similar question, it will provide it to the user. If not, it will save it as a new question in the database and add it to the list of desired answers.

[0857] 4. Enter and evaluate your answers

[0858] Respondents select questions from a list of desired answers and provide solutions. At this time, the answers are sent from the respondent's device to the server and stored in a database. Users review the answers provided and rate them. Emotional data is also collected during the rating process.

[0859] 5. Update usefulness score

[0860] The server updates the helpfulness score of answers based on user ratings and sentiment data, and highly rated answers are prioritized when other users ask similar questions.

[0861] 6. Payment of Rewards

[0862] Each time an answer is viewed, the server pays the respondent a reward, which is calculated based on the number of views, ratings, and sentiment data.

[0863] Hardware and software used

[0864] Smart glasses (e.g. Google Glass)

[0865] Voice recognition software (e.g., SpeechRecognition)

[0866] Sentiment analysis engine (Virtual Library: Futabado)

[0867] Database (e.g. MongoDB)

[0868] AI models (e.g., neural networks for natural language processing)

[0869] Specific examples

[0870] For example, a user can use smart glasses to voice-input a question such as "Please tell me how to use this product." The sentiment analysis engine then analyzes the user's sentiment as "confused." The server then searches a database for similar questions and provides an appropriate answer. When a customer rates the answer as "satisfied," the answer's usefulness score is updated. This process ensures that other users can receive a prompt and appropriate answer when they ask a similar question.

[0871] Example prompt for generative AI model:

[0872] Q: How do I use this product?

[0873] Emotion: Confused

[0874] Generate the appropriate answer.

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The user uses the smart glasses to input a question by voice. This voice data is converted into text data by the smart glasses' voice recognition software (e.g., SpeechRecognition). The input is voice data, and the output is text data. The specific operation at this point is that the voice recognition software converts the voice signal into text.

[0878] Step 2:

[0879] The server analyzes the received question text and uses AI to search for similar questions in a database. The input is the user's question text, and the output is similar questions and their answers. Specifically, it uses natural language processing (NLP) technology to break down the question text into keywords and compare them with previous questions in the database.

[0880] Step 3:

[0881] The server uses a sentiment analysis engine to analyze the user's emotions. The input is the user's question text and voice data, and the output is the analyzed emotion data. The specific operation is to determine the user's emotional state based on the voice tone, speaking rate, text content, etc. extracted from the voice data.

[0882] Step 4:

[0883] If the server finds an answer to a similar question, it provides that answer to the user. If not found, it saves it as a new question in the database and adds it to the list of desired answers. The input is the question text and emotion data, and the output is saving the answer or a new question in the database. Specifically, if a similar question is found, the answer is sent to the user's device; if not, it is saved as a new question in the database.

[0884] Step 5:

[0885] The respondent selects a question from the list of desired answers and provides a solution. The input is the question from the list of desired answers, and the output is the provided answer. The specific operation is that the respondent selects a question using their own terminal, enters the solution, and submits it.

[0886] Step 6:

[0887] The user reviews the provided answer and rates it. This rating is sent to the server, and emotion data is collected at the same time. The input is the user's rating and emotion data, and the output is the saved rating data. The specific operation is that the user enters a star rating or text comment for the answer, and sends the emotion data to the server.

[0888] Step 7:

[0889] The server updates the helpfulness score of an answer based on the user's rating and sentiment data. The input is the rating data and sentiment data, and the output is the updated helpfulness score. The specific operation is to analyze the rating data and sentiment data and adjust / update the helpfulness score of an answer based on it.

[0890] Step 8:

[0891] Each time an answer is viewed, the server pays the answerer a reward. The input is the number of views of the answer and the rating data, and the output is the calculated reward. The specific operation is to calculate the reward based on the number of views and the rating data, and notify the answerer of the result.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] [Third embodiment]

[0896] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0897] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0898] 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).

[0899] 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.

[0900] 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.

[0901] 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).

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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."

[0908] The present invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. This system has the following means to solve conventional problems:

[0909] System Overview

[0910] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[0911] This sends the question to the server.

[0912] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[0913] If the server finds a similar question, it provides the answer to the user.

[0914] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[0915] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[0916] The answers provided by the respondent are sent to the server and stored in a database.

[0917] Users review the answers provided and rate whether they are helpful.

[0918] The user's ratings are sent to the server via the device.

[0919] The server updates the helpfulness score of the answer based on the evaluation results, so that answers with higher helpfulness are displayed more frequently.

[0920] Answers that are more useful will be displayed preferentially when other users ask the same question.

[0921] Each time an answer is displayed, the server pays the answerer a reward.

[0922] Rewards are calculated based on the number of times an answer is viewed and its rating.

[0923] Example system operation

[0924] The process from posting a question to providing an answer

[0925] For example, user A enters the question "How to implement asynchronous processing in JavaScript," sets the price as 200 yen, and submits it. At this time, user A's device sends this data to the server.

[0926] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions.

[0927] Since no similar questions were found, the question is saved in the database as a new question and added to the list of questions to be answered.

[0928] Respondent B selects this question from the list of preferred answers and answers as follows:

[0929] "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[0930] This answer is sent from respondent B's terminal to the server and stored in the database.

[0931] If User A checks the answer and finds it useful, he or she rates it 4 stars. This rating is sent from User A's device to the server.

[0932] The server receives this rating and updates the helpfulness score of the answer.

[0933] Because of its usefulness, the next time someone searches for a question on "JavaScript asynchronous processing," this answer will be prioritized.

[0934] Furthermore, the server pays a reward to respondent B each time an answer is displayed.

[0935] Rewards are calculated based on the number of times an answer is viewed and user ratings.

[0936] In this way, the system of the present invention allows users to quickly obtain high-quality answers, and respondents receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[0937] The processing flow will be explained below.

[0938] Step 1:

[0939] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[0940] Step 2:

[0941] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[0942] Step 3:

[0943] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[0944] Step 4:

[0945] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[0946] Step 5:

[0947] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[0948] Step 6:

[0949] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[0950] Step 7:

[0951] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[0952] Step 8:

[0953] The server stores the received answers in a database, where the answers are linked to the related questions.

[0954] Step 9:

[0955] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[0956] Step 10:

[0957] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[0958] Step 11:

[0959] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and stored in the database.

[0960] Step 12:

[0961] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[0962] Step 13:

[0963] The server pays the answerer a reward each time their answer is viewed. The reward is calculated based on the rating and number of views, and recorded in the answerer's account.

[0964] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[0965] Example 1

[0966] 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."

[0967] Previously, the exchange of questions and answers for users to obtain specialized knowledge was inefficient, with problems in the quality and speed of answers. Furthermore, respondents were not sufficiently motivated, making it difficult to obtain high-quality answers. This resulted in a decrease in the efficiency of knowledge sharing and dissatisfaction for both users and respondents.

[0968] 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.

[0969] In this invention, the server includes means for a user to input an inquiry, set a price, and send it, means for comparing the inquiry received by the server with a database of similar inquiries using artificial intelligence to search, means for the server to provide an answer to the user if a similar inquiry is found, or to save it as a new inquiry if no similar inquiry is found, means for adding the new inquiry to a list of desired solutions, means for a respondent to select an inquiry and input a solution, means for sending the answer to the server and saving it in the database when an answer is provided, means for the user to check the answer, rate it, and send the rating results to the server, means for the server to update the usefulness score of the answer based on the rating results, means for adding highly useful answers to a list of frequently displayed inquiries, and means for paying a reward to the respondent each time an answer is displayed. This allows users to quickly obtain high-quality answers, motivates responders by receiving appropriate rewards, and enables effective knowledge sharing.

[0970] "User" means any person or entity that uses this system to enter an inquiry and obtain a solution.

[0971] "Device" refers to electronic devices such as computers, smartphones, tablets, etc. used by users or respondents.

[0972] "Server" refers to the central computer system that receives and processes data submitted by users or respondents.

[0973] "Artificial intelligence" refers to the AI ​​technology used by the server to analyze queries and search for similar queries.

[0974] A "databank" refers to a database system in which past inquiries and their responses are recorded and stored.

[0975] "Similar inquiries" refer to past inquiries that are similar in content to the inquiry entered by the user.

[0976] The "List of Requests for Resolution" refers to a list that lists newly submitted inquiries from users and displays them so that respondents can select from them.

[0977] "Respondent" refers to an individual or corporation that selects an inquiry from the list of solutions desired and provides the solution.

[0978] "Evaluation" refers to the feedback that a user sends to the server based on whether the provided answer is useful or not.

[0979] "Usefulness score" refers to an index that the server uses to quantify the usefulness of an answer based on the evaluation results.

[0980] "Display frequency" refers to how often the server displays your answer to other users based on its helpfulness score.

[0981] "Reward" refers to the amount paid by the server each time an answer provided by an answerer is displayed.

[0982] The present invention relates to a knowledge sharing system in which users input and submit inquiries and respondents provide solutions, resulting in mutual benefits. This system provides a means for promoting the effective sharing and utilization of knowledge by allowing users to quickly obtain high-quality answers and by providing appropriate compensation to respondents.

[0983] Specifically, the system allows users to input inquiries using a terminal, set a price, and submit the inquiry. The user-inputted inquiry is then sent to a server. When the server receives the inquiry, it analyzes it using a generative AI model (e.g., OpenAI GPT-3) to extract keywords. It then compares the inquiry with past inquiries in a database to search for similar inquiries.

[0984] If a similar query is found, the server provides the answer to the user. If no similar query is found, the server saves it as a new query in the database and adds it to a list of queries to be resolved. This list can be accessed by the respondent using their terminal, and the respondent can select queries of interest from it.

[0985] After the respondent selects a question, they enter a solution and send it to the server. For example, they provide an answer such as "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." This answer is sent to the server and stored in the database at the same time.

[0986] The user reviews the provided answer and rates it if it is useful. The user sends the rating to the server using their device. The server receives the rating result and updates the helpfulness score of the answer. Based on the updated helpfulness score, answers with high helpfulness are displayed preferentially in the search results for subsequent queries.

[0987] Furthermore, the server pays the answerer a reward each time their answer is displayed, based on the frequency of display and the rating results, which motivates the answerer to continue providing high-quality answers.

[0988] As a specific example, if User A enters "How to implement asynchronous processing in JavaScript" as a question, sets the price to 200 yen, and submits it, the server will extract keywords such as "JavaScript asynchronous processing" and search its past database using a generative AI model. If no similar inquiries are found, the inquiry will be saved as a new inquiry and displayed in the list of desired solutions. If Respondent B selects this inquiry and answers with specific methods for asynchronous processing, the answer will be provided to User A via the server. If User A rates the answer as useful (e.g., 4 stars), the rating result will be sent to the server, and the answer's usefulness score will be updated.

[0989] An example of a prompt is as follows:

[0990] "Please tell me how to implement asynchronous processing in JavaScript. Please include examples of using Promises and async / await."

[0991] As described above, the present invention improves the efficiency and effectiveness of knowledge sharing systems and provides a beneficial environment for both users and respondents.

[0992] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0993] Step 1:

[0994] User enters inquiry, sets price and submits.

[0995] Input: The user uses a terminal to enter an inquiry and price.

[0996] Data processing: The terminal converts the input data into a data format that can be sent to the server.

[0997] Output: The terminal sends the query and price data to the server.

[0998] Step 2:

[0999] The server receives the query.

[1000] Input: Enquiry and pricing data sent from the device.

[1001] Data processing: The server analyzes the received data and extracts keywords such as "JavaScript asynchronous processing."

[1002] Output: Extracted keywords.

[1003] Step 3:

[1004] The server searches the database using the extracted keywords.

[1005] Input: Extracted keywords.

[1006] Data processing: Using a generative AI model (e.g., GPT-3), search for similar queries by comparing them with past queries in a database.

[1007] Output: Search results for similar queries.

[1008] Step 4:

[1009] The server serves similar queries or stores the new query.

[1010] Input: Search results for similar queries.

[1011] Data processing: If a similar query is found, provide the answer to the user. If not, save it as a new query.

[1012] Output: Answers to similar queries or new queries are stored in the databank.

[1013] Step 5:

[1014] Add new inquiries to the list of issues to be resolved.

[1015] Input: New inquiry data.

[1016] Data processing: The server registers the inquiry details in a list of requests for resolution.

[1017] Output: Updated resolution list.

[1018] Step 6:

[1019] The respondent selects the query and provides a solution.

[1020] Input: List of desired solutions.

[1021] Data processing: The respondent uses a terminal to select an inquiry from a list and enter a solution.

[1022] Output: The input solution data.

[1023] Step 7:

[1024] The server receives and stores the solution.

[1025] Input: Solution data.

[1026] Data processing: The server stores the received solutions in a databank.

[1027] Output: Saved solution data.

[1028] Step 8:

[1029] The user reviews the solution and rates it.

[1030] Input: Saved solution data.

[1031] Data processing: The user uses a device to view the solution and evaluate whether it is useful.

[1032] Output: User rating data.

[1033] Step 9:

[1034] The server updates the helpfulness score of the answer based on the evaluation results.

[1035] Input: User rating data.

[1036] Data processing: The server receives the evaluation results and calculates and updates the usefulness score.

[1037] Output: Updated usefulness score.

[1038] Step 10:

[1039] The server adds the most useful answers to a list of frequently asked questions.

[1040] Input: Updated usefulness score.

[1041] Data processing: The server prioritizes answers in future search results based on their usefulness score.

[1042] Output: The updated query list.

[1043] Step 11:

[1044] Respondents are paid a reward each time their answer is viewed.

[1045] Input: Answer display data and user rating data.

[1046] Data processing: The server calculates rewards based on the number of impressions and ratings.

[1047] Output: Respondent payment data.

[1048] (Application example 1)

[1049] 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."

[1050] Current knowledge sharing systems face challenges such as the inability to obtain useful answers quickly and limited opportunities for respondents to receive appropriate rewards. In particular, content distribution services lack mechanisms that enable users to quickly obtain information of interest. Existing systems also face challenges in the accuracy of searching for similar questions and the transparency of reward distribution. By resolving these challenges, it is hoped that we can improve user convenience and provide incentives to respondents.

[1051] 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.

[1052] In this invention, the server includes a means for a user to input a question, set a price, and send it, a means for comparing the question received by the server with a database of similar questions using a generative AI model, and a means for the server to provide an answer to the similar question if there is one, or to save the answer as a new question if there is not. This allows the user to quickly input and send a question, and enables the AI ​​model to provide an answer based on highly accurate search results.

[1053] "User" refers to a general user who asks questions, answers, gives ratings, etc.

[1054] "Price" refers to the monetary value a user places on a question.

[1055] "Server" refers to the computer system used to store and process questions, answers, and ratings data.

[1056] A "generative AI model" refers to an artificial intelligence algorithm that analyzes data on past questions and answers to search for similar questions and generate optimal answers.

[1057] A "database of similar questions" refers to data storage that stores previously entered questions and their answers.

[1058] The "list of desired answers" refers to a list in which newly added questions are displayed in list form and are viewable by respondents.

[1059] "Solution" refers to the specific answer or solution provided by the respondent to the question.

[1060] "Usefulness score" refers to an indicator that quantifies the usefulness of an answer based on user ratings.

[1061] The "list of frequently displayed questions" refers to a group of items that lists questions and their answers that are displayed preferentially based on their usefulness scores.

[1062] "Reward" refers to monetary compensation received when a respondent provides a useful solution and their answer is viewed and evaluated.

[1063] "Smartphone application" refers to software for mobile devices that allows users and respondents to enter, check, and evaluate questions and answers.

[1064] "Prompt sentence" refers to the input data that a generative AI model uses to optimize questions and answers.

[1065] This invention is a knowledge sharing system that starts when a user inputs a question, sets a price, and submits it. The system is implemented using a server and a smartphone application. The server can use a cloud platform such as Microsoft Azure or Amazon Web Services, and the smartphone application is developed as an application that runs on iOS or Android.

[1066] System configuration

[1067] 1. User inputs and submits question

[1068] Users can submit their questions and set the price for each question through a smartphone application, and the question data is then sent to the server.

[1069] 2. Server parsing and searching the query

[1070] The server analyzes the received question using a generative AI model and compares it with a database of similar questions to perform a search. For example, the AI ​​model can be built using Python machine learning libraries such as TensorFlow and PyTorch.

[1071] 3. Suggesting similar questions and saving new questions

[1072] If the server finds a similar question, it provides the answer to the user, and if there is no similar question, it saves it in the database as a new question.

[1073] 4. Update the list of questions you would like answered

[1074] When a new question is saved to the database, it is automatically added to the list of questions you want answered, which is displayed for other respondents to see.

[1075] 5. Respondents provide answers

[1076] The respondent selects a question from a list of desired answers and provides a solution, which is sent to the server and stored in a database.

[1077] 6. User Rating of Answers

[1078] Users review the answers provided and rate their usefulness, and the rating data is sent to the server.

[1079] 7. Server Update of Usefulness Score

[1080] The server updates the usefulness score of the answer based on the evaluation result and adds the highly useful answers to the list of frequently displayed questions.

[1081] 8. Reward Distribution

[1082] Each time an answer is displayed, the server automatically pays the answerer a reward, a process that can also be achieved using smart contract technology.

[1083] Specific examples

[1084] For example, a user might use the application to set up and submit a question such as "I want to know the latest movie trends" for 500 yen. The server analyzes the question and uses a generative AI model to search a database of similar questions. If there are no similar questions, the question is saved in the database as a new question and added to the list of desired answers.

[1085] If a respondent selects this question and provides an answer such as "Current movie trends are...", the answer is stored on the server and notified to the user. If the user rates this answer as useful and the rating is sent to the server, the server updates the answer's usefulness score. If the answer is deemed useful, it will be displayed preferentially the next time a similar question is searched.

[1086] Prompt Sentence Examples

[1087] Below are some examples of prompts that generative AI models use to optimize questions and answers:

[1088] "What are the latest movie trends?"

[1089] In this way, the system of the present invention allows users to quickly obtain high-quality answers and respondents to receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[1090] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1091] Step 1:

[1092] A user uses a smartphone application to input a question and the price for that question, and then submits it. The inputs include the user name, question, set price, and current time. This data is sent to the server in JSON format.

[1093] Step 2:

[1094] The server receives the received question data and passes it to a generative AI model to analyze similarities. The question content and a database of past questions are given to the generative AI model as input. Data processing involves extracting keywords from the question content using natural language processing technology. The generative AI model compares the question with past questions and evaluates whether there are any similar questions. The output is a list of similar questions or a result indicating that there are no similar questions.

[1095] Step 3:

[1096] The server generates a list of similar questions, and if there are any similar questions, it provides the results to the user. If there are no similar questions, it saves the new question in the database. The input is the data of the new question (user name, question content, price, time), and the output is a confirmation message indicating that the new question has been saved.

[1097] Step 4:

[1098] The server adds a new question to the list of desired answers. The server receives the new question's ID, question content, price, and time as input. The data is processed by adding the new question's data to the database of the list of desired answers. The output is the updated list of desired answers.

[1099] Step 5:

[1100] The respondent uses a smartphone application to select a question from a list of desired answers and provide a solution. The respondent enters the selected question ID and answer content as input into the application and sends them to the server. The output is the answer data sent to the server.

[1101] Step 6:

[1102] The server stores the received response data in a database. The server receives the response content, respondent name, question ID, and time as input. The data is processed by saving the response data in the database. The output is a confirmation message indicating that the response has been saved.

[1103] Step 7:

[1104] The user reviews the provided answers and submits their rating using a smartphone application. As input, the rating score and question ID are entered into the application and sent to the server. The output is a confirmation message indicating that the rating score has arrived at the server.

[1105] Step 8:

[1106] The server updates the usefulness score of the answer based on the evaluation results. The evaluation score and question ID are given as input, and the cumulative score of the answer is calculated as a data operation. The output is the updated usefulness score.

[1107] Step 9:

[1108] The server adds useful answers to a list of frequently asked questions. As input, answers with high evaluation scores and their question IDs are given. In data processing, the server sorts the list of questions based on their usefulness scores, placing useful answers at the top. The output is the updated list of questions.

[1109] Step 10:

[1110] Each time an answer is displayed, the server pays a reward to the respondent. The server receives the number of impressions, rating score, and respondent ID as input. This information is combined to calculate the reward amount as a data calculation. The output is the reward amount paid to the respondent.

[1111] 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.

[1112] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits. This system provides a means to further improve existing problems by incorporating an emotion engine that recognizes users' emotions.

[1113] System Overview

[1114] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[1115] This sends the question and the user's emotional data to the server.

[1116] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[1117] The server then uses an emotion engine to analyze the user's emotions when entering a question.

[1118] If the server finds a similar question, it provides the answer to the user.

[1119] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[1120] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[1121] When the respondent enters and submits their answer, the emotion engine also collects emotional data from the user when rating the answer.

[1122] Users review the answers provided and rate whether they are helpful.

[1123] The user's ratings are sent to the server via the device.

[1124] The server then again uses the emotion engine to analyze the user's emotions at the time of rating.

[1125] The server updates the helpfulness score of the answer based on the evaluation results.

[1126] The usefulness score is adjusted based on the emotional data provided by the emotion engine.

[1127] Answers that are highly useful will be displayed preferentially when other users ask the same question.

[1128] Each time an answer is displayed, the server pays the answerer a reward.

[1129] Rewards are calculated based on the number of times an answer is viewed and its rating.

[1130] Emotional data is also taken into account in reward calculations.

[1131] Example system operation

[1132] The process from posting a question to providing an answer

[1133] For example, user A enters a question such as "How to implement asynchronous processing in JavaScript," sets the price to 200 yen, and submits the question. At the time of question submission, the emotion engine analyzes user A's emotions (e.g., troubled, anxious).

[1134] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions, while also recording emotional data.

[1135] Since no similar questions were found, the question is saved as a new question in the database and added to the list of desired answers. Respondent B selects this question from the list of desired answers and answers as follows: "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[1136] This answer is sent from respondent B's terminal to the server and stored in the database.

[1137] User A reviews the answer and, if he finds it useful, he rates it with 4 stars. During this rating process, the emotion engine again analyzes User A's emotions (satisfied, happy).

[1138] The server receives this rating and sentiment data and updates the helpfulness score of the answer.

[1139] Because of its high usefulness, the next time another user searches for a question on "JavaScript asynchronous processing," this answer will be displayed preferentially. Furthermore, each time the answer is displayed, the server pays a reward to Answerer B. The reward is calculated taking into account the number of views, user ratings, and emotional data.

[1140] In this way, the system of the present invention takes into account the user's emotions to provide high-quality answers more quickly, increase the motivation of respondents, and maximize the effectiveness of knowledge sharing.

[1141] The processing flow will be explained below.

[1142] Step 1:

[1143] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[1144] Step 2:

[1145] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[1146] Step 3:

[1147] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[1148] Step 4:

[1149] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[1150] Step 5:

[1151] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[1152] Step 6:

[1153] The emotion engine analyzes the user's emotions during the question submission process, for example, by analyzing the user's facial expressions and typing speed to determine whether the user is confused or anxious.

[1154] Step 7:

[1155] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[1156] Step 8:

[1157] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[1158] Step 9:

[1159] The server stores the received answers in a database, where the answers are linked to the related questions.

[1160] Step 10:

[1161] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[1162] Step 11:

[1163] The emotion engine analyzes the user's emotions during the user rating process, for example, whether they are satisfied or happy.

[1164] Step 12:

[1165] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[1166] Step 13:

[1167] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and sentiment data and stored in the database.

[1168] Step 14:

[1169] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[1170] Step 15:

[1171] The server pays the respondent a reward each time their answer is displayed. The reward is calculated based on the rating, number of views, and emotional data, and recorded in the respondent's account.

[1172] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[1173] Example 2

[1174] 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."

[1175] Conventional knowledge sharing systems have difficulty in quickly providing appropriate answers to questions entered by users. Furthermore, they have had problems with low user satisfaction because they judge the usefulness of answers solely on quantitative evaluations without considering the user's feelings. Furthermore, the compensation paid to respondents was uniform, which lacked motivation to improve the quality of answers.

[1176] 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.

[1177] In this invention, the server includes means for a user to input a question, set a price, and send it, means for comparing the received question with a database of similar questions using AI to search, means for the server to provide an answer to the similar question if one is found and saving it as a new question if one is not found, means for analyzing the user's emotions when the question is input, means for receiving the user's emotion data, means for adding a new question to a list of desired answers, means for a respondent to select a question and provide a solution, means for sending and saving the answer to the server when an answer is provided, means for the user to check the answer, rate it, and send the rating to the server, means for collecting the user's emotion at the time of rating, means for the server to update the answer's usefulness score based on the rating result, means for correcting the answer's usefulness score based on the emotion data, means for adding highly useful answers to a list of frequently displayed questions, means for paying a reward to the respondent each time an answer is displayed, and means for calculating the reward to the respondent taking the emotion data into consideration. This makes it possible to provide quick and appropriate answers that take the user's emotions into consideration and to realize a reward system that increases the motivation of respondents.

[1178] A "user" is an entity that enters a question and receives an answer in a knowledge sharing system.

[1179] A "question" is information that a user enters and sends to a server to obtain a solution.

[1180] "Price" is the amount of reward that a user sets for a question.

[1181] A "server" is a central control device that receives, processes, searches, stores, and provides answers to questions.

[1182] "AI" is an artificial intelligence technology that analyzes questions, compares them with past questions, and searches for similar questions.

[1183] A "similar question" is a question whose content is similar to that of a newly entered question in the past question database.

[1184] A "database" is a collection of information that stores questions and answers that have been entered in the past.

[1185] A "new question" is a newly entered question for which no similar questions exist in the database.

[1186] An "emotion engine" is a software engine for analyzing a user's emotional state when entering a question or rating.

[1187] "Emotion data" is information about the user's emotional state analyzed by the emotion engine.

[1188] A "wanted answer list" is a list of questions that a respondent can select to provide a solution after a new question has been added.

[1189] A "respondent" is an entity that selects a question from a list of desired answers and provides a solution.

[1190] A "solution" is the content of the answer or advice provided by the respondent to a question.

[1191] A "rating" is feedback that a user gives to indicate the usefulness or satisfaction of a provided answer.

[1192] The "usefulness score" is an index that indicates the usefulness of an answer, calculated based on the user's evaluation results and emotional data.

[1193] The "list of frequently displayed questions" is a list in which questions containing highly useful answers are displayed with priority.

[1194] "Reward" refers to monetary compensation paid to respondents based on user ratings, number of views, and emotional data.

[1195] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. Specifically, this system incorporates an emotion engine to consider the user's emotions and provide high-quality answers.

[1196] Overall system overview

[1197] The user uses the terminal to enter a question, set a price, and submit.

[1198] The user uses a device such as a smartphone or PC to enter the question and reward amount, then presses the send button. This sends the question and the user's emotional data to the server. For example, a user might enter, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await," and set a reward of 200 yen. At this time, the emotion engine analyzes the user's emotions (e.g., troubled, anxious).

[1199] The server receives the question and the user's emotion data.

[1200] The server receives the user's emotion data collected using an emotion engine (e.g., Emotion API) along with the user's submitted question data. The received data is stored in a database.

[1201] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[1202] The server analyzes the received question data using AI (e.g., generative AI models such as BERT or GPT) to understand the content of the question. At the same time, an emotion engine analyzes the user's emotions when they entered the question. The results of this analysis are used for subsequent processing.

[1203] The server compares the question with previous questions in a database to find similar questions.

[1204] The server extracts keywords from the question (e.g., "JavaScript asynchronous processing") and compares them with a database of past questions to search for similar questions. It also uses AI to deeply understand the intent of the question and checks whether similar questions exist in the database.

[1205] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[1206] If a similar question is found, the answer is immediately provided to the user. For example, if a similar question such as "JavaScript asynchronous processing" has previously been answered with the answer "Implement it using Promise or async / await," the answer will be displayed to the user. If no similar question is found, the question is saved in the database as a new question and added to the list of desired answers.

[1207] Respondents use a terminal to select questions and provide solutions.

[1208] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution to that question, and submit it. For example, a respondent might enter a solution such as "Asynchronous processing in JavaScript is implemented using Promise or async / await. A concrete example would be as follows." and submit it.

[1209] Users review the answers provided and rate whether they are helpful.

[1210] The user checks the provided answer on their device and, if they find it useful, rates it with four stars. By pressing the rating button, the rating data is sent to the server. At this time, the emotion engine again analyzes the user's emotions (e.g., satisfied, happy).

[1211] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[1212] The server analyzes the received rating along with the sentiment data (e.g., satisfied) and updates the answer's helpfulness score, which determines whether the answer will be prioritized the next time the same question is asked.

[1213] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[1214] The server calculates and pays rewards to respondents based on the number of times the answer has been viewed, user ratings, and even emotional data. If the answer provided by the respondent is useful to many users and receives a high rating, the respondent will receive a corresponding reward. Reward calculations use payment services (e.g., PayPal or bank transfer).

[1215] Specific examples

[1216] For example, user A sets a question with a reward of 200 yen, saying, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await." The server receives this question, and the emotion engine analyzes user A's emotion as "troubled." The AI ​​then searches the database of past questions to confirm that no similar questions exist, and adds the question as a new question.

[1217] Respondent B selects this new question and provides the following solution: "Asynchronous processing is implemented using Promise or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." User A checks this answer and sends the emotion data "Satisfied" along with a four-star rating to the server. The server updates the usefulness score based on this and pays a reward to Respondent B. In this way, a system is built that provides high-quality answers quickly and increases respondent motivation.

[1218] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1219] Step 1:

[1220] The user inputs and sends a question using a terminal.

[1221] A user uses a smartphone or computer to enter the question and the desired reward amount, then presses the send button. At this time, the following input data is sent from the device to the server: the question, reward amount, user ID, and the user's emotion at the time of input (e.g., text input "How do I implement asynchronous processing in JavaScript?" and reward amount 200 yen). Based on this input, the server receives the question data and the user's emotion data.

[1222] Step 2:

[1223] The server receives the question and the user's emotion data.

[1224] The server receives the question data sent by the user and simultaneously analyzes the user's emotional data using an emotion engine (e.g., EmotionAPI). The input is the text data and emotional data sent by the user, and the output is the question data and emotional data containing the analysis results. These data are stored in a database.

[1225] Step 3:

[1226] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[1227] The server analyzes the received question data using an AI model (e.g., BERT or GPT) to understand the content of the question. This AI model converts the input question text into data in a more understandable format. At the same time, the emotion engine re-analyzes the user's emotions. The input to this process is the question text and emotion data submitted by the user, and the output is the question labeling and emotion analysis results.

[1228] Step 4:

[1229] The server compares the question with previous questions in a database to find similar questions.

[1230] The server extracts keywords from the question analyzed by the AI ​​model (e.g., "JavaScript asynchronous processing") and uses those keywords to compare it with a database of past questions. The input is the question keywords and the database of past questions, and the output is a list of similar questions. The server searches the database for similar questions and generates a list of the results.

[1231] Step 5:

[1232] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[1233] The server displays a list of similar questions to the user, along with the answers to those questions. If no similar questions are found, the question is saved as a new question in the database and added to the list of desired answers. The input to this process is a list of similar questions and their answers, and the output is either displaying the answers to the user or saving the new question.

[1234] Step 6:

[1235] Respondents use a terminal to select questions and provide solutions.

[1236] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution for that question, and submit it. The input includes the solution text, respondent ID, and the selected question ID. The output is the submission of the answer and its storage in a database. For example, a solution such as "Asynchronous processing is implemented using Promises or async / await" may be entered.

[1237] Step 7:

[1238] The user reviews the answers provided and rates whether they are helpful.

[1239] The user checks the provided answer, enters a rating for it, and sends it to the server. At this time, the user's emotions at the time of rating are also analyzed using the emotion engine. The input includes the rating score, user ID, answer ID, and emotion data at the time of rating. The output is the transmission of the rating data and the emotion analysis results. For example, a four-star rating and the emotion "Satisfied" are sent.

[1240] Step 8:

[1241] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[1242] The server analyzes the received rating data and user emotion data and updates the helpfulness score of the answer. This score serves as the basis for prioritizing the answer the next time the same question is asked. The input is the rating data, emotion data, and existing score data, and the output is the updated helpfulness score.

[1243] Step 9:

[1244] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[1245] The server calculates the reward based on the number of times the answer has been viewed, the results of user ratings, and emotional data, and pays it to the respondent. The input is the number of views, rating data, emotional data, and the respondent's ID, and the output is the calculated reward amount and payment. Payment is made using a payment service (e.g., PayPal or bank transfer).

[1246] In this way, based on the detailed processing steps and their specific operations, the system of the present invention provides answers efficiently and in consideration of the user's feelings.

[1247] (Application example 2)

[1248] 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."

[1249] Conventional knowledge sharing systems have the problem that the quality of answers given to users is uniform, making it difficult to respond appropriately to the user's emotions and situation. Furthermore, in brick-and-mortar stores, sales staff are unable to respond appropriately to customers' questions, resulting in a decline in customer satisfaction. A particular issue is the lack of a means to analyze customers' emotions and provide the most appropriate answer for each situation. Furthermore, a method to improve the accuracy of evaluating the usefulness of answers was also needed.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1251] In this invention, the server includes: means for a user to input a question, set a price, and send it; means for comparing the received question with a database of similar questions using AI to search; means for the server to provide an answer to the user if a similar question is found, or to save the answer as a new question if one is not found; means for adding the new question to a list of desired answers; means for a respondent to select a question and provide a solution; means for transmitting and saving the provided answer to the server; means for the user to review the answer and rate it, and send the rating to the server; means for the server to update the usefulness score of the answer based on the rating result; means for adding highly useful answers to a list of frequently displayed questions; means for paying a reward to the respondent each time an answer is displayed; means for acquiring questions using voice recognition using smart glasses; means for analyzing emotions at the time of asking the question using an emotion analysis engine; means for the server to provide an optimal answer based on the emotion data; and means for collecting emotion data at the time of rating and improving the quality of customer service. This makes it possible to analyze users' emotions, provide answers adapted to the situation, and improve the quality of customer service in physical stores.

[1252] A "user" is an individual or organization that uses the system to enter questions and receive answers.

[1253] A "Question" is text or audio data about a question or problem that a user wants solved.

[1254] "Price" is the amount of compensation set by the user for providing an answer to a question.

[1255] A "server" is a computer system that processes the data it receives, communicates with the database, and performs analysis.

[1256] "AI" refers to programs or algorithms that use artificial intelligence technology to analyze and process data.

[1257] A "database" is a collection of data that stores questions and their answers and manages them in a searchable format.

[1258] "Similar questions" are past questions that are similar in content to the question entered by the user.

[1259] A "new question" is a question that is newly added because there is no similar question in the database.

[1260] The "answer preference list" is a list of unanswered questions that the respondent can select.

[1261] A "respondent" is an individual or organization that provides solutions or answers to users' questions.

[1262] An "answer" is a solution or information to a user's question provided by a respondent.

[1263] A "rating" is an act by a user indicating the usefulness or satisfaction of a provided answer.

[1264] The "usefulness score" is an evaluation value that indicates the usefulness of an answer.

[1265] "Smart glasses" are wearable devices equipped with information display and voice recognition functions.

[1266] "Speech recognition" is a technology that converts voice data into text data.

[1267] A "sentiment analysis engine" is an algorithm or program that analyzes a user's emotions and outputs the results.

[1268] "Emotion data" is data that indicates the emotional state of the user.

[1269] The present invention is a system that applies a knowledge sharing system using an emotion engine to customer service in a brick-and-mortar store. Specific embodiments of the invention will be described in detail below.

[1270] System configuration

[1271] The system consists of the following main components:

[1272] 1. User Device

[1273] Users input their questions using the smart glasses, which are equipped with voice recognition software that captures the user's questions in real time.

[1274] 2. Server

[1275] The server uses artificial intelligence (AI) to compare the received question with a database of similar questions, and the sentiment at the time of the question is analyzed by a sentiment analysis engine.

[1276] 3. Sentiment Analysis Engine

[1277] The sentiment analysis engine includes algorithms that interpret emotions from user speech and voice data, which is then used by the server to provide and rate answers.

[1278] 4. Database

[1279] A database that stores questions and their answers, searches for similar questions, saves new questions, and updates answer helpfulness scores based on ratings.

[1280] 5. Respondent Device

[1281] Respondents use devices such as smartphones or tablets to select questions from a list of desired answers and enter solutions.

[1282] System Operation

[1283] 1. Questions

[1284] The user uses the smart glasses to voice their inquiry, set a price, and submit. Speech recognition software (e.g., SpeechRecognition) converts this voice data into text data.

[1285] 2. Question analysis and sentiment analysis

[1286] The server analyzes the received question and uses AI to search for similar questions in the database, while a sentiment analysis engine analyzes the user's emotional data.

[1287] 3. Providing answers

[1288] If the server finds an answer to a similar question, it will provide it to the user. If not, it will save it as a new question in the database and add it to the list of desired answers.

[1289] 4. Enter and evaluate your answers

[1290] Respondents select questions from a list of desired answers and provide solutions. At this time, the answers are sent from the respondent's device to the server and stored in a database. Users review the answers provided and rate them. Emotional data is also collected during the rating process.

[1291] 5. Update usefulness score

[1292] The server updates the helpfulness score of answers based on user ratings and sentiment data, and highly rated answers are prioritized when other users ask similar questions.

[1293] 6. Payment of Rewards

[1294] Each time an answer is viewed, the server pays the respondent a reward, which is calculated based on the number of views, ratings, and sentiment data.

[1295] Hardware and software used

[1296] Smart glasses (e.g. Google Glass)

[1297] Voice recognition software (e.g., SpeechRecognition)

[1298] Sentiment analysis engine (Virtual Library: Futabado)

[1299] Database (e.g. MongoDB)

[1300] AI models (e.g., neural networks for natural language processing)

[1301] Specific examples

[1302] For example, a user can use smart glasses to voice-input a question such as "Please tell me how to use this product." The sentiment analysis engine then analyzes the user's sentiment as "confused." The server then searches a database for similar questions and provides an appropriate answer. When a customer rates the answer as "satisfied," the answer's usefulness score is updated. This process ensures that other users can receive a prompt and appropriate answer when they ask a similar question.

[1303] Example prompt for generative AI model:

[1304] Q: How do I use this product?

[1305] Emotion: Confused

[1306] Generate the appropriate answer.

[1307] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1308] Step 1:

[1309] The user uses the smart glasses to input a question by voice. This voice data is converted into text data by the smart glasses' voice recognition software (e.g., SpeechRecognition). The input is voice data, and the output is text data. The specific operation at this point is that the voice recognition software converts the voice signal into text.

[1310] Step 2:

[1311] The server analyzes the received question text and uses AI to search for similar questions in a database. The input is the user's question text, and the output is similar questions and their answers. Specifically, it uses natural language processing (NLP) technology to break down the question text into keywords and compare them with previous questions in the database.

[1312] Step 3:

[1313] The server uses a sentiment analysis engine to analyze the user's emotions. The input is the user's question text and voice data, and the output is the analyzed emotion data. The specific operation is to determine the user's emotional state based on the voice tone, speaking rate, text content, etc. extracted from the voice data.

[1314] Step 4:

[1315] If the server finds an answer to a similar question, it provides that answer to the user. If not found, it saves it as a new question in the database and adds it to the list of desired answers. The input is the question text and emotion data, and the output is saving the answer or a new question in the database. Specifically, if a similar question is found, the answer is sent to the user's device; if not, it is saved as a new question in the database.

[1316] Step 5:

[1317] The respondent selects a question from the list of desired answers and provides a solution. The input is the question from the list of desired answers, and the output is the provided answer. The specific operation is that the respondent selects a question using their own terminal, enters the solution, and submits it.

[1318] Step 6:

[1319] The user reviews the provided answer and rates it. This rating is sent to the server, and emotion data is collected at the same time. The input is the user's rating and emotion data, and the output is the saved rating data. The specific operation is that the user enters a star rating or text comment for the answer, and sends the emotion data to the server.

[1320] Step 7:

[1321] The server updates the helpfulness score of an answer based on the user's rating and sentiment data. The input is the rating data and sentiment data, and the output is the updated helpfulness score. The specific operation is to analyze the rating data and sentiment data and adjust / update the helpfulness score of an answer based on it.

[1322] Step 8:

[1323] Each time an answer is viewed, the server pays the answerer a reward. The input is the number of views of the answer and the rating data, and the output is the calculated reward. The specific operation is to calculate the reward based on the number of views and the rating data, and notify the answerer of the result.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] [Fourth embodiment]

[1328] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1329] 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.

[1330] 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).

[1331] 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.

[1332] 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.

[1333] 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).

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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."

[1341] The present invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. This system has the following means to solve conventional problems:

[1342] System Overview

[1343] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[1344] This sends the question to the server.

[1345] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[1346] If the server finds a similar question, it provides the answer to the user.

[1347] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[1348] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[1349] The answers provided by the respondent are sent to the server and stored in a database.

[1350] Users review the answers provided and rate whether they are helpful.

[1351] The user's ratings are sent to the server via the device.

[1352] The server updates the helpfulness score of the answer based on the evaluation results, so that answers with higher helpfulness are displayed more frequently.

[1353] Answers that are more useful will be displayed preferentially when other users ask the same question.

[1354] Each time an answer is displayed, the server pays the answerer a reward.

[1355] Rewards are calculated based on the number of times an answer is viewed and its rating.

[1356] Example system operation

[1357] The process from posting a question to providing an answer

[1358] For example, user A enters the question "How to implement asynchronous processing in JavaScript," sets the price as 200 yen, and submits it. At this time, user A's device sends this data to the server.

[1359] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions.

[1360] Since no similar questions were found, the question is saved in the database as a new question and added to the list of questions to be answered.

[1361] Respondent B selects this question from the list of preferred answers and answers as follows:

[1362] "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[1363] This answer is sent from respondent B's terminal to the server and stored in the database.

[1364] If User A checks the answer and finds it useful, he or she rates it 4 stars. This rating is sent from User A's device to the server.

[1365] The server receives this rating and updates the helpfulness score of the answer.

[1366] Because of its usefulness, the next time someone searches for a question on "JavaScript asynchronous processing," this answer will be prioritized.

[1367] Furthermore, the server pays a reward to respondent B each time an answer is displayed.

[1368] Rewards are calculated based on the number of times an answer is viewed and user ratings.

[1369] In this way, the system of the present invention allows users to quickly obtain high-quality answers, and respondents receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[1370] The processing flow will be explained below.

[1371] Step 1:

[1372] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[1373] Step 2:

[1374] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[1375] Step 3:

[1376] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[1377] Step 4:

[1378] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[1379] Step 5:

[1380] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[1381] Step 6:

[1382] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[1383] Step 7:

[1384] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[1385] Step 8:

[1386] The server stores the received answers in a database, where the answers are linked to the related questions.

[1387] Step 9:

[1388] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[1389] Step 10:

[1390] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[1391] Step 11:

[1392] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and stored in the database.

[1393] Step 12:

[1394] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[1395] Step 13:

[1396] The server pays the answerer a reward each time their answer is viewed. The reward is calculated based on the rating and number of views, and recorded in the answerer's account.

[1397] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[1398] Example 1

[1399] 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."

[1400] Previously, the exchange of questions and answers for users to obtain specialized knowledge was inefficient, with problems in the quality and speed of answers. Furthermore, respondents were not sufficiently motivated, making it difficult to obtain high-quality answers. This resulted in a decrease in the efficiency of knowledge sharing and dissatisfaction for both users and respondents.

[1401] 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.

[1402] In this invention, the server includes means for a user to input an inquiry, set a price, and send it, means for comparing the inquiry received by the server with a database of similar inquiries using artificial intelligence to search, means for the server to provide an answer to the user if a similar inquiry is found, or to save it as a new inquiry if no similar inquiry is found, means for adding the new inquiry to a list of desired solutions, means for a respondent to select an inquiry and input a solution, means for sending the answer to the server and saving it in the database when an answer is provided, means for the user to check the answer, rate it, and send the rating results to the server, means for the server to update the usefulness score of the answer based on the rating results, means for adding highly useful answers to a list of frequently displayed inquiries, and means for paying a reward to the respondent each time an answer is displayed. This allows users to quickly obtain high-quality answers, motivates responders by receiving appropriate rewards, and enables effective knowledge sharing.

[1403] "User" means any person or entity that uses this system to enter an inquiry and obtain a solution.

[1404] "Device" refers to electronic devices such as computers, smartphones, tablets, etc. used by users or respondents.

[1405] "Server" refers to the central computer system that receives and processes data submitted by users or respondents.

[1406] "Artificial intelligence" refers to the AI ​​technology used by the server to analyze queries and search for similar queries.

[1407] A "databank" refers to a database system in which past inquiries and their responses are recorded and stored.

[1408] "Similar inquiries" refer to past inquiries that are similar in content to the inquiry entered by the user.

[1409] The "List of Requests for Resolution" refers to a list that lists newly submitted inquiries from users and displays them so that respondents can select from them.

[1410] "Respondent" refers to an individual or corporation that selects an inquiry from the list of solutions desired and provides the solution.

[1411] "Evaluation" refers to the feedback that a user sends to the server based on whether the provided answer is useful or not.

[1412] "Usefulness score" refers to an index that the server uses to quantify the usefulness of an answer based on the evaluation results.

[1413] "Display frequency" refers to how often the server displays your answer to other users based on its helpfulness score.

[1414] "Reward" refers to the amount paid by the server each time an answer provided by an answerer is displayed.

[1415] The present invention relates to a knowledge sharing system in which users input and submit inquiries and respondents provide solutions, resulting in mutual benefits. This system provides a means for promoting the effective sharing and utilization of knowledge by allowing users to quickly obtain high-quality answers and by providing appropriate compensation to respondents.

[1416] Specifically, the system allows users to input inquiries using a terminal, set a price, and submit the inquiry. The user-inputted inquiry is then sent to a server. When the server receives the inquiry, it analyzes it using a generative AI model (e.g., OpenAI GPT-3) to extract keywords. It then compares the inquiry with past inquiries in a database to search for similar inquiries.

[1417] If a similar query is found, the server provides the answer to the user. If no similar query is found, the server saves it as a new query in the database and adds it to a list of queries to be resolved. This list can be accessed by the respondent using their terminal, and the respondent can select queries of interest from it.

[1418] After the respondent selects a question, they enter a solution and send it to the server. For example, they provide an answer such as "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." This answer is sent to the server and stored in the database at the same time.

[1419] The user reviews the provided answer and rates it if it is useful. The user sends the rating to the server using their device. The server receives the rating result and updates the helpfulness score of the answer. Based on the updated helpfulness score, answers with high helpfulness are displayed preferentially in the search results for subsequent queries.

[1420] Furthermore, the server pays the answerer a reward each time their answer is displayed, based on the frequency of display and the rating results, which motivates the answerer to continue providing high-quality answers.

[1421] As a specific example, if User A enters "How to implement asynchronous processing in JavaScript" as a question, sets the price to 200 yen, and submits it, the server will extract keywords such as "JavaScript asynchronous processing" and search its past database using a generative AI model. If no similar inquiries are found, the inquiry will be saved as a new inquiry and displayed in the list of desired solutions. If Respondent B selects this inquiry and answers with specific methods for asynchronous processing, the answer will be provided to User A via the server. If User A rates the answer as useful (e.g., 4 stars), the rating result will be sent to the server, and the answer's usefulness score will be updated.

[1422] An example of a prompt is as follows:

[1423] "Please tell me how to implement asynchronous processing in JavaScript. Please include examples of using Promises and async / await."

[1424] As described above, the present invention improves the efficiency and effectiveness of knowledge sharing systems and provides a beneficial environment for both users and respondents.

[1425] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] User enters inquiry, sets price and submits.

[1428] Input: The user uses a terminal to enter an inquiry and price.

[1429] Data processing: The terminal converts the input data into a data format that can be sent to the server.

[1430] Output: The terminal sends the query and price data to the server.

[1431] Step 2:

[1432] The server receives the query.

[1433] Input: Enquiry and pricing data sent from the device.

[1434] Data processing: The server analyzes the received data and extracts keywords such as "JavaScript asynchronous processing."

[1435] Output: Extracted keywords.

[1436] Step 3:

[1437] The server searches the database using the extracted keywords.

[1438] Input: Extracted keywords.

[1439] Data processing: Using a generative AI model (e.g., GPT-3), search for similar queries by comparing them with past queries in a database.

[1440] Output: Search results for similar queries.

[1441] Step 4:

[1442] The server serves similar queries or stores the new query.

[1443] Input: Search results for similar queries.

[1444] Data processing: If a similar query is found, provide the answer to the user. If not, save it as a new query.

[1445] Output: Answers to similar queries or new queries are stored in the databank.

[1446] Step 5:

[1447] Add new inquiries to the list of issues to be resolved.

[1448] Input: New inquiry data.

[1449] Data processing: The server registers the inquiry details in a list of requests for resolution.

[1450] Output: Updated resolution list.

[1451] Step 6:

[1452] The respondent selects the query and provides a solution.

[1453] Input: List of desired solutions.

[1454] Data processing: The respondent uses a terminal to select an inquiry from a list and enter a solution.

[1455] Output: The input solution data.

[1456] Step 7:

[1457] The server receives and stores the solution.

[1458] Input: Solution data.

[1459] Data processing: The server stores the received solutions in a databank.

[1460] Output: Saved solution data.

[1461] Step 8:

[1462] The user reviews the solution and rates it.

[1463] Input: Saved solution data.

[1464] Data processing: The user uses a device to view the solution and evaluate whether it is useful.

[1465] Output: User rating data.

[1466] Step 9:

[1467] The server updates the helpfulness score of the answer based on the evaluation results.

[1468] Input: User rating data.

[1469] Data processing: The server receives the evaluation results and calculates and updates the usefulness score.

[1470] Output: Updated usefulness score.

[1471] Step 10:

[1472] The server adds the most useful answers to a list of frequently asked questions.

[1473] Input: Updated usefulness score.

[1474] Data processing: The server prioritizes answers in future search results based on their usefulness score.

[1475] Output: The updated query list.

[1476] Step 11:

[1477] Respondents are paid a reward each time their answer is viewed.

[1478] Input: Answer display data and user rating data.

[1479] Data processing: The server calculates rewards based on the number of impressions and ratings.

[1480] Output: Respondent payment data.

[1481] (Application example 1)

[1482] 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."

[1483] Current knowledge sharing systems face challenges such as the inability to obtain useful answers quickly and limited opportunities for respondents to receive appropriate rewards. In particular, content distribution services lack mechanisms that enable users to quickly obtain information of interest. Existing systems also face challenges in the accuracy of searching for similar questions and the transparency of reward distribution. By resolving these challenges, it is hoped that we can improve user convenience and provide incentives to respondents.

[1484] 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.

[1485] In this invention, the server includes a means for a user to input a question, set a price, and send it, a means for comparing the question received by the server with a database of similar questions using a generative AI model, and a means for the server to provide an answer to the similar question if there is one, or to save the answer as a new question if there is not. This allows the user to quickly input and send a question, and enables the AI ​​model to provide an answer based on highly accurate search results.

[1486] "User" refers to a general user who asks questions, answers, gives ratings, etc.

[1487] "Price" refers to the monetary value a user places on a question.

[1488] "Server" refers to the computer system used to store and process questions, answers, and ratings data.

[1489] A "generative AI model" refers to an artificial intelligence algorithm that analyzes data on past questions and answers to search for similar questions and generate optimal answers.

[1490] A "database of similar questions" refers to data storage that stores previously entered questions and their answers.

[1491] The "list of desired answers" refers to a list in which newly added questions are displayed in list form and are viewable by respondents.

[1492] "Solution" refers to the specific answer or solution provided by the respondent to the question.

[1493] "Usefulness score" refers to an indicator that quantifies the usefulness of an answer based on user ratings.

[1494] The "list of frequently displayed questions" refers to a group of items that lists questions and their answers that are displayed preferentially based on their usefulness scores.

[1495] "Reward" refers to monetary compensation received when a respondent provides a useful solution and their answer is viewed and evaluated.

[1496] "Smartphone application" refers to software for mobile devices that allows users and respondents to enter, check, and evaluate questions and answers.

[1497] "Prompt sentence" refers to the input data that a generative AI model uses to optimize questions and answers.

[1498] This invention is a knowledge sharing system that starts when a user inputs a question, sets a price, and submits it. The system is implemented using a server and a smartphone application. The server can use a cloud platform such as Microsoft Azure or Amazon Web Services, and the smartphone application is developed as an application that runs on iOS or Android.

[1499] System configuration

[1500] 1. User inputs and submits question

[1501] Users can submit their questions and set the price for each question through a smartphone application, and the question data is then sent to the server.

[1502] 2. Server parsing and searching the query

[1503] The server analyzes the received question using a generative AI model and compares it with a database of similar questions to perform a search. For example, the AI ​​model can be built using Python machine learning libraries such as TensorFlow and PyTorch.

[1504] 3. Suggesting similar questions and saving new questions

[1505] If the server finds a similar question, it provides the answer to the user, and if there is no similar question, it saves it in the database as a new question.

[1506] 4. Update the list of questions you would like answered

[1507] When a new question is saved to the database, it is automatically added to the list of questions you want answered, which is displayed for other respondents to see.

[1508] 5. Respondents provide answers

[1509] The respondent selects a question from a list of desired answers and provides a solution, which is sent to the server and stored in a database.

[1510] 6. User Rating of Answers

[1511] Users review the answers provided and rate their usefulness, and the rating data is sent to the server.

[1512] 7. Server Update of Usefulness Score

[1513] The server updates the usefulness score of the answer based on the evaluation result and adds the highly useful answers to the list of frequently displayed questions.

[1514] 8. Reward Distribution

[1515] Each time an answer is displayed, the server automatically pays the answerer a reward, a process that can also be achieved using smart contract technology.

[1516] Specific examples

[1517] For example, a user might use the application to set up and submit a question such as "I want to know the latest movie trends" for 500 yen. The server analyzes the question and uses a generative AI model to search a database of similar questions. If there are no similar questions, the question is saved in the database as a new question and added to the list of desired answers.

[1518] If a respondent selects this question and provides an answer such as "Current movie trends are...", the answer is stored on the server and notified to the user. If the user rates this answer as useful and the rating is sent to the server, the server updates the answer's usefulness score. If the answer is deemed useful, it will be displayed preferentially the next time a similar question is searched.

[1519] Prompt Sentence Examples

[1520] Below are some examples of prompts that generative AI models use to optimize questions and answers:

[1521] "What are the latest movie trends?"

[1522] In this way, the system of the present invention allows users to quickly obtain high-quality answers and respondents to receive appropriate compensation, thereby promoting the effective sharing and utilization of knowledge.

[1523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1524] Step 1:

[1525] A user uses a smartphone application to input a question and the price for that question, and then submits it. The inputs include the user name, question, set price, and current time. This data is sent to the server in JSON format.

[1526] Step 2:

[1527] The server receives the received question data and passes it to a generative AI model to analyze similarities. The question content and a database of past questions are given to the generative AI model as input. Data processing involves extracting keywords from the question content using natural language processing technology. The generative AI model compares the question with past questions and evaluates whether there are any similar questions. The output is a list of similar questions or a result indicating that there are no similar questions.

[1528] Step 3:

[1529] The server generates a list of similar questions, and if there are any similar questions, it provides the results to the user. If there are no similar questions, it saves the new question in the database. The input is the data of the new question (user name, question content, price, time), and the output is a confirmation message indicating that the new question has been saved.

[1530] Step 4:

[1531] The server adds a new question to the list of desired answers. The server receives the new question's ID, question content, price, and time as input. The data is processed by adding the new question's data to the database of the list of desired answers. The output is the updated list of desired answers.

[1532] Step 5:

[1533] The respondent uses a smartphone application to select a question from a list of desired answers and provide a solution. The respondent enters the selected question ID and answer content as input into the application and sends them to the server. The output is the answer data sent to the server.

[1534] Step 6:

[1535] The server stores the received response data in a database. The server receives the response content, respondent name, question ID, and time as input. The data is processed by saving the response data in the database. The output is a confirmation message indicating that the response has been saved.

[1536] Step 7:

[1537] The user reviews the provided answers and submits their rating using a smartphone application. As input, the rating score and question ID are entered into the application and sent to the server. The output is a confirmation message indicating that the rating score has arrived at the server.

[1538] Step 8:

[1539] The server updates the usefulness score of the answer based on the evaluation results. The evaluation score and question ID are given as input, and the cumulative score of the answer is calculated as a data operation. The output is the updated usefulness score.

[1540] Step 9:

[1541] The server adds useful answers to a list of frequently asked questions. As input, answers with high evaluation scores and their question IDs are given. In data processing, the server sorts the list of questions based on their usefulness scores, placing useful answers at the top. The output is the updated list of questions.

[1542] Step 10:

[1543] Each time an answer is displayed, the server pays a reward to the respondent. The server receives the number of impressions, rating score, and respondent ID as input. This information is combined to calculate the reward amount as a data calculation. The output is the reward amount paid to the respondent.

[1544] 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.

[1545] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits. This system provides a means to further improve existing problems by incorporating an emotion engine that recognizes users' emotions.

[1546] System Overview

[1547] The user uses a terminal to input a question, set a price according to the difficulty level, and send it.

[1548] This sends the question and the user's emotional data to the server.

[1549] The server uses AI to compare the received question with past questions in a database and search for similar questions.

[1550] The server then uses an emotion engine to analyze the user's emotions when entering a question.

[1551] If the server finds a similar question, it provides the answer to the user.

[1552] If no similar question is found, it will be saved as a new question in the database and added to the list of questions to be answered.

[1553] The respondent uses a terminal to select a question from a list of desired answers and provide a solution.

[1554] When the respondent enters and submits their answer, the emotion engine also collects emotional data from the user when rating the answer.

[1555] Users review the answers provided and rate whether they are helpful.

[1556] The user's ratings are sent to the server via the device.

[1557] The server then again uses the emotion engine to analyze the user's emotions at the time of rating.

[1558] The server updates the helpfulness score of the answer based on the evaluation results.

[1559] The usefulness score is adjusted based on the emotional data provided by the emotion engine.

[1560] Answers that are highly useful will be displayed preferentially when other users ask the same question.

[1561] Each time an answer is displayed, the server pays the answerer a reward.

[1562] Rewards are calculated based on the number of times an answer is viewed and its rating.

[1563] Emotional data is also taken into account in reward calculations.

[1564] Example system operation

[1565] The process from posting a question to providing an answer

[1566] For example, user A enters a question such as "How to implement asynchronous processing in JavaScript," sets the price to 200 yen, and submits the question. At the time of question submission, the emotion engine analyzes user A's emotions (e.g., troubled, anxious).

[1567] The server extracts keywords such as "JavaScript asynchronous processing" and uses AI to search a database of past questions, while also recording emotional data.

[1568] Since no similar questions were found, the question is saved as a new question in the database and added to the list of desired answers. Respondent B selects this question from the list of desired answers and answers as follows: "Asynchronous processing is implemented using Promises or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}"

[1569] This answer is sent from respondent B's terminal to the server and stored in the database.

[1570] User A reviews the answer and, if he finds it useful, he rates it with 4 stars. During this rating process, the emotion engine again analyzes User A's emotions (satisfied, happy).

[1571] The server receives this rating and sentiment data and updates the helpfulness score of the answer.

[1572] Because of its high usefulness, the next time another user searches for a question on "JavaScript asynchronous processing," this answer will be displayed preferentially. Furthermore, each time the answer is displayed, the server pays a reward to Answerer B. The reward is calculated taking into account the number of views, user ratings, and emotional data.

[1573] In this way, the system of the present invention takes into account the user's emotions to provide high-quality answers more quickly, increase the motivation of respondents, and maximize the effectiveness of knowledge sharing.

[1574] The processing flow will be explained below.

[1575] Step 1:

[1576] User enters question, sets price and submits. User enters question and price using terminal and clicks submit button.

[1577] Step 2:

[1578] The device sends the question and price entered by the user to the server, sending the data to the server as an HTTP request.

[1579] Step 3:

[1580] The server uses AI to compare the received question with past questions in the database and calculates the similarity of the question using an AI algorithm.

[1581] Step 4:

[1582] The server determines whether a similar question is found. If a similar question is found, it provides the answer to the user. If not, it saves the answer as a new question in the database.

[1583] Step 5:

[1584] The server adds the new question to the list of desired answers, which are then added to a list on the server and made available to respondents.

[1585] Step 6:

[1586] The emotion engine analyzes the user's emotions during the question submission process, for example, by analyzing the user's facial expressions and typing speed to determine whether the user is confused or anxious.

[1587] Step 7:

[1588] The respondent uses the device to select a question from the list of answers they wish to answer and enters the solution. The respondent enters the answer and clicks the send button.

[1589] Step 8:

[1590] The device sends the answers entered by the respondent to the server. The data is sent using an HTTP request.

[1591] Step 9:

[1592] The server stores the received answers in a database, where the answers are linked to the related questions.

[1593] Step 10:

[1594] The user checks the provided answers and rates them. The user checks the answers using the terminal, enters their rating, and submits them.

[1595] Step 11:

[1596] The emotion engine analyzes the user's emotions during the user rating process, for example, whether they are satisfied or happy.

[1597] Step 12:

[1598] The device sends the user's rating to the server. The rating data is sent to the server as an HTTP request.

[1599] Step 13:

[1600] The server updates the helpfulness score of the answer based on the ratings received. The helpfulness score is recalculated using the rating data and sentiment data and stored in the database.

[1601] Step 14:

[1602] The server adds useful answers to a list of frequently asked questions and adjusts their ranking based on their usefulness score.

[1603] Step 15:

[1604] The server pays the respondent a reward each time their answer is displayed. The reward is calculated based on the rating, number of views, and emotional data, and recorded in the respondent's account.

[1605] In this way, each entity plays a role at each processing step, allowing the entire system to function smoothly.

[1606] Example 2

[1607] 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."

[1608] Conventional knowledge sharing systems have difficulty in quickly providing appropriate answers to questions entered by users. Furthermore, they have had problems with low user satisfaction because they judge the usefulness of answers solely on quantitative evaluations without considering the user's feelings. Furthermore, the compensation paid to respondents was uniform, which lacked motivation to improve the quality of answers.

[1609] 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.

[1610] In this invention, the server includes means for a user to input a question, set a price, and send it, means for comparing the received question with a database of similar questions using AI to search, means for the server to provide an answer to the similar question if one is found and saving it as a new question if one is not found, means for analyzing the user's emotions when the question is input, means for receiving the user's emotion data, means for adding a new question to a list of desired answers, means for a respondent to select a question and provide a solution, means for sending and saving the answer to the server when an answer is provided, means for the user to check the answer, rate it, and send the rating to the server, means for collecting the user's emotion at the time of rating, means for the server to update the answer's usefulness score based on the rating result, means for correcting the answer's usefulness score based on the emotion data, means for adding highly useful answers to a list of frequently displayed questions, means for paying a reward to the respondent each time an answer is displayed, and means for calculating the reward to the respondent taking the emotion data into consideration. This makes it possible to provide quick and appropriate answers that take the user's emotions into consideration and to realize a reward system that increases the motivation of respondents.

[1611] A "user" is an entity that enters a question and receives an answer in a knowledge sharing system.

[1612] A "question" is information that a user enters and sends to a server to obtain a solution.

[1613] "Price" is the amount of reward that a user sets for a question.

[1614] A "server" is a central control device that receives, processes, searches, stores, and provides answers to questions.

[1615] "AI" is an artificial intelligence technology that analyzes questions, compares them with past questions, and searches for similar questions.

[1616] A "similar question" is a question whose content is similar to that of a newly entered question in the past question database.

[1617] A "database" is a collection of information that stores questions and answers that have been entered in the past.

[1618] A "new question" is a newly entered question for which no similar questions exist in the database.

[1619] An "emotion engine" is a software engine for analyzing a user's emotional state when entering a question or rating.

[1620] "Emotion data" is information about the user's emotional state analyzed by the emotion engine.

[1621] A "wanted answer list" is a list of questions that a respondent can select to provide a solution after a new question has been added.

[1622] A "respondent" is an entity that selects a question from a list of desired answers and provides a solution.

[1623] A "solution" is the content of the answer or advice provided by the respondent to a question.

[1624] A "rating" is feedback that a user gives to indicate the usefulness or satisfaction of a provided answer.

[1625] The "usefulness score" is an index that indicates the usefulness of an answer, calculated based on the user's evaluation results and emotional data.

[1626] The "list of frequently displayed questions" is a list in which questions containing highly useful answers are displayed with priority.

[1627] "Reward" refers to monetary compensation paid to respondents based on user ratings, number of views, and emotional data.

[1628] This invention relates to a knowledge sharing system in which users input and submit questions, and answerers provide solutions, resulting in mutual benefits for both parties. Specifically, this system incorporates an emotion engine to consider the user's emotions and provide high-quality answers.

[1629] Overall system overview

[1630] The user uses the terminal to enter a question, set a price, and submit.

[1631] The user uses a device such as a smartphone or PC to enter the question and reward amount, then presses the send button. This sends the question and the user's emotional data to the server. For example, a user might enter, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await," and set a reward of 200 yen. At this time, the emotion engine analyzes the user's emotions (e.g., troubled, anxious).

[1632] The server receives the question and the user's emotion data.

[1633] The server receives the user's emotion data collected using an emotion engine (e.g., Emotion API) along with the user's submitted question data. The received data is stored in a database.

[1634] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[1635] The server analyzes the received question data using AI (e.g., generative AI models such as BERT or GPT) to understand the content of the question. At the same time, an emotion engine analyzes the user's emotions when they entered the question. The results of this analysis are used for subsequent processing.

[1636] The server compares the question with previous questions in a database to find similar questions.

[1637] The server extracts keywords from the question (e.g., "JavaScript asynchronous processing") and compares them with a database of past questions to search for similar questions. It also uses AI to deeply understand the intent of the question and checks whether similar questions exist in the database.

[1638] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[1639] If a similar question is found, the answer is immediately provided to the user. For example, if a similar question such as "JavaScript asynchronous processing" has previously been answered with the answer "Implement it using Promise or async / await," the answer will be displayed to the user. If no similar question is found, the question is saved in the database as a new question and added to the list of desired answers.

[1640] Respondents use a terminal to select questions and provide solutions.

[1641] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution to that question, and submit it. For example, a respondent might enter a solution such as "Asynchronous processing in JavaScript is implemented using Promise or async / await. A concrete example would be as follows." and submit it.

[1642] Users review the answers provided and rate whether they are helpful.

[1643] The user checks the provided answer on their device and, if they find it useful, rates it with four stars. By pressing the rating button, the rating data is sent to the server. At this time, the emotion engine again analyzes the user's emotions (e.g., satisfied, happy).

[1644] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[1645] The server analyzes the received rating along with the sentiment data (e.g., satisfied) and updates the answer's helpfulness score, which determines whether the answer will be prioritized the next time the same question is asked.

[1646] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[1647] The server calculates and pays rewards to respondents based on the number of times the answer has been viewed, user ratings, and even emotional data. If the answer provided by the respondent is useful to many users and receives a high rating, the respondent will receive a corresponding reward. Reward calculations use payment services (e.g., PayPal or bank transfer).

[1648] Specific examples

[1649] For example, user A sets a question with a reward of 200 yen, saying, "Please tell me how to implement asynchronous processing in JavaScript. Please explain in detail how to use Promise and async / await." The server receives this question, and the emotion engine analyzes user A's emotion as "troubled." The AI ​​then searches the database of past questions to confirm that no similar questions exist, and adds the question as a new question.

[1650] Respondent B selects this new question and provides the following solution: "Asynchronous processing is implemented using Promise or async / await. Example: async function fetchData() { try { const response = await fetch('url'); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}}." User A checks this answer and sends the emotion data "Satisfied" along with a four-star rating to the server. The server updates the usefulness score based on this and pays a reward to Respondent B. In this way, a system is built that provides high-quality answers quickly and increases respondent motivation.

[1651] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1652] Step 1:

[1653] The user inputs and sends a question using a terminal.

[1654] A user uses a smartphone or computer to enter the question and the desired reward amount, then presses the send button. At this time, the following input data is sent from the device to the server: the question, reward amount, user ID, and the user's emotion at the time of input (e.g., text input "How do I implement asynchronous processing in JavaScript?" and reward amount 200 yen). Based on this input, the server receives the question data and the user's emotion data.

[1655] Step 2:

[1656] The server receives the question and the user's emotion data.

[1657] The server receives the question data sent by the user and simultaneously analyzes the user's emotional data using an emotion engine (e.g., EmotionAPI). The input is the text data and emotional data sent by the user, and the output is the question data and emotional data containing the analysis results. These data are stored in a database.

[1658] Step 3:

[1659] The server uses AI to analyze the questions it receives, and an emotion engine analyzes the user's emotions.

[1660] The server analyzes the received question data using an AI model (e.g., BERT or GPT) to understand the content of the question. This AI model converts the input question text into data in a more understandable format. At the same time, the emotion engine re-analyzes the user's emotions. The input to this process is the question text and emotion data submitted by the user, and the output is the question labeling and emotion analysis results.

[1661] Step 4:

[1662] The server compares the question with previous questions in a database to find similar questions.

[1663] The server extracts keywords from the question analyzed by the AI ​​model (e.g., "JavaScript asynchronous processing") and uses those keywords to compare it with a database of past questions. The input is the question keywords and the database of past questions, and the output is a list of similar questions. The server searches the database for similar questions and generates a list of the results.

[1664] Step 5:

[1665] If the server finds a similar question, it provides the answer to the user, and if the question is new, it stores it in a database.

[1666] The server displays a list of similar questions to the user, along with the answers to those questions. If no similar questions are found, the question is saved as a new question in the database and added to the list of desired answers. The input to this process is a list of similar questions and their answers, and the output is either displaying the answers to the user or saving the new question.

[1667] Step 6:

[1668] Respondents use a terminal to select questions and provide solutions.

[1669] Respondents use their own devices to select a question they are interested in from a list of desired answers, enter a solution for that question, and submit it. The input includes the solution text, respondent ID, and the selected question ID. The output is the submission of the answer and its storage in a database. For example, a solution such as "Asynchronous processing is implemented using Promises or async / await" may be entered.

[1670] Step 7:

[1671] The user reviews the answers provided and rates whether they are helpful.

[1672] The user checks the provided answer, enters a rating for it, and sends it to the server. At this time, the user's emotions at the time of rating are also analyzed using the emotion engine. The input includes the rating score, user ID, answer ID, and emotion data at the time of rating. The output is the transmission of the rating data and the emotion analysis results. For example, a four-star rating and the emotion "Satisfied" are sent.

[1673] Step 8:

[1674] The server updates the helpfulness score of the answer based on the rating and sentiment data.

[1675] The server analyzes the received rating data and user emotion data and updates the helpfulness score of the answer. This score serves as the basis for prioritizing the answer the next time the same question is asked. The input is the rating data, emotion data, and existing score data, and the output is the updated helpfulness score.

[1676] Step 9:

[1677] The server pays the respondent a reward based on the number of times the answer is displayed and the evaluation results.

[1678] The server calculates the reward based on the number of times the answer has been viewed, the results of user ratings, and emotional data, and pays it to the respondent. The input is the number of views, rating data, emotional data, and the respondent's ID, and the output is the calculated reward amount and payment. Payment is made using a payment service (e.g., PayPal or bank transfer).

[1679] In this way, based on the detailed processing steps and their specific operations, the system of the present invention provides answers efficiently and in consideration of the user's feelings.

[1680] (Application example 2)

[1681] 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."

[1682] Conventional knowledge sharing systems have the problem that the quality of answers given to users is uniform, making it difficult to respond appropriately to the user's emotions and situation. Furthermore, in brick-and-mortar stores, sales staff are unable to respond appropriately to customers' questions, resulting in a decline in customer satisfaction. A particular issue is the lack of a means to analyze customers' emotions and provide the most appropriate answer for each situation. Furthermore, a method to improve the accuracy of evaluating the usefulness of answers was also needed.

[1683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1684] In this invention, the server includes: means for a user to input a question, set a price, and send it; means for comparing the received question with a database of similar questions using AI to search; means for the server to provide an answer to the user if a similar question is found, or to save the answer as a new question if one is not found; means for adding the new question to a list of desired answers; means for a respondent to select a question and provide a solution; means for transmitting and saving the provided answer to the server; means for the user to review the answer and rate it, and send the rating to the server; means for the server to update the usefulness score of the answer based on the rating result; means for adding highly useful answers to a list of frequently displayed questions; means for paying a reward to the respondent each time an answer is displayed; means for acquiring questions using voice recognition using smart glasses; means for analyzing emotions at the time of asking the question using an emotion analysis engine; means for the server to provide an optimal answer based on the emotion data; and means for collecting emotion data at the time of rating and improving the quality of customer service. This makes it possible to analyze users' emotions, provide answers adapted to the situation, and improve the quality of customer service in physical stores.

[1685] A "user" is an individual or organization that uses the system to enter questions and receive answers.

[1686] A "Question" is text or audio data about a question or problem that a user wants solved.

[1687] "Price" is the amount of compensation set by the user for providing an answer to a question.

[1688] A "server" is a computer system that processes the data it receives, communicates with the database, and performs analysis.

[1689] "AI" refers to programs or algorithms that use artificial intelligence technology to analyze and process data.

[1690] A "database" is a collection of data that stores questions and their answers and manages them in a searchable format.

[1691] "Similar questions" are past questions that are similar in content to the question entered by the user.

[1692] A "new question" is a question that is newly added because there is no similar question in the database.

[1693] The "answer preference list" is a list of unanswered questions that the respondent can select.

[1694] A "respondent" is an individual or organization that provides solutions or answers to users' questions.

[1695] An "answer" is a solution or information to a user's question provided by a respondent.

[1696] A "rating" is an act by a user indicating the usefulness or satisfaction of a provided answer.

[1697] The "usefulness score" is an evaluation value that indicates the usefulness of an answer.

[1698] "Smart glasses" are wearable devices equipped with information display and voice recognition functions.

[1699] "Speech recognition" is a technology that converts voice data into text data.

[1700] A "sentiment analysis engine" is an algorithm or program that analyzes a user's emotions and outputs the results.

[1701] "Emotion data" is data that indicates the emotional state of the user.

[1702] The present invention is a system that applies a knowledge sharing system using an emotion engine to customer service in a brick-and-mortar store. Specific embodiments of the invention will be described in detail below.

[1703] System configuration

[1704] The system consists of the following main components:

[1705] 1. User Device

[1706] Users input their questions using the smart glasses, which are equipped with voice recognition software that captures the user's questions in real time.

[1707] 2. Server

[1708] The server uses artificial intelligence (AI) to compare the received question with a database of similar questions, and the sentiment at the time of the question is analyzed by a sentiment analysis engine.

[1709] 3. Sentiment Analysis Engine

[1710] The sentiment analysis engine includes algorithms that interpret emotions from user speech and voice data, which is then used by the server to provide and rate answers.

[1711] 4. Database

[1712] A database that stores questions and their answers, searches for similar questions, saves new questions, and updates answer helpfulness scores based on ratings.

[1713] 5. Respondent Device

[1714] Respondents use devices such as smartphones or tablets to select questions from a list of desired answers and enter solutions.

[1715] System Operation

[1716] 1. Questions

[1717] The user uses the smart glasses to voice their inquiry, set a price, and submit. Speech recognition software (e.g., SpeechRecognition) converts this voice data into text data.

[1718] 2. Question analysis and sentiment analysis

[1719] The server analyzes the received question and uses AI to search for similar questions in the database, while a sentiment analysis engine analyzes the user's emotional data.

[1720] 3. Providing answers

[1721] If the server finds an answer to a similar question, it will provide it to the user. If not, it will save it as a new question in the database and add it to the list of desired answers.

[1722] 4. Enter and evaluate your answers

[1723] Respondents select questions from a list of desired answers and provide solutions. At this time, the answers are sent from the respondent's device to the server and stored in a database. Users review the answers provided and rate them. Emotional data is also collected during the rating process.

[1724] 5. Update usefulness score

[1725] The server updates the helpfulness score of answers based on user ratings and sentiment data, and highly rated answers are prioritized when other users ask similar questions.

[1726] 6. Payment of Rewards

[1727] Each time an answer is viewed, the server pays the respondent a reward, which is calculated based on the number of views, ratings, and sentiment data.

[1728] Hardware and software used

[1729] Smart glasses (e.g. Google Glass)

[1730] Voice recognition software (e.g., SpeechRecognition)

[1731] Sentiment analysis engine (Virtual Library: Futabado)

[1732] Database (e.g. MongoDB)

[1733] AI models (e.g., neural networks for natural language processing)

[1734] Specific examples

[1735] For example, a user can use smart glasses to voice-input a question such as "Please tell me how to use this product." The sentiment analysis engine then analyzes the user's sentiment as "confused." The server then searches a database for similar questions and provides an appropriate answer. When a customer rates the answer as "satisfied," the answer's usefulness score is updated. This process ensures that other users can receive a prompt and appropriate answer when they ask a similar question.

[1736] Example prompt for generative AI model:

[1737] Q: How do I use this product?

[1738] Emotion: Confused

[1739] Generate the appropriate answer.

[1740] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1741] Step 1:

[1742] The user uses the smart glasses to input a question by voice. This voice data is converted into text data by the smart glasses' voice recognition software (e.g., SpeechRecognition). The input is voice data, and the output is text data. The specific operation at this point is that the voice recognition software converts the voice signal into text.

[1743] Step 2:

[1744] The server analyzes the received question text and uses AI to search for similar questions in a database. The input is the user's question text, and the output is similar questions and their answers. Specifically, it uses natural language processing (NLP) technology to break down the question text into keywords and compare them with previous questions in the database.

[1745] Step 3:

[1746] The server uses a sentiment analysis engine to analyze the user's emotions. The input is the user's question text and voice data, and the output is the analyzed emotion data. The specific operation is to determine the user's emotional state based on the voice tone, speaking rate, text content, etc. extracted from the voice data.

[1747] Step 4:

[1748] If the server finds an answer to a similar question, it provides that answer to the user. If not found, it saves it as a new question in the database and adds it to the list of desired answers. The input is the question text and emotion data, and the output is saving the answer or a new question in the database. Specifically, if a similar question is found, the answer is sent to the user's device; if not, it is saved as a new question in the database.

[1749] Step 5:

[1750] The respondent selects a question from the list of desired answers and provides a solution. The input is the question from the list of desired answers, and the output is the provided answer. The specific operation is that the respondent selects a question using their own terminal, enters the solution, and submits it.

[1751] Step 6:

[1752] The user reviews the provided answer and rates it. This rating is sent to the server, and emotion data is collected at the same time. The input is the user's rating and emotion data, and the output is the saved rating data. The specific operation is that the user enters a star rating or text comment for the answer, and sends the emotion data to the server.

[1753] Step 7:

[1754] The server updates the helpfulness score of an answer based on the user's rating and sentiment data. The input is the rating data and sentiment data, and the output is the updated helpfulness score. The specific operation is to analyze the rating data and sentiment data and adjust / update the helpfulness score of an answer based on it.

[1755] Step 8:

[1756] Each time an answer is viewed, the server pays the answerer a reward. The input is the number of views of the answer and the rating data, and the output is the calculated reward. The specific operation is to calculate the reward based on the number of views and the rating data, and notify the answerer of the result.

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] FIG. 9 illustrates 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 behaviors 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.

[1762] 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.

[1763] 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).

[1764] 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.

[1765] 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."

[1766] 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.

[1767] 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).

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] The following is further disclosed regarding the above embodiment.

[1779] (Claim 1)

[1780] A way for users to enter their question, set a price, and submit it;

[1781] A means for the server to search by comparing the received question with a database of similar questions using AI;

[1782] The server provides the answer to a similar question to the user if there is one, and saves it as a new question if there is no similar question.

[1783] A way to add new questions to the wish list,

[1784] a means for respondents to select questions and provide solutions;

[1785] means for transmitting and storing the answer on a server once the answer is provided;

[1786] A means for the user to review the answers, rate them, and transmit the ratings to a server;

[1787] a means for the server to update the helpfulness score of the answer based on the evaluation results;

[1788] A way to add useful answers to a list of frequently asked questions, and

[1789] A means of paying respondents each time their answer is viewed; and

[1790] A system including:

[1791] (Claim 2)

[1792] 10. The system of claim 1, wherein the server further comprises means for calculating a reward for the answerer based on the frequency of providing the answer.

[1793] (Claim 3)

[1794] 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display.

[1795] "Example 1"

[1796] (Claim 1)

[1797] A means for users to enter, price and submit their enquiries;

[1798] A means for searching the query received by the server by comparing it with a database of similar queries using artificial intelligence;

[1799] a means for the server to provide an answer to a similar query to the user if there is one, and to save the answer as a new query if there is no similar query;

[1800] A way to add new inquiries to the resolution list,

[1801] a means for respondents to select an inquiry and enter a solution;

[1802] means for transmitting the answers, once provided, to a server for storage in a data bank;

[1803] A means for the user to review and rate the answers and transmit the results of the ratings to a server;

[1804] a means for the server to update the helpfulness score of the answer based on the evaluation results;

[1805] A way to add useful answers to a list of frequently viewed inquiries,

[1806] A means of paying respondents each time their answer is viewed; and

[1807] A system including:

[1808] (Claim 2)

[1809] 10. The system of claim 1, wherein the server further comprises means for calculating a reward for the answerer based on the frequency of providing the answer.

[1810] (Claim 3)

[1811] 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display.

[1812] "Application Example 1"

[1813] Claim Revision

[1814] (Claim 1)

[1815] A way for users to enter their question, set a price, and submit it;

[1816] A means for searching the received question by the server by comparing it with a database of similar questions using a generative AI model;

[1817] The server provides the answer to a similar question to the user if there is one, and saves it as a new question if there is no similar question.

[1818] A way to add new questions to the wish list,

[1819] a means for respondents to select questions and provide solutions;

[1820] means for transmitting and storing the answer on a server once the answer is provided;

[1821] A means for the user to review the answers, rate them, and transmit the ratings to a server;

[1822] a means for the server to update the helpfulness score of the answer based on the evaluation results;

[1823] A way to add useful answers to a list of frequently asked questions, and

[1824] A means of paying respondents each time their answer is viewed; and

[1825] means for managing data processing and reward distribution relating to questions and answers, the means including a smartphone application;

[1826] A means for the generative AI model to optimize questions and answers using prompt sentences, and

[1827] A system including:

[1828] (Claim 2)

[1829] 10. The system of claim 1, wherein the server further comprises means for calculating a reward for the answerer based on the frequency of providing the answer.

[1830] (Claim 3)

[1831] 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display.

[1832] "Example 2: Combining Emotion Engines"

[1833] (Claim 1)

[1834] A way for users to enter their question, set a price, and submit it;

[1835] A means for the server to search by comparing the received question with a database of similar questions using AI;

[1836] The server provides the answer to a similar question to the user if there is one, and saves it as a new question if there is no similar question.

[1837] A means of analyzing the user's sentiment when entering a question;

[1838] means for receiving user emotion data;

[1839] A way to add new questions to the wish list,

[1840] a means for respondents to select questions and provide solutions;

[1841] means for transmitting and storing the answer on a server once the answer is provided;

[1842] A means for the user to review the answers, rate them, and transmit the ratings to a server;

[1843] A means of collecting user sentiment during evaluation;

[1844] a means for the server to update the helpfulness score of the answer based on the evaluation results;

[1845] means for correcting the helpfulness score of the answer based on the sentiment data;

[1846] A way to add useful answers to a list of frequently asked questions, and

[1847] A means of paying respondents each time their answer is viewed; and

[1848] a means for calculating rewards for respondents taking into account the emotional data;

[1849] A system including:

[1850] (Claim 2)

[1851] 10. The system of claim 1, wherein the server further comprises means for calculating a reward for the answerer based on the frequency of providing the answer.

[1852] (Claim 3)

[1853] 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display.

[1854] "Application example 2 when combining emotion engines"

[1855] (Claim 1)

[1856] A way for users to enter their question, set a price, and submit it;

[1857] A means for the server to search by comparing the received question with a database of similar questions using AI;

[1858] The server provides the answer to a similar question to the user if there is one, and saves it as a new question if there is no similar question.

[1859] A way to add new questions to the wish list,

[1860] a means for respondents to select questions and provide solutions;

[1861] means for transmitting and storing the answer on a server once the answer is provided;

[1862] A means for the user to review the answers, rate them, and transmit the ratings to a server;

[1863] a means for the server to update the helpfulness score of the answer based on the evaluation results;

[1864] A way to add useful answers to a list of frequently asked questions, and

[1865] A means of paying respondents each time their answer is viewed; and

[1866] means for obtaining a question by voice recognition using smart glasses;

[1867] A means of analyzing the emotions expressed at the time of the question using a sentiment analysis engine,

[1868] A means for the server to provide an optimal answer based on the emotion data;

[1869] A means to collect emotional data during evaluation and improve the quality of customer service;

[1870] A system including:

[1871] (Claim 2)

[1872] 10. The system of claim 1, wherein the server further comprises means for calculating a reward for the answerer based on the frequency of providing the answer.

[1873] (Claim 3)

[1874] 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display. [Explanation of symbols]

[1875] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A way for users to enter their question, set a price, and submit it; A means for the server to search by comparing the received question with a database of similar questions using AI; The server provides the answer to a similar question to the user if there is one, and saves it as a new question if there is no similar question. A way to add new questions to the wish list, a means for respondents to select questions and provide solutions; means for transmitting and storing the answer on a server once the answer is provided; A means for the user to review the answers, rate them, and transmit the ratings to a server; a means for the server to update the helpfulness score of the answer based on the evaluation results; A way to add useful answers to a list of frequently asked questions, and A means of paying respondents each time their answer is viewed; and A system including:

2. 2. The system of claim 1, wherein the server further comprises means for calculating compensation for respondents based on the frequency of providing answers.

3. 2. The system of claim 1, further comprising means for the server to calculate the usefulness of the answer based on the user's rating and determine the frequency of its next display.

Images