system

Abstract

Provide a system. 【Solution means】 Means for the information processing system to activate a plurality of machine learning algorithms, Means for the information processing system to receive an inquiry input from a user device, Means for the information processing system to execute means for distributing the received inquiry to a plurality of machine learning algorithms, Means for each machine learning algorithm to generate a response to the inquiry and return it to the information processing system, Means for the information processing system to compare the returned responses and perform cross-validation processing to evaluate the reliability, Means for selecting a highly reliable response based on the cross-validation processing, Means for returning the selected response to the user device, Means for providing a technical advisor function to the devices used by the user in the home, A system including.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is to eliminate the anxiety about the reliability of information provided by a plurality of artificial intelligence models and to provide an environment in which new or inexperienced engineers can quickly and accurately solve technical problems. Also, it is necessary to improve the efficiency of technical support in enterprises, reduce system downtime, and improve customer satisfaction.

Means for Solving the Problems

[0005] The information processing device activates multiple artificial intelligence algorithms, receives a question from a user terminal, and distributes it to the multiple AI algorithms. Each AI algorithm generates an answer to the question and sends it back to the information processing device. The information processing device compares the returned answers and evaluates their reliability through cross-validation. Furthermore, by providing a system that selects the most reliable answer based on this evaluation and returns it to the user terminal, this problem is solved.

[0006] An "information processing device" refers to a system that executes multiple artificial intelligence algorithms and has the function of receiving and processing user input.

[0007] An "artificial intelligence algorithm" is a program or model that performs mimicked decision-making or problem-solving based on specific inputs.

[0008] A "user terminal" refers to an electronic device that a user directly operates to input data into an information processing device or receive results from it.

[0009] A "question" refers to a technical or other question or problem that a user enters into an information processing device in an attempt to find a solution.

[0010] "Cross-validation processing" refers to a method of comparing answers generated by multiple artificial intelligence algorithms, evaluating their reliability, and making a selection.

[0011] "Reliability" is an indicator that shows the degree to which a response is considered accurate or valid. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system that utilizes multiple artificial intelligence algorithms via an information processing device to provide highly reliable answers to user questions. The embodiments thereof are described below in natural language.

[0034] System Overview

[0035] This system provides users with answers from multiple artificial intelligence algorithms, cross-validated to help them resolve technical problems and questions. This increases the reliability of the answers and enables engineers and technical support personnel to solve problems quickly and accurately.

[0036] System operation

[0037] 1. User input of question

[0038] Users use a terminal to enter technical questions. These questions can range from troubleshooting network connectivity issues to inquiries about software errors.

[0039] 2. Sending and receiving questions

[0040] The question entered from the terminal is instantly sent to the server. The server receives the question, verifies that it is in the correct format, and then proceeds with further processing.

[0041] 3. Execution of artificial intelligence algorithms

[0042] The server activates multiple artificial intelligence algorithms and distributes the received questions to each of them. Each algorithm analyzes the question in its own way and generates an answer based on that analysis.

[0043] 4. Collection and evaluation of responses

[0044] The generated responses are sent back to the server. The server collects these responses and performs cross-validation. That is, it thoroughly evaluates the consistency and reliability of each response and selects the most valid and reliable response.

[0045] 5. Sending responses back to users

[0046] The selected response is sent back from the server to the user's terminal. This allows the user to immediately obtain the technical information or solution they were looking for.

[0047] Specific example

[0048] For example, consider a user who enters the question, "My server connection is frequently dropping." The server distributes this to multiple AI algorithms. One algorithm might recommend "checking network settings," while another might suggest "resetting the hardware." Based on these responses, the server selects "checking network settings" as the most reliable answer, considering past performance and the current situation, and sends it back to the user. Through this process, the user receives specific steps to quickly resolve the problem.

[0049] This system will be an effective tool for receiving high-quality support, especially for new technical support staff and engineers. It is expected to contribute to strengthening corporate competitiveness and improving customer satisfaction.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user uses their device to input the technical problem or question they want to solve in natural language. Once they have finished inputting, the user sends it to the server as question data by pressing the send button on their device.

[0053] Step 2:

[0054] The terminal receives question data entered by the user and sends it to the server via the internet. The transmitted data is usually sent using protocols such as HTTP.

[0055] Step 3:

[0056] The server receives the question data sent from the terminal and validates its content through a pre-programmed filtering process to determine if it is appropriate. If the format and content of the question are appropriate, the process proceeds to the next step.

[0057] Step 4:

[0058] The server distributes the question data to multiple artificial intelligence algorithms. Each algorithm uses a different method, operates independently, and can generate answers to the questions from its own perspective.

[0059] Step 5:

[0060] Each artificial intelligence algorithm receives a question from the server and generates an answer based on its own internal logic and model. The generated answer may include the reasoning behind the answer and any points to confirm.

[0061] Step 6:

[0062] The responses generated by each artificial intelligence algorithm are sent back to the server. When the responses are sent back, the confidence level of the response and related metadata may also be provided.

[0063] Step 7:

[0064] The server collects responses from all artificial intelligence algorithms. The server compares these responses and uses a cross-validation algorithm to evaluate their consistency and reliability. This process also utilizes past response history and supplementary information.

[0065] Step 8:

[0066] The server selects the most reliable and useful answer based on the cross-validation results. The degree of agreement and confidence score of the answers are important evaluation criteria in this selection process.

[0067] Step 9:

[0068] The server selects the most reliable answers and sends them back to the terminal. The returned answers are then formatted in a way that is easy for the user to understand.

[0069] Step 10:

[0070] The terminal receives the response sent back from the server and displays its contents on the user screen. This allows the user to obtain the technical information and solutions they were looking for.

[0071] (Example 1)

[0072] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0073] In the field of information technology, providing reliable, real-time solutions to user problems and technical questions is crucial. However, conventional systems often rely on a single algorithm, making it difficult to provide optimal solutions to complex questions.

[0074] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0075] In this invention, the server includes means for the information processing device to activate multiple machine learning algorithms, means for the information processing device to transmit the received problem content to the multiple machine learning algorithms, and means for performing data verification processing to compare the returned solutions and evaluate their reliability. This makes it possible to analyze the problem content from multiple angles using multiple algorithms and to quickly provide the most reliable solution.

[0076] An "information processing device" is a computing device that receives input from a user and executes multiple machine learning algorithms.

[0077] A "machine learning algorithm" is a program that analyzes the content of a problem received from a user and generates a solution based on that analysis.

[0078] A "user-operated terminal" is an electronic device used by the user to input the details of a problem and receive the selected solution.

[0079] "Problem description" refers to the technical issues or questions that users are seeking to resolve.

[0080] "Reliability" is an indicator used to evaluate the accuracy and applicability of the generated solutions.

[0081] "Data validation processing" is the process of comparing the outputs from multiple machine learning algorithms, evaluating their reliability, and selecting the optimal solution.

[0082] "Solution" refers to specific countermeasures or advice regarding the user's problem.

[0083] This invention is a system that uses an information processing device to activate multiple machine learning algorithms and provide the optimal solution to a problem submitted by a user via a terminal.

[0084] The server distributes the received problem content to multiple machine learning algorithms. The server uses a cloud platform to run these algorithms by executing machine learning libraries such as TENSORFLOW® and PyTorch. Each algorithm analyzes the received problem content and generates a solution based on that analysis. The generated solutions are returned to the server for confidence evaluation. This confidence evaluation involves data validation using tools like Scikit-learn, and the best solution is selected.

[0085] As a concrete example, consider a case where a user inputs a problem such as "slow internet connection." The server sends this information to multiple machine learning algorithms. One algorithm might generate a solution such as "try restarting the router," while another might suggest "checking the device settings." The server compares these returned solutions, uses data validation to select the best one, and sends it back to the user.

[0086] This process allows us to provide users with quick and reliable solutions to the technical challenges they face. For example, a user could input a prompt to the generating AI model such as, "I would like to contact technical support to find out how to improve the issue of 'web pages loading slowly'."

[0087] This system aims to utilize generative AI models and prompt statements to appropriately select and provide users with answers generated by multiple algorithms.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The user uses a terminal to input details of a technical problem. This input is sent to the server as text data. When the user inputs a problem such as "the printer is not working," the terminal converts it into digital data format and sends it to the server.

[0091] Step 2:

[0092] The server receives the assignment content submitted by the user and verifies whether it is in the correct format. Specifically, the server checks the consistency of the text format and prompts the user to re-enter the data if there are any deficiencies. In this step, data processing such as format verification and normalization of line breaks is performed based on the input data.

[0093] Step 3:

[0094] The server distributes the confirmed problem details to multiple generative AI models. Each model runs using machine learning libraries such as TensorFlow or PyTorch. Specifically, the server sends the problem details as prompts to each model and generates solutions based on them. During this process, new data calculations are performed within the AI ​​models, resulting in the generated solutions.

[0095] Step 4:

[0096] The server collects the solutions returned from the generated AI model. The server then subjects these solutions to a data validation process to evaluate their confidence. This process involves cross-validation using tools like Scikit-learn, analyzing the consistency and accuracy of each output. Based on the evaluation results, the most appropriate solution is selected.

[0097] Step 5:

[0098] The server sends the selected optimal solution back to the user's device. The user can then review the solution on their device and use it to resolve the problem. This step includes configuring the user's device to receive a notification or display the solution on the screen. The generated solution is output as text data and provided to the user.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] In consumer technology devices, there is a need to resolve technical problems and questions users face quickly and with reliable information. However, currently, users often require technical knowledge, which can hinder the effective use of the device. Therefore, there is a need to develop a system that supports users in obtaining technical information without requiring expert assistance.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes means for activating multiple machine learning algorithms and analyzing queries received from user devices, means for evaluating the responses generated by each algorithm based on cross-validation, and means for selecting a highly reliable response from the evaluation results and returning it to the user device. This makes it possible for users to obtain quick and effective solutions to complex technical problems in devices used in their homes.

[0104] An "information processing system" is a device that receives inquiries from users and has the function of generating and evaluating responses using multiple machine learning algorithms.

[0105] A "machine learning algorithm" is a computational method for learning patterns from given data and generating appropriate responses based on new data.

[0106] "User equipment" refers to digital devices used within the home that work in conjunction with an information processing system to send and receive user inquiries.

[0107] "Reliability" is an index that quantitatively evaluates the accuracy and applicability of the generated response.

[0108] Cross-validation is a technique for comparing responses generated by multiple algorithms to verify their consistency and reliability.

[0109] The "technical advisor function" is an auxiliary function that enables the user's device to automatically provide solutions to technical problems.

[0110] In the system implementing this invention, a server is used as the central point for information processing. The server first receives inquiries from user devices via the network and analyzes their content. The analyzed content is supplied to several pre-configured machine learning algorithms, and each algorithm generates a response based on its respective methodology.

[0111] The server receives these responses and uses cross-validation techniques to evaluate the confidence level of each response. The confidence scores provided by each algorithm are used for the confidence evaluation, and the most effective response is selected based on these scores. The selected response is then sent back to the user's device via the network. In this process, the server uses programming languages ​​such as Python and related machine learning libraries (e.g., TensorFlow, PyTorch).

[0112] For example, if a user enters a question such as "My robot vacuum cleaner cannot connect to the Wi-Fi network," the server will provide recommendations such as reviewing network settings or optimizing the connection distance to the router. In this case, the server will use an example prompt message like the following for the machine learning model: "When a user asks 'My robot cannot connect to Wi-Fi,' please suggest an appropriate solution."

[0113] The introduction of this system will significantly improve convenience, as users will be able to obtain quick and accurate solutions to technical problems within their homes.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The user uses a terminal to input inquiries about technical problems. These inquiries cover a wide range of topics, such as "My robotic vacuum cleaner cannot connect to Wi-Fi." The terminal converts these inquiries into data format and sends them to the server via the network. The input is the user's inquiry text, and the output is the data format sent to the server.

[0117] Step 2:

[0118] The server receives queries sent from terminals and parses their content. This parsing uses natural language processing techniques to understand the queries and interpret their meaning. The input is query data received from terminals, and the output is the structure data of the parsed queries.

[0119] Step 3:

[0120] The server distributes the analyzed query to multiple generative AI models, each of which generates a response based on its own algorithm. Prompts are used to instruct the models during this process. The input is the analyzed query data, and the output is the response candidates generated by each model.

[0121] Step 4:

[0122] The server collects responses returned from each generating AI model and performs cross-validation. It compares confidence scores to determine the most reliable response. The input consists of multiple response candidates and their confidence scores, and the output is the selected optimal response.

[0123] Step 5:

[0124] The server resends the selected, reliable response to the terminal via the network. The user can then view the specific problem-solving solution through the terminal. The input is the selected response, and the output is the text information of the solution displayed on the user's terminal.

[0125] This process allows us to respond quickly and accurately to users' technical problems.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] The present invention is a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device. It provides highly reliable answers to user questions while simultaneously considering the user's emotional state to deliver more personalized information. The embodiments thereof are described in detail below.

[0128] System Overview

[0129] This system works by having the user ask technical questions in natural language through a terminal, which are then received by an information processing unit. After receiving the questions, the information processing unit distributes them to multiple artificial intelligence algorithms, each of which generates an answer. In addition, an emotion engine recognizes the user's emotions in real time, and performs cross-validation processing while considering the user's state to select the most reliable answer.

[0130] System operation

[0131] 1. User question input and sentiment detection

[0132] The user enters a technical question into the device. During this process, the device uses sensors such as a camera and microphone to acquire emotional data from the user's voice tone and facial expressions.

[0133] 2. Sending questions and sentiment data

[0134] The terminal sends the entered question and user sentiment data to the server. The server receives this data and prepares for the next step.

[0135] 3. Emotional analysis using an emotional engine

[0136] The emotion engine within the server analyzes the received emotion data to determine the user's emotional state. This determination becomes an important input for subsequent processing.

[0137] 4. Application of artificial intelligence algorithms

[0138] The server distributes the question to multiple artificial intelligence algorithms, each generating an answer. Here, the user's emotional state influences the answer generation process of each algorithm, potentially adjusting the tone and content of the response.

[0139] 5. Cross-validation and response selection

[0140] The server collects responses from each algorithm and performs cross-validation. During this process, the most appropriate and reliable response is selected, taking into account the emotional state output by the emotion engine.

[0141] 6. Providing responses and feedback

[0142] The selected answers are returned to the terminal and displayed to the user. The user can also input feedback on those answers from the terminal and send it to the server. This feedback contributes to further improving the system's accuracy.

[0143] Specific example

[0144] As a concrete example, consider a scenario where a user, expressing anger, inputs, "A system error has stopped my work. What should I do?" The terminal sends this expression as emotional data to the server. The server's emotion engine identifies this data as "anger," and based on this information, an artificial intelligence algorithm works to generate a response that includes more polite and prompt solutions. Finally, the server returns this response to the user, thereby reducing the user's anxiety and stress.

[0145] Thus, the invention is a system that enables more effective and humane support by taking user emotions into consideration.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The user uses the device to input the technical problem they want to solve in natural language. During input, the device simultaneously uses the camera and microphone to capture emotional data from the user's facial expressions and voice.

[0149] Step 2:

[0150] The terminal sends the entered question and acquired sentiment data to the server. Communication takes place over the internet, and the data format follows a predefined protocol.

[0151] Step 3:

[0152] The server receives questions and emotion data sent from the terminal. An emotion engine within the server analyzes the emotion data and determines the user's current emotional state. At this point, it generates emotion labels such as "joy," "anxiety," and "anger."

[0153] Step 4:

[0154] The server prepares the question data and distributes it to multiple artificial intelligence algorithms. Each algorithm receives this question data and performs analysis using its own model.

[0155] Step 5:

[0156] Each artificial intelligence algorithm generates an answer to a question. During this process, it uses emotional state information provided by the server to adjust the tone and content of the answer. For example, if the user's emotion is "anger," the answer will use more careful and considerate language.

[0157] Step 6:

[0158] Each artificial intelligence algorithm sends its generated response back to the server. The server receives all of these responses and prepares them for the next processing step.

[0159] Step 7:

[0160] The server performs cross-validation on the received responses. Here, the server evaluates the results considering the consistency, reliability, and emotional state of the responses. It selects the response that is most reliable and best reflects the user's emotions.

[0161] Step 8:

[0162] The server sends the selected, optimal answer back to the terminal. The answer may include emotionally sensitive explanations and is provided in a format that is easy for the user to understand.

[0163] Step 9:

[0164] The device receives the response sent back from the server and displays it on the user screen. The user can then review the response and take the next steps to resolve the problem.

[0165] Step 10:

[0166] The user sends feedback on the answers they provide from their device to the server. The server receives this feedback and can use the data to improve system performance.

[0167] (Example 2)

[0168] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0169] In many information processing systems, the quality of automated responses to user inquiries is crucial. Furthermore, answers that do not consider the user's emotional state do not necessarily lead to user satisfaction. Therefore, there is a need to provide reliable and personalized answers that reflect the user's emotional state.

[0170] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0171] In this invention, the server includes means for an information processing device to activate multiple computational models, means for receiving questions input from a user terminal, and means for distributing the received questions to the multiple computational models. This makes it possible to provide appropriate and reliable automated responses that take into account the user's emotional state.

[0172] An "information processing device" is a hardware or software system equipped with electronic functions for receiving, processing, and analyzing data and providing responses to users.

[0173] A "computational model" is a mathematical model designed by combining algorithmic methods and data to generate automated responses to specific tasks or questions.

[0174] A "user terminal" is a computing device used by a user to input and receive information.

[0175] "Emotional data" refers to data obtained from the user's voice tone, facial expressions, etc., and is used to determine the user's emotional state.

[0176] A "confidence score" is an evaluation value returned by each computational model to assess how accurate and suitable the generated response is for its intended purpose.

[0177] The "evaluation process" is the process of comparing responses returned from multiple models, evaluating their reliability and suitability, and selecting the most appropriate response.

[0178] This invention provides a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device, aiming to provide highly reliable answers to user questions. Furthermore, this system achieves more personalized information delivery by taking into account the user's emotional state. Specific embodiments are described below.

[0179] The user inputs questions using natural language through their device. The device is equipped with sensors such as a camera and microphone, which simultaneously capture emotional data such as the user's voice tone and facial expressions. This emotional data is transmitted to the server in real time.

[0180] Within the server, the emotion engine analyzes the received emotion data to determine the user's emotional state. This emotional state plays a crucial role in generating responses in the next stage. Based on this emotional state, the server uses multiple generative AI models to generate answers to the user's questions. Each model reflects the emotion data and adjusts the response to have the optimal tone and content.

[0181] After considering the accuracy of the responses and their relevance to the user's emotions, the server selects the most appropriate response. This selected response is then sent back to the terminal and displayed to the user.

[0182] For example, if a user enters "A system error has stopped operations. What should I do?" while displaying an angry expression, the terminal sends that expression to the server as emotion data. On the server, the emotion engine determines the emotion data to be "anger" and adjusts the generation AI model to create a response that includes more polite and prompt solutions. An example of a prompt message that can be used is: "If the user is in an angry emotional state, generate a prompt and polite response. Question: 'A system error has stopped operations. What should I do?'"

[0183] This system allows users to receive appropriate, humane support that reflects their emotions.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The user inputs a technical question in natural language into the user's device. The device records the question as text data. Simultaneously, the device's camera and microphone are used to acquire emotional data such as voice tone and facial expressions, which are then recorded as sensor data. The input includes both the user's question and emotional data.

[0187] Step 2:

[0188] The terminal sends the acquired question and sentiment data to the server. The protocol used is either HTTP or WebSocket, encrypted with SSL / TLS to ensure secure communication. The entered text data and sentiment data reach the server.

[0189] Step 3:

[0190] The server inputs the received emotional data into the emotion engine. The emotion engine uses machine learning algorithms to analyze the emotional data and determine the user's emotional state. This determination becomes important input for subsequent processing steps, outputting the user's emotional state as a numerical value or category.

[0191] Step 4:

[0192] The server distributes the user's question to multiple generative AI models. Each model generates the optimal answer from its own perspective, taking into account the user's emotional state. The user's emotional data is used as input, and the generated answers are output as text.

[0193] Step 5:

[0194] The server collects the responses returned from each generative AI model and performs cross-validation. This process comprehensively evaluates the confidence scores and emotional state judgments provided by the generative AI models. Based on the resulting evaluation scores, the server selects the most reliable response. The selected response is then output as the result of the selection.

[0195] Step 6:

[0196] The server sends the selected answers to the terminal. The user can receive and view the selected answers via the terminal. The output answers serve as the basis for user confirmation and feedback input.

[0197] Step 7:

[0198] Users input feedback on the provided answers via a terminal. The terminal sends this feedback back to the server. This feedback is stored in the server's database to improve system performance. The feedback data is input and output as basic system data.

[0199] (Application Example 2)

[0200] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0201] In recent years, with the advancement of information technology, there has been a growing demand for personalized information that takes into account the emotional state of individual users. However, conventional information processing systems are unable to provide responses that adequately consider the user's emotions. As a result, there is a lack of support that takes users' emotions into account, and in particular, in nursing care settings, more appropriate responses are needed to stabilize the emotions of residents.

[0202] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0203] In this invention, the server includes means for an information processing device to activate multiple machine learning algorithms, means for receiving questions and sentiment information input from a user terminal, and means for distributing them to the machine learning algorithms. This makes it possible to propose highly reliable answers that take the user's emotions into consideration, and appropriate dialogue methods that correspond to the user's emotional state.

[0204] An "information processing device" is a computing device that analyzes input data from a user and generates appropriate output.

[0205] A "machine learning algorithm" is a set of computational methods that use data to learn patterns and make predictions or decisions.

[0206] A "user terminal" is an electronic device used by users to input data and receive results.

[0207] "Emotional information" refers to data that indicates the user's emotional state, and is obtained from sources such as voice tone and facial expressions.

[0208] A "confidence score" is a numerical indicator used to evaluate the reliability of a generated response.

[0209] "Blocking verification processing" is a technique for comparing results from different algorithms to confirm the integrity and reliability of data.

[0210] "Emotional state" refers to a user's instantaneous emotional response and is a factor that influences the system's response generation.

[0211] "Evaluation information" refers to feedback provided by users, which is used to improve the quality of the system's response.

[0212] In this embodiment of the system, a user terminal, such as smart glasses, is first used to collect user questions and emotional information. The terminal is equipped with a camera and microphone, and these sensors capture the user's facial expressions and voice tone in real time. The acquired data is analyzed as user emotional information.

[0213] The server distributes the user's question, along with this sentiment information, to multiple machine learning algorithms. Each algorithm generates an answer based on the received question and sentiment information, returning a response based on reliability and how well it adapts to the user's sentiment. The server then evaluates the answers from each algorithm through cross-validation and selects the most reliable answer.

[0214] The selected responses are adjusted to take the user's emotional state into consideration and delivered to the user's device. At the same time, the system also suggests appropriate response methods to the user, enabling better interaction. For example, staff at a nursing home could use smart glasses to assist with daily resident care. If a resident appears anxious, the system might ask, "What are you worried about today?" and suggest appropriate ways to comfort or reassure them.

[0215] Through a generative AI model, the system generates prompts and engages in adaptive dialogue that takes emotions into account. A concrete example of this application is a prompt such as, "Analyze the emotions of elderly people in real time and generate suggestions for care support that will alleviate their anxiety."

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The user's device uses its camera and microphone to capture the user's facial expressions and voice tone in real time. This data is preprocessed within the device to generate digitized emotional data for analysis as emotional information. The output at this stage includes the analyzed emotional state and the question text.

[0219] Step 2:

[0220] The terminal sends the generated question text and sentiment information to the server. The input here is the sentiment state and question data from the user terminal, and the output is a format conversion of this data, which is then used for further processing on the server.

[0221] Step 3:

[0222] The server distributes the received question text and sentiment information to multiple machine learning algorithms. The input is data from the terminal, and each algorithm generates a response adapted to the sentiment. The output is the response data from each algorithm.

[0223] Step 4:

[0224] The server evaluates the responses returned from each machine learning algorithm using cross-validation. The input consists of multiple response datasets, which are compared and evaluated to select those with high reliability and sentiment adaptability. The output is the most appropriate response dataset.

[0225] Step 5:

[0226] The server adjusts the selected response to reflect the user's emotions and sends it back to the user's terminal. The input data is the selected response, and the output is a final response adapted to the emotions, which is then sent to the terminal.

[0227] Step 6:

[0228] The system facilitates interaction with the user based on the responses received by the user's terminal. The input here is the final response from the server, and the output is displayed to the user and supports subsequent interactions.

[0229] This process enables the delivery of more personalized information that takes user emotions into consideration.

[0230] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0231] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0232] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0233] [Second Embodiment]

[0234] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0235] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0236] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0237] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0238] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0239] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0240] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0241] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0242] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0243] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0244] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0245] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0246] This invention is a system that utilizes multiple artificial intelligence algorithms via an information processing device to provide highly reliable answers to user questions. The embodiments thereof are described below in natural language.

[0247] System Overview

[0248] This system provides users with answers from multiple artificial intelligence algorithms, cross-validated to help them resolve technical problems and questions. This increases the reliability of the answers and enables engineers and technical support personnel to solve problems quickly and accurately.

[0249] System operation

[0250] 1. User input of question

[0251] Users use a terminal to enter technical questions. These questions can range from troubleshooting network connectivity issues to inquiries about software errors.

[0252] 2. Sending and receiving questions

[0253] The question entered from the terminal is instantly sent to the server. The server receives the question, verifies that it is in the correct format, and then proceeds with further processing.

[0254] 3. Execution of artificial intelligence algorithms

[0255] The server activates multiple artificial intelligence algorithms and distributes the received questions to each of them. Each algorithm analyzes the question in its own way and generates an answer based on that analysis.

[0256] 4. Collection and evaluation of responses

[0257] The generated responses are sent back to the server. The server collects these responses and performs cross-validation. That is, it thoroughly evaluates the consistency and reliability of each response and selects the most valid and reliable response.

[0258] 5. Sending responses back to users

[0259] The selected response is sent back from the server to the user's terminal. This allows the user to immediately obtain the technical information or solution they were looking for.

[0260] Specific example

[0261] For example, consider a user who enters the question, "My server connection is frequently dropping." The server distributes this to multiple AI algorithms. One algorithm might recommend "checking network settings," while another might suggest "resetting the hardware." Based on these responses, the server selects "checking network settings" as the most reliable answer, considering past performance and the current situation, and sends it back to the user. Through this process, the user receives specific steps to quickly resolve the problem.

[0262] This system will be an effective tool for receiving high-quality support, especially for new technical support staff and engineers. It is expected to contribute to strengthening corporate competitiveness and improving customer satisfaction.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The user uses their device to input the technical problem or question they want to solve in natural language. Once they have finished inputting, the user sends it to the server as question data by pressing the send button on their device.

[0266] Step 2:

[0267] The terminal receives question data entered by the user and sends it to the server via the internet. The transmitted data is usually sent using protocols such as HTTP.

[0268] Step 3:

[0269] The server receives the question data sent from the terminal and validates its content through a pre-programmed filtering process to determine if it is appropriate. If the format and content of the question are appropriate, the process proceeds to the next step.

[0270] Step 4:

[0271] The server distributes the question data to multiple artificial intelligence algorithms. Each algorithm uses a different method, operates independently, and can generate answers to the questions from its own perspective.

[0272] Step 5:

[0273] Each artificial intelligence algorithm receives a question from the server and generates an answer based on its own internal logic and model. The generated answer may include the reasoning behind the answer and any points to confirm.

[0274] Step 6:

[0275] The responses generated by each artificial intelligence algorithm are sent back to the server. When the responses are sent back, the confidence level of the response and related metadata may also be provided.

[0276] Step 7:

[0277] The server collects responses from all artificial intelligence algorithms. The server compares these responses and uses a cross-validation algorithm to evaluate their consistency and reliability. This process also utilizes past response history and supplementary information.

[0278] Step 8:

[0279] The server selects the most reliable and useful answer based on the cross-validation results. The degree of agreement and confidence score of the answers are important evaluation criteria in this selection process.

[0280] Step 9:

[0281] The server selects the most reliable answers and sends them back to the terminal. The returned answers are then formatted in a way that is easy for the user to understand.

[0282] Step 10:

[0283] The terminal receives the response sent from the server and displays the content on the user screen. As a result, the user can obtain the technical information and solutions that the user wants to know.

[0284] (Example 1)

[0285] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0286] In the field of information technology, it is important to provide highly reliable solutions in real time for the problem content and technical questions from users. However, conventional systems often rely on a single algorithm and have the problem that it is difficult to provide an optimal solution for complex questions.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0288] In this invention, the server includes means for the information processing device to start a plurality of machine learning algorithms, means for the information processing device to send the received problem content to the plurality of machine learning algorithms, and means for performing a data verification process to compare the returned solutions and evaluate the reliability. As a result, it is possible to analyze the problem content from multiple perspectives using a plurality of algorithms and quickly provide the most reliable solution.

[0289] The "information processing device" is a computing device that receives input from a user and executes a plurality of machine learning algorithms.

[0290] The "machine learning algorithm" is a program for analyzing the problem content received from a user and generating a solution based on it.

[0291] A "user-operated terminal" is an electronic device used by the user to input the details of a problem and receive the selected solution.

[0292] "Problem description" refers to the technical issues or questions that users are seeking to resolve.

[0293] "Reliability" is an indicator used to evaluate the accuracy and applicability of the generated solutions.

[0294] "Data validation processing" is the process of comparing the outputs from multiple machine learning algorithms, evaluating their reliability, and selecting the optimal solution.

[0295] "Solution" refers to specific countermeasures or advice regarding the user's problem.

[0296] This invention is a system that uses an information processing device to activate multiple machine learning algorithms and provide the optimal solution to a problem submitted by a user via a terminal.

[0297] The server distributes the received problem content to multiple machine learning algorithms. The server uses a cloud platform to run these algorithms by executing machine learning libraries such as TensorFlow and PyTorch. Each algorithm analyzes the received problem content and generates a solution based on that analysis. The generated solutions are returned to the server for confidence evaluation. This confidence evaluation involves data validation using tools like Scikit-learn, and the best solution is selected.

[0298] As a concrete example, consider a case where a user inputs a problem such as "slow internet connection." The server sends this information to multiple machine learning algorithms. One algorithm might generate a solution such as "try restarting the router," while another might suggest "checking the device settings." The server compares these returned solutions, uses data validation to select the best one, and sends it back to the user.

[0299] This process allows us to provide users with quick and reliable solutions to the technical challenges they face. For example, a user could input a prompt to the generating AI model such as, "I would like to contact technical support to find out how to improve the issue of 'web pages loading slowly'."

[0300] This system aims to utilize generative AI models and prompt statements to appropriately select and provide users with answers generated by multiple algorithms.

[0301] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0302] Step 1:

[0303] The user uses a terminal to input details of a technical problem. This input is sent to the server as text data. When the user inputs a problem such as "the printer is not working," the terminal converts it into digital data format and sends it to the server.

[0304] Step 2:

[0305] The server receives the assignment content submitted by the user and verifies whether it is in the correct format. Specifically, the server checks the consistency of the text format and prompts the user to re-enter the data if there are any deficiencies. In this step, data processing such as format verification and normalization of line breaks is performed based on the input data.

[0306] Step 3:

[0307] The server distributes the confirmed problem content to multiple generative AI models. Each model is executed using a machine learning library such as TensorFlow or PyTorch. Specifically, the server sends the problem content as a prompt text to each model and performs the operation of generating a solution based on it. At this time, new data operations are executed within the AI model and become the generated solutions.

[0308] Step 4:

[0309] The server collects the solutions returned from the generative AI models. The server subjects these solutions to data verification processing and evaluates their reliability. In this process, cross-validation is performed using Scikit-learn or the like, and the consistency and accuracy of each output are analyzed. Based on the evaluation results, the most appropriate solution is selected.

[0310] Step 5:

[0311] The server returns the selected optimal solution to the user's terminal. The user can check the solution on the terminal and use it to solve the problem. This step includes the operation of setting so that the solution is notified to the user's terminal or displayed on the screen. The generated solution is output as text data and provided to the user.

[0312] (Application Example 1)

[0313] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0314] In consumer technology devices, it is required to solve technical problems and questions faced by users quickly and with highly reliable information. However, currently, in many cases, users need technical knowledge, and as a result, the effective use of the device may be hindered. Therefore, it is necessary to develop a system that supports users in obtaining technical information without professional support.

[0315] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0316] In this invention, the server includes means for activating multiple machine learning algorithms and analyzing queries received from user devices, means for evaluating the responses generated by each algorithm based on cross-validation, and means for selecting a highly reliable response from the evaluation results and returning it to the user device. This makes it possible for users to obtain quick and effective solutions to complex technical problems in devices used in their homes.

[0317] An "information processing system" is a device that receives inquiries from users and has the function of generating and evaluating responses using multiple machine learning algorithms.

[0318] A "machine learning algorithm" is a computational method for learning patterns from given data and generating appropriate responses based on new data.

[0319] "User equipment" refers to digital devices used within the home that work in conjunction with an information processing system to send and receive user inquiries.

[0320] "Reliability" is an index that quantitatively evaluates the accuracy and applicability of the generated response.

[0321] Cross-validation is a technique for comparing responses generated by multiple algorithms to verify their consistency and reliability.

[0322] The "technical advisor function" is an auxiliary function that enables the user's device to automatically provide solutions to technical problems.

[0323] In the system implementing this invention, a server is used as the central point for information processing. The server first receives inquiries from user devices via the network and analyzes their content. The analyzed content is supplied to several pre-configured machine learning algorithms, and each algorithm generates a response based on its respective methodology.

[0324] The server receives these responses and uses cross-validation techniques to evaluate the confidence level of each response. The confidence scores provided by each algorithm are used for the confidence evaluation, and the most effective response is selected based on these scores. The selected response is then sent back to the user's device via the network. In this process, the server uses programming languages ​​such as Python and related machine learning libraries (e.g., TensorFlow, PyTorch).

[0325] For example, if a user enters a question such as "My robot vacuum cleaner cannot connect to the Wi-Fi network," the server will provide recommendations such as reviewing network settings or optimizing the connection distance to the router. In this case, the server will use a prompt example like the following for the machine learning model: "When a user asks 'My robot cannot connect to Wi-Fi,' please suggest an appropriate solution."

[0326] The introduction of this system will significantly improve convenience, as users will be able to obtain quick and accurate solutions to technical problems within their homes.

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The user uses a terminal to input inquiries about technical problems. These inquiries cover a wide range of topics, such as "My robotic vacuum cleaner cannot connect to Wi-Fi." The terminal converts these inquiries into data format and sends them to the server via the network. The input is the user's inquiry text, and the output is the data format sent to the server.

[0330] Step 2:

[0331] The server receives queries sent from terminals and parses their content. This parsing uses natural language processing techniques to understand the queries and interpret their meaning. The input is query data received from terminals, and the output is the structure data of the parsed queries.

[0332] Step 3:

[0333] The server distributes the analyzed query to multiple generative AI models, each of which generates a response based on its own algorithm. Prompts are used to instruct the models during this process. The input is the analyzed query data, and the output is the response candidates generated by each model.

[0334] Step 4:

[0335] The server collects responses returned from each generating AI model and performs cross-validation. It compares confidence scores to determine the most reliable response. The input consists of multiple response candidates and their confidence scores, and the output is the selected optimal response.

[0336] Step 5:

[0337] The server resends the selected, reliable response to the terminal via the network. The user can then view the specific problem-solving solution through the terminal. The input is the selected response, and the output is the text information of the solution displayed on the user's terminal.

[0338] This process allows us to respond quickly and accurately to users' technical problems.

[0339] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0340] The present invention is a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device. It provides highly reliable answers to user questions while simultaneously considering the user's emotional state to deliver more personalized information. The embodiments thereof are described in detail below.

[0341] System Overview

[0342] This system works by having the user ask technical questions in natural language through a terminal, which are then received by an information processing unit. After receiving the questions, the information processing unit distributes them to multiple artificial intelligence algorithms, each of which generates an answer. In addition, an emotion engine recognizes the user's emotions in real time, and performs cross-validation processing while considering the user's state to select the most reliable answer.

[0343] System operation

[0344] 1. User question input and sentiment detection

[0345] The user enters a technical question into the device. During this process, the device uses sensors such as a camera and microphone to acquire emotional data from the user's voice tone and facial expressions.

[0346] 2. Sending questions and sentiment data

[0347] The terminal sends the entered question and user sentiment data to the server. The server receives this data and prepares for the next step.

[0348] 3. Emotional analysis using an emotional engine

[0349] The emotion engine within the server analyzes the received emotion data to determine the user's emotional state. This determination becomes an important input for subsequent processing.

[0350] 4. Application of artificial intelligence algorithms

[0351] The server distributes the question to multiple artificial intelligence algorithms, each generating an answer. Here, the user's emotional state influences the answer generation process of each algorithm, potentially adjusting the tone and content of the response.

[0352] 5. Cross-validation and response selection

[0353] The server collects responses from each algorithm and performs cross-validation. During this process, the most appropriate and reliable response is selected, taking into account the emotional state output by the emotion engine.

[0354] 6. Providing responses and feedback

[0355] The selected answers are returned to the terminal and displayed to the user. The user can also input feedback on those answers from the terminal and send it to the server. This feedback contributes to further improving the system's accuracy.

[0356] Specific example

[0357] As a concrete example, consider a scenario where a user, expressing anger, inputs, "A system error has stopped my work. What should I do?" The terminal sends this expression as emotional data to the server. The server's emotion engine identifies this data as "anger," and based on this information, an artificial intelligence algorithm works to generate a response that includes more polite and prompt solutions. Finally, the server returns this response to the user, thereby reducing the user's anxiety and stress.

[0358] Thus, the invention is a system that enables more effective and humane support by taking user emotions into consideration.

[0359] The following describes the processing flow.

[0360] Step 1:

[0361] The user uses the device to input the technical problem they want to solve in natural language. During input, the device simultaneously uses the camera and microphone to capture emotional data from the user's facial expressions and voice.

[0362] Step 2:

[0363] The terminal sends the entered question and acquired sentiment data to the server. Communication takes place over the internet, and the data format follows a predefined protocol.

[0364] Step 3:

[0365] The server receives questions and emotion data sent from the terminal. An emotion engine within the server analyzes the emotion data and determines the user's current emotional state. At this point, it generates emotion labels such as "joy," "anxiety," and "anger."

[0366] Step 4:

[0367] The server prepares the question data and distributes it to multiple artificial intelligence algorithms. Each algorithm receives this question data and performs analysis using its own model.

[0368] Step 5:

[0369] Each artificial intelligence algorithm generates an answer to a question. During this process, it uses emotional state information provided by the server to adjust the tone and content of the answer. For example, if the user's emotion is "anger," the answer will use more careful and considerate language.

[0370] Step 6:

[0371] Each artificial intelligence algorithm sends its generated response back to the server. The server receives all of these responses and prepares them for the next processing step.

[0372] Step 7:

[0373] The server performs cross-validation on the received responses. Here, the server evaluates the results considering the consistency, reliability, and emotional state of the responses. It selects the response that is most reliable and best reflects the user's emotions.

[0374] Step 8:

[0375] The server sends the selected, optimal answer back to the terminal. The answer may include emotionally sensitive explanations and is provided in a format that is easy for the user to understand.

[0376] Step 9:

[0377] The device receives the response sent back from the server and displays it on the user screen. The user can then review the response and take the next steps to resolve the problem.

[0378] Step 10:

[0379] The user sends feedback on the answers they provide from their device to the server. The server receives this feedback and can use the data to improve system performance.

[0380] (Example 2)

[0381] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0382] In many information processing systems, the quality of automated responses to user inquiries is crucial. Furthermore, answers that do not consider the user's emotional state do not necessarily lead to user satisfaction. Therefore, there is a need to provide reliable and personalized answers that reflect the user's emotional state.

[0383] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0384] In this invention, the server includes means for an information processing device to activate multiple computational models, means for receiving questions input from a user terminal, and means for distributing the received questions to the multiple computational models. This makes it possible to provide appropriate and reliable automated responses that take into account the user's emotional state.

[0385] An "information processing device" is a hardware or software system equipped with electronic functions for receiving, processing, and analyzing data and providing responses to users.

[0386] A "computational model" is a mathematical model designed by combining algorithmic methods and data to generate automated responses to specific tasks or questions.

[0387] A "user terminal" is a computing device used by a user to input and receive information.

[0388] "Emotional data" refers to data obtained from the user's voice tone, facial expressions, etc., and is used to determine the user's emotional state.

[0389] A "confidence score" is an evaluation value returned by each computational model to assess how accurate and suitable the generated response is for its intended purpose.

[0390] The "evaluation process" is the process of comparing responses returned from multiple models, evaluating their reliability and suitability, and selecting the most appropriate response.

[0391] This invention provides a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device, aiming to provide highly reliable answers to user questions. Furthermore, this system achieves more personalized information delivery by taking into account the user's emotional state. Specific embodiments are described below.

[0392] The user inputs questions using natural language through their device. The device is equipped with sensors such as a camera and microphone, which simultaneously capture emotional data such as the user's voice tone and facial expressions. This emotional data is transmitted to the server in real time.

[0393] Within the server, the emotion engine analyzes the received emotion data to determine the user's emotional state. This emotional state plays a crucial role in generating responses in the next stage. Based on this emotional state, the server uses multiple generative AI models to generate answers to the user's questions. Each model reflects the emotion data and adjusts the response to have the optimal tone and content.

[0394] After considering the accuracy of the responses and their relevance to the user's emotions, the server selects the most appropriate response. This selected response is then sent back to the terminal and displayed to the user.

[0395] For example, if a user enters "A system error has stopped operations. What should I do?" while displaying an angry expression, the terminal sends that expression to the server as emotion data. On the server, the emotion engine determines the emotion data to be "anger" and adjusts the generation AI model to create a response that includes more polite and prompt solutions. An example of a prompt message that can be used is: "If the user is in an angry emotional state, generate a prompt and polite response. Question: 'A system error has stopped operations. What should I do?'"

[0396] This system allows users to receive appropriate, humane support that reflects their emotions.

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1:

[0399] The user inputs a technical question in natural language into the user's device. The device records the question as text data. Simultaneously, the device's camera and microphone are used to acquire emotional data such as voice tone and facial expressions, which are then recorded as sensor data. The input includes both the user's question and emotional data.

[0400] Step 2:

[0401] The terminal sends the acquired question and sentiment data to the server. The protocol used is either HTTP or WebSocket, encrypted with SSL / TLS to ensure secure communication. The entered text data and sentiment data reach the server.

[0402] Step 3:

[0403] The server inputs the received emotional data into the emotion engine. The emotion engine uses machine learning algorithms to analyze the emotional data and determine the user's emotional state. This determination becomes important input for subsequent processing steps, outputting the user's emotional state as a numerical value or category.

[0404] Step 4:

[0405] The server distributes the user's question to multiple generative AI models. Each model generates the optimal answer from its own perspective, taking into account the user's emotional state. The user's emotional data is used as input, and the generated answers are output as text.

[0406] Step 5:

[0407] The server collects the responses returned from each generative AI model and performs cross-validation. This process comprehensively evaluates the confidence scores and emotional state judgments provided by the generative AI models. Based on the resulting evaluation scores, the server selects the most reliable response. The selected response is then output as the result of the selection.

[0408] Step 6:

[0409] The server sends the selected answers to the terminal. The user can receive and view the selected answers via the terminal. The output answers serve as the basis for user confirmation and feedback input.

[0410] Step 7:

[0411] Users input feedback on the provided answers via a terminal. The terminal sends this feedback back to the server. This feedback is stored in the server's database to improve system performance. The feedback data is input and output as basic system data.

[0412] (Application Example 2)

[0413] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0414] In recent years, with the advancement of information technology, there has been a growing demand for personalized information that takes into account the emotional state of individual users. However, conventional information processing systems are unable to provide responses that adequately consider the user's emotions. As a result, there is a lack of support that takes users' emotions into account, and in particular, in nursing care settings, more appropriate responses are needed to stabilize the emotions of residents.

[0415] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0416] In this invention, the server includes means for an information processing device to activate multiple machine learning algorithms, means for receiving questions and sentiment information input from a user terminal, and means for distributing them to the machine learning algorithms. This makes it possible to propose highly reliable answers that take the user's emotions into consideration, and appropriate dialogue methods that correspond to the user's emotional state.

[0417] An "information processing device" is a computing device that analyzes input data from a user and generates appropriate output.

[0418] A "machine learning algorithm" is a set of computational methods that use data to learn patterns and make predictions or decisions.

[0419] A "user terminal" is an electronic device used by users to input data and receive results.

[0420] "Emotional information" refers to data that indicates the user's emotional state, and is obtained from sources such as voice tone and facial expressions.

[0421] A "confidence score" is a numerical indicator used to evaluate the reliability of a generated response.

[0422] "Blocking verification processing" is a technique for comparing results from different algorithms to confirm the integrity and reliability of data.

[0423] "Emotional state" refers to a user's instantaneous emotional response and is a factor that influences the system's response generation.

[0424] "Evaluation information" refers to feedback provided by users, which is used to improve the quality of the system's response.

[0425] In this embodiment of the system, a user terminal, such as smart glasses, is first used to collect user questions and emotional information. The terminal is equipped with a camera and microphone, and these sensors capture the user's facial expressions and voice tone in real time. The acquired data is analyzed as user emotional information.

[0426] The server distributes the user's question, along with this sentiment information, to multiple machine learning algorithms. Each algorithm generates an answer based on the received question and sentiment information, returning a response based on reliability and how well it adapts to the user's sentiment. The server then evaluates the answers from each algorithm through cross-validation and selects the most reliable answer.

[0427] The selected responses are adjusted to take the user's emotional state into consideration and delivered to the user's device. At the same time, the system also suggests appropriate response methods to the user, enabling better interaction. For example, staff at a nursing home could use smart glasses to assist with daily resident care. If a resident appears anxious, the system might ask, "What are you worried about today?" and suggest appropriate ways to comfort or reassure them.

[0428] Through a generative AI model, the system generates prompts and engages in adaptive dialogue that takes emotions into account. A concrete example of this application is a prompt such as, "Analyze the emotions of elderly people in real time and generate suggestions for care support that will alleviate their anxiety."

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1:

[0431] The user's device uses its camera and microphone to capture the user's facial expressions and voice tone in real time. This data is preprocessed within the device to generate digitized emotional data for analysis as emotional information. The output at this stage includes the analyzed emotional state and the question text.

[0432] Step 2:

[0433] The terminal sends the generated question text and sentiment information to the server. The input here is the sentiment state and question data from the user terminal, and the output is a format conversion of this data, which is then used for further processing on the server.

[0434] Step 3:

[0435] The server distributes the received question text and sentiment information to multiple machine learning algorithms. The input is data from the terminal, and each algorithm generates a response adapted to the sentiment. The output is the response data from each algorithm.

[0436] Step 4:

[0437] The server evaluates the responses returned from each machine learning algorithm using cross-validation. The input consists of multiple response datasets, which are compared and evaluated to select those with high reliability and sentiment adaptability. The output is the most appropriate response dataset.

[0438] Step 5:

[0439] The server adjusts the selected response to reflect the user's emotions and sends it back to the user's terminal. The input data is the selected response, and the output is a final response adapted to the emotions, which is then sent to the terminal.

[0440] Step 6:

[0441] The system facilitates interaction with the user based on the responses received by the user's terminal. The input here is the final response from the server, and the output is displayed to the user and supports subsequent interactions.

[0442] This process enables the delivery of more personalized information that takes user emotions into consideration.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0444] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0449] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0450] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0451] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0453] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0454] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0455] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0456] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0457] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0458] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0459] This invention is a system that utilizes multiple artificial intelligence algorithms via an information processing device to provide highly reliable answers to user questions. The embodiments thereof are described below in natural language.

[0460] System Overview

[0461] This system provides users with answers from multiple artificial intelligence algorithms, cross-validated to help them resolve technical problems and questions. This increases the reliability of the answers and enables engineers and technical support personnel to solve problems quickly and accurately.

[0462] System operation

[0463] 1. User input of question

[0464] Users use a terminal to enter technical questions. These questions can range from troubleshooting network connectivity issues to inquiries about software errors.

[0465] 2. Sending and receiving questions

[0466] The question entered from the terminal is instantly sent to the server. The server receives the question, verifies that it is in the correct format, and then proceeds with further processing.

[0467] 3. Execution of artificial intelligence algorithms

[0468] The server activates multiple artificial intelligence algorithms and distributes the received questions to each of them. Each algorithm analyzes the question in its own way and generates an answer based on that analysis.

[0469] 4. Collection and evaluation of responses

[0470] The generated responses are sent back to the server. The server collects these responses and performs cross-validation. That is, it thoroughly evaluates the consistency and reliability of each response and selects the most valid and reliable response.

[0471] 5. Sending responses back to users

[0472] The selected response is sent back from the server to the user's terminal. This allows the user to immediately obtain the technical information or solution they were looking for.

[0473] Specific example

[0474] For example, consider a user who enters the question, "My server connection is frequently dropping." The server distributes this to multiple AI algorithms. One algorithm might recommend "checking network settings," while another might suggest "resetting the hardware." Based on these responses, the server selects "checking network settings" as the most reliable answer, considering past performance and the current situation, and sends it back to the user. Through this process, the user receives specific steps to quickly resolve the problem.

[0475] This system will be an effective tool for receiving high-quality support, especially for new technical support staff and engineers. It is expected to contribute to strengthening corporate competitiveness and improving customer satisfaction.

[0476] The following describes the processing flow.

[0477] Step 1:

[0478] The user uses their device to input the technical problem or question they want to solve in natural language. Once they have finished inputting, the user sends it to the server as question data by pressing the send button on their device.

[0479] Step 2:

[0480] The terminal receives question data entered by the user and sends it to the server via the internet. The transmitted data is usually sent using protocols such as HTTP.

[0481] Step 3:

[0482] The server receives the question data sent from the terminal and validates its content through a pre-programmed filtering process to determine if it is appropriate. If the format and content of the question are appropriate, the process proceeds to the next step.

[0483] Step 4:

[0484] The server distributes the question data to multiple artificial intelligence algorithms. Each algorithm uses a different method, operates independently, and can generate answers to the questions from its own perspective.

[0485] Step 5:

[0486] Each artificial intelligence algorithm receives a question from the server and generates an answer based on its own internal logic and model. The generated answer may include the reasoning behind the answer and any points to confirm.

[0487] Step 6:

[0488] The responses generated by each artificial intelligence algorithm are sent back to the server. When the responses are sent back, the confidence level of the response and related metadata may also be provided.

[0489] Step 7:

[0490] The server collects responses from all artificial intelligence algorithms. The server compares these responses and uses a cross-validation algorithm to evaluate their consistency and reliability. This process also utilizes past response history and supplementary information.

[0491] Step 8:

[0492] The server selects the most reliable and useful answer based on the cross-validation results. The degree of agreement and confidence score of the answers are important evaluation criteria in this selection process.

[0493] Step 9:

[0494] The server selects the most reliable answers and sends them back to the terminal. The returned answers are then formatted in a way that is easy for the user to understand.

[0495] Step 10:

[0496] The terminal receives the response sent back from the server and displays its contents on the user screen. This allows the user to obtain the technical information and solutions they were looking for.

[0497] (Example 1)

[0498] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0499] In the field of information technology, providing reliable, real-time solutions to user problems and technical questions is crucial. However, conventional systems often rely on a single algorithm, making it difficult to provide optimal solutions to complex questions.

[0500] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0501] In this invention, the server includes means for the information processing device to activate multiple machine learning algorithms, means for the information processing device to transmit the received problem content to the multiple machine learning algorithms, and means for performing data verification processing to compare the returned solutions and evaluate their reliability. This makes it possible to analyze the problem content from multiple angles using multiple algorithms and to quickly provide the most reliable solution.

[0502] An "information processing device" is a computing device that receives input from a user and executes multiple machine learning algorithms.

[0503] A "machine learning algorithm" is a program that analyzes the content of a problem received from a user and generates a solution based on that analysis.

[0504] A "user-operated terminal" is an electronic device used by the user to input the details of a problem and receive the selected solution.

[0505] "Problem description" refers to the technical issues or questions that users are seeking to resolve.

[0506] "Reliability" is an indicator used to evaluate the accuracy and applicability of the generated solutions.

[0507] "Data validation processing" is the process of comparing the outputs from multiple machine learning algorithms, evaluating their reliability, and selecting the optimal solution.

[0508] "Solution" refers to specific countermeasures or advice regarding the user's problem.

[0509] This invention is a system that uses an information processing device to activate multiple machine learning algorithms and provide the optimal solution to a problem submitted by a user via a terminal.

[0510] The server distributes the received problem content to multiple machine learning algorithms. The server uses a cloud platform to run these algorithms by executing machine learning libraries such as TensorFlow and PyTorch. Each algorithm analyzes the received problem content and generates a solution based on that analysis. The generated solutions are returned to the server for confidence evaluation. This confidence evaluation involves data validation using tools like Scikit-learn, and the best solution is selected.

[0511] As a concrete example, consider a case where a user inputs a problem such as "slow internet connection." The server sends this information to multiple machine learning algorithms. One algorithm might generate a solution such as "try restarting the router," while another might suggest "checking the device settings." The server compares these returned solutions, uses data validation to select the best one, and sends it back to the user.

[0512] This process allows us to provide users with quick and reliable solutions to the technical challenges they face. For example, a user could input a prompt to the generating AI model such as, "I would like to contact technical support to find out how to improve the issue of 'web pages loading slowly'."

[0513] This system aims to utilize generative AI models and prompt statements to appropriately select and provide users with answers generated by multiple algorithms.

[0514] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0515] Step 1:

[0516] The user uses a terminal to input details of a technical problem. This input is sent to the server as text data. When the user inputs a problem such as "the printer is not working," the terminal converts it into digital data format and sends it to the server.

[0517] Step 2:

[0518] The server receives the assignment content submitted by the user and verifies whether it is in the correct format. Specifically, the server checks the consistency of the text format and prompts the user to re-enter the data if there are any deficiencies. In this step, data processing such as format verification and normalization of line breaks is performed based on the input data.

[0519] Step 3:

[0520] The server distributes the confirmed problem details to multiple generative AI models. Each model runs using machine learning libraries such as TensorFlow or PyTorch. Specifically, the server sends the problem details as prompts to each model and generates solutions based on them. During this process, new data calculations are performed within the AI ​​models, resulting in the generated solutions.

[0521] Step 4:

[0522] The server collects the solutions returned from the generated AI model. The server then subjects these solutions to a data validation process to evaluate their confidence. This process involves cross-validation using tools like Scikit-learn, analyzing the consistency and accuracy of each output. Based on the evaluation results, the most appropriate solution is selected.

[0523] Step 5:

[0524] The server sends the selected optimal solution back to the user's device. The user can then review the solution on their device and use it to resolve the problem. This step includes configuring the user's device to receive a notification or display the solution on the screen. The generated solution is output as text data and provided to the user.

[0525] (Application Example 1)

[0526] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0527] In consumer technology devices, there is a need to resolve technical problems and questions users face quickly and with reliable information. However, currently, users often require technical knowledge, which can hinder the effective use of the device. Therefore, there is a need to develop a system that supports users in obtaining technical information without requiring expert assistance.

[0528] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0529] In this invention, the server includes means for activating multiple machine learning algorithms and analyzing queries received from user devices, means for evaluating the responses generated by each algorithm based on cross-validation, and means for selecting a highly reliable response from the evaluation results and returning it to the user device. This makes it possible for users to obtain quick and effective solutions to complex technical problems in devices used in their homes.

[0530] An "information processing system" is a device that receives inquiries from users and has the function of generating and evaluating responses using multiple machine learning algorithms.

[0531] A "machine learning algorithm" is a computational method for learning patterns from given data and generating appropriate responses based on new data.

[0532] "User equipment" refers to digital devices used within the home that work in conjunction with an information processing system to send and receive user inquiries.

[0533] "Reliability" is an index that quantitatively evaluates the accuracy and applicability of the generated response.

[0534] Cross-validation is a technique for comparing responses generated by multiple algorithms to verify their consistency and reliability.

[0535] The "technical advisor function" is an auxiliary function that enables the user's device to automatically provide solutions to technical problems.

[0536] In the system implementing this invention, a server is used as the central point for information processing. The server first receives inquiries from user devices via the network and analyzes their content. The analyzed content is supplied to several pre-configured machine learning algorithms, and each algorithm generates a response based on its respective methodology.

[0537] The server receives these responses and uses cross-validation techniques to evaluate the confidence level of each response. The confidence scores provided by each algorithm are used for the confidence evaluation, and the most effective response is selected based on these scores. The selected response is then sent back to the user's device via the network. In this process, the server uses programming languages ​​such as Python and related machine learning libraries (e.g., TensorFlow, PyTorch).

[0538] For example, if a user enters a question such as "My robot vacuum cleaner cannot connect to the Wi-Fi network," the server will provide recommendations such as reviewing network settings or optimizing the connection distance to the router. In this case, the server will use a prompt example like the following for the machine learning model: "When a user asks 'My robot cannot connect to Wi-Fi,' please suggest an appropriate solution."

[0539] The introduction of this system will significantly improve convenience, as users will be able to obtain quick and accurate solutions to technical problems within their homes.

[0540] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0541] Step 1:

[0542] The user uses a terminal to input inquiries about technical problems. These inquiries cover a wide range of topics, such as "My robotic vacuum cleaner cannot connect to Wi-Fi." The terminal converts these inquiries into data format and sends them to the server via the network. The input is the user's inquiry text, and the output is the data format sent to the server.

[0543] Step 2:

[0544] The server receives queries sent from terminals and parses their content. This parsing uses natural language processing techniques to understand the queries and interpret their meaning. The input is query data received from terminals, and the output is the structure data of the parsed queries.

[0545] Step 3:

[0546] The server distributes the analyzed query to multiple generative AI models, each of which generates a response based on its own algorithm. Prompts are used to instruct the models during this process. The input is the analyzed query data, and the output is the response candidates generated by each model.

[0547] Step 4:

[0548] The server collects responses returned from each generating AI model and performs cross-validation. It compares confidence scores to determine the most reliable response. The input consists of multiple response candidates and their confidence scores, and the output is the selected optimal response.

[0549] Step 5:

[0550] The server resends the selected, reliable response to the terminal via the network. The user can then view the specific problem-solving solution through the terminal. The input is the selected response, and the output is the text information of the solution displayed on the user's terminal.

[0551] This process allows us to respond quickly and accurately to users' technical problems.

[0552] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0553] The present invention is a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device. It provides highly reliable answers to user questions while simultaneously considering the user's emotional state to deliver more personalized information. The embodiments thereof are described in detail below.

[0554] System Overview

[0555] This system works by having the user ask technical questions in natural language through a terminal, which are then received by an information processing unit. After receiving the questions, the information processing unit distributes them to multiple artificial intelligence algorithms, each of which generates an answer. In addition, an emotion engine recognizes the user's emotions in real time, and performs cross-validation processing while considering the user's state to select the most reliable answer.

[0556] System operation

[0557] 1. User question input and sentiment detection

[0558] The user enters a technical question into the device. During this process, the device uses sensors such as a camera and microphone to acquire emotional data from the user's voice tone and facial expressions.

[0559] 2. Sending questions and sentiment data

[0560] The terminal sends the entered question and user sentiment data to the server. The server receives this data and prepares for the next step.

[0561] 3. Emotional analysis using an emotional engine

[0562] The emotion engine within the server analyzes the received emotion data to determine the user's emotional state. This determination becomes an important input for subsequent processing.

[0563] 4. Application of artificial intelligence algorithms

[0564] The server distributes the question to multiple artificial intelligence algorithms, each generating an answer. Here, the user's emotional state influences the answer generation process of each algorithm, potentially adjusting the tone and content of the response.

[0565] 5. Cross-validation and response selection

[0566] The server collects responses from each algorithm and performs cross-validation. During this process, the most appropriate and reliable response is selected, taking into account the emotional state output by the emotion engine.

[0567] 6. Providing responses and feedback

[0568] The selected answers are returned to the terminal and displayed to the user. The user can also input feedback on those answers from the terminal and send it to the server. This feedback contributes to further improving the system's accuracy.

[0569] Specific example

[0570] As a concrete example, consider a scenario where a user, expressing anger, inputs, "A system error has stopped my work. What should I do?" The terminal sends this expression as emotional data to the server. The server's emotion engine identifies this data as "anger," and based on this information, an artificial intelligence algorithm works to generate a response that includes more polite and prompt solutions. Finally, the server returns this response to the user, thereby reducing the user's anxiety and stress.

[0571] Thus, the invention is a system that enables more effective and humane support by taking user emotions into consideration.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The user uses the device to input the technical problem they want to solve in natural language. During input, the device simultaneously uses the camera and microphone to capture emotional data from the user's facial expressions and voice.

[0575] Step 2:

[0576] The terminal sends the entered question and acquired sentiment data to the server. Communication takes place over the internet, and the data format follows a predefined protocol.

[0577] Step 3:

[0578] The server receives questions and emotion data sent from the terminal. An emotion engine within the server analyzes the emotion data and determines the user's current emotional state. At this point, it generates emotion labels such as "joy," "anxiety," and "anger."

[0579] Step 4:

[0580] The server prepares the question data and distributes it to multiple artificial intelligence algorithms. Each algorithm receives this question data and performs analysis using its own model.

[0581] Step 5:

[0582] Each artificial intelligence algorithm generates an answer to a question. During this process, it uses emotional state information provided by the server to adjust the tone and content of the answer. For example, if the user's emotion is "anger," the answer will use more careful and considerate language.

[0583] Step 6:

[0584] Each artificial intelligence algorithm sends its generated response back to the server. The server receives all of these responses and prepares them for the next processing step.

[0585] Step 7:

[0586] The server performs cross-validation on the received responses. Here, the server evaluates the results considering the consistency, reliability, and emotional state of the responses. It selects the response that is most reliable and best reflects the user's emotions.

[0587] Step 8:

[0588] The server sends the selected, optimal answer back to the terminal. The answer may include emotionally sensitive explanations and is provided in a format that is easy for the user to understand.

[0589] Step 9:

[0590] The device receives the response sent back from the server and displays it on the user screen. The user can then review the response and take the next steps to resolve the problem.

[0591] Step 10:

[0592] The user sends feedback on the answers they provide from their device to the server. The server receives this feedback and can use the data to improve system performance.

[0593] (Example 2)

[0594] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0595] In many information processing systems, the quality of automated responses to user inquiries is crucial. Furthermore, answers that do not consider the user's emotional state do not necessarily lead to user satisfaction. Therefore, there is a need to provide reliable and personalized answers that reflect the user's emotional state.

[0596] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0597] In this invention, the server includes means for an information processing device to activate multiple computational models, means for receiving questions input from a user terminal, and means for distributing the received questions to the multiple computational models. This makes it possible to provide appropriate and reliable automated responses that take into account the user's emotional state.

[0598] An "information processing device" is a hardware or software system equipped with electronic functions for receiving, processing, and analyzing data and providing responses to users.

[0599] A "computational model" is a mathematical model designed by combining algorithmic methods and data to generate automated responses to specific tasks or questions.

[0600] A "user terminal" is a computing device used by a user to input and receive information.

[0601] "Emotional data" refers to data obtained from the user's voice tone, facial expressions, etc., and is used to determine the user's emotional state.

[0602] A "confidence score" is an evaluation value returned by each computational model to assess how accurate and suitable the generated response is for its intended purpose.

[0603] The "evaluation process" is the process of comparing responses returned from multiple models, evaluating their reliability and suitability, and selecting the most appropriate response.

[0604] This invention provides a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device, aiming to provide highly reliable answers to user questions. Furthermore, this system achieves more personalized information delivery by taking into account the user's emotional state. Specific embodiments are described below.

[0605] The user inputs questions using natural language through their device. The device is equipped with sensors such as a camera and microphone, which simultaneously capture emotional data such as the user's voice tone and facial expressions. This emotional data is transmitted to the server in real time.

[0606] Within the server, the emotion engine analyzes the received emotion data to determine the user's emotional state. This emotional state plays a crucial role in generating responses in the next stage. Based on this emotional state, the server uses multiple generative AI models to generate answers to the user's questions. Each model reflects the emotion data and adjusts the response to have the optimal tone and content.

[0607] After considering the accuracy of the responses and their relevance to the user's emotions, the server selects the most appropriate response. This selected response is then sent back to the terminal and displayed to the user.

[0608] For example, if a user enters "A system error has stopped operations. What should I do?" while displaying an angry expression, the terminal sends that expression to the server as emotion data. On the server, the emotion engine determines the emotion data to be "anger" and adjusts the generation AI model to create a response that includes more polite and prompt solutions. An example of a prompt message that can be used is: "If the user is in an angry emotional state, generate a prompt and polite response. Question: 'A system error has stopped operations. What should I do?'"

[0609] This system allows users to receive appropriate, humane support that reflects their emotions.

[0610] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0611] Step 1:

[0612] The user inputs a technical question in natural language into the user's device. The device records the question as text data. Simultaneously, the device's camera and microphone are used to acquire emotional data such as voice tone and facial expressions, which are then recorded as sensor data. The input includes both the user's question and emotional data.

[0613] Step 2:

[0614] The terminal sends the acquired question and sentiment data to the server. The protocol used is either HTTP or WebSocket, encrypted with SSL / TLS to ensure secure communication. The entered text data and sentiment data reach the server.

[0615] Step 3:

[0616] The server inputs the received emotional data into the emotion engine. The emotion engine uses machine learning algorithms to analyze the emotional data and determine the user's emotional state. This determination becomes important input for subsequent processing steps, outputting the user's emotional state as a numerical value or category.

[0617] Step 4:

[0618] The server distributes the user's question to multiple generative AI models. Each model generates the optimal answer from its own perspective, taking into account the user's emotional state. The user's emotional data is used as input, and the generated answers are output as text.

[0619] Step 5:

[0620] The server collects the responses returned from each generative AI model and performs cross-validation. This process comprehensively evaluates the confidence scores and emotional state judgments provided by the generative AI models. Based on the resulting evaluation scores, the server selects the most reliable response. The selected response is then output as the result of the selection.

[0621] Step 6:

[0622] The server sends the selected answers to the terminal. The user can receive and view the selected answers via the terminal. The output answers serve as the basis for user confirmation and feedback input.

[0623] Step 7:

[0624] Users input feedback on the provided answers via a terminal. The terminal sends this feedback back to the server. This feedback is stored in the server's database to improve system performance. The feedback data is input and output as basic system data.

[0625] (Application Example 2)

[0626] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0627] In recent years, with the advancement of information technology, there has been a growing demand for personalized information that takes into account the emotional state of individual users. However, conventional information processing systems are unable to provide responses that adequately consider the user's emotions. As a result, there is a lack of support that takes users' emotions into account, and in particular, in nursing care settings, more appropriate responses are needed to stabilize the emotions of residents.

[0628] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0629] In this invention, the server includes means for an information processing device to activate multiple machine learning algorithms, means for receiving questions and sentiment information input from a user terminal, and means for distributing them to the machine learning algorithms. This makes it possible to propose highly reliable answers that take the user's emotions into consideration, and appropriate dialogue methods that correspond to the user's emotional state.

[0630] An "information processing device" is a computing device that analyzes input data from a user and generates appropriate output.

[0631] A "machine learning algorithm" is a set of computational methods that use data to learn patterns and make predictions or decisions.

[0632] A "user terminal" is an electronic device used by users to input data and receive results.

[0633] "Emotional information" refers to data that indicates the user's emotional state, and is obtained from sources such as voice tone and facial expressions.

[0634] A "confidence score" is a numerical indicator used to evaluate the reliability of a generated response.

[0635] "Blocking verification processing" is a technique for comparing results from different algorithms to confirm the integrity and reliability of data.

[0636] "Emotional state" refers to a user's instantaneous emotional response and is a factor that influences the system's response generation.

[0637] "Evaluation information" refers to feedback provided by users, which is used to improve the quality of the system's response.

[0638] In this embodiment of the system, a user terminal, such as smart glasses, is first used to collect user questions and emotional information. The terminal is equipped with a camera and microphone, and these sensors capture the user's facial expressions and voice tone in real time. The acquired data is analyzed as user emotional information.

[0639] The server distributes the user's question, along with this sentiment information, to multiple machine learning algorithms. Each algorithm generates an answer based on the received question and sentiment information, returning a response based on reliability and how well it adapts to the user's sentiment. The server then evaluates the answers from each algorithm through cross-validation and selects the most reliable answer.

[0640] The selected responses are adjusted to take the user's emotional state into consideration and delivered to the user's device. At the same time, the system also suggests appropriate response methods to the user, enabling better interaction. For example, staff at a nursing home could use smart glasses to assist with daily resident care. If a resident appears anxious, the system might ask, "What are you worried about today?" and suggest appropriate ways to comfort or reassure them.

[0641] Through a generative AI model, the system generates prompts and engages in adaptive dialogue that takes emotions into account. A concrete example of this application is a prompt such as, "Analyze the emotions of elderly people in real time and generate suggestions for care support that will alleviate their anxiety."

[0642] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0643] Step 1:

[0644] The user's device uses its camera and microphone to capture the user's facial expressions and voice tone in real time. This data is preprocessed within the device to generate digitized emotional data for analysis as emotional information. The output at this stage includes the analyzed emotional state and the question text.

[0645] Step 2:

[0646] The terminal sends the generated question text and sentiment information to the server. The input here is the sentiment state and question data from the user terminal, and the output is a format conversion of this data, which is then used for further processing on the server.

[0647] Step 3:

[0648] The server distributes the received question text and sentiment information to multiple machine learning algorithms. The input is data from the terminal, and each algorithm generates a response adapted to the sentiment. The output is the response data from each algorithm.

[0649] Step 4:

[0650] The server evaluates the responses returned from each machine learning algorithm using cross-validation. The input consists of multiple response datasets, which are compared and evaluated to select those with high reliability and sentiment adaptability. The output is the most appropriate response dataset.

[0651] Step 5:

[0652] The server adjusts the selected response to reflect the user's emotions and sends it back to the user's terminal. The input data is the selected response, and the output is a final response adapted to the emotions, which is then sent to the terminal.

[0653] Step 6:

[0654] The system facilitates interaction with the user based on the responses received by the user's terminal. The input here is the final response from the server, and the output is displayed to the user and supports subsequent interactions.

[0655] This process enables the delivery of more personalized information that takes user emotions into consideration.

[0656] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0657] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0658] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0659] [Fourth Embodiment]

[0660] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0661] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0662] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0663] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0664] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0665] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0666] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0667] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0668] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0669] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0670] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0671] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0672] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] This invention is a system that utilizes multiple artificial intelligence algorithms via an information processing device to provide highly reliable answers to user questions. The embodiments thereof are described below in natural language.

[0674] System Overview

[0675] This system provides users with answers from multiple artificial intelligence algorithms, cross-validated to help them resolve technical problems and questions. This increases the reliability of the answers and enables engineers and technical support personnel to solve problems quickly and accurately.

[0676] System operation

[0677] 1. User input of question

[0678] Users use a terminal to enter technical questions. These questions can range from troubleshooting network connectivity issues to inquiries about software errors.

[0679] 2. Sending and receiving questions

[0680] The question entered from the terminal is instantly sent to the server. The server receives the question, verifies that it is in the correct format, and then proceeds with further processing.

[0681] 3. Execution of artificial intelligence algorithms

[0682] The server activates multiple artificial intelligence algorithms and distributes the received questions to each of them. Each algorithm analyzes the question in its own way and generates an answer based on that analysis.

[0683] 4. Collection and evaluation of responses

[0684] The generated responses are sent back to the server. The server collects these responses and performs cross-validation. That is, it thoroughly evaluates the consistency and reliability of each response and selects the most valid and reliable response.

[0685] 5. Sending responses back to users

[0686] The selected response is sent back from the server to the user's terminal. This allows the user to immediately obtain the technical information or solution they were looking for.

[0687] Specific example

[0688] For example, consider a user who enters the question, "My server connection is frequently dropping." The server distributes this to multiple AI algorithms. One algorithm might recommend "checking network settings," while another might suggest "resetting the hardware." Based on these responses, the server selects "checking network settings" as the most reliable answer, considering past performance and the current situation, and sends it back to the user. Through this process, the user receives specific steps to quickly resolve the problem.

[0689] This system will be an effective tool for receiving high-quality support, especially for new technical support staff and engineers. It is expected to contribute to strengthening corporate competitiveness and improving customer satisfaction.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The user uses their device to input the technical problem or question they want to solve in natural language. Once they have finished inputting, the user sends it to the server as question data by pressing the send button on their device.

[0693] Step 2:

[0694] The terminal receives question data entered by the user and sends it to the server via the internet. The transmitted data is usually sent using protocols such as HTTP.

[0695] Step 3:

[0696] The server receives the question data sent from the terminal and validates its content through a pre-programmed filtering process to determine if it is appropriate. If the format and content of the question are appropriate, the process proceeds to the next step.

[0697] Step 4:

[0698] The server distributes the question data to multiple artificial intelligence algorithms. Each algorithm uses a different method, operates independently, and can generate answers to the questions from its own perspective.

[0699] Step 5:

[0700] Each artificial intelligence algorithm receives a question from the server and generates an answer based on its own internal logic and model. The generated answer may include the reasoning behind the answer and any points to confirm.

[0701] Step 6:

[0702] The responses generated by each artificial intelligence algorithm are sent back to the server. When the responses are sent back, the confidence level of the response and related metadata may also be provided.

[0703] Step 7:

[0704] The server collects responses from all artificial intelligence algorithms. The server compares these responses and uses a cross-validation algorithm to evaluate their consistency and reliability. This process also utilizes past response history and supplementary information.

[0705] Step 8:

[0706] The server selects the most reliable and useful answer based on the cross-validation results. The degree of agreement and confidence score of the answers are important evaluation criteria in this selection process.

[0707] Step 9:

[0708] The server selects the most reliable answers and sends them back to the terminal. The returned answers are then formatted in a way that is easy for the user to understand.

[0709] Step 10:

[0710] The terminal receives the response sent back from the server and displays its contents on the user screen. This allows the user to obtain the technical information and solutions they were looking for.

[0711] (Example 1)

[0712] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0713] In the field of information technology, providing reliable, real-time solutions to user problems and technical questions is crucial. However, conventional systems often rely on a single algorithm, making it difficult to provide optimal solutions to complex questions.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0715] In this invention, the server includes means for the information processing device to activate multiple machine learning algorithms, means for the information processing device to transmit the received problem content to the multiple machine learning algorithms, and means for performing data verification processing to compare the returned solutions and evaluate their reliability. This makes it possible to analyze the problem content from multiple angles using multiple algorithms and to quickly provide the most reliable solution.

[0716] An "information processing device" is a computing device that receives input from a user and executes multiple machine learning algorithms.

[0717] A "machine learning algorithm" is a program that analyzes the content of a problem received from a user and generates a solution based on that analysis.

[0718] A "user-operated terminal" is an electronic device used by the user to input the details of a problem and receive the selected solution.

[0719] "Problem description" refers to the technical issues or questions that users are seeking to resolve.

[0720] "Reliability" is an indicator used to evaluate the accuracy and applicability of the generated solutions.

[0721] "Data validation processing" is the process of comparing the outputs from multiple machine learning algorithms, evaluating their reliability, and selecting the optimal solution.

[0722] "Solution" refers to specific countermeasures or advice regarding the user's problem.

[0723] This invention is a system that uses an information processing device to activate multiple machine learning algorithms and provide the optimal solution to a problem submitted by a user via a terminal.

[0724] The server distributes the received problem content to multiple machine learning algorithms. The server uses a cloud platform to run these algorithms by executing machine learning libraries such as TensorFlow and PyTorch. Each algorithm analyzes the received problem content and generates a solution based on that analysis. The generated solutions are returned to the server for confidence evaluation. This confidence evaluation involves data validation using tools like Scikit-learn, and the best solution is selected.

[0725] As a concrete example, consider a case where a user inputs a problem such as "slow internet connection." The server sends this information to multiple machine learning algorithms. One algorithm might generate a solution such as "try restarting the router," while another might suggest "checking the device settings." The server compares these returned solutions, uses data validation to select the best one, and sends it back to the user.

[0726] This process allows us to provide users with quick and reliable solutions to the technical challenges they face. For example, a user could input a prompt to the generating AI model such as, "I would like to contact technical support to find out how to improve the issue of 'web pages loading slowly'."

[0727] This system aims to utilize generative AI models and prompt statements to appropriately select and provide users with answers generated by multiple algorithms.

[0728] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0729] Step 1:

[0730] The user uses a terminal to input details of a technical problem. This input is sent to the server as text data. When the user inputs a problem such as "the printer is not working," the terminal converts it into digital data format and sends it to the server.

[0731] Step 2:

[0732] The server receives the assignment content submitted by the user and verifies whether it is in the correct format. Specifically, the server checks the consistency of the text format and prompts the user to re-enter the data if there are any deficiencies. In this step, data processing such as format verification and normalization of line breaks is performed based on the input data.

[0733] Step 3:

[0734] The server distributes the confirmed problem details to multiple generative AI models. Each model runs using machine learning libraries such as TensorFlow or PyTorch. Specifically, the server sends the problem details as prompts to each model and generates solutions based on them. During this process, new data calculations are performed within the AI ​​models, resulting in the generated solutions.

[0735] Step 4:

[0736] The server collects the solutions returned from the generated AI model. The server then subjects these solutions to a data validation process to evaluate their confidence. This process involves cross-validation using tools like Scikit-learn, analyzing the consistency and accuracy of each output. Based on the evaluation results, the most appropriate solution is selected.

[0737] Step 5:

[0738] The server sends the selected optimal solution back to the user's device. The user can then review the solution on their device and use it to resolve the problem. This step includes configuring the user's device to receive a notification or display the solution on the screen. The generated solution is output as text data and provided to the user.

[0739] (Application Example 1)

[0740] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0741] In consumer technology devices, there is a need to resolve technical problems and questions users face quickly and with reliable information. However, currently, users often require technical knowledge, which can hinder the effective use of the device. Therefore, there is a need to develop a system that supports users in obtaining technical information without requiring expert assistance.

[0742] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0743] In this invention, the server includes means for activating multiple machine learning algorithms and analyzing queries received from user devices, means for evaluating the responses generated by each algorithm based on cross-validation, and means for selecting a highly reliable response from the evaluation results and returning it to the user device. This makes it possible for users to obtain quick and effective solutions to complex technical problems in devices used in their homes.

[0744] An "information processing system" is a device that receives inquiries from users and has the function of generating and evaluating responses using multiple machine learning algorithms.

[0745] A "machine learning algorithm" is a computational method for learning patterns from given data and generating appropriate responses based on new data.

[0746] "User equipment" refers to digital devices used within the home that work in conjunction with an information processing system to send and receive user inquiries.

[0747] "Reliability" is an index that quantitatively evaluates the accuracy and applicability of the generated response.

[0748] Cross-validation is a technique for comparing responses generated by multiple algorithms to verify their consistency and reliability.

[0749] The "technical advisor function" is an auxiliary function that enables the user's device to automatically provide solutions to technical problems.

[0750] In the system implementing this invention, a server is used as the central point for information processing. The server first receives inquiries from user devices via the network and analyzes their content. The analyzed content is supplied to several pre-configured machine learning algorithms, and each algorithm generates a response based on its respective methodology.

[0751] The server receives these responses and uses cross-validation techniques to evaluate the confidence level of each response. The confidence scores provided by each algorithm are used for the confidence evaluation, and the most effective response is selected based on these scores. The selected response is then sent back to the user's device via the network. In this process, the server uses programming languages ​​such as Python and related machine learning libraries (e.g., TensorFlow, PyTorch).

[0752] For example, if a user enters a question such as "My robot vacuum cleaner cannot connect to the Wi-Fi network," the server will provide recommendations such as reviewing network settings or optimizing the connection distance to the router. In this case, the server will use a prompt example like the following for the machine learning model: "When a user asks 'My robot cannot connect to Wi-Fi,' please suggest an appropriate solution."

[0753] The introduction of this system will significantly improve convenience, as users will be able to obtain quick and accurate solutions to technical problems within their homes.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] The user uses a terminal to input inquiries about technical problems. These inquiries cover a wide range of topics, such as "My robotic vacuum cleaner cannot connect to Wi-Fi." The terminal converts these inquiries into data format and sends them to the server via the network. The input is the user's inquiry text, and the output is the data format sent to the server.

[0757] Step 2:

[0758] The server receives queries sent from terminals and parses their content. This parsing uses natural language processing techniques to understand the queries and interpret their meaning. The input is query data received from terminals, and the output is the structure data of the parsed queries.

[0759] Step 3:

[0760] The server distributes the analyzed query to multiple generative AI models, each of which generates a response based on its own algorithm. Prompts are used to instruct the models during this process. The input is the analyzed query data, and the output is the response candidates generated by each model.

[0761] Step 4:

[0762] The server collects responses returned from each generating AI model and performs cross-validation. It compares confidence scores to determine the most reliable response. The input consists of multiple response candidates and their confidence scores, and the output is the selected optimal response.

[0763] Step 5:

[0764] The server resends the selected, reliable response to the terminal via the network. The user can then view the specific problem-solving solution through the terminal. The input is the selected response, and the output is the text information of the solution displayed on the user's terminal.

[0765] This process allows us to respond quickly and accurately to users' technical problems.

[0766] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0767] The present invention is a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device. It provides highly reliable answers to user questions while simultaneously considering the user's emotional state to deliver more personalized information. The embodiments thereof are described in detail below.

[0768] System Overview

[0769] This system works by having the user ask technical questions in natural language through a terminal, which are then received by an information processing unit. After receiving the questions, the information processing unit distributes them to multiple artificial intelligence algorithms, each of which generates an answer. In addition, an emotion engine recognizes the user's emotions in real time, and performs cross-validation processing while considering the user's state to select the most reliable answer.

[0770] System operation

[0771] 1. User question input and sentiment detection

[0772] The user enters a technical question into the device. During this process, the device uses sensors such as a camera and microphone to acquire emotional data from the user's voice tone and facial expressions.

[0773] 2. Sending questions and sentiment data

[0774] The terminal sends the entered question and user sentiment data to the server. The server receives this data and prepares for the next step.

[0775] 3. Emotional analysis using an emotional engine

[0776] The emotion engine within the server analyzes the received emotion data to determine the user's emotional state. This determination becomes an important input for subsequent processing.

[0777] 4. Application of artificial intelligence algorithms

[0778] The server distributes the question to multiple artificial intelligence algorithms, each generating an answer. Here, the user's emotional state influences the answer generation process of each algorithm, potentially adjusting the tone and content of the response.

[0779] 5. Cross-validation and response selection

[0780] The server collects responses from each algorithm and performs cross-validation. During this process, the most appropriate and reliable response is selected, taking into account the emotional state output by the emotion engine.

[0781] 6. Providing responses and feedback

[0782] The selected answers are returned to the terminal and displayed to the user. The user can also input feedback on those answers from the terminal and send it to the server. This feedback contributes to further improving the system's accuracy.

[0783] Specific example

[0784] As a concrete example, consider a scenario where a user, expressing anger, inputs, "A system error has stopped my work. What should I do?" The terminal sends this expression as emotional data to the server. The server's emotion engine identifies this data as "anger," and based on this information, an artificial intelligence algorithm works to generate a response that includes more polite and prompt solutions. Finally, the server returns this response to the user, thereby reducing the user's anxiety and stress.

[0785] Thus, the invention is a system that enables more effective and humane support by taking user emotions into consideration.

[0786] The following describes the processing flow.

[0787] Step 1:

[0788] The user uses the device to input the technical problem they want to solve in natural language. During input, the device simultaneously uses the camera and microphone to capture emotional data from the user's facial expressions and voice.

[0789] Step 2:

[0790] The terminal sends the entered question and acquired sentiment data to the server. Communication takes place over the internet, and the data format follows a predefined protocol.

[0791] Step 3:

[0792] The server receives questions and emotion data sent from the terminal. An emotion engine within the server analyzes the emotion data and determines the user's current emotional state. At this point, it generates emotion labels such as "joy," "anxiety," and "anger."

[0793] Step 4:

[0794] The server prepares the question data and distributes it to multiple artificial intelligence algorithms. Each algorithm receives this question data and performs analysis using its own model.

[0795] Step 5:

[0796] Each artificial intelligence algorithm generates an answer to a question. During this process, it uses emotional state information provided by the server to adjust the tone and content of the answer. For example, if the user's emotion is "anger," the answer will use more careful and considerate language.

[0797] Step 6:

[0798] Each artificial intelligence algorithm sends its generated response back to the server. The server receives all of these responses and prepares them for the next processing step.

[0799] Step 7:

[0800] The server performs cross-validation on the received responses. Here, the server evaluates the results considering the consistency, reliability, and emotional state of the responses. It selects the response that is most reliable and best reflects the user's emotions.

[0801] Step 8:

[0802] The server sends the selected, optimal answer back to the terminal. The answer may include emotionally sensitive explanations and is provided in a format that is easy for the user to understand.

[0803] Step 9:

[0804] The device receives the response sent back from the server and displays it on the user screen. The user can then review the response and take the next steps to resolve the problem.

[0805] Step 10:

[0806] The user sends feedback on the answers they provide from their device to the server. The server receives this feedback and can use the data to improve system performance.

[0807] (Example 2)

[0808] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0809] In many information processing systems, the quality of automated responses to user inquiries is crucial. Furthermore, answers that do not consider the user's emotional state do not necessarily lead to user satisfaction. Therefore, there is a need to provide reliable and personalized answers that reflect the user's emotional state.

[0810] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0811] In this invention, the server includes means for an information processing device to activate multiple computational models, means for receiving questions input from a user terminal, and means for distributing the received questions to the multiple computational models. This makes it possible to provide appropriate and reliable automated responses that take into account the user's emotional state.

[0812] An "information processing device" is a hardware or software system equipped with electronic functions for receiving, processing, and analyzing data and providing responses to users.

[0813] A "computational model" is a mathematical model designed by combining algorithmic methods and data to generate automated responses to specific tasks or questions.

[0814] A "user terminal" is a computing device used by a user to input and receive information.

[0815] "Emotional data" refers to data obtained from the user's voice tone, facial expressions, etc., and is used to determine the user's emotional state.

[0816] A "confidence score" is an evaluation value returned by each computational model to assess how accurate and suitable the generated response is for its intended purpose.

[0817] The "evaluation process" is the process of comparing responses returned from multiple models, evaluating their reliability and suitability, and selecting the most appropriate response.

[0818] This invention provides a system that incorporates an emotion engine with emotion recognition capabilities into an information processing device, aiming to provide highly reliable answers to user questions. Furthermore, this system achieves more personalized information delivery by taking into account the user's emotional state. Specific embodiments are described below.

[0819] The user inputs questions using natural language through their device. The device is equipped with sensors such as a camera and microphone, which simultaneously capture emotional data such as the user's voice tone and facial expressions. This emotional data is transmitted to the server in real time.

[0820] Within the server, the emotion engine analyzes the received emotion data to determine the user's emotional state. This emotional state plays a crucial role in generating responses in the next stage. Based on this emotional state, the server uses multiple generative AI models to generate answers to the user's questions. Each model reflects the emotion data and adjusts the response to have the optimal tone and content.

[0821] After considering the accuracy of the responses and their relevance to the user's emotions, the server selects the most appropriate response. This selected response is then sent back to the terminal and displayed to the user.

[0822] For example, if a user enters "A system error has stopped operations. What should I do?" while displaying an angry expression, the terminal sends that expression to the server as emotion data. On the server, the emotion engine determines the emotion data to be "anger" and adjusts the generation AI model to create a response that includes more polite and prompt solutions. An example of a prompt message that can be used is: "If the user is in an angry emotional state, generate a prompt and polite response. Question: 'A system error has stopped operations. What should I do?'"

[0823] This system allows users to receive appropriate, humane support that reflects their emotions.

[0824] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0825] Step 1:

[0826] The user inputs a technical question in natural language into the user's device. The device records the question as text data. Simultaneously, the device's camera and microphone are used to acquire emotional data such as voice tone and facial expressions, which are then recorded as sensor data. The input includes both the user's question and emotional data.

[0827] Step 2:

[0828] The terminal sends the acquired question and sentiment data to the server. The protocol used is either HTTP or WebSocket, encrypted with SSL / TLS to ensure secure communication. The entered text data and sentiment data reach the server.

[0829] Step 3:

[0830] The server inputs the received emotional data into the emotion engine. The emotion engine uses machine learning algorithms to analyze the emotional data and determine the user's emotional state. This determination becomes important input for subsequent processing steps, outputting the user's emotional state as a numerical value or category.

[0831] Step 4:

[0832] The server distributes the user's question to multiple generative AI models. Each model generates the optimal answer from its own perspective, taking into account the user's emotional state. The user's emotional data is used as input, and the generated answers are output as text.

[0833] Step 5:

[0834] The server collects the responses returned from each generative AI model and performs cross-validation. This process comprehensively evaluates the confidence scores and emotional state judgments provided by the generative AI models. Based on the resulting evaluation scores, the server selects the most reliable response. The selected response is then output as the result of the selection.

[0835] Step 6:

[0836] The server sends the selected answers to the terminal. The user can receive and view the selected answers via the terminal. The output answers serve as the basis for user confirmation and feedback input.

[0837] Step 7:

[0838] Users input feedback on the provided answers via a terminal. The terminal sends this feedback back to the server. This feedback is stored in the server's database to improve system performance. The feedback data is input and output as basic system data.

[0839] (Application Example 2)

[0840] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0841] In recent years, with the advancement of information technology, there has been a growing demand for personalized information that takes into account the emotional state of individual users. However, conventional information processing systems are unable to provide responses that adequately consider the user's emotions. As a result, there is a lack of support that takes users' emotions into account, and in particular, in nursing care settings, more appropriate responses are needed to stabilize the emotions of residents.

[0842] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0843] In this invention, the server includes means for an information processing device to activate multiple machine learning algorithms, means for receiving questions and sentiment information input from a user terminal, and means for distributing them to the machine learning algorithms. This makes it possible to propose highly reliable answers that take the user's emotions into consideration, and appropriate dialogue methods that correspond to the user's emotional state.

[0844] An "information processing device" is a computing device that analyzes input data from a user and generates appropriate output.

[0845] A "machine learning algorithm" is a set of computational methods that use data to learn patterns and make predictions or decisions.

[0846] A "user terminal" is an electronic device used by users to input data and receive results.

[0847] "Emotional information" refers to data that indicates the user's emotional state, and is obtained from sources such as voice tone and facial expressions.

[0848] A "confidence score" is a numerical indicator used to evaluate the reliability of a generated response.

[0849] "Blocking verification processing" is a technique for comparing results from different algorithms to confirm the integrity and reliability of data.

[0850] "Emotional state" refers to a user's instantaneous emotional response and is a factor that influences the system's response generation.

[0851] "Evaluation information" refers to feedback provided by users, which is used to improve the quality of the system's response.

[0852] In this embodiment of the system, a user terminal, such as smart glasses, is first used to collect user questions and emotional information. The terminal is equipped with a camera and microphone, and these sensors capture the user's facial expressions and voice tone in real time. The acquired data is analyzed as user emotional information.

[0853] The server distributes the user's question, along with this sentiment information, to multiple machine learning algorithms. Each algorithm generates an answer based on the received question and sentiment information, returning a response based on reliability and how well it adapts to the user's sentiment. The server then evaluates the answers from each algorithm through cross-validation and selects the most reliable answer.

[0854] The selected responses are adjusted to take the user's emotional state into consideration and delivered to the user's device. At the same time, the system also suggests appropriate response methods to the user, enabling better interaction. For example, staff at a nursing home could use smart glasses to assist with daily resident care. If a resident appears anxious, the system might ask, "What are you worried about today?" and suggest appropriate ways to comfort or reassure them.

[0855] Through a generative AI model, the system generates prompts and engages in adaptive dialogue that takes emotions into account. A concrete example of this application is a prompt such as, "Analyze the emotions of elderly people in real time and generate suggestions for care support that will alleviate their anxiety."

[0856] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0857] Step 1:

[0858] The user's device uses its camera and microphone to capture the user's facial expressions and voice tone in real time. This data is preprocessed within the device to generate digitized emotional data for analysis as emotional information. The output at this stage includes the analyzed emotional state and the question text.

[0859] Step 2:

[0860] The terminal sends the generated question text and sentiment information to the server. The input here is the sentiment state and question data from the user terminal, and the output is a format conversion of this data, which is then used for further processing on the server.

[0861] Step 3:

[0862] The server distributes the received question text and sentiment information to multiple machine learning algorithms. The input is data from the terminal, and each algorithm generates a response adapted to the sentiment. The output is the response data from each algorithm.

[0863] Step 4:

[0864] The server evaluates the responses returned from each machine learning algorithm using cross-validation. The input consists of multiple response datasets, which are compared and evaluated to select those with high reliability and sentiment adaptability. The output is the most appropriate response dataset.

[0865] Step 5:

[0866] The server adjusts the selected response to reflect the user's emotions and sends it back to the user's terminal. The input data is the selected response, and the output is a final response adapted to the emotions, which is then sent to the terminal.

[0867] Step 6:

[0868] The system facilitates interaction with the user based on the responses received by the user's terminal. The input here is the final response from the server, and the output is displayed to the user and supports subsequent interactions.

[0869] This process enables the delivery of more personalized information that takes user emotions into consideration.

[0870] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0871] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0872] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0873] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0874] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0875] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0876] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0877] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0878] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0879] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0880] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0881] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0882] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0883] 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.

[0884] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0885] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0886] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0887] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0888] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0889] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0890] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0891] The following is further disclosed regarding the embodiments described above.

[0892] (Claim 1)

[0893] A means by which an information processing device activates multiple artificial intelligence algorithms,

[0894] A means by which an information processing device receives a question entered from a user terminal,

[0895] The information processing device performs a means of distributing the received question to multiple artificial intelligence algorithms,

[0896] Each artificial intelligence algorithm generates an answer to a question and sends it back to the information processing device,

[0897] A means for performing cross-validation processing, in which an information processing device compares the returned responses and evaluates their reliability,

[0898] A method for selecting highly reliable answers based on cross-validation processing,

[0899] A system that includes a means of returning the selected answer to the user's terminal.

[0900] (Claim 2)

[0901] The system according to claim 1, wherein the information processing device evaluates the response using the confidence score returned from each artificial intelligence algorithm.

[0902] (Claim 3)

[0903] The system according to claim 1, further comprising means for transmitting feedback to an information processing device regarding the answer selected by the user terminal.

[0904] "Example 1"

[0905] (Claim 1)

[0906] A means by which an information processing device can launch multiple machine learning algorithms,

[0907] A means by which an information processing device receives the task content entered from a terminal operated by the user,

[0908] The information processing device performs a means of transmitting the received task content to multiple machine learning algorithms.

[0909] A means by which each machine learning algorithm generates a solution to the problem and sends it back to the information processing device,

[0910] A means for performing data validation processing to compare the returned solutions and evaluate their reliability,

[0911] A means of selecting a highly reliable solution based on data validation processing,

[0912] A system that includes a means of returning the selected solution to the terminal operated by the user.

[0913] (Claim 2)

[0914] The system according to claim 1, wherein the information processing device evaluates a solution using the confidence index returned from each machine learning algorithm.

[0915] (Claim 3)

[0916] The system according to claim 1, further comprising means for transmitting an evaluation of a solution selected by a terminal operated by a user to an information processing device.

[0917] "Application Example 1"

[0918] (Claim 1)

[0919] A means for an information processing system to launch multiple machine learning algorithms,

[0920] A means by which the information processing system receives inquiries entered from user devices,

[0921] The information processing system executes a means to distribute received inquiries to multiple machine learning algorithms,

[0922] Each machine learning algorithm generates a response to a query and sends it back to the information processing system,

[0923] A means for performing cross-validation processing to compare the responses returned by the information processing system and evaluate their reliability,

[0924] A means for selecting a highly reliable response based on cross-validation processing,

[0925] A means of returning the selected response to the user's device,

[0926] A means of providing technical advisory functions to devices used by users in their homes,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, wherein the information processing system evaluates the response using the confidence scores returned from each machine learning algorithm.

[0930] (Claim 3)

[0931] The system according to claim 1, further comprising means for transmitting feedback on the response selected by the user device to an information processing system.

[0932] "Example 2 of combining an emotion engine"

[0933] (Claim 1)

[0934] A means by which an information processing device can launch multiple computational models,

[0935] A means by which an information processing device receives questions entered from a user terminal,

[0936] The information processing device performs a means of distributing the received question to multiple computational models,

[0937] Each computational model generates an answer to a question and sends it back to the information processing device,

[0938] The information processing device includes means for analyzing user emotion data, and means for adjusting the generation process based on the analysis results,

[0939] A means for performing an evaluation process in which an information processing device compares the returned responses and evaluates their reliability,

[0940] A means of selecting highly reliable answers based on the evaluation process,

[0941] A system that includes a means of returning the selected answer to the user's terminal.

[0942] (Claim 2)

[0943] The system according to claim 1, wherein the information processing device evaluates the response using the confidence score returned from each computational model and the user's emotional state data.

[0944] (Claim 3)

[0945] The system according to claim 1, further comprising means for transmitting feedback to an information processing device regarding the answer selected by the user terminal.

[0946] "Application example 2 when combining with an emotional engine"

[0947] (Claim 1)

[0948] A means by which an information processing device can launch multiple machine learning algorithms,

[0949] A means by which an information processing device receives questions and sentiment information entered from a user terminal,

[0950] The information processing device performs a means of distributing received question and sentiment information to multiple machine learning algorithms,

[0951] Each machine learning algorithm generates an answer to a question and sentiment information and sends it back to the information processing device.

[0952] A means for performing a blocking verification process that compares the returned responses of an information processing device and evaluates their reliability,

[0953] A means for selecting a highly reliable and emotionally appropriate response based on a blocking and verification process,

[0954] A means of returning the selected answer to the user's terminal,

[0955] A system that provides means to suggest response methods that take into account the user's emotional state.

[0956] (Claim 2)

[0957] The system according to claim 1, wherein the information processing device evaluates the response using the confidence score and emotional state returned from each machine learning algorithm.

[0958] (Claim 3)

[0959] The system according to claim 1, further comprising means for transmitting evaluation information and emotional feedback for the response selected by the user terminal to an information processing device. [Explanation of symbols]

[0960] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for an information processing system to launch multiple machine learning algorithms, A means by which the information processing system receives inquiries entered from user devices, The information processing system executes a means to distribute received inquiries to multiple machine learning algorithms, Each machine learning algorithm generates a response to a query and sends it back to the information processing system, A means for performing cross-validation processing to compare the responses returned by the information processing system and evaluate their reliability, A means for selecting a highly reliable response based on cross-validation processing, A means of returning the selected response to the user's device, A means of providing technical advisory functions to devices used by users in their homes, A system that includes this.

2. The system according to claim 1, wherein the information processing system evaluates the response using the confidence score returned from each machine learning algorithm.

3. The system according to claim 1, further comprising means for transmitting feedback on the response selected by the user device to an information processing system.

Images