System

Abstract

An object of the system according to the embodiment is to present the most correct answer by avoiding an incorrect answer due to the generated AI.SOLUTION: A system includes a question input part, an answer collection part, a matching rate calculation part, and an answer presentation part. The question input unit inputs a question from a user. The answer collecting part transmits the question inputted by the question inputting part to the plurality of generation AI and collects answers. The matching rate calculation unit calculates a matching rate of the answers collected by the answer collection unit. The answer presentation unit presents the most correct answer based on the matching rate calculated by the matching rate calculation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to avoid incorrect answers from the generating AI, and users had to take the survey again to confirm the accuracy of the answer.

[0005] The system according to the embodiment aims to avoid incorrect answers given by the generation AI and to present the most correct answer. [Means for solving the problem]

[0006] The system according to the embodiment includes a question input unit, an answer collection unit, a match rate calculation unit, and an answer presentation unit. The question input unit inputs a question from a user. The answer collection unit transmits the question input by the question input unit to multiple generation AIs and collects answers. The match rate calculation unit calculates the match rate of the answers collected by the answer collection unit. The answer presentation unit presents the most correct answer based on the match rate calculated by the match rate calculation unit. [Effects of the Invention]

[0007] The system according to the embodiment can avoid incorrect answers given by the generation AI and present the most correct answer. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The generation AI portal according to an embodiment of the present invention is a system that allows users to increase their confidence in the answers of the generation AI and reduce the need for users to recheck or reexamine the answers themselves. This allows the generation AI portal to increase users' confidence in the answers of the generation AI and reduce the need for users to recheck or reexamine the answers themselves.

[0029] A generation AI portal according to an embodiment includes a question input unit, an answer collection unit, a match rate calculation unit, and an answer presentation unit. The question input unit inputs a question from a user. For example, the user inputs the question in text format. The question input unit also supports voice input, allowing the user to input the question using a microphone. The question input unit also supports handwritten input, allowing the user to input the question by hand using a tablet. The answer collection unit sends the question input by the question input unit to multiple generation AIs and collects the answers. For example, if the question is "What is the diameter of the Earth?", the answer collection unit sends this question to multiple generation AIs. The generation AIs may be text generation AIs (e.g., LLMs) or multimodal generation AIs, and each generation AI generates an answer. The match rate calculation unit calculates the match rate of the answers collected by the answer collection unit. For example, if generation AI A answers "The diameter of the Earth is approximately 12,742 km," and generation AI B also answers "The diameter of the Earth is approximately 12,742 km," the match rate will be high. On the other hand, if the generated AI C answers "The diameter of the Earth is approximately 10,000 km," the match rate will be low. The match rate calculation unit calculates the match rate of the answers using, for example, cosine similarity. Alternatively, the match rate can be calculated using the Jaccard coefficient. Furthermore, the match rate can be calculated using TF-IDF. The answer presentation unit presents the answer that is most likely correct based on the match rate calculated by the match rate calculation unit. For example, if the answer with the highest match rate among multiple generated AIs is "The diameter of the Earth is approximately 12,742 km," this answer is presented to the user. This allows the generated AI portal according to the embodiment to increase the user's trust in the generated AI's answers and reduce the need to recheck or research the answers themselves. For example, by comparing the answers of multiple generated AIs to academic questions or everyday questions, more accurate information can be obtained. Furthermore, users can be wary of answers with low match rates, thereby avoiding actions based on incorrect information.

[0030] The question input unit can automatically generate follow-up questions and ask the user for confirmation in order to understand the user's intention more accurately. For example, when a user inputs a question, the generation AI automatically detects any ambiguity in the question and generates a follow-up question to ask the user for confirmation. For example, in response to the question "What is the diameter of the Earth?", the AI ​​can ask a follow-up question such as "Is it the equatorial diameter or the polar diameter of the Earth?" This makes it possible to understand the user's intention more accurately and provide an appropriate answer.

[0031] The question input unit can refer to past question history and prioritize displaying answers to similar questions if they exist. For example, when a user inputs a question, the question input unit automatically searches past question history and prioritizes displaying answers to similar questions if they exist. For example, if a similar question has been asked in the past in response to the question "What is the diameter of the Earth?", that answer will be displayed. This makes it possible to utilize past question history and quickly provide appropriate answers.

[0032] The question input unit can support different input methods, such as voice input or handwriting input. For example, the question input unit may add a function to support voice input when a user inputs a question, allowing the user to input the question using a microphone. For example, the question "What is the diameter of the Earth?" may be input by voice. The question input unit may also support handwriting input, allowing the user to input the question by handwriting using a tablet. This improves user convenience.

[0033] The question input unit can attach related images and videos. For example, the question input unit adds a function that allows users to attach related images and videos when entering a question, and the generation AI understands the question based on that visual information. For example, an image can be attached to the question, "How tall is the building in this image?" This allows the generation AI to understand the question from a more multifaceted perspective.

[0034] The match rate calculation unit can assign a reliability score to the answer of each generation AI and adjust the match rate based on that score. For example, the match rate calculation unit can develop an algorithm that assigns a reliability score to the answer of each generation AI and adjust the match rate based on that score. For example, answers from highly reliable generation AIs can be assigned a high score, increasing the match rate. This allows highly reliable answers to be displayed preferentially.

[0035] The answer collection unit can collect answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, the answer collection unit builds a system that collects answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, without waiting for the answer of a generation AI that is slow to respond, it will prioritize collecting answers from other generation AIs. This allows answers to be collected efficiently.

[0036] The answer presentation unit can provide detailed explanations of the basis and reasons for the answer when presenting the most likely correct answer. For example, when presenting the most likely correct answer, the answer presentation unit adds a function to provide detailed explanations of the basis and reasons for the answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," the unit can provide an explanation such as "This information is based on data from NASA." This makes it easier for users to judge the reliability of the answer.

[0037] The answer presentation unit can display related additional information and references when presenting the most likely correct answer. For example, the answer presentation unit adds a function to display related additional information and references when presenting the most likely correct answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," it displays information such as "Related academic papers are here." This makes it easier for users to understand the background information of the answer.

[0038] The answer presentation unit can support display in different formats when presenting the most likely correct answer. For example, the answer presentation unit builds a system that supports display in different formats, such as text, audio, and video, when presenting the most likely correct answer. For example, the answer "The diameter of the Earth is approximately 12,742 km" is not only displayed in text, but also in audio and video. This allows the user to receive the answer in their preferred format.

[0039] The answer presentation unit adds a function that allows users to provide feedback on the answer, and this feedback can be used to help the generative AI learn. For example, when presenting the answer that is likely to be correct, the answer presentation unit adds a function that allows users to provide feedback on that answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," the unit asks for feedback such as "Was this answer helpful?" User feedback is used to help the generative AI learn and contributes to improving accuracy. This makes it possible to improve the accuracy of the generative AI based on user feedback.

[0040] The match rate calculation unit can detect abnormal values ​​by comparing the match rate with past data when displaying the match rate and display a warning to the user. The match rate calculation unit, for example, builds a system that detects abnormal values ​​by comparing the match rate with past data when displaying the match rate and displays a warning to the user. For example, a warning is displayed when the match rate is significantly lower than the average value in the past. This makes it possible to quickly detect abnormal answers and display a warning to the user.

[0041] The matching rate calculation unit allows the generation AI to automatically reevaluate answers with a low matching rate and recalculate the matching rate. The matching rate calculation unit builds a system in which the generation AI automatically reevaluates answers with a low matching rate and recalculates the matching rate. For example, reevaluation is performed when the matching rate is 50% or less. This allows answers with a low matching rate to be reevaluated and improve reliability.

[0042] The match rate calculation unit can use different visual display methods (graphs, charts) when displaying the match rate to allow the user to intuitively understand. The match rate calculation unit, for example, uses different visual display methods (graphs, charts) when displaying the match rate to build a system that allows the user to intuitively understand. For example, the match rate is displayed as a bar graph or a pie chart. This allows the user to intuitively understand the match rate.

[0043] The matching rate calculation unit can provide complementary information for answers with a low matching rate by referencing data from other highly reliable information sources. The matching rate calculation unit, for example, builds a system that provides complementary information for answers with a low matching rate by referencing data from other highly reliable information sources. For example, for answers with a low matching rate, related academic papers and databases are referenced. This makes it possible to provide reliable information and reduce user anxiety.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] To more accurately understand the user's intent, the question input unit can analyze the context of the question using natural language processing technology and automatically extract related keywords. For example, in response to the question, "What is the diameter of the Earth?", keywords such as "Earth" and "diameter" are extracted and a question is sent to the generation AI based on these. The question input unit can also analyze the context of the question entered by the user and automatically provide related additional information. For example, in response to the question, "What is the diameter of the Earth?", additional information such as, "Would you also like to know the difference between the Earth's equatorial diameter and polar diameter?" is provided. This allows for a more accurate understanding of the user's intent and the provision of an appropriate answer.

[0046] The answer collection unit can collect user feedback on the answers of the generation AI and improve the accuracy of the answers of the generation AI based on that feedback. For example, a function that allows users to provide feedback such as "Was this answer helpful?" can be added to collect user feedback. The learning data of the generation AI can also be updated based on the collected feedback to improve the accuracy of the answers. This makes it possible to utilize user feedback to improve the accuracy of the generation AI.

[0047] The match rate calculation unit assigns a reliability score to each generated AI's answer and can adjust the match rate based on that score. For example, a high score can be assigned to a highly reliable generated AI's answer, increasing the match rate. A low score can be assigned to a less reliable generated AI's answer, decreasing the match rate. This allows highly reliable answers to be displayed preferentially.

[0048] The answer presentation unit can support display in different formats when presenting the most likely correct answer. For example, a system can be constructed that supports display in different formats, such as text, audio, and video, when presenting the most likely correct answer. For example, the answer "The diameter of the Earth is approximately 12,742 km" can be displayed not only in text but also in audio and video. This allows the user to receive the answer in their preferred format.

[0049] The answer collection unit can collect answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, a system can be constructed that collects answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, answers from other generation AIs can be collected preferentially, without waiting for the answer from a generation AI that is slow to respond. This allows answers to be collected efficiently.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The question input unit inputs a question from the user. For example, the user inputs a question in text format. The question input unit may also support voice input, allowing the user to input a question using a microphone. The question input unit may also support handwriting input, allowing the user to input a question by handwriting using a tablet. Step 2: The answer collection unit sends the question input by the question input unit to multiple generation AIs and collects answers. For example, if the question is "What is the diameter of the Earth?", the answer collection unit sends this question to multiple generation AIs. The generation AIs may be text generation AIs (e.g., LLMs) or multimodal generation AIs, and each generation AI generates an answer. Step 3: The matching rate calculation unit calculates the matching rate of the answers collected by the answer collection unit. For example, if generation AI A answers "The diameter of the Earth is approximately 12,742 km," and generation AI B also answers "The diameter of the Earth is approximately 12,742 km," the matching rate will be high. On the other hand, if generation AI C answers "The diameter of the Earth is approximately 10,000 km," the matching rate will be low. The matching rate calculation unit calculates the matching rate of the answers using, for example, cosine similarity. The matching rate can also be calculated using the Jaccard coefficient. Furthermore, the matching rate can also be calculated using TF-IDF. Step 4: The answer presentation unit presents the answer that is most likely to be correct based on the match rate calculated by the match rate calculation unit. For example, if the answer with the highest match rate among the answers of multiple generated AIs is "The diameter of the Earth is approximately 12,742 km," this answer is presented to the user. This allows the generated AI portal according to the embodiment to increase the user's confidence in the answers of the generated AI and reduce the need for users to recheck or research the answers themselves.

[0052] (Example 2) The generation AI portal according to an embodiment of the present invention is a system that allows users to increase their confidence in the answers of the generation AI and reduce the need for users to recheck or reexamine the answers themselves. This allows the generation AI portal to increase users' confidence in the answers of the generation AI and reduce the need for users to recheck or reexamine the answers themselves.

[0053] A generation AI portal according to an embodiment includes a question input unit, an answer collection unit, a match rate calculation unit, and an answer presentation unit. The question input unit inputs a question from a user. For example, the user inputs the question in text format. The question input unit also supports voice input, allowing the user to input the question using a microphone. The question input unit also supports handwritten input, allowing the user to input the question by hand using a tablet. The answer collection unit sends the question input by the question input unit to multiple generation AIs and collects the answers. For example, if the question is "What is the diameter of the Earth?", the answer collection unit sends this question to multiple generation AIs. The generation AIs may be text generation AIs (e.g., LLMs) or multimodal generation AIs, and each generation AI generates an answer. The match rate calculation unit calculates the match rate of the answers collected by the answer collection unit. For example, if generation AI A answers "The diameter of the Earth is approximately 12,742 km," and generation AI B also answers "The diameter of the Earth is approximately 12,742 km," the match rate will be high. On the other hand, if the generated AI C answers "The diameter of the Earth is approximately 10,000 km," the match rate will be low. The match rate calculation unit calculates the match rate of the answers using, for example, cosine similarity. Alternatively, the match rate can be calculated using the Jaccard coefficient. Furthermore, the match rate can be calculated using TF-IDF. The answer presentation unit presents the answer that is most likely correct based on the match rate calculated by the match rate calculation unit. For example, if the answer with the highest match rate among multiple generated AIs is "The diameter of the Earth is approximately 12,742 km," this answer is presented to the user. This allows the generated AI portal according to the embodiment to increase the user's trust in the generated AI's answers and reduce the need to recheck or research the answers themselves. For example, by comparing the answers of multiple generated AIs to academic questions or everyday questions, more accurate information can be obtained. Furthermore, users can be wary of answers with low match rates, thereby avoiding actions based on incorrect information.

[0054] The question input unit can automatically generate follow-up questions and ask the user for confirmation in order to understand the user's intention more accurately. For example, when a user inputs a question, the generation AI automatically detects any ambiguity in the question and generates a follow-up question to ask the user for confirmation. For example, in response to the question "What is the diameter of the Earth?", the AI ​​can ask a follow-up question such as "Is it the equatorial diameter or the polar diameter of the Earth?" This makes it possible to understand the user's intention more accurately and provide an appropriate answer.

[0055] The question input unit can refer to past question history and prioritize displaying answers to similar questions if they exist. For example, when a user inputs a question, the question input unit automatically searches past question history and prioritizes displaying answers to similar questions if they exist. For example, if a similar question has been asked in the past in response to the question "What is the diameter of the Earth?", that answer will be displayed. This makes it possible to utilize past question history and quickly provide appropriate answers.

[0056] The question input unit can analyze the user's emotions and display a support message to reduce stress or anxiety. For example, when a user inputs a question, the question input unit uses the emotion estimation function to analyze the user's emotions in real time and display a support message to reduce stress or anxiety. For example, in response to the question "What is the diameter of the Earth?", a message such as "Please feel free to ask questions in a relaxed manner. We will support you" is displayed. This reduces the user's stress and anxiety and provides a comfortable questioning experience.

[0057] The question input unit can support different input methods, such as voice input or handwriting input. For example, the question input unit may add a function to support voice input when a user inputs a question, allowing the user to input the question using a microphone. For example, the question "What is the diameter of the Earth?" may be input by voice. The question input unit may also support handwriting input, allowing the user to input the question by handwriting using a tablet. This improves user convenience.

[0058] The question input unit can attach related images and videos. For example, the question input unit adds a function that allows users to attach related images and videos when entering a question, and the generation AI understands the question based on that visual information. For example, an image can be attached to the question, "How tall is the building in this image?" This allows the generation AI to understand the question from a more multifaceted perspective.

[0059] The question input unit can analyze the user's emotions in real time and make suggestions to elicit positive emotions. For example, when a user inputs a question, the generative AI uses the emotion estimation function to analyze the user's emotions in real time and make suggestions to elicit positive emotions. For example, in response to the question "What is the diameter of the Earth?", a message such as "That's a great question!" is displayed. This elicits positive emotions from the user and provides a pleasant questioning experience.

[0060] The match rate calculation unit can assign a reliability score to the answer of each generation AI and adjust the match rate based on that score. For example, the match rate calculation unit can develop an algorithm that assigns a reliability score to the answer of each generation AI and adjust the match rate based on that score. For example, answers from highly reliable generation AIs can be assigned a high score, increasing the match rate. This allows highly reliable answers to be displayed preferentially.

[0061] The answer collection unit can collect answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, the answer collection unit builds a system that collects answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, without waiting for the answer of a generation AI that is slow to respond, it will prioritize collecting answers from other generation AIs. This allows answers to be collected efficiently.

[0062] The answer collection unit uses the emotion estimation function to analyze the user's emotional response to each generation AI's answer and can prioritize displaying answers with a high number of positive responses. The answer collection unit, for example, collects the user's emotional response to each generation AI's answer in real time and builds a system that prioritizes displaying answers with a high number of positive responses. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. This makes it possible to provide the optimal answer based on the user's emotions.

[0063] The answer presentation unit can provide detailed explanations of the basis and reasons for the answer when presenting the most likely correct answer. For example, when presenting the most likely correct answer, the answer presentation unit adds a function to provide detailed explanations of the basis and reasons for the answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," the unit can provide an explanation such as "This information is based on data from NASA." This makes it easier for users to judge the reliability of the answer.

[0064] The answer presentation unit can display related additional information and references when presenting the most likely correct answer. For example, the answer presentation unit adds a function to display related additional information and references when presenting the most likely correct answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," it displays information such as "Related academic papers are here." This makes it easier for users to understand the background information of the answer.

[0065] The answer presentation unit can use the emotion estimation function to present the answer that gives the user the most comfort. For example, the answer presentation unit uses the emotion estimation function to build a system that presents the answer that gives the user the most comfort. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," the unit can provide an explanation such as "This information is based on highly reliable data." This allows the user to receive the answer with a sense of security.

[0066] The answer presentation unit can support display in different formats when presenting the most likely correct answer. For example, the answer presentation unit builds a system that supports display in different formats, such as text, audio, and video, when presenting the most likely correct answer. For example, the answer "The diameter of the Earth is approximately 12,742 km" is not only displayed in text, but also in audio and video. This allows the user to receive the answer in their preferred format.

[0067] The answer presentation unit adds a function that allows users to provide feedback on the answer, and this feedback can be used to help the generative AI learn. For example, when presenting the answer that is likely to be correct, the answer presentation unit adds a function that allows users to provide feedback on that answer. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," the unit asks for feedback such as "Was this answer helpful?" User feedback is used to help the generative AI learn and contributes to improving accuracy. This makes it possible to improve the accuracy of the generative AI based on user feedback.

[0068] The answer presentation unit can use the emotion estimation function to present the answer that will evoke the most positive emotion in the user in real time. For example, the answer presentation unit uses the emotion estimation function to build a system that presents the answer that will evoke the most positive emotion in the user in real time. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," a message such as "That's a great question!" is displayed. This allows the user to receive the answer with positive emotion.

[0069] The match rate calculation unit can detect abnormal values ​​by comparing the match rate with past data when displaying the match rate and display a warning to the user. The match rate calculation unit, for example, builds a system that detects abnormal values ​​by comparing the match rate with past data when displaying the match rate and displays a warning to the user. For example, a warning is displayed when the match rate is significantly lower than the average value in the past. This makes it possible to quickly detect abnormal answers and display a warning to the user.

[0070] The matching rate calculation unit allows the generation AI to automatically reevaluate answers with a low matching rate and recalculate the matching rate. The matching rate calculation unit builds a system in which the generation AI automatically reevaluates answers with a low matching rate and recalculates the matching rate. For example, reevaluation is performed when the matching rate is 50% or less. This allows answers with a low matching rate to be reevaluated and improve reliability.

[0071] The matching rate calculation unit can use the emotion estimation function to provide additional information to alleviate a user's anxiety when the user feels anxious about an answer with a low matching rate. The matching rate calculation unit, for example, uses the emotion estimation function to build a system that provides additional information to alleviate a user's anxiety when the user feels anxious about an answer with a low matching rate. For example, the matching rate calculation unit displays related additional information and references for an answer with a low matching rate. This can alleviate the user's anxiety and improve reliability.

[0072] The match rate calculation unit can use different visual display methods (graphs, charts) when displaying the match rate to allow the user to intuitively understand. The match rate calculation unit, for example, uses different visual display methods (graphs, charts) when displaying the match rate to build a system that allows the user to intuitively understand. For example, the match rate is displayed as a bar graph or a pie chart. This allows the user to intuitively understand the match rate.

[0073] The matching rate calculation unit can provide complementary information for answers with a low matching rate by referencing data from other highly reliable information sources. The matching rate calculation unit, for example, builds a system that provides complementary information for answers with a low matching rate by referencing data from other highly reliable information sources. For example, for answers with a low matching rate, related academic papers and databases are referenced. This makes it possible to provide reliable information and reduce user anxiety.

[0074] The matching rate calculation unit uses the emotion estimation function to analyze in real time what emotions a user will have in response to an answer with a low matching rate, and can take the optimal response based on the results. The matching rate calculation unit, for example, uses the emotion estimation function to analyze in real time what emotions a user will have in response to an answer with a low matching rate, and can build a system that takes the optimal response based on the results. For example, if the user feels anxious, additional information is provided. This makes it possible to take the optimal response based on the user's emotions and improve reliability.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] To more accurately understand the user's intent, the question input unit can analyze the context of the question using natural language processing technology and automatically extract related keywords. For example, in response to the question, "What is the diameter of the Earth?", keywords such as "Earth" and "diameter" are extracted and a question is sent to the generation AI based on these. The question input unit can also analyze the context of the question entered by the user and automatically provide related additional information. For example, in response to the question, "What is the diameter of the Earth?", additional information such as, "Would you also like to know the difference between the Earth's equatorial diameter and polar diameter?" is provided. This allows for a more accurate understanding of the user's intent and the provision of an appropriate answer.

[0077] The question input unit can analyze the user's emotions in real time and provide appropriate feedback depending on the user's emotional state when entering a question. For example, if the user feels stressed when entering a question, a message such as "Please relax and ask your question. We will support you" is displayed. On the other hand, if the user has positive emotions, a message such as "That's a great question!" is displayed. This allows the system to provide appropriate feedback according to the user's emotions and provide a pleasant questioning experience.

[0078] The answer collection unit can collect user feedback on the answers of the generation AI and improve the accuracy of the answers of the generation AI based on that feedback. For example, a function that allows users to provide feedback such as "Was this answer helpful?" can be added to collect user feedback. The learning data of the generation AI can also be updated based on the collected feedback to improve the accuracy of the answers. This makes it possible to utilize user feedback to improve the accuracy of the generation AI.

[0079] The answer presentation unit can use the emotion estimation function to present the answer that gives the user the most peace of mind. For example, if the user asks, "What is the diameter of the Earth?", the unit can explain, "This information is based on data from NASA." If the user feels uneasy, the unit can display a message such as, "This information is based on highly reliable data, so please rest assured." This allows the user to receive the answer with a sense of security.

[0080] The match rate calculation unit assigns a reliability score to each generated AI's answer and can adjust the match rate based on that score. For example, a high score can be assigned to a highly reliable generated AI's answer, increasing the match rate. A low score can be assigned to a less reliable generated AI's answer, decreasing the match rate. This allows highly reliable answers to be displayed preferentially.

[0081] The question input unit can analyze the user's emotions in real time and display a support message to reduce stress or anxiety. For example, when a user inputs a question, the generation AI uses the emotion estimation function to analyze the user's emotions in real time and display a support message to reduce stress and anxiety. For example, in response to the question "What is the diameter of the Earth?", a message such as "Please feel free to ask your question. We will support you" is displayed. This reduces the user's stress and anxiety and provides a comfortable questioning experience.

[0082] The answer presentation unit can support display in different formats when presenting the most likely correct answer. For example, a system can be constructed that supports display in different formats, such as text, audio, and video, when presenting the most likely correct answer. For example, the answer "The diameter of the Earth is approximately 12,742 km" can be displayed not only in text but also in audio and video. This allows the user to receive the answer in their preferred format.

[0083] The matching rate calculation unit can use the emotion estimation function to provide additional information to alleviate anxiety when a user feels uneasy about an answer with a low matching rate. For example, the matching rate calculation unit can display related additional information or references for an answer with a low matching rate. This can alleviate the user's anxiety and improve reliability.

[0084] The answer collection unit can collect answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, a system can be constructed that collects answers at the optimal timing, taking into account the response time and processing load of the generation AI. For example, answers from other generation AIs can be collected preferentially, without waiting for the answer from a generation AI that is slow to respond. This allows answers to be collected efficiently.

[0085] The answer presentation unit uses the emotion estimation function to present the answer that elicits the most positive emotion in real time. For example, in response to the answer "The diameter of the Earth is approximately 12,742 km," a message such as "That's a great question!" is displayed. This allows the user to receive the answer with positive emotion.

[0086] The processing flow of the second embodiment will be briefly explained below.

[0087] Step 1: The question input unit inputs a question from the user. For example, the user inputs a question in text format. The question input unit may also support voice input, allowing the user to input a question using a microphone. The question input unit may also support handwriting input, allowing the user to input a question by handwriting using a tablet. Step 2: The answer collection unit sends the question input by the question input unit to multiple generation AIs and collects answers. For example, if the question is "What is the diameter of the Earth?", the answer collection unit sends this question to multiple generation AIs. The generation AIs may be text generation AIs (e.g., LLMs) or multimodal generation AIs, and each generation AI generates an answer. Step 3: The matching rate calculation unit calculates the matching rate of the answers collected by the answer collection unit. For example, if generation AI A answers "The diameter of the Earth is approximately 12,742 km," and generation AI B also answers "The diameter of the Earth is approximately 12,742 km," the matching rate will be high. On the other hand, if generation AI C answers "The diameter of the Earth is approximately 10,000 km," the matching rate will be low. The matching rate calculation unit calculates the matching rate of the answers using, for example, cosine similarity. The matching rate can also be calculated using the Jaccard coefficient. Furthermore, the matching rate can also be calculated using TF-IDF. Step 4: The answer presentation unit presents the answer that is most likely to be correct based on the match rate calculated by the match rate calculation unit. For example, if the answer with the highest match rate among the answers of multiple generated AIs is "The diameter of the Earth is approximately 12,742 km," this answer is presented to the user. This allows the generated AI portal according to the embodiment to increase the user's confidence in the answers of the generated AI and reduce the need for users to recheck or research the answers themselves.

[0088] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0089] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0090] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0091] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0092] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0093] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0094] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0095] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0096] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0097] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0098] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0099] 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.

[0100] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0101] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0102] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0106] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0107] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0122] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0129] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0132] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0138] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0139] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0140] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0141] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0142] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0143] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0144] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0145] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0146] 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.

[0147] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0148] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0149] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0150] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0151] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0152] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0153] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0154] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0155] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a question input unit for inputting a question from a user; an answer collection unit that transmits the question input by the question input unit to a plurality of generation AIs and collects answers; a matching rate calculation unit that calculates a matching rate of the answers collected by the answer collection unit; an answer presentation unit that presents the most correct answer based on the match rate calculated by the match rate calculation unit; A system characterized by:

2. The question input unit Analyze the user's emotions and display supportive messages to reduce stress or anxiety 2. The system of claim 1.

3. The question input unit You can attach relevant images and videos 2. The system of claim 1.

4. The match rate calculation unit A reliability score is assigned to each generated AI answer, and the match rate is adjusted based on that score.

2. The system of claim 1.

5. The answer presentation unit When presenting the most likely correct answer, provide a detailed explanation of the rationale and reasons for your answer.

2. The system of claim 1.

6. The match rate calculation unit If users are concerned about low match rates, provide additional information to alleviate their concerns.

2. The system of claim 1.

7. The match rate calculation unit Analyze in real time how users feel about answers with low matching rates, and then take the optimal action based on the results.

2. The system of claim 1.

Images