System

Abstract

To provide highly reliable responses on the basis of discussion results by multiple pieces of generative AI.SOLUTION: A system according to an embodiment comprises a reception unit, multiple generation units, an evaluation unit, and a provision unit. The reception unit inputs a question. The multiple generation units individually generate responses to the question input by the reception unit. The evaluation unit compares and evaluates the responses generated by the multiple generation units. The provision unit provides the response selected by the evaluation 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the quality of answers provided by generative AI was inconsistent, making it difficult to obtain reliable answers.

[0005] The system of the embodiment aims to provide highly reliable answers based on the discussion results of multiple generation AIs. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, a plurality of generating units, an evaluation unit, and a providing unit. The receiving unit inputs a question. The plurality of generating units individually generate answers to the question input by the receiving unit. The evaluation unit compares and evaluates the answers generated by the plurality of generating units. The providing unit provides the answer selected by the evaluation unit. Effect of the Invention

[0007] The system according to the embodiment can provide highly reliable answers based on the results of discussions by multiple generation AIs. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

[0009] 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.

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded 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), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the 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 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A system according to an embodiment of the present invention is a system that outputs the results of discussions by multiple AIs when creating an answer by a generation AI. In this system, a user inputs a question, and multiple generation AIs individually generate answers to the question. The generated answers are sent to a discussion module, where the answers of each generation AI are compared and evaluated. Finally, the most appropriate answer is selected as the discussion result and provided to the user. This mechanism makes it possible to correct bias in the answer content due to prompts and data, and provide a more reliable answer. For example, if a user asks, "Please tell me about the impact of climate change," the discussion module integrates the answers of multiple generation AIs and provides a comprehensive answer that includes scientific data and social impacts. This allows the system to correct bias in the answer content due to prompts and data, and provide a more reliable answer.

[0029] The discussion system according to the embodiment includes a reception unit, a plurality of generation units, an evaluation unit, and a provision unit. The reception unit is a unit for a user to input a question. The question input by the user includes, for example, a text format or a voice format, but is not limited to such examples. The reception unit allows the user to input a specific question such as "Please tell me about the impact of climate change." Next, the plurality of generation units individually generate answers to the questions input by the reception unit. Each generation unit generates an answer using its own algorithm and data set. For example, the generation unit 1 generates an answer based on scientific data, and the generation unit 2 generates an answer based on social impact. The generation unit generates an answer using a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Next, the evaluation unit compares and evaluates the answers generated by the plurality of generation units. For example, if the answer of the generation AI1 is scientifically accurate but the answer of the generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. Finally, the provision unit provides the most appropriate answer selected by the evaluation unit to the user. The provision unit provides the user with an answer selected as a discussion result, for example. In this way, the discussion system according to the embodiment can output discussion results by multiple generation AIs in response to a user's question and provide a highly reliable answer.

[0030] The reception unit is a part for a user to input a question. The question input by the user includes, for example, a text format and a voice format, but is not limited to such examples. Specifically, the reception unit allows the user to input a specific question such as "Please tell me about the impact of climate change." The reception unit provides an interface for the user to input a question, and includes a text input field and a voice input button. The text input field is for the user to input a question using a keyboard, and the voice input button is for the user to input a question by voice using a microphone. In the case of voice input, the voice is converted into text using voice recognition technology and transmitted to the reception unit as a question. Furthermore, the reception unit includes a preprocessing function for appropriately processing the question input by the user. For example, the reception unit performs a grammar check and a spell check on the question, and corrects errors. In addition, the reception unit analyzes the content of the question and extracts related keywords, so that the subsequent generation unit can efficiently generate an answer. The reception unit not only accepts the user's question, but also plays a role of appropriately analyzing the content of the question and providing information necessary for subsequent processing. As a result, the reception unit can accurately and efficiently process the question input by the user, thereby improving the performance of the entire system.

[0031] The multiple generation units individually generate answers to the questions input by the reception unit. Each generation unit generates an answer using its own algorithm and data set. For example, the generation unit 1 generates an answer based on scientific data, and the generation unit 2 generates an answer based on social influence. The generation unit generates an answer using a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Specifically, the generation unit 1 refers to a scientific database or research paper to generate a scientifically accurate answer. The generation unit 2 refers to social data or statistical information to generate an answer based on social influence. The generation AI generates an appropriate answer to the user's question using natural language processing technology. For example, the generation AI analyzes the content of the question, searches for related information, and generates an answer. The generation AI has an advanced algorithm for understanding the context of the question and generating an appropriate answer. Furthermore, the generation unit has a function of evaluating the quality of the generated answer and making corrections if necessary. For example, if the generated answer is incomplete or contains an error, the generation unit refers to additional data and corrects the answer. This enables the generation unit to provide a high-quality answer to the user's question.

[0032] The evaluation unit compares and evaluates the answers generated by multiple generation units. For example, if the answer of generation AI1 is scientifically accurate but the answer of generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. Specifically, the evaluation unit analyzes the answers provided by each generation unit and evaluates the quality and reliability of the answers. The evaluation unit performs evaluation based on criteria such as whether the content of the answer is accurate, whether it is easy for the user to understand, and whether the information is consistent. The evaluation unit selects the optimal answer based on the evaluation results of each answer. For example, it integrates a scientifically accurate answer and a user-friendly answer to generate an answer that is easy for the user to understand while maintaining scientific accuracy. The evaluation unit uses an integration algorithm to optimally combine multiple answers to provide the most appropriate answer for the user. Furthermore, the evaluation unit can continuously improve the evaluation criteria and algorithms based on past evaluation results and user feedback. This enables the evaluation unit to consistently provide high-quality answers, improving the reliability of the entire system and user satisfaction.

[0033] The providing unit provides the user with the most appropriate answer selected by the evaluation unit. The providing unit provides the user with, for example, an answer selected as a discussion result. Specifically, the providing unit displays the answer selected by the evaluation unit in the interface where the user inputs the question. The providing unit can provide the answer in text format or audio format. In the case of text format, the answer is displayed on the user's screen, and the user can read the answer. In the case of audio format, the answer is provided by voice using voice synthesis technology, and the user can hear the answer. Furthermore, the providing unit has an interface for the user to provide feedback on the answer. The user can provide feedback such as whether the answer was useful or whether the content of the answer was easy to understand. The providing unit collects user feedback and provides the feedback to the evaluation unit and the generation unit, thereby improving the performance of the entire system. The providing unit not only provides the user with a prompt and appropriate answer, but also plays a role in continuously improving the system based on the user's feedback. In this way, the providing unit can provide high-quality answers to the user and improve user satisfaction.

[0034] The multiple generation units can generate answers using their own algorithms and data sets. The generation unit generates answers using algorithms such as neural networks, decision trees, and support vector machines. The generation unit generates answers using data sets such as scientific data, social data, and historical data. As a result, each generation AI uses its own algorithm and data set to obtain answers from various perspectives. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input answers generated using its own algorithms and data sets to the generation AI, and the generation AI can generate an answer.

[0035] The evaluation unit can compare and evaluate the answers of each generation AI and select the most appropriate answer. For example, if the answer of generation AI1 is scientifically accurate but the answer of generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. This allows the answers of each generation AI to be compared and evaluated to select the most appropriate answer. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can select the optimal answer using a generation AI model that inputs the answer of the generation AI and outputs the optimal answer.

[0036] The evaluation unit can integrate the answers of the generation AIs to generate an optimal answer. For example, if the answer of the generation AI1 is scientifically accurate but the answer of the generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. In this way, a more comprehensive and optimal answer can be obtained by integrating the answers of the generation AIs. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can generate an optimal answer using a generation AI model that inputs the answers of the generation AI and outputs an optimal answer.

[0037] The providing unit can provide the answer selected as the discussion result to the user. The providing unit, for example, provides the answer selected as the discussion result to the user. The providing unit can provide the answer through, for example, a web application or a mobile application. The providing unit can also send the answer by email, for example. Thereby, by providing the answer selected as the discussion result to the user, a highly reliable answer can be obtained. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the answer selected by the generation AI to the user.

[0038] The reception unit can analyze the user's past question history and select the optimal question reception method. The reception unit, for example, analyzes the pattern of questions frequently asked by the user in the past and proposes the optimal reception method. The reception unit, for example, selects the optimal reception method for a specific time period from the user's past question history. The reception unit, for example, selects the most efficient reception method based on the user's past question history. In this way, the optimal question reception method can be selected by analyzing the user's past question history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit inputs the user's past question history into the generation AI and allows the generation AI to select the optimal reception method.

[0039] The reception unit can filter the question content based on the user's current field of interest when receiving a question. The reception unit, for example, preferentially receives questions related to topics in which the user is currently interested. The reception unit, for example, filters questions with low relevance based on the user's field of interest. The reception unit, for example, analyzes the user's current field of interest and proposes optimal question content. As a result, by filtering the question content based on the user's current field of interest, it is possible to preferentially receive questions with high relevance. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's field of interest to the generation AI and cause the generation AI to filter the question content.

[0040] The reception unit can preferentially receive questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, when the user is in a specific area, the reception unit preferentially receives questions related to the area. The reception unit, for example, filters questions with high relevance based on the user's current location. For example, the reception unit analyzes the geographical location information of the user and suggests optimal question content. In this way, by considering the geographical location information of the user, questions with high relevance can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute filtering of the question content.

[0041] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. The reception unit preferentially receives related questions based on, for example, the user's social media activity. The reception unit, for example, analyzes the user's topics of interest on social media and suggests optimal question content. The reception unit, for example, filters highly relevant questions based on the user's social media activity history. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant questions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's social media activity to the generation AI and cause the generation AI to filter the question content.

[0042] The multiple generation units can select a generation algorithm based on the importance of the question when generating an answer. For example, for a question with high importance, the multiple generation units select a generation algorithm with high accuracy. For example, for a question with low importance, the multiple generation units select an algorithm that quickly generates an answer. For example, the multiple generation units select an optimal generation algorithm according to the importance of the question. In this way, by selecting a generation algorithm based on the importance of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the importance of the question to the generation AI and cause the generation AI to select a generation algorithm.

[0043] The multiple generation units can apply different generation algorithms depending on the category of the question when generating an answer. For example, for a scientific question, the multiple generation units apply a generation algorithm based on scientific data. For example, for a social question, the multiple generation units apply a generation algorithm based on social data. For example, the multiple generation units apply an optimal generation algorithm depending on the category of the question. In this way, by applying different generation algorithms depending on the category of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the category of the question to the generation AI and cause the generation AI to apply the generation algorithm.

[0044] The multiple generation units can determine the priority of the generation algorithms based on the time of question submission when generating an answer. The multiple generation units select an optimal generation algorithm based on, for example, the time period when the question is submitted. The multiple generation units adjust the priority of the generation algorithms according to, for example, the time period when the question is submitted. The multiple generation units apply an optimal generation algorithm, for example, taking into account the time period when the question is submitted. In this way, a more appropriate answer can be generated by determining the priority of the generation algorithms based on the time period when the question is submitted. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the time period when the question is submitted to the generation AI and cause the generation AI to determine the priority of the generation algorithms.

[0045] The multiple generation units can adjust the order of the generation algorithms based on the relevance of the question when generating an answer. For example, when the relevance of the question is high, the multiple generation units prioritize a generation algorithm with high accuracy. For example, when the relevance of the question is low, the multiple generation units prioritize an algorithm that quickly generates an answer. For example, the multiple generation units adjust the order of the generation algorithms according to the relevance of the question. In this way, by adjusting the order of the generation algorithms based on the relevance of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the relevance of the question to the generation AI and cause the generation AI to adjust the order of the generation algorithms.

[0046] The evaluation unit can improve the accuracy of the evaluation by considering the interrelationships of the generated answers during the evaluation. The evaluation unit, for example, analyzes the interrelationships of the answers of each generation AI and improves the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion by considering the interrelationships of the generated answers. The evaluation unit, for example, improves the accuracy of the evaluation based on the interrelationships of the answers of each generation AI. As a result, the accuracy of the evaluation is improved by considering the interrelationships of the generated answers. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the interrelationships of the answers of the generation AI to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0047] The evaluation unit can perform the evaluation while taking into consideration the attribute information of the answer submitter. The evaluation unit performs the evaluation while taking into consideration, for example, the specialized knowledge of the answer submitter. The evaluation unit performs the evaluation based on, for example, the past evaluation history of the answer submitter. The evaluation unit analyzes, for example, the attribute information of the answer submitter and applies optimal evaluation criteria. In this way, a more appropriate evaluation can be performed by taking into consideration the attribute information of the answer submitter. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the attribute information of the answer submitter to the generation AI and cause the generation AI to perform the evaluation.

[0048] The evaluation unit can perform the evaluation while taking into account the geographic distribution of the answers. The evaluation unit, for example, analyzes the geographic distribution of the answers to improve the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion while taking into account the geographic distribution of the answers. The evaluation unit, for example, improves the accuracy of the evaluation based on the geographic distribution of the answers. Thereby, the accuracy of the evaluation is improved by taking into account the geographic distribution of the answers. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the geographic distribution of the answers to the generation AI and cause the generation AI to perform the evaluation.

[0049] The evaluation unit can improve the accuracy of the evaluation by referring to the relevant literature of the answer at the time of evaluation. The evaluation unit, for example, refers to the relevant literature of the answer and improves the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion based on the relevant literature of the answer. The evaluation unit, for example, analyzes the relevant literature of the answer and improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is improved by referring to the relevant literature of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the relevant literature of the answer to the generation AI and cause the generation AI to execute the evaluation.

[0050] The providing unit can select the optimal answer by referring to the user's past question history at the time of providing. The providing unit selects the optimal answer based on, for example, the user's past question history. The providing unit preferentially provides, for example, highly relevant answers from the user's past question history. The providing unit, for example, analyzes the user's past question history and selects the most appropriate answer. In this way, the optimal answer can be selected by referring to the user's past question history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's past question history to the generation AI and cause the generation AI to select the optimal answer.

[0051] The providing unit can customize the answer content based on the user's current field of interest at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's current field of interest. The providing unit, for example, analyzes the user's field of interest and customizes optimal answer content. The providing unit adjusts the answer content according to, for example, the user's current field of interest. In this way, by customizing the answer content based on the user's current field of interest, a more relevant answer can be provided. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's field of interest to the generation AI and cause the generation AI to customize the answer content.

[0052] The providing unit can select an optimal answer by considering the geographical location information of the user at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's current location. The providing unit, for example, analyzes the geographical location information of the user and selects an optimal answer. The providing unit, for example, adjusts the answer content according to the geographical location information of the user. In this way, the optimal answer can be provided by considering the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the geographical location information of the user to the generation AI and cause the generation AI to select an optimal answer.

[0053] The providing unit can analyze the user's social media activity and suggest the answer content at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's social media activity content. The providing unit analyzes, for example, the user's topics of interest on social media and suggests the optimal answer content. The providing unit suggests a highly relevant answer based on, for example, the user's social media activity history. In this way, a highly relevant answer can be provided by analyzing the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's social media activity to the generation AI and cause the generation AI to execute the suggestion of the answer content.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The reception unit can analyze the user's input in real time and estimate the intent of the question. For example, if the user inputs an ambiguous question, the reception unit can estimate the intent of the question and convert it into a more specific question. Also, if the user inputs multiple questions at once, the reception unit can split those questions and process them separately. Furthermore, the reception unit can take into account the context in which the user inputs the question and provide additional related information. This makes the user's question clearer and improves the accuracy of the answer provided by the generation unit.

[0056] The multiple generation units can refer to the user's past question history and generate a new answer based on the past answers. For example, if the user has previously asked a similar question, the new answer can be generated by referring to the answer. In addition, a specific pattern can be found from the user's past question history and an answer can be generated based on the pattern. Furthermore, the user's past question history can be analyzed and information related to the user's field of interest can be provided preferentially. In this way, by utilizing the user's past question history, a more personalized answer can be provided.

[0057] The evaluation unit can refer to external reliable data sources to evaluate the reliability of the generated answers. For example, for scientific questions, reliable academic papers and databases can be referenced to confirm the accuracy of the generated answers. For social questions, government agencies and public statistical data can be referenced to evaluate the reliability of the answers. Furthermore, the evaluation unit can also periodically update the data sources to check whether the generated answers are based on the latest information. This makes it possible to improve the reliability of the generated answers by utilizing external reliable data sources.

[0058] The evaluation unit can compare answers from different perspectives to evaluate the diversity of the generated answers. For example, it can compare answers generated by different generation AIs to the same question and evaluate whether each answer provides a different perspective. It can also analyze the content of the answer to check whether the generated answer is biased toward a specific bias. In addition, the evaluation unit can collect user feedback and adjust the evaluation criteria based on it to evaluate whether the generated answer meets the diverse needs of users. This allows the diversity of the generated answers to be evaluated, thereby providing more comprehensive and balanced answers.

[0059] The providing unit can collect user feedback and improve the answers to be provided based on the feedback. For example, the providing unit can provide a function for the user to rate the provided answers and improve the quality of the answers based on the ratings. The providing unit can also provide a function for the user to ask additional questions about the provided answers and quickly generate answers to those questions. Furthermore, the providing unit can analyze the user feedback, identify common problems, and take measures to improve them. In this way, the quality of the answers to be provided can be continuously improved by utilizing the user feedback.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The reception unit is a section where the user inputs a question. The user can input a question in text format, voice format, or the like. For example, the user inputs a specific question such as "Please tell me about the effects of climate change." Step 2: The multiple generators individually generate answers to the questions input by the reception unit. Each generator generates answers using its own algorithm and dataset. For example, generator 1 generates answers based on scientific data, and generator 2 generates answers based on social influences. The generators generate answers using generation AI, and include text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The evaluation unit compares and evaluates the answers generated by multiple generation units. For example, if the answer of generation AI1 is scientifically accurate, but the answer of generation AI2 is more user-friendly, these answers are combined to generate the optimal answer. The evaluation unit can also combine the answers of the generation AIs using a weighted average or consensus algorithm. Step 4: The providing unit provides the most appropriate answer selected by the evaluating unit to the user. For example, the answer selected as a discussion result is provided to the user.

[0062] (Example 2) A system according to an embodiment of the present invention is a system that outputs the results of discussions by multiple AIs when creating an answer by a generation AI. In this system, a user inputs a question, and multiple generation AIs individually generate answers to the question. The generated answers are sent to a discussion module, where the answers of each generation AI are compared and evaluated. Finally, the most appropriate answer is selected as the discussion result and provided to the user. This mechanism makes it possible to correct bias in the answer content due to prompts and data, and provide a more reliable answer. For example, if a user asks, "Please tell me about the impact of climate change," the discussion module integrates the answers of multiple generation AIs and provides a comprehensive answer that includes scientific data and social impacts. This allows the system to correct bias in the answer content due to prompts and data, and provide a more reliable answer.

[0063] The discussion system according to the embodiment includes a reception unit, a plurality of generation units, an evaluation unit, and a provision unit. The reception unit is a unit for a user to input a question. The question input by the user includes, for example, a text format or a voice format, but is not limited to such examples. The reception unit allows the user to input a specific question such as "Please tell me about the impact of climate change." Next, the plurality of generation units individually generate answers to the questions input by the reception unit. Each generation unit generates an answer using its own algorithm and data set. For example, the generation unit 1 generates an answer based on scientific data, and the generation unit 2 generates an answer based on social impact. The generation unit generates an answer using a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. Next, the evaluation unit compares and evaluates the answers generated by the plurality of generation units. For example, if the answer of the generation AI1 is scientifically accurate but the answer of the generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. Finally, the provision unit provides the most appropriate answer selected by the evaluation unit to the user. The provision unit provides the user with an answer selected as a discussion result, for example. In this way, the discussion system according to the embodiment can output discussion results by multiple generation AIs in response to a user's question and provide a highly reliable answer.

[0064] The reception unit is a part for a user to input a question. The question input by the user includes, for example, a text format and a voice format, but is not limited to such examples. Specifically, the reception unit allows the user to input a specific question such as "Please tell me about the impact of climate change." The reception unit provides an interface for the user to input a question, and includes a text input field and a voice input button. The text input field is for the user to input a question using a keyboard, and the voice input button is for the user to input a question by voice using a microphone. In the case of voice input, the voice is converted into text using voice recognition technology and transmitted to the reception unit as a question. Furthermore, the reception unit includes a preprocessing function for appropriately processing the question input by the user. For example, the reception unit performs a grammar check and a spell check on the question, and corrects errors. In addition, the reception unit analyzes the content of the question and extracts related keywords, so that the subsequent generation unit can efficiently generate an answer. The reception unit not only accepts the user's question, but also plays a role of appropriately analyzing the content of the question and providing information necessary for subsequent processing. As a result, the reception unit can accurately and efficiently process the question input by the user, thereby improving the performance of the entire system.

[0065] The multiple generation units individually generate answers to the questions input by the reception unit. Each generation unit generates an answer using its own algorithm and data set. For example, the generation unit 1 generates an answer based on scientific data, and the generation unit 2 generates an answer based on social influence. The generation unit generates an answer using a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Specifically, the generation unit 1 refers to a scientific database or research paper to generate a scientifically accurate answer. The generation unit 2 refers to social data or statistical information to generate an answer based on social influence. The generation AI generates an appropriate answer to the user's question using natural language processing technology. For example, the generation AI analyzes the content of the question, searches for related information, and generates an answer. The generation AI has an advanced algorithm for understanding the context of the question and generating an appropriate answer. Furthermore, the generation unit has a function of evaluating the quality of the generated answer and making corrections if necessary. For example, if the generated answer is incomplete or contains an error, the generation unit refers to additional data and corrects the answer. This enables the generation unit to provide a high-quality answer to the user's question.

[0066] The evaluation unit compares and evaluates the answers generated by multiple generation units. For example, if the answer of generation AI1 is scientifically accurate but the answer of generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. Specifically, the evaluation unit analyzes the answers provided by each generation unit and evaluates the quality and reliability of the answers. The evaluation unit performs evaluation based on criteria such as whether the content of the answer is accurate, whether it is easy for the user to understand, and whether the information is consistent. The evaluation unit selects the optimal answer based on the evaluation results of each answer. For example, it integrates a scientifically accurate answer and a user-friendly answer to generate an answer that is easy for the user to understand while maintaining scientific accuracy. The evaluation unit uses an integration algorithm to optimally combine multiple answers to provide the most appropriate answer for the user. Furthermore, the evaluation unit can continuously improve the evaluation criteria and algorithms based on past evaluation results and user feedback. This enables the evaluation unit to consistently provide high-quality answers, improving the reliability of the entire system and user satisfaction.

[0067] The providing unit provides the user with the most appropriate answer selected by the evaluation unit. The providing unit provides the user with, for example, an answer selected as a discussion result. Specifically, the providing unit displays the answer selected by the evaluation unit in the interface where the user inputs the question. The providing unit can provide the answer in text format or audio format. In the case of text format, the answer is displayed on the user's screen, and the user can read the answer. In the case of audio format, the answer is provided by voice using voice synthesis technology, and the user can hear the answer. Furthermore, the providing unit has an interface for the user to provide feedback on the answer. The user can provide feedback such as whether the answer was useful or whether the content of the answer was easy to understand. The providing unit collects user feedback and provides the feedback to the evaluation unit and the generation unit, thereby improving the performance of the entire system. The providing unit not only provides the user with a prompt and appropriate answer, but also plays a role in continuously improving the system based on the user's feedback. In this way, the providing unit can provide high-quality answers to the user and improve user satisfaction.

[0068] The multiple generation units can generate answers using their own algorithms and data sets. The generation unit generates answers using algorithms such as neural networks, decision trees, and support vector machines. The generation unit generates answers using data sets such as scientific data, social data, and historical data. As a result, each generation AI uses its own algorithm and data set to obtain answers from various perspectives. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input answers generated using its own algorithms and data sets to the generation AI, and the generation AI can generate an answer.

[0069] The evaluation unit can compare and evaluate the answers of each generation AI and select the most appropriate answer. For example, if the answer of generation AI1 is scientifically accurate but the answer of generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. This allows the answers of each generation AI to be compared and evaluated to select the most appropriate answer. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can select the optimal answer using a generation AI model that inputs the answer of the generation AI and outputs the optimal answer.

[0070] The evaluation unit can integrate the answers of the generation AIs to generate an optimal answer. For example, if the answer of the generation AI1 is scientifically accurate but the answer of the generation AI2 is more user-friendly, the evaluation unit integrates these answers to generate an optimal answer. The evaluation unit can also integrate the answers of the generation AIs to generate an optimal answer. For example, the evaluation unit integrates the answers of the generation AIs using a weighted average or a consensus algorithm. In this way, a more comprehensive and optimal answer can be obtained by integrating the answers of the generation AIs. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can generate an optimal answer using a generation AI model that inputs the answers of the generation AI and outputs an optimal answer.

[0071] The providing unit can provide the answer selected as the discussion result to the user. The providing unit, for example, provides the answer selected as the discussion result to the user. The providing unit can provide the answer through, for example, a web application or a mobile application. The providing unit can also send the answer by email, for example. Thereby, by providing the answer selected as the discussion result to the user, a highly reliable answer can be obtained. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can provide the answer selected by the generation AI to the user.

[0072] The reception unit can estimate the user's emotion and adjust the timing of receiving the question based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit temporarily delays the reception of the question to provide time for the user to relax. For example, when the user is relaxed, the reception unit immediately receives the question and starts processing quickly. For example, when the user is in a hurry, the reception unit prioritizes the reception of the question and performs processing quickly. In this way, the timing of receiving the question can be adjusted according to the user's emotion, so that the question can be received at a more appropriate timing. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion estimation.

[0073] The reception unit can analyze the user's past question history and select the optimal question reception method. The reception unit, for example, analyzes the pattern of questions frequently asked by the user in the past and proposes the optimal reception method. The reception unit, for example, selects the optimal reception method for a specific time period from the user's past question history. The reception unit, for example, selects the most efficient reception method based on the user's past question history. In this way, the optimal question reception method can be selected by analyzing the user's past question history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit inputs the user's past question history into the generation AI and allows the generation AI to select the optimal reception method.

[0074] The reception unit can filter the question content based on the user's current field of interest when receiving a question. The reception unit, for example, preferentially receives questions related to topics in which the user is currently interested. The reception unit, for example, filters questions with low relevance based on the user's field of interest. The reception unit, for example, analyzes the user's current field of interest and proposes optimal question content. As a result, by filtering the question content based on the user's current field of interest, it is possible to preferentially receive questions with high relevance. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's field of interest to the generation AI and cause the generation AI to filter the question content.

[0075] The reception unit can estimate the user's emotion and determine the priority of questions to be received based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit postpones questions with low importance. For example, when the user is relaxed, the reception unit preferentially receives questions with high importance. For example, when the user is in a hurry, the reception unit preferentially receives questions with high urgency. In this way, by determining the priority of questions according to the user's emotion, more appropriate questions can be preferentially received. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0076] The reception unit can preferentially receive questions with high relevance in consideration of the geographical location information of the user when receiving a question. For example, when the user is in a specific area, the reception unit preferentially receives questions related to the area. The reception unit, for example, filters questions with high relevance based on the user's current location. For example, the reception unit analyzes the geographical location information of the user and suggests optimal question content. In this way, by considering the geographical location information of the user, questions with high relevance can be preferentially received. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute filtering of the question content.

[0077] The reception unit can analyze the user's social media activity and receive related questions when receiving a question. The reception unit preferentially receives related questions based on, for example, the user's social media activity. The reception unit, for example, analyzes the user's topics of interest on social media and suggests optimal question content. The reception unit, for example, filters highly relevant questions based on the user's social media activity history. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant questions. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's social media activity to the generation AI and cause the generation AI to filter the question content.

[0078] The multiple generation units can estimate the user's emotions and adjust the answer generation method based on the estimated user's emotions. For example, when the user is relaxed, the multiple generation units generate a detailed answer. For example, when the user is in a hurry, the multiple generation units generate a concise answer. For example, when the user is excited, the multiple generation units generate a visually stimulating answer. This allows a more appropriate answer to be generated by adjusting the answer generation method according to the user's emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the multiple generation units can input the user's emotion data to the generation AI and cause the generation AI to adjust the answer generation method.

[0079] The multiple generation units can select a generation algorithm based on the importance of the question when generating an answer. For example, for a question with high importance, the multiple generation units select a generation algorithm with high accuracy. For example, for a question with low importance, the multiple generation units select an algorithm that quickly generates an answer. For example, the multiple generation units select an optimal generation algorithm according to the importance of the question. In this way, by selecting a generation algorithm based on the importance of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the importance of the question to the generation AI and cause the generation AI to select a generation algorithm.

[0080] The multiple generation units can apply different generation algorithms depending on the category of the question when generating an answer. For example, for a scientific question, the multiple generation units apply a generation algorithm based on scientific data. For example, for a social question, the multiple generation units apply a generation algorithm based on social data. For example, the multiple generation units apply an optimal generation algorithm depending on the category of the question. In this way, by applying different generation algorithms depending on the category of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the category of the question to the generation AI and cause the generation AI to apply the generation algorithm.

[0081] The multiple generation units can estimate the user's emotion and adjust the length of the answer to be generated based on the estimated user's emotion. For example, when the user is relaxed, the multiple generation units generate a detailed and long answer. For example, when the user is in a hurry, the multiple generation units generate a concise and short answer. For example, when the user is excited, the multiple generation units generate a visually stimulating answer. This allows a more appropriate answer to be generated by adjusting the length of the answer according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the multiple generation units can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the answer.

[0082] The multiple generation units can determine the priority of the generation algorithms based on the time of question submission when generating an answer. The multiple generation units select an optimal generation algorithm based on, for example, the time period when the question is submitted. The multiple generation units adjust the priority of the generation algorithms according to, for example, the time period when the question is submitted. The multiple generation units apply an optimal generation algorithm, for example, taking into account the time period when the question is submitted. In this way, a more appropriate answer can be generated by determining the priority of the generation algorithms based on the time period when the question is submitted. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the time period when the question is submitted to the generation AI and cause the generation AI to determine the priority of the generation algorithms.

[0083] The multiple generation units can adjust the order of the generation algorithms based on the relevance of the question when generating an answer. For example, when the relevance of the question is high, the multiple generation units prioritize a generation algorithm with high accuracy. For example, when the relevance of the question is low, the multiple generation units prioritize an algorithm that quickly generates an answer. For example, the multiple generation units adjust the order of the generation algorithms according to the relevance of the question. In this way, by adjusting the order of the generation algorithms based on the relevance of the question, a more appropriate answer can be generated. A part or all of the above-mentioned processing in the multiple generation units may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the multiple generation units can input the relevance of the question to the generation AI and cause the generation AI to adjust the order of the generation algorithms.

[0084] The evaluation unit can estimate the user's emotion and adjust the evaluation criteria based on the estimated user's emotion. For example, when the user is relaxed, the evaluation unit applies detailed evaluation criteria. For example, when the user is in a hurry, the evaluation unit applies concise evaluation criteria. For example, when the user is excited, the evaluation unit applies visually stimulating evaluation criteria. This allows for more appropriate evaluation by adjusting the evaluation criteria according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the evaluation criteria.

[0085] The evaluation unit can improve the accuracy of the evaluation by considering the interrelationships of the generated answers during the evaluation. The evaluation unit, for example, analyzes the interrelationships of the answers of each generation AI and improves the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion by considering the interrelationships of the generated answers. The evaluation unit, for example, improves the accuracy of the evaluation based on the interrelationships of the answers of each generation AI. As a result, the accuracy of the evaluation is improved by considering the interrelationships of the generated answers. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the interrelationships of the answers of the generation AI to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation.

[0086] The evaluation unit can perform the evaluation while taking into consideration the attribute information of the answer submitter. The evaluation unit performs the evaluation while taking into consideration, for example, the specialized knowledge of the answer submitter. The evaluation unit performs the evaluation based on, for example, the past evaluation history of the answer submitter. The evaluation unit analyzes, for example, the attribute information of the answer submitter and applies optimal evaluation criteria. In this way, a more appropriate evaluation can be performed by taking into consideration the attribute information of the answer submitter. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the attribute information of the answer submitter to the generation AI and cause the generation AI to perform the evaluation.

[0087] The evaluation unit can estimate the user's emotion and adjust the display order of the evaluation results based on the estimated user's emotion. For example, when the user is relaxed, the evaluation unit preferentially displays detailed evaluation results. For example, when the user is in a hurry, the evaluation unit preferentially displays brief evaluation results. For example, when the user is excited, the evaluation unit preferentially displays visually stimulating evaluation results. In this way, by adjusting the display order of the evaluation results according to the user's emotion, a more appropriate evaluation result can be provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of the evaluation results.

[0088] The evaluation unit can perform the evaluation while taking into account the geographic distribution of the answers. The evaluation unit, for example, analyzes the geographic distribution of the answers to improve the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion while taking into account the geographic distribution of the answers. The evaluation unit, for example, improves the accuracy of the evaluation based on the geographic distribution of the answers. Thereby, the accuracy of the evaluation is improved by taking into account the geographic distribution of the answers. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the geographic distribution of the answers to the generation AI and cause the generation AI to perform the evaluation.

[0089] The evaluation unit can improve the accuracy of the evaluation by referring to the relevant literature of the answer at the time of evaluation. The evaluation unit, for example, refers to the relevant literature of the answer and improves the accuracy of the evaluation. The evaluation unit, for example, applies an optimal evaluation criterion based on the relevant literature of the answer. The evaluation unit, for example, analyzes the relevant literature of the answer and improves the accuracy of the evaluation. As a result, the accuracy of the evaluation is improved by referring to the relevant literature of the answer. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the evaluation unit can input the relevant literature of the answer to the generation AI and cause the generation AI to execute the evaluation.

[0090] The providing unit can estimate the user's emotion and adjust the expression method of the answer to be provided based on the estimated user's emotion. For example, when the user is relaxed, the providing unit provides a detailed answer. For example, when the user is in a hurry, the providing unit provides a concise answer. For example, when the user is excited, the providing unit provides a visually stimulating answer. This allows a more appropriate answer to be provided by adjusting the expression method of the answer according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the answer.

[0091] The providing unit can select the optimal answer by referring to the user's past question history at the time of providing. The providing unit selects the optimal answer based on, for example, the user's past question history. The providing unit preferentially provides, for example, highly relevant answers from the user's past question history. The providing unit, for example, analyzes the user's past question history and selects the most appropriate answer. In this way, the optimal answer can be selected by referring to the user's past question history. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's past question history to the generation AI and cause the generation AI to select the optimal answer.

[0092] The providing unit can customize the answer content based on the user's current field of interest at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's current field of interest. The providing unit, for example, analyzes the user's field of interest and customizes optimal answer content. The providing unit adjusts the answer content according to, for example, the user's current field of interest. In this way, by customizing the answer content based on the user's current field of interest, a more relevant answer can be provided. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's field of interest to the generation AI and cause the generation AI to customize the answer content.

[0093] The providing unit can estimate the user's emotion and determine the priority of answers to be provided based on the estimated user's emotion. For example, when the user is relaxed, the providing unit preferentially provides detailed answers. For example, when the user is in a hurry, the providing unit preferentially provides concise answers. For example, when the user is excited, the providing unit preferentially provides visually stimulating answers. This allows more appropriate answers to be provided by determining the priority of answers according to the user's emotion. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of answers.

[0094] The providing unit can select an optimal answer by considering the geographical location information of the user at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's current location. The providing unit, for example, analyzes the geographical location information of the user and selects an optimal answer. The providing unit, for example, adjusts the answer content according to the geographical location information of the user. In this way, the optimal answer can be provided by considering the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the geographical location information of the user to the generation AI and cause the generation AI to select an optimal answer.

[0095] The providing unit can analyze the user's social media activity and suggest the answer content at the time of providing. The providing unit provides a highly relevant answer based on, for example, the user's social media activity content. The providing unit analyzes, for example, the user's topics of interest on social media and suggests the optimal answer content. The providing unit suggests a highly relevant answer based on, for example, the user's social media activity history. In this way, a highly relevant answer can be provided by analyzing the user's social media activity. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the providing unit can input the user's social media activity to the generation AI and cause the generation AI to execute the suggestion of the answer content.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] The reception unit can analyze the user's input in real time and estimate the intent of the question. For example, if the user inputs an ambiguous question, the reception unit can estimate the intent of the question and convert it into a more specific question. Also, if the user inputs multiple questions at once, the reception unit can split those questions and process them separately. Furthermore, the reception unit can take into account the context in which the user inputs the question and provide additional related information. This makes the user's question clearer and improves the accuracy of the answer provided by the generation unit.

[0098] The multiple generation units can refer to the user's past question history and generate a new answer based on the past answers. For example, if the user has previously asked a similar question, the new answer can be generated by referring to the answer. In addition, a specific pattern can be found from the user's past question history and an answer can be generated based on the pattern. Furthermore, the user's past question history can be analyzed and information related to the user's field of interest can be provided preferentially. In this way, by utilizing the user's past question history, a more personalized answer can be provided.

[0099] The evaluation unit can refer to external reliable data sources to evaluate the reliability of the generated answers. For example, for scientific questions, reliable academic papers and databases can be referenced to confirm the accuracy of the generated answers. For social questions, government agencies and public statistical data can be referenced to evaluate the reliability of the answers. Furthermore, the evaluation unit can also periodically update the data sources to check whether the generated answers are based on the latest information. This makes it possible to improve the reliability of the generated answers by utilizing external reliable data sources.

[0100] The evaluation unit can compare answers from different perspectives to evaluate the diversity of the generated answers. For example, it can compare answers generated by different generation AIs to the same question and evaluate whether each answer provides a different perspective. It can also analyze the content of the answer to check whether the generated answer is biased toward a specific bias. In addition, the evaluation unit can collect user feedback and adjust the evaluation criteria based on it to evaluate whether the generated answer meets the diverse needs of users. This allows the diversity of the generated answers to be evaluated, thereby providing more comprehensive and balanced answers.

[0101] The providing unit can collect user feedback and improve the answers to be provided based on the feedback. For example, the providing unit can provide a function for the user to rate the provided answers and improve the quality of the answers based on the ratings. The providing unit can also provide a function for the user to ask additional questions about the provided answers and quickly generate answers to those questions. Furthermore, the providing unit can analyze the user feedback, identify common problems, and take measures to improve them. In this way, the quality of the answers to be provided can be continuously improved by utilizing the user feedback.

[0102] The reception unit can estimate the user's emotions and customize the method of receiving questions based on the estimated user's emotions. For example, when the user is feeling stressed, the reception unit can simplify the reception of questions and provide an interface that allows the user to relax. Also, when the user is relaxed, an interface for receiving detailed questions can be provided. Furthermore, when the user is excited, a visually stimulating interface can be provided to keep the user interested. In this way, a more comfortable user experience can be provided by customizing the method of receiving questions according to the user's emotions.

[0103] The reception unit can analyze the user's past question history and track changes in the user's emotions. For example, it can identify the times when the user felt stressed and the times when he / she was relaxed in the past, and adjust the method of receiving questions based on that information. It can also receive questions at an appropriate time according to changes in the user's emotions. It can also predict changes in the user's emotions and adjust the method of receiving questions in advance based on the predicted emotions. In this way, it is possible to receive questions at a more appropriate time by tracking changes in the user's emotions.

[0104] The reception unit can estimate the user's emotions and adjust the content of the questions to be received based on the estimated user's emotions. For example, when the user is stressed, the reception unit preferentially receives simple and clear questions. When the user is relaxed, detailed questions can be received. Furthermore, when the user is excited, visually stimulating questions can be received. In this way, by adjusting the content of the questions to be received according to the user's emotions, more appropriate questions can be received.

[0105] The reception unit can estimate the user's emotions and adjust the reception format of the questions based on the estimated user's emotions. For example, when the user is stressed, the reception unit preferentially receives questions in text format. When the user is relaxed, questions in audio format can be received. Furthermore, when the user is excited, questions in video format can be received. In this way, by adjusting the reception format of the questions according to the user's emotions, questions can be received in a more appropriate format.

[0106] The reception unit can estimate the user's emotions and adjust the frequency of question reception based on the estimated user's emotions. For example, when the user is stressed, the reception unit can reduce the frequency of question reception to provide the user with time to relax. When the user is relaxed, the reception unit can increase the frequency of question reception to provide quick answers. Furthermore, when the user is excited, the reception unit can adjust the frequency of question reception to keep the user interested. Thus, by adjusting the frequency of question reception according to the user's emotions, questions can be received at a more appropriate time.

[0107] The process flow of the second embodiment will be briefly described below.

[0108] Step 1: The reception unit is a section where the user inputs a question. The user can input a question in text format, voice format, or the like. For example, the user inputs a specific question such as "Please tell me about the effects of climate change." Step 2: The multiple generators individually generate answers to the questions input by the reception unit. Each generator generates answers using its own algorithm and dataset. For example, generator 1 generates answers based on scientific data, and generator 2 generates answers based on social influences. The generators generate answers using generation AI, and include text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The evaluation unit compares and evaluates the answers generated by multiple generation units. For example, if the answer of generation AI1 is scientifically accurate, but the answer of generation AI2 is more user-friendly, these answers are combined to generate the optimal answer. The evaluation unit can also combine the answers of the generation AIs using a weighted average or consensus algorithm. Step 4: The providing unit provides the most appropriate answer selected by the evaluating unit to the user. For example, the answer selected as a discussion result is provided to the user.

[0109] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0110] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0111] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements including the above-mentioned reception unit, generation unit, evaluation unit, and provision unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14, and the user can input a question in text format or voice format. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and each generation AI generates an answer using its own algorithm and data set. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and compares and evaluates the generated answers to generate an optimal answer. The provision unit is realized, for example, by the output device 40 of the smart device 14, and provides the user with the most appropriate answer selected by the evaluation unit. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 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.

[0115] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] 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.

[0117] 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 the voice according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0119] 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 performed in a secure state.

[0120] Fig. 4 shows an example of 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.

[0121] 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.

[0122] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0123] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0124] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0125] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0126] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0127] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements including the above-mentioned reception unit, generation unit, evaluation unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214, and the user can input a question in the form of voice. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and each generation AI generates an answer using its own algorithm and data set. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and compares and evaluates the generated answers to generate an optimal answer. The provision unit is realized, for example, by the speaker 240 of the smart glasses 214, and provides the user with the most appropriate answer selected by the evaluation unit. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 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.

[0131] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] 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.

[0133] 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 the voice according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0135] 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 performed in a secure state.

[0136] 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.

[0137] 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.

[0138] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0139] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0140] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0141] 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 voice indicating a user input for 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.

[0142] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0143] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements including the above-mentioned reception unit, generation unit, evaluation unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset type terminal 314, and the user can input a question in the form of voice. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and each generation AI generates an answer using its own algorithm and data set. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and compares and evaluates the generated answers to generate an optimal answer. The provision unit is realized, for example, by the speaker 240 of the headset type terminal 314, and provides the user with the most appropriate answer selected by the evaluation unit. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] 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.

[0149] 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 the voice according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0151] 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 performed in a secure state.

[0152] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0153] 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.

[0154] 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.

[0155] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0156] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0157] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0158] 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 a voice indicating a user input for 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.

[0159] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0160] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0161] Each of the multiple elements including the above-mentioned reception unit, generation unit, evaluation unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414, and the user can input a question in the form of voice. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and each generation AI generates an answer using its own algorithm and data set. The evaluation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and compares and evaluates the generated answers to generate an optimal answer. The provision unit is realized, for example, by the speaker 240 of the robot 414, and provides the user with the most appropriate answer selected by the evaluation unit. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0162] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0163] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0165] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0167] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0169] 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.

[0170] 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 Universal Serial Bus (USB) 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.

[0171] In addition, 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 upon request from the data processing device 12.

[0172] 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.

[0173] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0174] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0175] As an example of a configuration using one 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 configuration in which a processor is used that realizes the functions of the 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.

[0176] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0178] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0180] (Appendix 1) a reception section for inputting a question; a plurality of generation units each generating an answer to each of the questions input by the reception unit; An evaluation unit that compares and evaluates the answers generated by the multiple generation units; A providing unit that provides the answer selected by the evaluation unit. A system characterized by: (Appendix 2) The plurality of generating units include Generate answers using proprietary algorithms and data sets 2. The system of claim 1, (Appendix 3) The evaluation unit is Compare and evaluate the answers of each AI generator to select the most appropriate answer. 2. The system of claim 1, (Appendix 4) The evaluation unit is Generate answers by integrating answers from generative AI 2. The system of claim 1, (Appendix 5) The providing unit is Providing users with selected answers as a result of discussion 2. The system of claim 1, (Appendix 6) The reception unit is The system estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions. 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past question history and select the optimal method for accepting questions 2. The system of claim 1, (Appendix 8) The reception unit is As questions are submitted, filter them based on the user's current areas of interest 2. The system of claim 1, (Appendix 9) The reception unit is Estimate the user's emotions and prioritize questions to be accepted based on the estimated user emotions. 2. The system of claim 1, (Appendix 10) The reception unit is When accepting questions, the system takes into account the user's geographic location information to prioritize questions that are more relevant to the user. 2. The system of claim 1, (Appendix 11) The reception unit is When a question is submitted, we analyze the user's social media activity and submit related questions. 2. The system of claim 1, (Appendix 12) The plurality of generating units include Infer user sentiment and adjust answer generation method based on the inferred user sentiment 2. The system of claim 1, (Appendix 13) The plurality of generating units include When generating answers, the generation algorithm is selected based on the importance of the question. 2. The system of claim 1, (Appendix 14) The plurality of generating units include When generating answers, different generation algorithms are applied depending on the question category. 2. The system of claim 1, (Appendix 15) The plurality of generating units include Infer the user's emotions and adjust the length of the answer based on the estimated user emotions 2. The system of claim 1, (Appendix 16) The plurality of generating units include When generating answers, prioritize generation algorithms based on when a question was submitted 2. The system of claim 1, (Appendix 17) The plurality of generating units include When generating answers, adjust the order of generation algorithms based on the relevance of the question 2. The system of claim 1, (Appendix 18) The evaluation unit is Inferring a user's emotion and adjusting the evaluation criteria based on the estimated user's emotion 2. The system of claim 1, (Appendix 19) The evaluation unit is During evaluation, correlations between generated answers are considered to improve the accuracy of the evaluation. 2. The system of claim 1, (Appendix 20) The evaluation unit is When evaluating, the attributes of the person submitting the answer are taken into consideration. 2. The system of claim 1, (Appendix 21) The evaluation unit is Inferring user emotions and adjusting the display order of rating results based on the estimated user emotions 2. The system of claim 1, (Appendix 22) The evaluation unit is The geographical distribution of responses will be taken into account during evaluation. 2. The system of claim 1, (Appendix 23) The evaluation unit is When assessing, refer to relevant literature for answers to improve the accuracy of your assessment 2. The system of claim 1, (Appendix 24) The providing unit is Infer the user's emotions and adjust the way answers are presented based on the inferred user emotions 2. The system of claim 1, (Appendix 25) The providing unit is When providing a question, the most appropriate answer is selected by referring to the user's past question history. 2. The system of claim 1, (Appendix 26) The providing unit is When provided, tailor answers based on the user's current interests 2. The system of claim 1, (Appendix 27) The providing unit is Inferring user sentiment and prioritizing answers to provide based on the estimated user sentiment 2. The system of claim 1, (Appendix 28) The providing unit is When providing a response, the best answer is chosen taking into account the user's geographic location. 2. The system of claim 1, (Appendix 29) The providing unit is At the time of delivery, the system analyzes the user's social media activity to suggest answers. 2. The system of claim 1, [Explanation of symbols]

[0181] 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 reception section for inputting questions; a plurality of generation units that generate answers individually to the questions input by the reception unit; an evaluation unit that compares and evaluates the answers generated by the plurality of generation units; A providing unit that provides the answer selected by the evaluation unit. A system characterized by:

2. The plurality of generating units include Generate answers using proprietary algorithms and data sets 2. The system of claim 1 .

3. The evaluation unit is Compare and evaluate the responses of each AI generator to select the most appropriate response.

2. The system of claim 1 .

4. The evaluation unit is Integrate the answers from the generation AI to generate an answer 2. The system of claim 1 .

5. The providing unit is Providing users with selected answers as a result of discussion 2. The system of claim 1 .

6. The reception unit is The system estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions.

2. The system of claim 1 .

7. The reception unit is Analyze the user's past question history and select the optimal method for accepting questions 2. The system of claim 1 .

8. The reception unit is When questions are submitted, filter them based on the user's current areas of interest 2. The system of claim 1 .

Images