system

Abstract

The system according to the embodiment aims to quickly provide answers to user questions. [Solution] A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives a user's question. The analysis unit analyzes the question received by the reception unit. The generation unit generates an answer based on the result of the analysis by the analysis unit. The provision unit provides the answer generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have difficulty in quickly providing answers to user questions, and there is room for improvement.

[0005] The system according to the embodiment aims to quickly provide answers to user questions. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives a user's question. The analysis unit analyzes the question received by the reception unit. The generation unit generates an answer based on the analysis result by the analysis unit. The provision unit provides the answer generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly provide answers to users' questions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A question-answering system according to an embodiment of the present invention utilizes a generation AI to provide rapid answers to questions about KOALA posts. This system accepts user questions, analyzes them, and generates and provides appropriate answers. While conventional tools require manual intervention, the present invention utilizes a generation AI to automatically generate and provide answers to user questions. This allows users to quickly resolve their issues and improves efficiency. For example, if a user asks, "I don't know how to post on KOALA," the generation AI analyzes the question and generates an answer explaining the specific posting procedure. The user can then use the answer as a reference when posting on KOALA. This mechanism allows users to quickly resolve their issues and makes KOALA posts more convenient. Furthermore, utilizing a generation AI maintains consistent response quality and improves user satisfaction. This allows the question-answering system to quickly and automatically provide answers to user questions.

[0029] A question-answering system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives a user's question. The user's question may be, for example, in text format, audio format, or on a specific topic, but is not limited to these examples. The reception unit may, for example, receive a text-format question through a chatbot. The reception unit may also receive audio-format questions using speech recognition technology. For example, the reception unit may input a user's question through a microphone and convert the input into text using speech recognition technology. The reception unit may also filter questions on a specific topic and send them to an appropriate analysis unit. The analysis unit may use a generation AI to analyze the question received by the reception unit. The analysis may be performed using, for example, natural language processing technology, keyword extraction, grammar analysis, or other methods, but is not limited to these examples. For example, the analysis unit may use natural language processing technology to analyze the intent of the question and refer to a database or knowledge base to generate an appropriate answer. The analysis unit may also use keyword extraction technology to identify important parts of the question and perform analysis. Furthermore, the analysis unit can analyze the structure of the question using grammar analysis technology and extract information for generating an appropriate answer. The generation unit uses a generation AI to generate an answer based on the results of the analysis by the analysis unit. Generation is performed using, for example, models such as GPT-4 (registered trademark) and Gemini, but is not limited to these examples. For example, the generation unit generates a detailed answer to a question using GPT-4. The generation unit can also generate a concise answer to a question using Gemini. Furthermore, the generation unit can use a generation AI to generate an appropriate answer according to the context of the question. The provision unit provides the answer generated by the generation unit to the user. The provision can be performed in, for example, text format, audio format, image format, or the like, but is not limited to these examples. For example, the provision unit provides a text-format answer to the user through a chatbot. The provision unit can also provide an audio-format answer to the user using speech synthesis technology. Furthermore, the provision unit can provide an image-format answer to the user. This allows the question-answering system according to the embodiment to quickly and automatically provide answers to user questions.

[0030] The analysis unit can analyze the user's question using natural language processing technology and refer to a database or knowledge base. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit can use morphological analysis to divide the question into words and analyze the meaning of each word. The analysis unit can also use grammatical analysis to analyze the structure of the question sentence and understand the meaning of the sentence. Furthermore, the analysis unit can use semantic analysis to analyze the intent of the question and extract information for generating an appropriate answer. Databases or knowledge bases include, but are not limited to, FAQ databases, expert knowledge bases, etc. For example, the analysis unit can refer to an FAQ database to search for answers to similar questions in the past. The analysis unit can also refer to expert knowledge bases to obtain information for generating answers to specialized questions. This improves the accuracy of question analysis using natural language processing technology.

[0031] The generation unit can generate answers using a generative AI. Examples of generative AI include, but are not limited to, models such as GPT-4 and Gemini. The generation unit can generate detailed answers to questions using, for example, GPT-4. GPT-4 has trained on large amounts of text data and has advanced natural language processing capabilities. The generation unit can also generate concise answers to questions using Gemini. Gemini is a bidirectional Transformer model with excellent context understanding capabilities. Furthermore, the generation unit can use the generative AI to generate appropriate answers based on the context of the question. For example, the generation unit understands the context of the question and generates an answer based on that context. As a result, using the generative AI improves the accuracy of answer generation.

[0032] The providing unit can provide the generated answer to the user. The providing unit provides the answer in a method such as a text format, an audio format, or an image format. The text format answer is provided to the user, for example, through a chatbot. The audio format answer is provided to the user, for example, using a voice synthesis technology. The image format answer is provided to the user, for example, using an image generation technology. This allows the generated answer to be provided to the user quickly.

[0033] The reception unit can analyze the user's past question history and select an appropriate reception method. The reception unit analyzes, for example, the content, frequency, and quality of answers of past questions. The question history includes, for example, the content, frequency, and quality of answers of questions asked by the user in the past. The reception unit, for example, automatically recognizes the content of questions frequently asked by the user in the past and preferentially receives related questions. The reception unit can also preferentially suggest question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the question format to be used during a specific time period based on the user's past question history. The reception method can include, for example, chatbot, telephone, email, etc. In this way, the optimal reception method can be selected by analyzing the user's past question history.

[0034] The reception unit can filter questions based on the user's current areas of interest when receiving the question. The reception unit identifies the user's areas of interest using, for example, past question content, browsing history, survey results, etc. The areas of interest include, for example, topics or themes in which the user is currently interested. The reception unit, for example, preferentially receives questions related to topics in which the user is currently interested. The reception unit can also automatically filter and receive related questions based on the user's areas of interest. Furthermore, the reception unit can analyze the user's current areas of interest and preferentially receive related questions. Filtering methods include, for example, keyword matching and category classification. As a result, questions can be filtered based on the user's current areas of interest, allowing highly relevant questions to be preferentially received.

[0035] When accepting a question, the accepting unit can prioritize highly relevant questions by taking into account the user's geographical location information. The accepting unit acquires the user's geographical location information using, for example, GPS data, an IP address, etc. The geographical location information includes, for example, the user's current location and past location information. For example, if the user is in a specific area, the accepting unit prioritizes accepting questions related to that area. The accepting unit can also automatically filter and accept related questions based on the user's geographical location information. Furthermore, the accepting unit can prioritize highly relevant questions based on the user's current location. Highly relevant questions include, for example, geographical relevance and topic matching. This allows more appropriate questions to be accepted by preferentially accepting highly relevant questions based on the user's geographical location information.

[0036] When receiving a question, the reception unit can analyze the user's social media activity and receive related questions. The reception unit analyzes, for example, the user's posted content, the number of likes, the number of followers, etc. Social media activity includes, for example, posts and responses made by the user on social media. The reception unit, for example, analyzes the user's social media activity and preferentially receives related questions. The reception unit can also receive questions related to topics in which the user is interested on social media. Furthermore, the reception unit can automatically filter and receive related questions based on the user's social media activity. In this way, by analyzing the user's social media activity, related questions can be preferentially received.

[0037] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. The analysis unit evaluates the importance of the question using, for example, a user specification, past data, urgency, etc. The importance includes, for example, the importance specified by the user, the importance based on past data, and the urgency of the question. The analysis unit, for example, performs a detailed analysis for questions with high importance. The analysis unit can also perform a concise analysis for questions with low importance. Furthermore, the analysis unit can automatically adjust the level of detail of the analysis according to the importance of the question. The level of detail includes, for example, a concise summary, a detailed explanation, etc. In this way, by adjusting the level of detail of the analysis based on the importance of the question, more appropriate analysis results can be provided.

[0038] During analysis, the analysis unit can apply an appropriate analysis algorithm depending on the question category. The analysis unit selects an analysis algorithm based on the category, such as a technical question or a business question. Categories include, for example, technical questions, business questions, and general questions. The analysis unit applies a specialized analysis algorithm to technical questions. The analysis unit can also apply a simple analysis algorithm to general questions. Furthermore, the analysis unit can automatically select the optimal analysis algorithm depending on the question category. Analysis algorithms include, for example, machine learning algorithms and rule-based algorithms. In this way, analysis accuracy is improved by applying the optimal analysis algorithm depending on the question category.

[0039] During analysis, the analysis unit can determine the priority of analysis based on the time when the question was submitted. The analysis unit evaluates the time when the question was submitted using, for example, the submission date and time, the elapsed time since submission, etc. The submission date and time include, for example, the date and time when the question was submitted and the elapsed time since submission. The analysis unit sets the priority of analysis based on, for example, the time when the question was submitted. Furthermore, the analysis unit can set a low priority if the question was submitted earlier. Furthermore, the analysis unit can set a high priority if the question was submitted more recently. The priority includes, for example, urgency, importance, submission time, etc. In this way, by determining the priority of analysis based on the time when the question was submitted, it is possible to perform the analysis in a more appropriate order.

[0040] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the questions. The analysis unit evaluates the relevance of the questions using, for example, topic matching, past question content, etc. Relevance includes, for example, the degree of topic matching of the question and relevance to past question content. For example, the analysis unit prioritizes analysis when the question is highly relevant. Furthermore, the analysis unit can postpone analysis when the question is low in relevance. Furthermore, the analysis unit can automatically adjust the order of analysis based on the relevance of the questions. The order includes, for example, order of relevance, order of submission, etc. In this way, by adjusting the order of analysis based on the relevance of the questions, analysis can be performed in a more appropriate order.

[0041] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating the answer. The generation unit evaluates the importance of the question using, for example, a user specification, past data, urgency, etc. The importance includes, for example, the importance specified by the user, the importance based on past data, and the urgency of the question. The generation unit generates, for example, a detailed answer for a question with a high importance. The generation unit can also generate a concise answer for a question with a low importance. Furthermore, the generation unit can automatically adjust the level of detail of the answer depending on the importance of the question. The level of detail includes, for example, a concise summary, a detailed explanation, etc. In this way, by adjusting the level of detail of the answer based on the importance of the question, a more appropriate answer can be provided.

[0042] The generation unit can apply different generation algorithms depending on the question category during generation. The generation unit selects a generation algorithm based on the category, such as a technical question or a business question. Examples of categories include technical questions, business questions, and general questions. The generation unit applies a specialized generation algorithm to technical questions. The generation unit can also apply a simple generation algorithm to general questions. Furthermore, the generation unit can automatically select an optimal generation algorithm depending on the question category. Examples of generation algorithms include machine learning algorithms and rule-based algorithms. In this way, applying the optimal generation algorithm depending on the question category improves the accuracy of answer generation.

[0043] The generation unit can determine the priority of answers based on the time of submission of the question at the time of generation. The generation unit evaluates the time of submission of the question using, for example, the submission date and time, the elapsed time since submission, etc. The submission date includes, for example, the date and time when the question was submitted and the elapsed time since submission. The generation unit sets the priority of answers based on, for example, the time when the question was submitted. Furthermore, the generation unit can set a low priority if the question was submitted earlier. Furthermore, the generation unit can set a high priority if the question was submitted more recently. The priority includes, for example, urgency, importance, submission time, etc. In this way, by determining the priority of answers based on the time when the question was submitted, answers can be generated in a more appropriate order.

[0044] The generation unit can adjust the order of answers based on the relevance of the question when generating the answers. The generation unit evaluates the relevance of the question using, for example, topic matching, past question content, etc. Relevance includes, for example, the degree of topic matching of the question and relevance to past question content. For example, the generation unit generates an answer preferentially when the relevance of the question is high. Furthermore, the generation unit can postpone generating an answer when the relevance of the question is low. Furthermore, the generation unit can automatically adjust the order of answers based on the relevance of the question. The order includes, for example, order of relevance, order of submission, etc. In this way, by adjusting the order of answers based on the relevance of the question, answers can be generated in a more appropriate order.

[0045] When providing answers, the providing unit can select an appropriate providing method by referring to the user's past question history. The providing unit refers to, for example, the content, frequency, and quality of answers of past questions. The question history includes, for example, the content, frequency, and quality of answers of questions asked by the user in the past. The providing unit, for example, preferentially provides a providing method (text, voice, etc.) that the user has previously preferred. The providing unit can also automatically select an optimal providing method from the user's past question history. Furthermore, the providing unit can also provide related answers based on the user's past question history. The providing method can include, for example, text format, voice format, image format, etc. In this way, the optimal providing method can be selected by referring to the user's past question history.

[0046] The providing unit can select the optimal providing method by taking into consideration the user's geographical location information when providing the answer. The providing unit acquires the user's geographical location information using, for example, GPS data, an IP address, etc. The geographical location information includes, for example, the user's current location and past location information. For example, if the user is in a specific area, the providing unit prioritizes providing information related to that area. The providing unit can also automatically select the optimal providing method based on the user's geographical location information. Furthermore, the providing unit can provide highly relevant information based on the user's current location. The providing method can include, for example, text format, audio format, image format, etc. As a result, by selecting the optimal providing method based on the user's geographical location information, it is possible to provide answers in a more appropriate manner.

[0047] The providing unit can customize the provided content by analyzing the user's social media activity at the time of providing the content. The providing unit analyzes, for example, the user's posted content, the number of likes, the number of followers, etc. Social media activity includes, for example, the user's posts and reactions on social media. The providing unit, for example, analyzes the user's social media activity and provides related information preferentially. The providing unit can also provide information related to topics in which the user is interested on social media. Furthermore, the providing unit can automatically customize and provide related information based on the user's social media activity. The provided content includes, for example, customization based on the user's interests and customization based on past questions. In this way, the provided content can be customized by analyzing the user's social media activity.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] When accepting a user's question, the acceptance unit can obtain the user's device information and provide an optimal interface. For example, if the user is using a smartphone, a mobile-friendly interface can be provided. Also, if the user is using a desktop, an interface that can display more detailed information can be provided. Furthermore, if the user is using a voice assistant, an interface optimized for voice input can be provided. This improves the user experience by providing an optimal interface according to the user's device.

[0050] When analyzing a user's question, the analysis unit can also take into account background information about the question. For example, if the user has asked a similar question in the past, the analysis unit can refer to that history to perform a more accurate analysis. Also, if the user is asking a question about a specific industry or field, the analysis unit can refer to a database specialized for that industry or field. Furthermore, if the user is asking a question about a specific event or situation, the analysis unit can obtain the latest information related to that event or situation and reflect it in the analysis. By taking into account background information about the question, more appropriate analysis results can be provided.

[0051] The generator can also customize the answers it generates based on the user's learning style. For example, if the user is a visual learner, it can generate answers using diagrams and graphs. If the user is an auditory learner, it can generate answers in audio format. Furthermore, if the user is a hands-on learner, it can generate answers that include specific steps and examples. This allows for customization according to the user's learning style, thereby providing more effective answers.

[0052] When providing the generated answer, the providing unit can select the optimal method taking into account the user's network environment. For example, if the user is in a slow network environment, the providing unit can provide a text-format answer preferentially. If the user is in a high-speed network environment, the providing unit can provide rich content including images and videos. Furthermore, if the user is in an offline environment, the providing unit can provide the answer in a format that can be downloaded in advance. This improves the user experience by providing the answer in the optimal method according to the user's network environment.

[0053] The reception unit can also analyze the user's past question history, predict the user's question patterns, and prepare related information in advance. For example, if a user frequently asks questions about a specific topic, information related to that topic can be collected in advance. Also, if a user tends to ask questions during a specific time of day, resources can be prepared to respond to those times. Furthermore, if a user often asks questions in a specific format (text, voice, etc.), an interface optimized for that format can be provided. This makes it possible to predict the user's question patterns and prepare in advance, enabling quick and appropriate responses.

[0054] When accepting questions, the acceptance unit can also determine the priority of the questions taking into account the user's current activity status. For example, if the user is at work, work-related questions can be accepted with priority. Also, if the user is on a break, questions about relaxing topics can be accepted with priority. Furthermore, if the user is on the move, questions that can be answered in a short time can be accepted with priority. This allows for more appropriate responses by determining the priority of questions according to the user's current activity status.

[0055] When accepting questions, the acceptance unit can prioritize accepting highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, questions related to that area can be accepted with priority. Also, if the user is traveling, questions related to the trip can be accepted with priority. Furthermore, if the user is participating in a specific event, questions related to the event can be accepted with priority. In this way, by preferentially accepting highly relevant questions based on the user's geographical location information, more appropriate questions can be accepted.

[0056] When accepting a question, the acceptance unit can analyze the user's social media activity and accept related questions. For example, if the user shows interest in a specific topic on social media, questions related to that topic can be accepted with priority. It can also accept questions related to posts that the user has received many responses to on social media. It can also accept questions related to accounts that the user follows on social media. By analyzing the user's social media activity, it is possible to accept related questions with priority.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The reception unit receives user questions. User questions can be in text format, voice format, or questions about specific topics. For example, text format questions can be received through a chatbot, and voice format questions can be received using voice recognition technology. Furthermore, questions about specific topics can be filtered and sent to the appropriate analysis unit. Step 2: The analysis unit analyzes the question received by the reception unit. The analysis is performed using methods such as natural language processing technology, keyword extraction, and grammatical analysis. For example, natural language processing technology is used to analyze the intent of the question and to refer to a database or knowledge base. Keyword extraction technology can also be used to identify important parts of the question, and grammatical analysis technology can be used to analyze the structure of the question. Step 3: The generator generates an answer based on the results of the analysis by the analyzer. Generation is performed using generative AI models such as GPT-4 and Gemini. For example, detailed answers can be generated using GPT-4, and concise answers can be generated using Gemini. Furthermore, appropriate answers can be generated based on the context of the question. Step 4: The providing unit provides the answer generated by the generating unit to the user. The answer may be provided in text format, audio format, image format, or other format. For example, a text format answer may be provided through a chatbot, and an audio format answer may be provided using speech synthesis technology. Additionally, an image format answer may also be provided.

[0059] (Example 2) A question-answering system according to an embodiment of the present invention utilizes a generation AI to provide rapid answers to questions about KOALA posts. This system accepts user questions, analyzes them, and generates and provides appropriate answers. While conventional tools require manual intervention, the present invention utilizes a generation AI to automatically generate and provide answers to user questions. This allows users to quickly resolve their issues and improves efficiency. For example, if a user asks, "I don't know how to post on KOALA," the generation AI analyzes the question and generates an answer explaining the specific posting procedure. The user can then use the answer as a reference when posting on KOALA. This mechanism allows users to quickly resolve their issues and makes KOALA posts more convenient. Furthermore, utilizing a generation AI maintains consistent response quality and improves user satisfaction. This allows the question-answering system to quickly and automatically provide answers to user questions.

[0060] A question-answering system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives a user's question. The user's question may be, for example, in text format, audio format, or on a specific topic, but is not limited to these examples. The reception unit may, for example, receive a text-format question through a chatbot. The reception unit may also receive audio-format questions using speech recognition technology. For example, the reception unit may input a user's question through a microphone and convert the input into text using speech recognition technology. The reception unit may also filter questions on a specific topic and send them to an appropriate analysis unit. The analysis unit may use a generation AI to analyze the question received by the reception unit. The analysis may be performed using, for example, natural language processing technology, keyword extraction, grammar analysis, or other methods, but is not limited to these examples. For example, the analysis unit may use natural language processing technology to analyze the intent of the question and refer to a database or knowledge base to generate an appropriate answer. The analysis unit may also use keyword extraction technology to identify important parts of the question and perform analysis. Furthermore, the analysis unit can analyze the structure of the question using grammar analysis technology and extract information for generating an appropriate answer. The generation unit uses a generation AI to generate an answer based on the results of the analysis by the analysis unit. Generation is performed using, for example, models such as GPT-4 and Gemini, but is not limited to these examples. For example, the generation unit generates a detailed answer to a question using GPT-4. The generation unit can also generate a concise answer to a question using Gemini. Furthermore, the generation unit can use a generation AI to generate an appropriate answer according to the context of the question. The provision unit provides the answer generated by the generation unit to the user. The provision is performed in, for example, text format, audio format, image format, or the like, but is not limited to these examples. For example, the provision unit provides a text-format answer to the user through a chatbot. The provision unit can also provide an audio-format answer to the user using speech synthesis technology. Furthermore, the provision unit can provide an image-format answer to the user. This allows the question-answering system according to the embodiment to quickly and automatically provide answers to user questions.

[0061] The analysis unit can analyze the user's question using natural language processing technology and refer to a database or knowledge base. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit can use morphological analysis to divide the question into words and analyze the meaning of each word. The analysis unit can also use grammatical analysis to analyze the structure of the question sentence and understand the meaning of the sentence. Furthermore, the analysis unit can use semantic analysis to analyze the intent of the question and extract information for generating an appropriate answer. Databases or knowledge bases include, but are not limited to, FAQ databases, expert knowledge bases, etc. For example, the analysis unit can refer to an FAQ database to search for answers to similar questions in the past. The analysis unit can also refer to expert knowledge bases to obtain information for generating answers to specialized questions. This improves the accuracy of question analysis using natural language processing technology.

[0062] The generation unit can generate answers using a generative AI. Examples of generative AI include, but are not limited to, models such as GPT-4 and Gemini. The generation unit can generate detailed answers to questions using, for example, GPT-4. GPT-4 has trained on large amounts of text data and has advanced natural language processing capabilities. The generation unit can also generate concise answers to questions using Gemini. Gemini is a bidirectional Transformer model with excellent context understanding capabilities. Furthermore, the generation unit can use the generative AI to generate appropriate answers based on the context of the question. For example, the generation unit understands the context of the question and generates an answer based on that context. As a result, using the generative AI improves the accuracy of answer generation.

[0063] The providing unit can provide the generated answer to the user. The providing unit provides the answer in a method such as a text format, an audio format, or an image format. The text format answer is provided to the user, for example, through a chatbot. The audio format answer is provided to the user, for example, using a voice synthesis technology. The image format answer is provided to the user, for example, using an image generation technology. This allows the generated answer to be provided to the user quickly.

[0064] The reception unit can estimate the user's emotions and adjust the timing of question reception based on the estimated user emotions. The reception unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The reception timing is adjusted, for example, in real time or with a fixed delay. For example, if the user is feeling stressed, the question can be received quickly and responded to immediately. Alternatively, if the user is relaxed, the question can be received at a normal pace to collect detailed information. Furthermore, if the user is in a hurry, the question can be received briefly and sent quickly to the analysis unit. In this way, the timing of question reception can be adjusted according to the user's emotions, allowing questions to be received at a more appropriate time.

[0065] The reception unit can analyze the user's past question history and select an appropriate reception method. The reception unit analyzes, for example, the content, frequency, and quality of answers of past questions. The question history includes, for example, the content, frequency, and quality of answers of questions asked by the user in the past. The reception unit, for example, automatically recognizes the content of questions frequently asked by the user in the past and preferentially receives related questions. The reception unit can also preferentially suggest question formats (text, voice, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the question format to be used during a specific time period based on the user's past question history. The reception method can include, for example, chatbot, telephone, email, etc. In this way, the optimal reception method can be selected by analyzing the user's past question history.

[0066] The reception unit can filter questions based on the user's current areas of interest when receiving the question. The reception unit identifies the user's areas of interest using, for example, past question content, browsing history, survey results, etc. The areas of interest include, for example, topics or themes in which the user is currently interested. The reception unit, for example, preferentially receives questions related to topics in which the user is currently interested. The reception unit can also automatically filter and receive related questions based on the user's areas of interest. Furthermore, the reception unit can analyze the user's current areas of interest and preferentially receive related questions. Filtering methods include, for example, keyword matching and category classification. As a result, questions can be filtered based on the user's current areas of interest, allowing highly relevant questions to be preferentially received.

[0067] The reception unit can estimate the user's emotions and determine the priority of questions to be received based on the estimated user's emotions. The reception unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The priority is determined based on criteria such as urgency, importance, and the user's emotions. For example, if the user is feeling stressed, the priority of the question can be set high and the question can be responded to quickly. Alternatively, if the user is relaxed, the priority of the question can be set to normal. Furthermore, if the user is in a hurry, the priority of the question can be set to the highest priority and the question can be responded to immediately. In this way, by determining the priority of questions according to the user's emotions, questions can be received in a more appropriate order.

[0068] When accepting a question, the accepting unit can prioritize highly relevant questions by taking into account the user's geographical location information. The accepting unit acquires the user's geographical location information using, for example, GPS data, an IP address, etc. The geographical location information includes, for example, the user's current location and past location information. For example, if the user is in a specific area, the accepting unit prioritizes accepting questions related to that area. The accepting unit can also automatically filter and accept related questions based on the user's geographical location information. Furthermore, the accepting unit can prioritize highly relevant questions based on the user's current location. Highly relevant questions include, for example, geographical relevance and topic matching. This allows more appropriate questions to be accepted by preferentially accepting highly relevant questions based on the user's geographical location information.

[0069] When receiving a question, the reception unit can analyze the user's social media activity and receive related questions. The reception unit analyzes, for example, the user's posted content, the number of likes, the number of followers, etc. Social media activity includes, for example, posts and responses made by the user on social media. The reception unit, for example, analyzes the user's social media activity and preferentially receives related questions. The reception unit can also receive questions related to topics in which the user is interested on social media. Furthermore, the reception unit can automatically filter and receive related questions based on the user's social media activity. In this way, by analyzing the user's social media activity, related questions can be preferentially received.

[0070] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user's emotions. The analysis unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The presentation method is adjusted based on criteria such as wording, level of detail, and format. For example, if the user is feeling stressed, the analysis result can be provided using a concise and clear presentation method. Also, if the user is relaxed, detailed analysis results can be provided. Furthermore, if the user is in a hurry, analysis results that focus on the main points can be provided. In this way, by adjusting the presentation method of the analysis according to the user's emotions, more appropriate analysis results can be provided.

[0071] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the question. The analysis unit evaluates the importance of the question using, for example, a user specification, past data, urgency, etc. The importance includes, for example, the importance specified by the user, the importance based on past data, and the urgency of the question. The analysis unit, for example, performs a detailed analysis for questions with high importance. The analysis unit can also perform a concise analysis for questions with low importance. Furthermore, the analysis unit can automatically adjust the level of detail of the analysis according to the importance of the question. The level of detail includes, for example, a concise summary, a detailed explanation, etc. In this way, by adjusting the level of detail of the analysis based on the importance of the question, more appropriate analysis results can be provided.

[0072] During analysis, the analysis unit can apply an appropriate analysis algorithm depending on the question category. The analysis unit selects an analysis algorithm based on the category, such as a technical question or a business question. Categories include, for example, technical questions, business questions, and general questions. The analysis unit applies a specialized analysis algorithm to technical questions. The analysis unit can also apply a simple analysis algorithm to general questions. Furthermore, the analysis unit can automatically select the optimal analysis algorithm depending on the question category. Analysis algorithms include, for example, machine learning algorithms and rule-based algorithms. In this way, analysis accuracy is improved by applying the optimal analysis algorithm depending on the question category.

[0073] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The length is adjusted based on criteria such as a short summary or a detailed explanation. For example, if the user is stressed, a short and concise analysis can be provided. Alternatively, if the user is relaxed, a detailed analysis can be provided. Furthermore, if the user is in a hurry, a concise analysis can be provided. In this way, by adjusting the length of the analysis according to the user's emotions, more appropriate analysis results can be provided.

[0074] During analysis, the analysis unit can determine the priority of analysis based on the time when the question was submitted. The analysis unit evaluates the time when the question was submitted using, for example, the submission date and time, the elapsed time since submission, etc. The submission date and time include, for example, the date and time when the question was submitted and the elapsed time since submission. The analysis unit sets the priority of analysis based on, for example, the time when the question was submitted. Furthermore, the analysis unit can set a low priority if the question was submitted earlier. Furthermore, the analysis unit can set a high priority if the question was submitted more recently. The priority includes, for example, urgency, importance, submission time, etc. In this way, by determining the priority of analysis based on the time when the question was submitted, it is possible to perform the analysis in a more appropriate order.

[0075] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the questions. The analysis unit evaluates the relevance of the questions using, for example, topic matching, past question content, etc. Relevance includes, for example, the degree of topic matching of the question and relevance to past question content. For example, the analysis unit prioritizes analysis when the question is highly relevant. Furthermore, the analysis unit can postpone analysis when the question is low in relevance. Furthermore, the analysis unit can automatically adjust the order of analysis based on the relevance of the questions. The order includes, for example, order of relevance, order of submission, etc. In this way, by adjusting the order of analysis based on the relevance of the questions, analysis can be performed in a more appropriate order.

[0076] The generation unit can estimate the user's emotions and adjust the expression style of the generated answer based on the estimated user's emotions. The generation unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The expression style is adjusted based on criteria such as wording, level of detail, and format. For example, if the user is feeling stressed, an answer can be generated using a concise and clear expression style. Also, if the user is relaxed, a detailed answer can be generated. Furthermore, if the user is in a hurry, an answer that gets to the point can be generated. In this way, by adjusting the expression style of the answer according to the user's emotions, a more appropriate answer can be provided.

[0077] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating the answer. The generation unit evaluates the importance of the question using, for example, a user specification, past data, urgency, etc. The importance includes, for example, the importance specified by the user, the importance based on past data, and the urgency of the question. The generation unit generates, for example, a detailed answer for a question with a high importance. The generation unit can also generate a concise answer for a question with a low importance. Furthermore, the generation unit can automatically adjust the level of detail of the answer depending on the importance of the question. The level of detail includes, for example, a concise summary, a detailed explanation, etc. In this way, by adjusting the level of detail of the answer based on the importance of the question, a more appropriate answer can be provided.

[0078] The generation unit can apply different generation algorithms depending on the question category during generation. The generation unit selects a generation algorithm based on the category, such as a technical question or a business question. Examples of categories include technical questions, business questions, and general questions. The generation unit applies a specialized generation algorithm to technical questions. The generation unit can also apply a simple generation algorithm to general questions. Furthermore, the generation unit can automatically select an optimal generation algorithm depending on the question category. Examples of generation algorithms include machine learning algorithms and rule-based algorithms. In this way, applying the optimal generation algorithm depending on the question category improves the accuracy of answer generation.

[0079] The generation unit can estimate the user's emotion and adjust the length of the generated answer based on the estimated user's emotion. The generation unit estimates the user's emotion using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expression captured by a camera to estimate the emotion. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate the emotion. Text analysis technology, for example, analyzes text entered by the user to estimate the emotion. The length is adjusted based on criteria such as a short summary or a detailed explanation. For example, if the user is stressed, a short and to-the-point answer can be generated. Also, if the user is relaxed, a detailed answer can be generated. Furthermore, if the user is in a hurry, a concise answer can be generated. In this way, by adjusting the length of the answer according to the user's emotion, more appropriate answers can be provided.

[0080] The generation unit can determine the priority of answers based on the time of submission of the question at the time of generation. The generation unit evaluates the time of submission of the question using, for example, the submission date and time, the elapsed time since submission, etc. The submission date includes, for example, the date and time when the question was submitted and the elapsed time since submission. The generation unit sets the priority of answers based on, for example, the time when the question was submitted. Furthermore, the generation unit can set a low priority if the question was submitted earlier. Furthermore, the generation unit can set a high priority if the question was submitted more recently. The priority includes, for example, urgency, importance, submission time, etc. In this way, by determining the priority of answers based on the time when the question was submitted, answers can be generated in a more appropriate order.

[0081] The generation unit can adjust the order of answers based on the relevance of the question when generating the answers. The generation unit evaluates the relevance of the question using, for example, topic matching, past question content, etc. Relevance includes, for example, the degree of topic matching of the question and relevance to past question content. For example, the generation unit generates an answer preferentially when the relevance of the question is high. Furthermore, the generation unit can postpone generating an answer when the relevance of the question is low. Furthermore, the generation unit can automatically adjust the order of answers based on the relevance of the question. The order includes, for example, order of relevance, order of submission, etc. In this way, by adjusting the order of answers based on the relevance of the question, answers can be generated in a more appropriate order.

[0082] The providing unit can estimate the user's emotions and adjust the answer providing method based on the estimated user's emotions. The providing unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The answer providing method is adjusted based on criteria such as text format, voice format, and image format. For example, if the user is feeling stressed, the answer can be provided in a concise and clear manner. Alternatively, if the user is relaxed, the answer can be provided in a detailed manner. Furthermore, if the user is in a hurry, the answer can be provided quickly. In this way, by adjusting the answer providing method according to the user's emotions, the answer can be provided in a more appropriate manner.

[0083] When providing answers, the providing unit can select an appropriate providing method by referring to the user's past question history. The providing unit refers to, for example, the content, frequency, and quality of answers of past questions. The question history includes, for example, the content, frequency, and quality of answers of questions asked by the user in the past. The providing unit, for example, preferentially provides a providing method (text, voice, etc.) that the user has previously preferred. The providing unit can also automatically select an optimal providing method from the user's past question history. Furthermore, the providing unit can also provide related answers based on the user's past question history. The providing method can include, for example, text format, voice format, image format, etc. In this way, the optimal providing method can be selected by referring to the user's past question history.

[0084] The providing unit can estimate the user's emotions and determine the order in which answers are provided based on the estimated user's emotions. The providing unit estimates the user's emotions using technologies such as facial expression recognition, voice analysis, and text analysis. Facial expression recognition technology, for example, analyzes the user's facial expressions captured by a camera to estimate emotions. Voice analysis technology, for example, analyzes the tone and speed of the user's voice to estimate emotions. Text analysis technology, for example, analyzes text entered by the user to estimate emotions. The providing order is determined based on criteria such as urgency, importance, and the user's emotions. For example, if the user is feeling stressed, important answers can be provided preferentially. Also, if the user is relaxed, answers can be provided in a normal order. Furthermore, if the user is in a hurry, the most important answers can be provided first. In this way, by determining the order in which answers are provided according to the user's emotions, answers can be provided in a more appropriate order.

[0085] The providing unit can select the optimal providing method by taking into consideration the user's geographical location information when providing the answer. The providing unit acquires the user's geographical location information using, for example, GPS data, an IP address, etc. The geographical location information includes, for example, the user's current location and past location information. For example, if the user is in a specific area, the providing unit prioritizes providing information related to that area. The providing unit can also automatically select the optimal providing method based on the user's geographical location information. Furthermore, the providing unit can provide highly relevant information based on the user's current location. The providing method can include, for example, text format, audio format, image format, etc. As a result, by selecting the optimal providing method based on the user's geographical location information, it is possible to provide answers in a more appropriate manner.

[0086] The providing unit can customize the provided content by analyzing the user's social media activity at the time of providing the content. The providing unit analyzes, for example, the user's posted content, the number of likes, the number of followers, etc. Social media activity includes, for example, the user's posts and reactions on social media. The providing unit, for example, analyzes the user's social media activity and provides related information preferentially. The providing unit can also provide information related to topics in which the user is interested on social media. Furthermore, the providing unit can automatically customize and provide related information based on the user's social media activity. The provided content includes, for example, customization based on the user's interests and customization based on past questions. In this way, the provided content can be customized by analyzing the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation 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 receives a user's question using the reception device 38 of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer based on the analysis result. The provision unit provides the generated answer to the user using the output device 40 of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation 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 receives a user's question using the microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer based on the analysis result. The provision unit provides the generated answer to the user using the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation 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 receives a user's question using the microphone 238 of the headset type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer based on the analysis result. The provision unit provides the generated answer to the user using the speaker 240 of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation 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 receives a user's question using the microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the question using a generation AI. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an answer based on the analysis result. The provision unit provides the generated answer to the user using the speaker 240 of the robot 414.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] When accepting a user's question, the acceptance unit can obtain the user's device information and provide an optimal interface. For example, if the user is using a smartphone, a mobile-friendly interface can be provided. Also, if the user is using a desktop, an interface that can display more detailed information can be provided. Furthermore, if the user is using a voice assistant, an interface optimized for voice input can be provided. This improves the user experience by providing an optimal interface according to the user's device.

[0089] When analyzing a user's question, the analysis unit can also take into account background information about the question. For example, if the user has asked a similar question in the past, the analysis unit can refer to that history to perform a more accurate analysis. Also, if the user is asking a question about a specific industry or field, the analysis unit can refer to a database specialized for that industry or field. Furthermore, if the user is asking a question about a specific event or situation, the analysis unit can obtain the latest information related to that event or situation and reflect it in the analysis. By taking into account background information about the question, more appropriate analysis results can be provided.

[0090] The generator can also customize the answers it generates based on the user's learning style. For example, if the user is a visual learner, it can generate answers using diagrams and graphs. If the user is an auditory learner, it can generate answers in audio format. Furthermore, if the user is a hands-on learner, it can generate answers that include specific steps and examples. This allows for customization according to the user's learning style, thereby providing more effective answers.

[0091] When providing the generated answer, the providing unit can select the optimal method taking into account the user's network environment. For example, if the user is in a slow network environment, the providing unit can provide a text-format answer preferentially. If the user is in a high-speed network environment, the providing unit can provide rich content including images and videos. Furthermore, if the user is in an offline environment, the providing unit can provide the answer in a format that can be downloaded in advance. This improves the user experience by providing the answer in the optimal method according to the user's network environment.

[0092] The reception unit can also estimate the user's emotions and adjust the way questions are received based on the estimated user emotions. For example, if the user is feeling anxious, the reception unit can receive questions in a gentle tone. If the user is excited, the reception unit can receive questions in a quick and concise manner. Furthermore, if the user is tired, the reception unit can provide a simple and intuitive interface. This allows the user to have a more comfortable question reception experience by providing a reception method that suits the user's emotions.

[0093] The reception unit can also analyze the user's past question history, predict the user's question patterns, and prepare related information in advance. For example, if a user frequently asks questions about a specific topic, information related to that topic can be collected in advance. Also, if a user tends to ask questions during a specific time of day, resources can be prepared to respond to those times. Furthermore, if a user often asks questions in a specific format (text, voice, etc.), an interface optimized for that format can be provided. This makes it possible to predict the user's question patterns and prepare in advance, enabling quick and appropriate responses.

[0094] When accepting questions, the acceptance unit can also determine the priority of the questions taking into account the user's current activity status. For example, if the user is at work, work-related questions can be accepted with priority. Also, if the user is on a break, questions about relaxing topics can be accepted with priority. Furthermore, if the user is on the move, questions that can be answered in a short time can be accepted with priority. This allows for more appropriate responses by determining the priority of questions according to the user's current activity status.

[0095] The reception unit can also estimate the user's emotions and adjust the timing of question reception based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can quickly receive questions and respond immediately. Alternatively, if the user is relaxed, the reception unit can receive questions at a normal pace and collect detailed information. Furthermore, if the user is in a hurry, the reception unit can receive simple questions and send them quickly to the analysis unit. In this way, by adjusting the timing of question reception according to the user's emotions, questions can be received at a more appropriate time.

[0096] When accepting questions, the acceptance unit can prioritize accepting highly relevant questions by taking into account the user's geographical location information. For example, if the user is in a specific area, questions related to that area can be accepted with priority. Also, if the user is traveling, questions related to the trip can be accepted with priority. Furthermore, if the user is participating in a specific event, questions related to the event can be accepted with priority. In this way, by preferentially accepting highly relevant questions based on the user's geographical location information, more appropriate questions can be accepted.

[0097] When accepting a question, the acceptance unit can analyze the user's social media activity and accept related questions. For example, if the user shows interest in a specific topic on social media, questions related to that topic can be accepted with priority. It can also accept questions related to posts that the user has received many responses to on social media. It can also accept questions related to accounts that the user follows on social media. By analyzing the user's social media activity, it is possible to accept related questions with priority.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The reception unit receives user questions. User questions can be in text format, voice format, or questions about specific topics. For example, text format questions can be received through a chatbot, and voice format questions can be received using voice recognition technology. Furthermore, questions about specific topics can be filtered and sent to the appropriate analysis unit. Step 2: The analysis unit analyzes the question received by the reception unit. The analysis is performed using methods such as natural language processing technology, keyword extraction, and grammatical analysis. For example, natural language processing technology is used to analyze the intent of the question and to refer to a database or knowledge base. Keyword extraction technology can also be used to identify important parts of the question, and grammatical analysis technology can be used to analyze the structure of the question. Step 3: The generator generates an answer based on the results of the analysis by the analyzer. Generation is performed using generative AI models such as GPT-4 and Gemini. For example, detailed answers can be generated using GPT-4, and concise answers can be generated using Gemini. Furthermore, appropriate answers can be generated based on the context of the question. Step 4: The providing unit provides the answer generated by the generating unit to the user. The answer may be provided in text format, audio format, image format, or other format. For example, a text format answer may be provided through a chatbot, and an audio format answer may be provided using speech synthesis technology. Additionally, an image format answer may also be provided.

[0100] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0102] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 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.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] 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.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] 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.

[0113] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] 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.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0127] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0128] 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.

[0129] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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.

[0131] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0134] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] 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.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] 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.

[0145] 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.

[0146] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] 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.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0163] 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.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0171] [Explanation of symbols]

[0172] 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 unit that receives questions from users; an analysis unit that analyzes the question received by the reception unit; a generation unit that generates an answer based on the result of the analysis by the analysis unit; a providing unit that provides the answer generated by the generating unit; Equipped with A system characterized by:

2. The analysis unit Use natural language processing technology to analyze the user's question and refer to a database or knowledge base 2. The system of claim 1.

3. The generation unit Generate answers using generative AI.

2. The system of claim 1.

4. The providing unit Provide the generated response to the user.

2. The system of claim 1.

5. The reception unit Estimates the user's emotions and adjusts the timing of accepting questions based on the estimated user emotions.

2. The system of claim 1.

6. The reception unit Analyze the user's past question history and select the appropriate reception method 2. The system of claim 1.

7. The reception unit When questions are asked, they are filtered based on the user's current interests.

2. The system of claim 1.

8. The reception unit Estimate the user's emotions and prioritize the questions to be accepted based on the estimated user emotions.

2. The system of claim 1.

Images