system

Abstract

The system according to the embodiment aims to generate and read out appropriate answers to questions from journalists in real time. [Solution] A system according to an embodiment includes a speech recognition unit, an analysis unit, a generation unit, and a reading unit. The speech recognition unit recognizes the speech of a reporter's question. The analysis unit analyzes the question recognized by the speech recognition unit. The generation unit generates an appropriate answer based on the question analyzed by the analysis unit. The reading unit reads out 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] With conventional technology, it was necessary to prepare a list of anticipated questions and answers in advance in response to reporters' questions, which made it difficult to respond in real time.

[0005] The system according to the embodiment aims to generate and read out appropriate answers to questions from journalists in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, an analysis unit, a generation unit, and a reading unit. The speech recognition unit performs speech recognition of questions from reporters. The analysis unit analyzes the questions recognized by the speech recognition unit. The generation unit generates appropriate answers based on the questions analyzed by the analysis unit. The reading unit reads out the answers generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can generate and read out appropriate answers to reporters' questions in real time. [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) An apology press conference support system according to an embodiment of the present invention does not prepare a list of anticipated questions and answers in advance. Instead, it recognizes or transcribes reporters' questions in real time, and AI generates and reads out optimal answers. This apology press conference support system recognizes or transcribes reporters' questions, analyzes the questions, and generates and reads out optimal answers. This eliminates the need to prepare a list of anticipated questions and answers in advance, and allows for quick and appropriate responses to unexpected questions. For example, if a reporter asks, "What are your thoughts on this scandal?", the question is transcribed by a voice recognition system. This transcribed question is then input into an AI. The AI ​​then analyzes the input question. The AI ​​understands the content of the question and generates an optimal answer. For example, in response to the question, "What are your thoughts on this scandal?", the AI ​​generates an answer such as, "We deeply regret this scandal and are taking specific measures to prevent it from recurring." The generated answer is then read out. For example, a speech synthesis system can read out the answer generated by the AI, allowing the person presenting the answer to announce it. In this way, reporters' questions can be responded to quickly and appropriately without having to prepare a list of anticipated questions and answers in advance. This system makes apology press conferences more effective. The press conference attendees can respond quickly to unexpected questions, reducing the risk of the apology press conference being negatively impacted. In addition, since AI generates optimal answers, the burden on the press conference attendees is reduced. For example, if AI learns from data on past apology press conferences and generates optimal answers, the press conference attendees can provide more reliable answers. This allows the apology press conference support system to respond quickly and appropriately to reporters' questions.

[0029] An apology press conference support system according to an embodiment includes a speech recognition unit, an analysis unit, a generation unit, and a reading unit. The speech recognition unit recognizes a reporter's question in speech. For example, the speech recognition unit can recognize the reporter's question in real time and convert it into text data. The speech recognition unit can also use noise canceling technology to improve the accuracy of the speech recognition. For example, the speech recognition unit can remove background noise from the press conference room in real time to improve the accuracy of the speech recognition. The speech recognition unit can also analyze the reporter's speaking speed and accent and apply an optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. The analysis unit analyzes the question recognized by the speech recognition unit. For example, the analysis unit can use AI to understand the content of the question and extract information for generating an optimal answer. The analysis unit can also improve the analysis accuracy by taking into account the context of the question. For example, the analysis unit can accurately analyze the intent of the question by taking into account the context before and after the question. The analysis unit can also include a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences, and the AI ​​learns from it to improve analysis accuracy. The generation unit generates optimal answers based on the questions analyzed by the analysis unit. For example, the generation unit can generate appropriate answers using AI. The generation unit can also adjust the level of detail in the answers based on the importance of the question. For example, the generation unit generates detailed answers for important questions and concise answers for general questions. The generation unit can also estimate the reporter's emotions and adjust the way the answers are expressed based on the estimated reporter's emotions. For example, the generation unit applies a calm and polite way of expression if the reporter is angry. The reading unit reads out the answers generated by the generation unit. For example, the reading unit can provide the generated answers aloud using speech synthesis technology. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit reads out in a calm and composed tone.This allows the apology press conference support system according to the embodiment to respond quickly and appropriately to questions from reporters.

[0030] The speech recognition unit can transcribe the reporter's question. For example, the speech recognition unit recognizes the reporter's question in real time and converts it into text data. For example, the speech recognition unit transcribes the reporter's question using speech recognition technology. The speech recognition unit can also use noise canceling technology to improve the accuracy of speech recognition. For example, the speech recognition unit can remove background noise in a press conference room in real time to improve the accuracy of speech recognition. Furthermore, the speech recognition unit can analyze the reporter's speaking speed and accent and apply the optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. By transcribing the reporter's question, the analysis unit can more accurately analyze the question.

[0031] The analysis unit can understand the content of the question using AI. For example, the analysis unit uses AI to understand the content of the question. For example, the analysis unit analyzes the content of the question using natural language processing technology and extracts information for generating an optimal answer. The analysis unit can also improve the accuracy of the analysis by taking into account the context of the question. For example, the analysis unit accurately analyzes the intent of the question by taking into account the context before and after the question. Furthermore, the analysis unit can be equipped with a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences and has AI learn from it to improve the accuracy of the analysis. As a result, the content of the question can be understood more accurately by using AI.

[0032] The generation unit can generate appropriate answers using AI. The generation unit generates appropriate answers using, for example, AI. For example, the generation unit generates optimal answers to questions using natural language generation technology. The generation unit can also adjust the level of detail in the answer based on the importance of the question. For example, the generation unit generates detailed answers for important questions and concise answers for general questions. Furthermore, the generation unit can estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. For example, if the reporter is angry, the generation unit applies a calm and polite way of expression. This makes it possible to quickly generate optimal answers by using AI.

[0033] The reading unit can provide the generated answer by voice. The reading unit can provide the generated answer by voice, for example, using voice synthesis technology. For example, the reading unit can synthesize the generated answer into voice in real time, allowing the reporter to announce the answer. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit can read in a calm and collected tone. This allows the reporter to announce the answer by providing the generated answer by voice.

[0034] The analysis unit can include a learning unit that learns data from past apology press conferences. The analysis unit includes, for example, a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences, and the AI ​​learns from it, thereby improving the accuracy of the analysis. For example, the learning unit collects data from past apology press conferences and builds a database from which the AI ​​can learn. The learning unit also provides an algorithm that the AI ​​uses to learn from the collected data. In this way, the analysis accuracy is improved by learning from data from past apology press conferences.

[0035] The learning unit can collect data on past apology press conferences and allow the AI ​​to learn from it. For example, the learning unit collects data on past apology press conferences and allows the AI ​​to learn from it. For example, the learning unit collects data on past apology press conferences and builds a database for the AI ​​to learn from it. The learning unit also provides an algorithm for the AI ​​to learn from the collected data. Furthermore, the learning unit can build a feedback loop for the AI ​​to learn from the collected data. For example, the learning unit allows the AI ​​to learn from the collected data, evaluates the results, and optimizes the learning algorithm. In this way, by collecting data on past apology press conferences and allowing the AI ​​to learn from it, the accuracy of analysis can be further improved.

[0036] The speech recognition unit can analyze the speaking speed and accent of the reporter and apply an appropriate speech recognition algorithm. The speech recognition unit can analyze, for example, the speaking speed and accent of the reporter and apply an appropriate speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that corresponds to fast speech. Furthermore, if the reporter speaks with a specific accent, the speech recognition unit can apply a speech recognition algorithm that corresponds to that accent. Furthermore, if the reporter speaks slowly, the speech recognition unit can apply a speech recognition algorithm that corresponds to slow speech. In this way, by applying a speech recognition algorithm that corresponds to the reporter's speaking speed and accent, recognition accuracy is improved.

[0037] The speech recognition unit can add a filtering function that removes background noise in real time during speech recognition. For example, the speech recognition unit adds a filtering function that removes background noise in real time during speech recognition. For example, the speech recognition unit can remove background noise in a press conference room in real time, improving the accuracy of speech recognition. The speech recognition unit can also remove sudden noise that occurs while a reporter is speaking in real time. Furthermore, the speech recognition unit can separate the reporter's speech from background noise and accurately recognize only the speech. As a result, the accuracy of speech recognition is improved by removing background noise in real time.

[0038] The analysis unit can improve the analysis accuracy by taking into account the context of the question when analyzing a question. For example, the analysis unit improves the analysis accuracy by taking into account the context of the question when analyzing a question. For example, the analysis unit accurately analyzes the intent of the question by taking into account the context before and after the question. The analysis unit can also improve the analysis accuracy based on the context by referring to background information about the question. Furthermore, the analysis unit can improve the analysis accuracy by taking into account topics related to the question. In this way, the analysis accuracy is improved by taking into account the context of the question.

[0039] The analysis unit can apply different analysis algorithms depending on the category of the question when analyzing the question. For example, the analysis unit applies different analysis algorithms depending on the category of the question when analyzing the question. For example, the analysis unit applies a specialized technical analysis algorithm to a technical question. The analysis unit can also apply a specialized legal analysis algorithm to a legal question. The analysis unit can also apply a specialized economic analysis algorithm to an economic question. In this way, by applying an analysis algorithm depending on the category of the question, the accuracy of the analysis is improved.

[0040] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. For example, the generation unit adjusts the level of detail of the answer based on the importance of the question when generating an answer. For example, the generation unit generates a detailed answer for an important question and a concise answer for a general question. Furthermore, the generation unit can generate a detailed answer including related information for a question about a specific topic. In this way, by adjusting the level of detail of the answer based on the importance of the question, it is possible to provide an appropriate answer.

[0041] The generation unit can apply different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit applies different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit can apply a technical generation algorithm to a technical question. Furthermore, the generation unit can apply a legal generation algorithm to a legal question. Furthermore, the generation unit can apply an economic generation algorithm to an economic question. In this way, by applying a generation algorithm depending on the category of the question, an appropriate answer can be provided.

[0042] The reading unit can adjust the emphasized portions of the reading based on the importance of the generated answer when reading aloud. For example, the reading unit adjusts the emphasized portions of the reading based on the importance of the generated answer when reading aloud. For example, the reading unit can emphasize and read out important answer portions. Also, the reading unit can read out general answer portions in a normal tone. Furthermore, the reading unit can emphasize and read out answer portions related to a specific topic. In this way, important information can be emphasized by adjusting the emphasized portions of the reading based on the importance of the generated answer.

[0043] The reading unit can apply different reading algorithms depending on the category of the answer when reading aloud. For example, the reading unit can apply different reading algorithms depending on the category of the answer when reading aloud. For example, the reading unit can apply a reading algorithm specialized for technology to technical answers. Furthermore, the reading unit can apply a reading algorithm specialized for legal answers. Furthermore, the reading unit can apply a reading algorithm specialized for economic answers. In this way, by applying a reading algorithm depending on the category of the answer, appropriate reading is possible.

[0044] The learning unit can optimize the learning algorithm by referring to past apology press conference data during learning. For example, the learning unit optimizes the learning algorithm by referring to past apology press conference data during learning. For example, the learning unit refers to past apology press conference data and applies an optimal learning algorithm. The learning unit can also optimize a learning algorithm for a specific topic from past apology press conference data. Furthermore, the learning unit can improve the accuracy of the learning algorithm based on past apology press conference data. As a result, the accuracy of the learning algorithm is improved by referring to past apology press conference data.

[0045] The learning unit can weight the learning data based on the timing of the apology press conference during learning. For example, the learning unit weights the learning data based on the timing of the apology press conference during learning. For example, the learning unit weights the learning data based on the most recent apology press conference data. The learning unit can also weight the learning data based on past apology press conference data. Furthermore, the learning unit can weight the learning data based on apology press conference data related to a specific time period. In this way, weighting the learning data based on the timing of the apology press conference improves the accuracy of learning.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The apology press conference support system can further include a question prediction unit. The question prediction unit predicts the question that a reporter is likely to ask next based on data from past apology press conferences. For example, the question prediction unit can analyze the frequency of questions about a specific topic from past data and predict the next question. The question prediction unit can also analyze the flow of questions from reporters in real time and predict the next question. Furthermore, the question prediction unit provides answers to predicted questions to the generation unit in advance, enabling a quick response. This allows for a quick and appropriate response to the predicted questions.

[0048] The apology press conference support system may further include a multilingual support unit. The multilingual support unit recognizes reporters' questions in multiple languages ​​and provides them to the analysis unit. For example, the multilingual support unit may perform speech recognition of reporters' questions in multiple languages, such as English, French, and Chinese, and convert them into text data. The multilingual support unit may also support the analysis unit to analyze questions in multiple languages. Furthermore, the multilingual support unit may support the generation unit to generate answers in multiple languages. This allows for prompt and appropriate responses even at international apology press conferences.

[0049] The apology press conference support system may further include a data security unit. The data security unit securely protects data such as reporters' questions and generated answers. For example, the data security unit may encrypt the reporters' questions and generated answers using data encryption technology. The data security unit may also perform data access control to ensure that only authorized users can access the data. Furthermore, the data security unit may periodically back up data to prevent data loss. This allows the data of the apology press conference to be securely protected.

[0050] The apology press conference support system can further include a real-time translation unit. The real-time translation unit translates reporters' questions in real time and provides the translation to the analysis unit. For example, the real-time translation unit can translate reporters' questions from English to Japanese, allowing the analysis unit to analyze the questions in Japanese. The real-time translation unit can also translate generated answers in real time and provide them to reporters. Furthermore, the real-time translation unit supports multiple languages, allowing for quick and appropriate responses even in international apology press conferences. This allows apology press conferences to be held across language barriers.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The speech recognition unit recognizes the reporter's question. For example, the speech recognition unit can recognize the reporter's question in real time and convert it into text data. The speech recognition unit can also use noise canceling technology to improve the accuracy of speech recognition. For example, the speech recognition unit can remove background noise in the press conference room in real time to improve the accuracy of speech recognition. Furthermore, the speech recognition unit can analyze the reporter's speaking speed and accent and apply the optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. Step 2: The analysis unit analyzes the question recognized by the voice recognition unit. For example, the analysis unit can use AI to understand the content of the question and extract information to generate an optimal answer. The analysis unit can also improve the accuracy of the analysis by taking into account the context of the question. For example, the analysis unit can accurately analyze the intent of the question by taking into account the context before and after the question. Furthermore, the analysis unit can be equipped with a learning unit that learns from data on past apology press conferences. For example, the analysis unit collects data on past apology press conferences and has AI learn from it to improve the accuracy of the analysis. Step 3: The generator generates an optimal answer based on the question analyzed by the analyzer. For example, the generator can use AI to generate an appropriate answer. The generator can also adjust the level of detail in the answer based on the importance of the question. For example, the generator can generate a detailed answer for an important question and a concise answer for a general question. Furthermore, the generator can estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. For example, the generator can apply a calm and polite way of expression if the reporter is angry. Step 4: The reading unit reads the answer generated by the generation unit. For example, the reading unit can provide the generated answer aloud using speech synthesis technology. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit reads in a calm and collected tone.

[0053] (Example 2) An apology press conference support system according to an embodiment of the present invention does not prepare a list of anticipated questions and answers in advance. Instead, it recognizes or transcribes reporters' questions in real time, and AI generates and reads out optimal answers. This apology press conference support system recognizes or transcribes reporters' questions, analyzes the questions, and generates and reads out optimal answers. This eliminates the need to prepare a list of anticipated questions and answers in advance, and allows for quick and appropriate responses to unexpected questions. For example, if a reporter asks, "What are your thoughts on this scandal?", the question is transcribed by a voice recognition system. This transcribed question is then input into an AI. The AI ​​then analyzes the input question. The AI ​​understands the content of the question and generates an optimal answer. For example, in response to the question, "What are your thoughts on this scandal?", the AI ​​generates an answer such as, "We deeply regret this scandal and are taking specific measures to prevent it from recurring." The generated answer is then read out. For example, a speech synthesis system can read out the answer generated by the AI, allowing the person presenting the answer to announce it. In this way, reporters' questions can be responded to quickly and appropriately without having to prepare a list of anticipated questions and answers in advance. This system makes apology press conferences more effective. The press conference attendees can respond quickly to unexpected questions, reducing the risk of the apology press conference being negatively impacted. In addition, since AI generates optimal answers, the burden on the press conference attendees is reduced. For example, if AI learns from data on past apology press conferences and generates optimal answers, the press conference attendees can provide more reliable answers. This allows the apology press conference support system to respond quickly and appropriately to reporters' questions.

[0054] An apology press conference support system according to an embodiment includes a speech recognition unit, an analysis unit, a generation unit, and a reading unit. The speech recognition unit recognizes a reporter's question in speech. For example, the speech recognition unit can recognize the reporter's question in real time and convert it into text data. The speech recognition unit can also use noise canceling technology to improve the accuracy of the speech recognition. For example, the speech recognition unit can remove background noise from the press conference room in real time to improve the accuracy of the speech recognition. The speech recognition unit can also analyze the reporter's speaking speed and accent and apply an optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. The analysis unit analyzes the question recognized by the speech recognition unit. For example, the analysis unit can use AI to understand the content of the question and extract information for generating an optimal answer. The analysis unit can also improve the analysis accuracy by taking into account the context of the question. For example, the analysis unit can accurately analyze the intent of the question by taking into account the context before and after the question. The analysis unit can also include a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences, and the AI ​​learns from it to improve analysis accuracy. The generation unit generates optimal answers based on the questions analyzed by the analysis unit. For example, the generation unit can generate appropriate answers using AI. The generation unit can also adjust the level of detail in the answers based on the importance of the question. For example, the generation unit generates detailed answers for important questions and concise answers for general questions. The generation unit can also estimate the reporter's emotions and adjust the way the answers are expressed based on the estimated reporter's emotions. For example, the generation unit applies a calm and polite way of expression if the reporter is angry. The reading unit reads out the answers generated by the generation unit. For example, the reading unit can provide the generated answers aloud using speech synthesis technology. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit reads out in a calm and composed tone.This allows the apology press conference support system according to the embodiment to respond quickly and appropriately to questions from reporters.

[0055] The speech recognition unit can transcribe the reporter's question. For example, the speech recognition unit recognizes the reporter's question in real time and converts it into text data. For example, the speech recognition unit transcribes the reporter's question using speech recognition technology. The speech recognition unit can also use noise canceling technology to improve the accuracy of speech recognition. For example, the speech recognition unit can remove background noise in a press conference room in real time to improve the accuracy of speech recognition. Furthermore, the speech recognition unit can analyze the reporter's speaking speed and accent and apply the optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. By transcribing the reporter's question, the analysis unit can more accurately analyze the question.

[0056] The analysis unit can understand the content of the question using AI. For example, the analysis unit uses AI to understand the content of the question. For example, the analysis unit analyzes the content of the question using natural language processing technology and extracts information for generating an optimal answer. The analysis unit can also improve the accuracy of the analysis by taking into account the context of the question. For example, the analysis unit accurately analyzes the intent of the question by taking into account the context before and after the question. Furthermore, the analysis unit can be equipped with a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences and has AI learn from it to improve the accuracy of the analysis. As a result, the content of the question can be understood more accurately by using AI.

[0057] The generation unit can generate appropriate answers using AI. The generation unit generates appropriate answers using, for example, AI. For example, the generation unit generates optimal answers to questions using natural language generation technology. The generation unit can also adjust the level of detail in the answer based on the importance of the question. For example, the generation unit generates detailed answers for important questions and concise answers for general questions. Furthermore, the generation unit can estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. For example, if the reporter is angry, the generation unit applies a calm and polite way of expression. This makes it possible to quickly generate optimal answers by using AI.

[0058] The reading unit can provide the generated answer by voice. The reading unit can provide the generated answer by voice, for example, using voice synthesis technology. For example, the reading unit can synthesize the generated answer into voice in real time, allowing the reporter to announce the answer. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit can read in a calm and collected tone. This allows the reporter to announce the answer by providing the generated answer by voice.

[0059] The analysis unit can include a learning unit that learns data from past apology press conferences. The analysis unit includes, for example, a learning unit that learns data from past apology press conferences. For example, the analysis unit collects data from past apology press conferences, and the AI ​​learns from it, thereby improving the accuracy of the analysis. For example, the learning unit collects data from past apology press conferences and builds a database from which the AI ​​can learn. The learning unit also provides an algorithm that the AI ​​uses to learn from the collected data. In this way, the analysis accuracy is improved by learning from data from past apology press conferences.

[0060] The learning unit can collect data on past apology press conferences and allow the AI ​​to learn from it. For example, the learning unit collects data on past apology press conferences and allows the AI ​​to learn from it. For example, the learning unit collects data on past apology press conferences and builds a database for the AI ​​to learn from it. The learning unit also provides an algorithm for the AI ​​to learn from the collected data. Furthermore, the learning unit can build a feedback loop for the AI ​​to learn from the collected data. For example, the learning unit allows the AI ​​to learn from the collected data, evaluates the results, and optimizes the learning algorithm. In this way, by collecting data on past apology press conferences and allowing the AI ​​to learn from it, the accuracy of analysis can be further improved.

[0061] The voice recognition unit can estimate the emotion of the reporter and adjust the accuracy of voice recognition based on the estimated emotion of the reporter. The voice recognition unit can, for example, estimate the emotion of the reporter and adjust the accuracy of voice recognition based on the estimated emotion of the reporter. For example, if the reporter is angry, the voice recognition unit can increase the accuracy of voice recognition to accurately recognize the details of the utterance. Furthermore, if the reporter is nervous, the voice recognition unit can adjust the accuracy of voice recognition to fill in the ambiguous parts of the utterance. Furthermore, if the reporter is relaxed, the voice recognition unit can perform recognition with normal voice recognition accuracy. In this way, by adjusting the accuracy of voice recognition based on the emotion of the reporter, the recognition accuracy is improved.

[0062] The speech recognition unit can analyze the speaking speed and accent of the reporter and apply an appropriate speech recognition algorithm. The speech recognition unit can analyze, for example, the speaking speed and accent of the reporter and apply an appropriate speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that corresponds to fast speech. Furthermore, if the reporter speaks with a specific accent, the speech recognition unit can apply a speech recognition algorithm that corresponds to that accent. Furthermore, if the reporter speaks slowly, the speech recognition unit can apply a speech recognition algorithm that corresponds to slow speech. In this way, by applying a speech recognition algorithm that corresponds to the reporter's speaking speed and accent, recognition accuracy is improved.

[0063] The speech recognition unit can add a filtering function that removes background noise in real time during speech recognition. For example, the speech recognition unit adds a filtering function that removes background noise in real time during speech recognition. For example, the speech recognition unit can remove background noise in a press conference room in real time, improving the accuracy of speech recognition. The speech recognition unit can also remove sudden noise that occurs while a reporter is speaking in real time. Furthermore, the speech recognition unit can separate the reporter's speech from background noise and accurately recognize only the speech. As a result, the accuracy of speech recognition is improved by removing background noise in real time.

[0064] The analysis unit can estimate the reporter's emotions and adjust the question analysis method based on the estimated reporter's emotions. The analysis unit, for example, estimates the reporter's emotions and adjusts the question analysis method based on the estimated reporter's emotions. For example, if the reporter is angry, the analysis unit adjusts the analysis method taking into account the tone of the question. Furthermore, if the reporter is nervous, the analysis unit can apply an analysis method that fills in the ambiguity of the question. Furthermore, if the reporter is relaxed, the analysis unit can apply a normal analysis method. In this way, by adjusting the question analysis method based on the reporter's emotions, analysis accuracy is improved.

[0065] The analysis unit can improve the analysis accuracy by taking into account the context of the question when analyzing a question. For example, the analysis unit improves the analysis accuracy by taking into account the context of the question when analyzing a question. For example, the analysis unit accurately analyzes the intent of the question by taking into account the context before and after the question. The analysis unit can also improve the analysis accuracy based on the context by referring to background information about the question. Furthermore, the analysis unit can improve the analysis accuracy by taking into account topics related to the question. In this way, the analysis accuracy is improved by taking into account the context of the question.

[0066] The analysis unit can apply different analysis algorithms depending on the category of the question when analyzing the question. For example, the analysis unit applies different analysis algorithms depending on the category of the question when analyzing the question. For example, the analysis unit applies a specialized technical analysis algorithm to a technical question. The analysis unit can also apply a specialized legal analysis algorithm to a legal question. The analysis unit can also apply a specialized economic analysis algorithm to an economic question. In this way, by applying an analysis algorithm depending on the category of the question, the accuracy of the analysis is improved.

[0067] The generation unit can estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. The generation unit can, for example, estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. For example, if the reporter is angry, the generation unit can apply a calm and polite way of expression. Also, if the reporter is nervous, the generation unit can apply a way of expression that gives a sense of security. Furthermore, if the reporter is relaxed, the generation unit can apply a normal way of expression. In this way, by adjusting the way the answer is expressed based on the reporter's emotions, a more appropriate answer can be provided.

[0068] The generation unit can adjust the level of detail of the answer based on the importance of the question when generating an answer. For example, the generation unit adjusts the level of detail of the answer based on the importance of the question when generating an answer. For example, the generation unit generates a detailed answer for an important question and a concise answer for a general question. Furthermore, the generation unit can generate a detailed answer including related information for a question about a specific topic. In this way, by adjusting the level of detail of the answer based on the importance of the question, it is possible to provide an appropriate answer.

[0069] The generation unit can apply different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit applies different generation algorithms depending on the category of the question when generating an answer. For example, the generation unit can apply a technical generation algorithm to a technical question. Furthermore, the generation unit can apply a legal generation algorithm to a legal question. Furthermore, the generation unit can apply an economic generation algorithm to an economic question. In this way, by applying a generation algorithm depending on the category of the question, an appropriate answer can be provided.

[0070] The reading unit can estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated emotions of the reporter. The reading unit can, for example, estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated emotions of the reporter. For example, if the reporter is angry, the reading unit can read in a calm and collected tone. Also, if the reporter is nervous, the reading unit can read in a reassuring tone. Furthermore, if the reporter is relaxed, the reading unit can read in a normal tone. In this way, by adjusting the tone and speed of the reading based on the reporter's emotions, more appropriate answers can be provided.

[0071] The reading unit can adjust the emphasized portions of the reading based on the importance of the generated answer when reading aloud. For example, the reading unit adjusts the emphasized portions of the reading based on the importance of the generated answer when reading aloud. For example, the reading unit can emphasize and read out important answer portions. Also, the reading unit can read out general answer portions in a normal tone. Furthermore, the reading unit can emphasize and read out answer portions related to a specific topic. In this way, important information can be emphasized by adjusting the emphasized portions of the reading based on the importance of the generated answer.

[0072] The reading unit can apply different reading algorithms depending on the category of the answer when reading aloud. For example, the reading unit can apply different reading algorithms depending on the category of the answer when reading aloud. For example, the reading unit can apply a reading algorithm specialized for technology to technical answers. Furthermore, the reading unit can apply a reading algorithm specialized for legal answers. Furthermore, the reading unit can apply a reading algorithm specialized for economic answers. In this way, by applying a reading algorithm depending on the category of the answer, appropriate reading is possible.

[0073] The learning unit can estimate the emotions of the reporter and select learning data based on the estimated emotions of the reporter. The learning unit can, for example, estimate the emotions of the reporter and select learning data based on the estimated emotions of the reporter. For example, if the reporter is angry, the learning unit can preferentially select learning data related to that emotion. Also, if the reporter is nervous, the learning unit can preferentially select learning data related to that emotion. Furthermore, if the reporter is relaxed, the learning unit can select normal learning data. In this way, by selecting learning data based on the emotions of the reporter, the accuracy of learning is improved.

[0074] The learning unit can optimize the learning algorithm by referring to past apology press conference data during learning. For example, the learning unit optimizes the learning algorithm by referring to past apology press conference data during learning. For example, the learning unit refers to past apology press conference data and applies an optimal learning algorithm. The learning unit can also optimize a learning algorithm for a specific topic from past apology press conference data. Furthermore, the learning unit can improve the accuracy of the learning algorithm based on past apology press conference data. As a result, the accuracy of the learning algorithm is improved by referring to past apology press conference data.

[0075] The learning unit can estimate the emotions of the reporter and adjust the frequency of learning based on the estimated emotions of the reporter. For example, the learning unit estimates the emotions of the reporter and adjusts the frequency of learning based on the estimated emotions of the reporter. For example, if the reporter is angry, the learning unit can frequently learn learning data related to that emotion. Also, if the reporter is nervous, the learning unit can frequently learn learning data related to that emotion. Furthermore, if the reporter is relaxed, the learning unit can perform learning at a normal frequency. Thus, by adjusting the frequency of learning based on the emotions of the reporter, the efficiency of learning is improved.

[0076] The learning unit can weight the learning data based on the timing of the apology press conference during learning. For example, the learning unit weights the learning data based on the timing of the apology press conference during learning. For example, the learning unit weights the learning data based on the most recent apology press conference data. The learning unit can also weight the learning data based on past apology press conference data. Furthermore, the learning unit can weight the learning data based on apology press conference data related to a specific time period. In this way, weighting the learning data based on the timing of the apology press conference improves the accuracy of learning. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned voice recognition unit, analysis unit, generation unit, and reading unit, is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit recognizes a reporter's question using the microphone 38B of the smart device 14 and converts it into text data using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the question using the specific processing unit 290 of the data processing device 12 and extracts information for generating an optimal answer. The generation unit generates an appropriate answer using the specific processing unit 290 of the data processing device 12, for example, and the reading unit provides the generated answer aloud using the speaker 40B of the smart device 14, for example. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice recognition unit, analysis unit, generation unit, and reading unit, is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit recognizes the reporter's question using the microphone 238 of the smart glasses 214 and converts it into text data using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the question using, for example, the specific processing unit 290 of the data processing device 12 and extracts information for generating an optimal answer. The generation unit generates an appropriate answer using, for example, the specific processing unit 290 of the data processing device 12, and the reading unit provides the generated answer aloud using, for example, the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned voice recognition unit, analysis unit, generation unit, and reading unit is realized, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the voice recognition unit recognizes the reporter's question using the microphone 238 of the headset-type terminal 314 and converts it into text data using the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the question using the specific processing unit 290 of the data processing device 12 and extracts information for generating an optimal answer. The generation unit generates an appropriate answer using the specific processing unit 290 of the data processing device 12, for example, and the reading unit provides the generated answer aloud using the speaker 240 of the headset-type terminal 314, for example. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned voice recognition unit, analysis unit, generation unit, and reading unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit recognizes the voice of a reporter's question using the microphone 238 of the robot 414 and converts it into text data by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the question using, for example, the specific processing unit 290 of the data processing device 12 and extracts information for generating an optimal answer. The generation unit generates an appropriate answer using, for example, the specific processing unit 290 of the data processing device 12, and the reading unit provides the generated answer aloud using, for example, the speaker 240 of the robot 414.

[0077] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0078] The apology press conference support system can further include an emotion feedback unit. The emotion feedback unit monitors the emotions of the interviewee in real time and provides feedback to the analysis unit. For example, if the interviewee is nervous, the emotion feedback unit sends that information to the analysis unit, which can then adjust the way the questions are analyzed. Alternatively, if the interviewee is relaxed, the analysis unit can apply the normal analysis method. Furthermore, the emotion feedback unit provides feedback to the generation unit based on the emotions of the interviewee, which can then adjust the way the answers are expressed. This improves the response accuracy of the entire system based on the emotions of the interviewee.

[0079] The apology press conference support system can further include a question prediction unit. The question prediction unit predicts the question that a reporter is likely to ask next based on data from past apology press conferences. For example, the question prediction unit can analyze the frequency of questions about a specific topic from past data and predict the next question. The question prediction unit can also analyze the flow of questions from reporters in real time and predict the next question. Furthermore, the question prediction unit provides answers to predicted questions to the generation unit in advance, enabling a quick response. This allows for a quick and appropriate response to the predicted questions.

[0080] The apology press conference support system may further include a multilingual support unit. The multilingual support unit recognizes reporters' questions in multiple languages ​​and provides them to the analysis unit. For example, the multilingual support unit may perform speech recognition of reporters' questions in multiple languages, such as English, French, and Chinese, and convert them into text data. The multilingual support unit may also support the analysis unit to analyze questions in multiple languages. Furthermore, the multilingual support unit may support the generation unit to generate answers in multiple languages. This allows for prompt and appropriate responses even at international apology press conferences.

[0081] The apology press conference support system may further include a data security unit. The data security unit securely protects data such as reporters' questions and generated answers. For example, the data security unit may encrypt the reporters' questions and generated answers using data encryption technology. The data security unit may also perform data access control to ensure that only authorized users can access the data. Furthermore, the data security unit may periodically back up data to prevent data loss. This allows the data of the apology press conference to be securely protected.

[0082] The apology press conference support system can further include a real-time translation unit. The real-time translation unit translates reporters' questions in real time and provides the translation to the analysis unit. For example, the real-time translation unit can translate reporters' questions from English to Japanese, allowing the analysis unit to analyze the questions in Japanese. The real-time translation unit can also translate generated answers in real time and provide them to reporters. Furthermore, the real-time translation unit supports multiple languages, allowing for quick and appropriate responses even in international apology press conferences. This allows apology press conferences to be held across language barriers.

[0083] The apology press conference support system can further include a sentiment analysis unit. The sentiment analysis unit analyzes the sentiment contained in the reporter's question and provides the analysis unit with the sentiment. For example, the sentiment analysis unit can infer the reporter's sentiment from the tone and wording of the question, allowing the analysis unit to analyze the question based on the sentiment. The sentiment analysis unit can also provide feedback to the generation unit based on the reporter's sentiment, allowing the generation unit to adjust the way the answer is expressed. The sentiment analysis unit can also provide feedback to the reading unit based on the reporter's sentiment, adjusting the tone and speed of the reading. This makes it possible to respond appropriately according to the reporter's sentiment.

[0084] The apology press conference support system may further include a stress reduction unit. The stress reduction unit monitors the stress level of the person presenting the press conference and provides feedback to the analysis unit. For example, the stress reduction unit may measure the heart rate or galvanic skin response of the person presenting the press conference to estimate the stress level. The stress reduction unit may also enable the analysis unit to adjust the method of analyzing questions based on the stress level of the person presenting the press conference. Furthermore, the stress reduction unit may enable the generation unit to adjust the method of expressing answers based on the stress level of the person presenting the press conference. This reduces the stress of the person presenting the press conference and enables a more effective apology press conference.

[0085] The apology press conference support system may further include an emotion history unit. The emotion history unit accumulates emotion data of reporters at past apology press conferences and provides it to the analysis unit. For example, the emotion history unit may record the emotions expressed by reporters at past apology press conferences, allowing the analysis unit to analyze questions based on that data. The emotion history unit may also enable the generation unit to adjust the way answers are expressed based on the past emotion data. Furthermore, the emotion history unit may enable the reading unit to adjust the tone and speed of reading based on the past emotion data. This makes it possible to utilize past emotion data to respond more appropriately.

[0086] The apology press conference support system can further include an emotion prediction unit. The emotion prediction unit predicts the emotion that is likely to be shown next based on the content and tone of the reporter's question and provides the prediction to the analysis unit. For example, if the reporter is showing anger, the emotion prediction unit can predict that the same emotion will likely continue in subsequent questions. Also, if the reporter is relaxed, the emotion prediction unit can predict that the subsequent questions will likely continue in a calm tone. Furthermore, the emotion prediction unit can enable the generation unit to adjust the way the answer is expressed based on the predicted emotion. This makes it possible to respond appropriately in accordance with changes in the reporter's emotions.

[0087] The apology press conference support system can further include an emotion training unit. The emotion training unit provides training to help the interviewee control their emotions. For example, the emotion training unit can instruct the interviewee on breathing techniques and mental exercises to help them relax. The emotion training unit can also provide the interviewee with techniques to reduce tension and stress. Furthermore, the emotion training unit can perform simulations to help the interviewee control their emotions. This allows the interviewee to control their emotions and hold a more effective apology press conference.

[0088] The processing flow of the second embodiment will be briefly explained below.

[0089] Step 1: The speech recognition unit recognizes the reporter's question. For example, the speech recognition unit can recognize the reporter's question in real time and convert it into text data. The speech recognition unit can also use noise canceling technology to improve the accuracy of speech recognition. For example, the speech recognition unit can remove background noise in the press conference room in real time to improve the accuracy of speech recognition. Furthermore, the speech recognition unit can analyze the reporter's speaking speed and accent and apply the optimal speech recognition algorithm. For example, if the reporter speaks quickly, the speech recognition unit can apply a speech recognition algorithm that supports fast speech. Step 2: The analysis unit analyzes the question recognized by the voice recognition unit. For example, the analysis unit can use AI to understand the content of the question and extract information to generate an optimal answer. The analysis unit can also improve the accuracy of the analysis by taking into account the context of the question. For example, the analysis unit can accurately analyze the intent of the question by taking into account the context before and after the question. Furthermore, the analysis unit can be equipped with a learning unit that learns from data on past apology press conferences. For example, the analysis unit collects data on past apology press conferences and has AI learn from it to improve the accuracy of the analysis. Step 3: The generator generates an optimal answer based on the question analyzed by the analyzer. For example, the generator can use AI to generate an appropriate answer. The generator can also adjust the level of detail in the answer based on the importance of the question. For example, the generator can generate a detailed answer for an important question and a concise answer for a general question. Furthermore, the generator can estimate the reporter's emotions and adjust the way the answer is expressed based on the estimated reporter's emotions. For example, the generator can apply a calm and polite way of expression if the reporter is angry. Step 4: The reading unit reads the answer generated by the generation unit. For example, the reading unit can provide the generated answer aloud using speech synthesis technology. The reading unit can also estimate the reporter's emotions and adjust the tone and speed of the reading based on the estimated reporter's emotions. For example, if the reporter is angry, the reading unit reads in a calm and collected tone.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0094] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0095] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0111] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on 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.

[0148] 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."

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] [Explanation of symbols]

[0162] 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 voice recognition unit that recognizes questions from reporters; an analysis unit that analyzes the question recognized by the speech recognition unit; a generation unit that generates an appropriate answer based on the question analyzed by the analysis unit; a reading unit that reads out the answer generated by the generation unit; Equipped with A system characterized by:

2. The voice recognition unit Transcribing reporters' questions 2. The system of claim 1.

3. The analysis unit Understanding the content of questions using AI 2. The system of claim 1.

4. The generation unit Generate appropriate answers using AI 2. The system of claim 1.

5. The reading unit Provide generated answers by voice 2. The system of claim 1.

6. The analysis unit Equipped with a learning unit that learns data from past apology press conferences 2. The system of claim 1.

7. The learning unit Data from past apology press conferences will be collected and the AI ​​will learn from it. The system of claim 6 .

8. The voice recognition unit Estimate the reporter's emotions and adjust the accuracy of the speech recognition based on the estimated emotions.

2. The system of claim 1.

Images