system

Abstract

The system according to this embodiment aims to engage in automated conversations with emotion in order to cheer up the user. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, an emotion-adding unit, and a speech unit. The reception unit receives statements from the user. The analysis unit analyzes the statements received by the reception unit. The generation unit generates a response based on the statements analyzed by the analysis unit. The emotion-adding unit adds emotions to the response generated by the generation unit. The speech unit speaks the response to which emotions have been added by the emotion-adding unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the focus is on the device that speaks text to speak appropriate content, and a conversation that makes people feel friendly cannot be carried out.

[0005] The system according to the embodiment aims to perform an automatic conversation with emotion to cheer up the user.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, an emotion-adding unit, and a speech unit. The reception unit receives a statement from the user. The analysis unit analyzes the statement received by the reception unit. The generation unit generates a response based on the statement analyzed by the analysis unit. The emotion-adding unit adds emotion to the response generated by the generation unit. The speech unit speaks the response to which emotion has been added by the emotion-adding unit. [Effects of the Invention]

[0007] The system according to this embodiment can engage in automated conversations with emotion in order to cheer up the user. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An embodiment of the present invention is a technology for developing an automated conversational robot system that possesses emotions and can cheer up users using a generative AI. In this automated conversational robot system, when a user speaks to the robot, the generative AI analyzes the content and generates an appropriate response. This response is imbued with emotions to cheer up the user. Next, the robot speaks the generated response. At this time, the robot is programmed to speak with emotion, making the user feel a sense of familiarity. As a result, the user can regain their energy through conversation with the robot. For example, a user might say to the robot, "I'm tired today." This information is input to the generative AI. The generative AI analyzes the input information and generates an appropriate response. For example, in response to the statement "I'm tired today," it generates a response such as, "Good job! Take a break and refresh yourself!" The generated response is imbued with emotions to cheer up the user. By imbuing the response with appropriate emotions, the generative AI can make the user feel a sense of familiarity. For example, the response "Good job!" is imbued with cheerful and bright emotions. Next, the robot speaks the generated response. The robot is programmed to speak responses generated by a generative AI with emotion. This allows users to regain their spirits through conversation with the robot. For example, if the robot cheerfully says, "Great job! Take a break and refresh yourself!", the user can regain their energy. This mechanism allows users to regain their spirits through conversation with the robot. Because the robot can make users feel a sense of familiarity, users can enjoy conversations with peace of mind without feeling lonely or isolated. For example, a user who feels lonely or isolated can regain their spirits and enrich their daily life by talking to the robot. Thus, the automated conversational robot system can cheer up the user by analyzing what the user says and speaking responses with added emotion.

[0029] The automated conversational robot system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, an emotion-assigning unit, and a speech unit. The reception unit receives statements from the user. Statements from the user include, but are not limited to, voice, text, and gestures. The reception unit receives voice statements using, for example, speech recognition technology. The reception unit can also receive text input. Furthermore, the reception unit can also receive gesture statements using gesture recognition technology. For example, the reception unit converts the user's voice statements into text data using speech recognition technology. Text input can be performed using a keyboard or touchscreen. Gesture recognition technology recognizes the user's gestures using a camera or sensors and receives them as statements. The analysis unit analyzes the statements received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit analyzes the content of the user's statements using natural language processing technology. The analysis unit can also analyze voice statements using speech recognition technology. Furthermore, the analysis unit can also analyze the emotions contained in the statements using emotion analysis technology. For example, the analysis unit uses natural language processing technology to understand the user's utterances and extracts information to generate an appropriate response. Speech recognition technology converts the speech data into text data and performs analysis. Sentiment analysis technology analyzes the emotions contained in the utterances and grasps the user's emotional state. The generation unit generates a response based on the utterances analyzed by the analysis unit. Generation is performed using, for example, a generation AI, but is not limited to such examples. For example, the generation unit uses a generation AI to generate an appropriate response based on the user's utterances. The generation unit can also use a generation AI to understand the user's utterances and generate a response based on relevant information. Furthermore, the generation unit can use a generation AI to generate an emotional response based on the user's utterances. For example, the generation unit uses a generation AI to analyze the user's utterances and generate an appropriate response. The generation AI understands the user's utterances and generates a response based on relevant information. The generation AI can generate an emotional response based on the user's utterances. The emotion implication unit imbues the response generated by the generation unit with emotion.Emotional assignment is performed, for example, using emotion analysis technology, but is not limited to such examples. For example, the emotion assignment unit assigns an appropriate emotion to the generated response. The emotion assignment unit can also assign an intensity of emotion to the generated response. The emotion assignment unit can also assign a type of emotion to the generated response. For example, the emotion assignment unit assigns an emotion to the generated response based on the user's emotional state. The emotion assignment unit assigns an emotion to the generated response with adjustment. The emotion assignment unit assigns an emotion to the generated response with adjustment. The speech unit speaks the response to which the emotion has been assigned by the emotion assignment unit. Speech is performed, for example, using speech synthesis technology, but is not limited to such examples. For example, the speech unit speaks the response to which the emotion has been assigned as speech using speech synthesis technology. The speech unit can also display the response to which the emotion has been assigned as text. The speech unit can also express the response to which the emotion has been assigned as a gesture. For example, the speech unit speaks the response to which the emotion has been assigned as speech using speech synthesis technology. The speech unit displays emotionally charged responses as text using text display technology. The speech unit also expresses emotionally charged responses as gestures using gesture recognition technology. As a result, the automated conversational robot system according to this embodiment can cheer up the user by analyzing the user's statements and uttering emotionally charged responses.

[0030] The reception desk receives user input. User input includes, but is not limited to, voice, text, and gestures. The reception desk can, for example, receive voice input using speech recognition technology. Specifically, speech recognition technology analyzes the user's voice in real time and converts the voice data into text data. This ensures that what the user says is immediately recorded as text. Speech recognition technology includes noise cancellation and voice filtering functions to remove ambient noise and background noise, achieving high-precision speech recognition. The reception desk can also receive text input. Text input can be done using a keyboard or touchscreen, and the reception desk receives input by the user directly typing characters. Furthermore, the reception desk can also receive gesture input using gesture recognition technology. Gesture recognition technology detects the user's movements using cameras and sensors and recognizes specific gestures as input. For example, it can analyze hand movements and facial expressions to understand the user's intent. This makes it possible to communicate using gestures even in situations where voice or text input is difficult. The reception desk integrates these diverse input methods and centrally manages user input. This allows users to express themselves in the way that suits them best, and the system to accurately receive their statements.

[0031] The analysis unit analyzes the statements received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to such examples. Specifically, natural language processing technology grammatically and semantically analyzes the content of the user's statements to understand their intent and meaning. For example, if a user says, "What's the weather like today?", the analysis unit analyzes this statement and understands that the user is seeking information about the weather. The analysis unit can also analyze spoken statements using speech recognition technology. Speech recognition technology converts spoken data into text data and performs analysis based on that text data. Furthermore, the analysis unit can also analyze the emotions contained in a statement using sentiment analysis technology. Sentiment analysis technology analyzes the tone of the statement, word choice, context, etc., to understand the user's emotional state. For example, if a user says, "I'm very tired today," the analysis unit understands from this statement that the user is tired and extracts information to generate an appropriate response. The analysis unit combines these technologies to analyze the content of the user's statements from multiple angles and provides the basic information necessary to generate the optimal response. This allows the analysis unit to accurately understand the user's statements and improve the overall response accuracy of the system.

[0032] The generation unit generates responses based on the utterances analyzed by the analysis unit. Generation is performed using, for example, a generative AI, but is not limited to such examples. Specifically, the generative AI uses an algorithm to understand the user's utterances and generate appropriate responses. For example, if a user says, "What's the weather like today?", the generative AI searches for information about the weather and generates a response such as, "It's sunny today." The generative AI uses text generation AI, and these models are trained on large amounts of data and possess advanced natural language generation capabilities. The generative AI can understand the user's utterances and generate responses based on relevant information. Furthermore, the generative AI can also generate emotional responses based on the user's utterances. For example, if a user says, "I'm very tired today," the generative AI generates an emotional response such as, "You must be tired. Please rest well." Using these generative AIs, the generation unit can generate appropriate and emotional responses to the user's utterances. This allows the generation unit to achieve natural dialogue with the user and improve user satisfaction.

[0033] The emotion-adding unit adds emotions to the responses generated by the generation unit. Emotion addition is performed, for example, using emotion analysis techniques, but is not limited to such examples. Specifically, the emotion-adding unit adds emotions to the generated responses based on the user's emotional state. For example, if a user says, "I'm very tired today," and the generation unit generates the response, "You must be tired. Please rest well," the emotion-adding unit will add feelings of kindness and encouragement to this response. The emotion-adding unit can also add the intensity of emotion to the generated response. For example, if the user is very sad, the emotion-adding unit will add a strong feeling of empathy to the response. Furthermore, the emotion-adding unit can also add the type of emotion to the generated response. For example, if the user is happy, the emotion-adding unit will add a feeling of joy to the response. By using these emotion-adding techniques, the emotion-adding unit can add appropriate emotions to the generated responses, making the interaction with the user more natural and emotionally rich. In this way, the emotion-adding unit can provide responses that are attentive to the user's emotions and improve user satisfaction.

[0034] The speaking unit utters responses to which emotions have been imbued by the emotion-imparting unit. Speech is performed using, for example, speech synthesis technology, but is not limited to such examples. Specifically, speech synthesis technology converts text data into speech data and utters emotionally imbued responses as natural speech. Speech synthesis technology includes functions to adjust the tone, pitch, and speed of the voice, allowing for accurate expression of emotional nuances. For example, it can speak slowly and in a soft tone to express kindness. The speaking unit can also display emotionally imbued responses as text. Text display technology uses displays or screens to visually display emotionally imbued responses. This allows users to confirm the content of the response even in environments where speech is difficult to hear. Furthermore, the speaking unit can also express emotionally imbued responses as gestures. Gesture recognition technology controls the robot's movements and facial expressions to visually express emotions. For example, the robot can convey emotions by waving its hand or making a smile. As a result, the speaking unit can communicate emotionally imbued responses to the user in a variety of ways using voice, text, and gestures. As a result, the automated conversational robot system according to this embodiment can cheer up the user by analyzing the user's statements and uttering emotionally charged responses.

[0035] The generation unit can analyze the user's statements using a generation AI and generate an appropriate response. For example, the generation unit can analyze the user's statements using a generation AI and generate an appropriate response. The generation unit can also, for example, understand the user's statements using a generation AI and generate a response based on relevant information. The generation unit can also, for example, generate an emotional response based on the user's statements using a generation AI. In this way, by using a generation AI, it is possible to generate an appropriate response based on the user's statements. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's statements into the generation AI, and the generation AI generates an appropriate response. The generation AI analyzes the user's statements and generates a response based on relevant information. The generation AI can generate an emotional response based on the user's statements.

[0036] The emotion-assigning unit can assign appropriate emotions to the generated responses. For example, the emotion-assigning unit assigns emotions to the generated responses based on the user's emotional state. The emotion-assigning unit can also assign emotions to the generated responses with adjustments to their intensity. The emotion-assigning unit can also assign emotions to the generated responses with adjustments to their type. This allows the user to feel a sense of familiarity by assigning emotions to the generated responses. Some or all of the above processing in the emotion-assigning unit is performed using AI. For example, the emotion-assigning unit inputs the generated responses into the AI, and the AI ​​assigns appropriate emotions. The AI ​​assigns emotions to the generated responses based on the user's emotional state. The AI ​​assigns emotions to the generated responses with adjustments to their intensity. The AI ​​assigns emotions to the generated responses with adjustments to their type.

[0037] The speech unit allows the robot to utter emotionally charged responses. The speech unit can, for example, use speech synthesis technology to utter emotionally charged responses as voice. The speech unit can also, for example, display emotionally charged responses as text. The speech unit can also, for example, express emotionally charged responses as gestures. This allows the robot to cheer up the user by uttering emotionally charged responses. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs an emotionally charged response to the AI, and the AI ​​makes an appropriate utterance. The AI ​​utters the emotionally charged response as voice. The AI ​​displays the emotionally charged response as text. The AI ​​expresses the emotionally charged response as gestures.

[0038] The reception desk can analyze the user's past communication history and select the optimal reception method. For example, the reception desk can prioritize receiving phrases that the user has frequently used in the past. The reception desk can also analyze the user's past communication patterns and receive messages at the appropriate time. The reception desk can also prioritize receiving topics that the user has preferred to discuss in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past communication history. Some or all of the above processing in the reception desk is performed using AI. For example, the reception desk inputs the user's past communication history into the AI, and the AI ​​selects the optimal reception method. The AI ​​analyzes the user's past communication history and prioritizes receiving frequently used phrases. The AI ​​analyzes the user's past communication patterns and receives messages at the appropriate time. The AI ​​prioritizes receiving topics that the user has preferred to discuss in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past communication history.

[0039] The reception unit can filter messages based on the user's current situation and areas of interest when receiving them. For example, the reception unit can prioritize receiving messages related to the user's current situation. The reception unit can also filter and receive relevant messages based on the user's areas of interest. The reception unit can also prioritize receiving messages related to the user's current activities. This allows for the generation of more relevant responses by filtering messages based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit inputs the user's current situation and areas of interest into the AI, and the AI ​​filters relevant messages. The AI ​​prioritizes receiving messages related to the user's current situation. The AI ​​filters and receives relevant messages based on the user's areas of interest. The AI ​​prioritizes receiving messages related to the user's current activities. This allows for the generation of more relevant responses by filtering messages based on the user's current situation and areas of interest.

[0040] The reception system can prioritize receiving messages based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize messages related to that location. If the user is traveling, the reception system can also prioritize messages related to their travel destination. If the user is at home, the reception system can also prioritize messages related to their home. By prioritizing messages based on the user's geographical location, more relevant responses can be generated. Some or all of the above processing in the reception system is performed using AI. For example, the reception system inputs the user's geographical location into the AI, which then prioritizes receiving relevant messages. If the user is in a specific location, the AI ​​will prioritize messages related to that location. If the user is traveling, the AI ​​will prioritize messages related to their travel destination. If the user is at home, the AI ​​will prioritize messages related to their home. By prioritizing messages based on the user's geographical location, more relevant responses can be generated.

[0041] The reception desk can analyze a user's social media activity when receiving a message and accept relevant messages. For example, the reception desk can prioritize receiving messages on topics the user is discussing on social media. The reception desk can also analyze the content of a user's social media posts and accept relevant messages. The reception desk can also prioritize receiving messages related to accounts the user follows on social media. In this way, relevant messages can be received by analyzing the user's social media activity. Some or all of the above processing in the reception desk is performed using AI. For example, the reception desk inputs the user's social media activity into the AI, and the AI ​​accepts relevant messages. The AI ​​prioritizes receiving messages on topics the user is discussing on social media. The AI ​​analyzes the content of a user's social media posts and accepts relevant messages. The AI ​​prioritizes receiving messages related to accounts the user follows on social media. In this way, relevant messages can be received by analyzing the user's social media activity.

[0042] The analysis unit can adjust the level of detail in its analysis based on the importance of the statement. For example, the analysis unit performs a detailed analysis for important statements. For example, the analysis unit can perform a simplified analysis for general statements. For example, the analysis unit can perform a rapid, detailed analysis for urgent statements. By adjusting the level of detail in the analysis based on the importance of the statement, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the importance of the statement to the AI, and the AI ​​adjusts the level of detail in the analysis. The AI ​​performs a detailed analysis for important statements. The AI ​​performs a simplified analysis for general statements. The AI ​​performs a rapid, detailed analysis for urgent statements. By adjusting the level of detail in the analysis based on the importance of the statement, a more appropriate response can be generated.

[0043] The analysis unit can apply different analysis algorithms depending on the category of the statement when analyzing it. For example, the analysis unit applies an emotion analysis algorithm to emotional statements. The analysis unit can also apply a fact-checking algorithm to fact-based statements. The analysis unit can also apply a question-answering algorithm to question-type statements. By applying different analysis algorithms depending on the category of the statement, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the category of the statement to the AI, and the AI ​​applies an appropriate analysis algorithm. The AI ​​applies an emotion analysis algorithm to emotional statements. The AI ​​applies a fact-checking algorithm to fact-based statements. The AI ​​applies a question-answering algorithm to question-type statements. By applying different analysis algorithms depending on the category of the statement, a more appropriate response can be generated.

[0044] The analysis unit can determine the priority of analysis based on when the statements were submitted. For example, the analysis unit may prioritize analyzing recent statements. The analysis unit may also prioritize analyzing statements of high urgency. The analysis unit may also prioritize analyzing statements made by the user during a specific time period. By determining the priority of analysis based on when the statements were submitted, it is possible to generate more appropriate responses. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the submission date of the statements to the AI, and the AI ​​determines the priority of analysis. The AI ​​prioritizes analyzing recent statements. The AI ​​prioritizes analyzing statements of high urgency. The AI ​​prioritizes analyzing statements made by the user during a specific time period. By determining the priority of analysis based on when the statements were submitted, it is possible to generate more appropriate responses.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the statements. For example, the analysis unit may prioritize analyzing statements that are highly relevant. The analysis unit may also prioritize analyzing statements that are relevant to the user's current situation. The analysis unit may also prioritize analyzing statements that are relevant to the user's past statements. By adjusting the order of analysis based on the relevance of the statements, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the relevance of the statements to the AI, and the AI ​​adjusts the order of analysis. The AI ​​prioritizes analyzing statements that are highly relevant. The AI ​​prioritizes analyzing statements that are relevant to the user's current situation. The AI ​​prioritizes analyzing statements that are relevant to the user's past statements. By adjusting the order of analysis based on the relevance of the statements, a more appropriate response can be generated.

[0046] The generation unit can adjust the level of detail in responses based on the importance of the statements when generating responses. For example, the generation unit generates detailed responses for important statements. The generation unit can also generate simplified responses for general statements. The generation unit can also quickly generate detailed responses for urgent statements. By adjusting the level of detail in responses based on the importance of the statements, more appropriate responses can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the importance of the statements to the generation AI, and the generation AI adjusts the level of detail in the responses. The generation AI generates detailed responses for important statements. The generation AI generates simplified responses for general statements. The generation AI quickly generates detailed responses for urgent statements. By adjusting the level of detail in responses based on the importance of the statements, more appropriate responses can be generated.

[0047] The generation unit can apply different generation algorithms depending on the category of the statement when generating a response. For example, the generation unit applies an emotional response algorithm to emotional statements. The generation unit can also apply a factual response algorithm to factual statements. The generation unit can also apply a question-answering algorithm to question-type statements. By applying different generation algorithms depending on the category of the statement, a more appropriate response can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the category of the statement to the generation AI, and the generation AI applies an appropriate generation algorithm. The generation AI applies an emotional response algorithm to emotional statements. The generation AI applies a factual response algorithm to factual statements. The generation AI applies a question-answering algorithm to question-type statements. By applying different generation algorithms depending on the category of the statement, a more appropriate response can be generated.

[0048] The generation unit can determine the priority of responses based on when the statements were submitted. For example, the generation unit can prioritize responses to recent statements. The generation unit can also prioritize responses to urgent statements. The generation unit can also prioritize responses to statements made by users within a specific time period. This allows for the generation of more appropriate responses by determining the priority of responses based on when the statements were submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the submission date of the statement to the generation AI, and the generation AI determines the priority of responses. The generation AI prioritizes responses to recent statements. The generation AI prioritizes responses to urgent statements. The generation AI prioritizes responses to statements made by users within a specific time period. This allows for the generation of more appropriate responses by determining the priority of responses based on when the statements were submitted.

[0049] The generation unit can adjust the order of responses based on the relevance of the statements when generating responses. For example, the generation unit can prioritize generating responses to highly relevant statements. The generation unit can also prioritize generating responses to statements related to the user's current situation. The generation unit can also prioritize generating responses to statements related to the user's past statements. By adjusting the order of responses based on the relevance of the statements, more appropriate responses can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the relevance of statements to the generation AI, and the generation AI adjusts the order of responses. The generation AI prioritizes generating responses to highly relevant statements. The generation AI prioritizes generating responses to statements related to the user's current situation. The generation AI prioritizes generating responses to statements related to the user's past statements. By adjusting the order of responses based on the relevance of the statements, more appropriate responses can be generated.

[0050] The emotion-generating unit can adjust the intensity of emotion based on the content of the response when generating emotion. For example, the emotion-generating unit can generate strong emotion for important responses. For example, the emotion-generating unit can generate moderate emotion for general responses. For example, the emotion-generating unit can generate strong emotion quickly for urgent responses. By adjusting the intensity of emotion based on the content of the response, it is possible to generate more appropriate emotions. Some or all of the above processing in the emotion-generating unit is performed using AI. For example, the emotion-generating unit inputs the content of the response into the AI, and the AI ​​adjusts the intensity of the emotion. The AI ​​generates strong emotion for important responses. The AI ​​generates moderate emotion for general responses. The AI ​​generates strong emotion quickly for urgent responses. By adjusting the intensity of emotion based on the content of the response, it is possible to generate more appropriate emotions.

[0051] The emotion-assigning unit can apply different emotion-assigning algorithms depending on the category of the response when assigning emotions. For example, the emotion-assigning unit can apply a comforting emotion-assigning algorithm to a comforting response. For example, the emotion-assigning unit can also apply a calming emotion-assigning algorithm to a calming response. For example, the emotion-assigning unit can also apply a relaxation emotion-assigning algorithm to a relaxing response. By applying different emotion-assigning algorithms depending on the category of the response, more appropriate emotions can be assigned. Some or all of the above processing in the emotion-assigning unit is performed using AI. For example, the emotion-assigning unit inputs the category of the response to the AI, and the AI ​​applies an appropriate emotion-assigning algorithm. The AI ​​applies a comforting emotion-assigning algorithm to a comforting response. The AI ​​applies a calming emotion-assigning algorithm to a calming response. The AI ​​applies a relaxation emotion-assigning algorithm to a relaxing response. By applying different emotion-assigning algorithms depending on the category of the response, more appropriate emotions can be assigned.

[0052] The emotion assignment unit can determine the priority of emotions based on the timing of response submission when assigning emotions. For example, the emotion assignment unit may prioritize assigning emotions to recent responses. The emotion assignment unit may also prioritize assigning emotions to responses that are urgent. The emotion assignment unit may also prioritize assigning emotions to responses made by the user within a specific time period. This allows for the assignment of more appropriate emotions by determining the priority of emotions based on the timing of response submission. Some or all of the above processing in the emotion assignment unit is performed using AI. For example, the emotion assignment unit inputs the timing of response submission to the AI, and the AI ​​determines the priority of emotions. The AI ​​prioritizes assigning emotions to recent responses. The AI ​​prioritizes assigning emotions to responses that are urgent. The AI ​​prioritizes assigning emotions to responses made by the user within a specific time period. This allows for the assignment of more appropriate emotions by determining the priority of emotions based on the timing of response submission.

[0053] The emotion assignment unit can adjust the order of emotions based on the relevance of the responses when assigning emotions. For example, the emotion assignment unit can preferentially assign emotions to highly relevant responses. The emotion assignment unit can also preferentially assign emotions to responses related to the user's current situation. The emotion assignment unit can also preferentially assign emotions to responses related to the user's past statements. By adjusting the order of emotions based on the relevance of the responses, more appropriate emotions can be assigned. Some or all of the above processing in the emotion assignment unit is performed using AI. For example, the emotion assignment unit inputs the relevance of the responses to the AI, and the AI ​​adjusts the order of emotions. The AI ​​preferentially assigns emotions to highly relevant responses. The AI ​​preferentially assigns emotions to responses related to the user's current situation. The AI ​​preferentially assigns emotions to responses related to the user's past statements. By adjusting the order of emotions based on the relevance of the responses, more appropriate emotions can be assigned.

[0054] The speech unit can adjust the level of detail in its utterances based on the importance of the response. For example, the speech unit will provide detailed utterances for important responses. For example, the speech unit can provide simplified utterances for general responses. For example, the speech unit can provide detailed utterances quickly for urgent responses. This allows for more appropriate utterances by adjusting the level of detail in utterances based on the importance of the response. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the importance of the response to the AI, and the AI ​​adjusts the level of detail in utterances. The AI ​​provides detailed utterances for important responses. The AI ​​provides simplified utterances for general responses. The AI ​​provides detailed utterances quickly for urgent responses. This allows for more appropriate utterances by adjusting the level of detail in utterances based on the importance of the response.

[0055] The speech unit can apply different speech algorithms depending on the category of the response when speaking. For example, the speech unit can apply a comforting speech algorithm to a comforting response. For example, the speech unit can also apply a calming speech algorithm to a soothing response. For example, the speech unit can also apply a relaxing speech algorithm to a relaxing response. This allows for more appropriate speech by applying different speech algorithms depending on the category of the response. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the category of the response to the AI, and the AI ​​applies an appropriate speech algorithm. The AI ​​applies a comforting speech algorithm to a comforting response. The AI ​​applies a calming speech algorithm to a soothing response. The AI ​​applies a relaxing speech algorithm to a relaxing response. This allows for more appropriate speech by applying different speech algorithms depending on the category of the response.

[0056] The speech unit can determine the priority of utterances based on the timing of response submissions. For example, the speech unit may prioritize utterances to recent responses. The speech unit may also prioritize utterances to responses of high urgency. The speech unit may also prioritize utterances to responses made by the user within a specific time period. This allows for more appropriate utterances by determining the priority of utterances based on the timing of response submissions. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the timing of response submissions to the AI, and the AI ​​determines the priority of utterances. The AI ​​prioritizes utterances to recent responses. The AI ​​prioritizes utterances to responses of high urgency. The AI ​​prioritizes utterances to responses made by the user within a specific time period. This allows for more appropriate utterances by determining the priority of utterances based on the timing of response submissions.

[0057] The speech unit can adjust the order of utterances based on the relevance of the responses when uttering. For example, the speech unit can prioritize utterances for highly relevant responses. The speech unit can also prioritize utterances for responses related to the user's current situation. The speech unit can also prioritize utterances for responses related to the user's past statements. This allows for more appropriate utterances by adjusting the order of utterances based on the relevance of the responses. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the relevance of the responses to the AI, and the AI ​​adjusts the order of utterances. The AI ​​prioritizes utterances for highly relevant responses. The AI ​​prioritizes utterances for responses related to the user's current situation. The AI ​​prioritizes utterances for responses related to the user's past statements. This allows for more appropriate utterances by adjusting the order of utterances based on the relevance of the responses.

[0058] The speech unit can provide multilingual speech at the time of speaking, according to the user's language settings. The speech unit can, for example, automatically set the language of speech based on the language settings of the user's device. The speech unit can also, for example, provide a language switching function if the user uses multiple languages. The speech unit can also, for example, provide speech in a specific language if the user selects that language. This allows for more appropriate speech by providing multilingual speech according to the user's language settings. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the user's language settings into the AI, and the AI ​​provides multilingual speech. The AI ​​automatically sets the language of speech based on the language settings of the user's device. The AI ​​provides a language switching function if the user uses multiple languages. The AI ​​provides speech in a specific language if the user selects that language. This allows for more appropriate speech by providing multilingual speech according to the user's language settings.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] An automated conversational robot system can estimate a user's health condition based on their statements and provide appropriate advice. For example, if a user says, "I haven't been sleeping well lately," the system can estimate the user's sleep patterns and offer advice on how to relax. If a user says, "My shoulder hurts," the system can estimate the user's physical condition and recommend stretching or rest. Furthermore, if a user says, "I have no appetite," the system can estimate the user's eating habits and suggest a nutritionally balanced meal. This allows the system to provide appropriate advice tailored to the user's health condition.

[0061] An automated conversational robot system can estimate a user's hobbies and interests based on what they say and provide relevant information. For example, if a user says, "I recently watched a movie," the system can estimate the user's movie preferences and provide information on related movies. Similarly, if a user says, "I want to try a new recipe," the system can estimate the user's interest in cooking and suggest recipes. Furthermore, if a user says, "I want to travel," the system can estimate the user's travel preferences and provide information on travel destinations. This allows the system to provide information tailored to the user's hobbies and interests.

[0062] An automated conversational robot system can estimate a user's learning needs based on their statements and provide appropriate learning resources. For example, if a user says, "I want to learn programming," the system can estimate the user's learning level and provide appropriate programming learning materials. Similarly, if a user says, "I want to study English," the system can estimate the user's English level and provide appropriate English learning resources. Furthermore, if a user says, "I want to learn more about history," the system can provide relevant historical information based on the user's interests. This allows the system to provide resources that meet the user's learning needs.

[0063] An automated conversational robot system can estimate a user's lifestyle based on their statements and provide advice for improvement. For example, if a user says, "I don't get enough exercise," the system can estimate the user's exercise habits and suggest an appropriate exercise plan. If a user says, "My diet is unhealthy," the system can estimate their eating habits and suggest a balanced diet. Furthermore, if a user says, "I'm stressed," the system can estimate their stress level and suggest relaxation methods. This allows the system to provide advice tailored to the user's lifestyle for improvement.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The reception desk receives information from the user. User information can include voice, text, and gestures. For example, voice recognition technology can be used to receive voice messages, text input via keyboard or touchscreen, and gesture recognition technology can be used to receive gesture messages. Step 2: The analysis unit analyzes the statements received by the reception unit. The analysis is performed using natural language processing technology, speech recognition technology, and sentiment analysis technology. For example, natural language processing technology is used to analyze the content of the statements, speech recognition technology is used to convert the audio data into text data, and sentiment analysis technology is used to analyze the emotions contained in the statements. Step 3: The generation unit generates a response based on the utterances analyzed by the analysis unit. Generation is performed using a generation AI to produce an appropriate response based on the user's utterances. For example, a text generation AI is used to generate a response, and the response is generated based on relevant information. Step 4: The emotion-adding unit adds emotions to the responses generated by the generation unit. Emotion addition is performed using emotion analysis technology to add appropriate emotions, emotional intensity, and types to the generated responses. For example, emotions based on the user's emotional state are added, and the emotional intensity and type are adjusted. Step 5: The utterance unit utters a response to which emotion has been added by the emotion-adding unit. The utterance is performed using speech synthesis technology, and the response to which emotion has been added is spoken as voice. Furthermore, it can also be displayed as text using text display technology, or expressed as a gesture using gesture recognition technology.

[0066] (Example of form 2) An embodiment of the present invention is a technology for developing an automated conversational robot system that possesses emotions and can cheer up users using a generative AI. In this automated conversational robot system, when a user speaks to the robot, the generative AI analyzes the content and generates an appropriate response. This response is imbued with emotions to cheer up the user. Next, the robot speaks the generated response. At this time, the robot is programmed to speak with emotion, making the user feel a sense of familiarity. As a result, the user can regain their energy through conversation with the robot. For example, a user might say to the robot, "I'm tired today." This information is input to the generative AI. The generative AI analyzes the input information and generates an appropriate response. For example, in response to the statement "I'm tired today," it generates a response such as, "Good job! Take a break and refresh yourself!" The generated response is imbued with emotions to cheer up the user. By imbuing the response with appropriate emotions, the generative AI can make the user feel a sense of familiarity. For example, the response "Good job!" is imbued with cheerful and bright emotions. Next, the robot speaks the generated response. The robot is programmed to speak responses generated by a generative AI with emotion. This allows users to regain their spirits through conversation with the robot. For example, if the robot cheerfully says, "Great job! Take a break and refresh yourself!", the user can regain their energy. This mechanism allows users to regain their spirits through conversation with the robot. Because the robot can make users feel a sense of familiarity, users can enjoy conversations with peace of mind without feeling lonely or isolated. For example, a user who feels lonely or isolated can regain their spirits and enrich their daily life by talking to the robot. Thus, the automated conversational robot system can cheer up the user by analyzing what the user says and speaking responses with added emotion.

[0067] The automated conversational robot system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, an emotion-assigning unit, and a speech unit. The reception unit receives statements from the user. Statements from the user include, but are not limited to, voice, text, and gestures. The reception unit receives voice statements using, for example, speech recognition technology. The reception unit can also receive text input. Furthermore, the reception unit can also receive gesture statements using gesture recognition technology. For example, the reception unit converts the user's voice statements into text data using speech recognition technology. Text input can be performed using a keyboard or touchscreen. Gesture recognition technology recognizes the user's gestures using a camera or sensors and receives them as statements. The analysis unit analyzes the statements received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit analyzes the content of the user's statements using natural language processing technology. The analysis unit can also analyze voice statements using speech recognition technology. Furthermore, the analysis unit can also analyze the emotions contained in the statements using emotion analysis technology. For example, the analysis unit uses natural language processing technology to understand the user's utterances and extracts information to generate an appropriate response. Speech recognition technology converts the speech data into text data and performs analysis. Sentiment analysis technology analyzes the emotions contained in the utterances and grasps the user's emotional state. The generation unit generates a response based on the utterances analyzed by the analysis unit. Generation is performed using, for example, a generation AI, but is not limited to such examples. For example, the generation unit uses a generation AI to generate an appropriate response based on the user's utterances. The generation unit can also use a generation AI to understand the user's utterances and generate a response based on relevant information. Furthermore, the generation unit can use a generation AI to generate an emotional response based on the user's utterances. For example, the generation unit uses a generation AI to analyze the user's utterances and generate an appropriate response. The generation AI understands the user's utterances and generates a response based on relevant information. The generation AI can generate an emotional response based on the user's utterances. The emotion implication unit imbues the response generated by the generation unit with emotion.Emotional assignment is performed, for example, using emotion analysis technology, but is not limited to such examples. For example, the emotion assignment unit assigns an appropriate emotion to the generated response. The emotion assignment unit can also assign an intensity of emotion to the generated response. The emotion assignment unit can also assign a type of emotion to the generated response. For example, the emotion assignment unit assigns an emotion to the generated response based on the user's emotional state. The emotion assignment unit assigns an emotion to the generated response with adjustment. The emotion assignment unit assigns an emotion to the generated response with adjustment. The speech unit speaks the response to which the emotion has been assigned by the emotion assignment unit. Speech is performed, for example, using speech synthesis technology, but is not limited to such examples. For example, the speech unit speaks the response to which the emotion has been assigned as speech using speech synthesis technology. The speech unit can also display the response to which the emotion has been assigned as text. The speech unit can also express the response to which the emotion has been assigned as a gesture. For example, the speech unit speaks the response to which the emotion has been assigned as speech using speech synthesis technology. The speech unit displays emotionally charged responses as text using text display technology. The speech unit also expresses emotionally charged responses as gestures using gesture recognition technology. As a result, the automated conversational robot system according to this embodiment can cheer up the user by analyzing the user's statements and uttering emotionally charged responses.

[0068] The reception desk receives user input. User input includes, but is not limited to, voice, text, and gestures. The reception desk can, for example, receive voice input using speech recognition technology. Specifically, speech recognition technology analyzes the user's voice in real time and converts the voice data into text data. This ensures that what the user says is immediately recorded as text. Speech recognition technology includes noise cancellation and voice filtering functions to remove ambient noise and background noise, achieving high-precision speech recognition. The reception desk can also receive text input. Text input can be done using a keyboard or touchscreen, and the reception desk receives input by the user directly typing characters. Furthermore, the reception desk can also receive gesture input using gesture recognition technology. Gesture recognition technology detects the user's movements using cameras and sensors and recognizes specific gestures as input. For example, it can analyze hand movements and facial expressions to understand the user's intent. This makes it possible to communicate using gestures even in situations where voice or text input is difficult. The reception desk integrates these diverse input methods and centrally manages user input. This allows users to express themselves in the way that suits them best, and the system to accurately receive their statements.

[0069] The analysis unit analyzes the statements received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to such examples. Specifically, natural language processing technology grammatically and semantically analyzes the content of the user's statements to understand their intent and meaning. For example, if a user says, "What's the weather like today?", the analysis unit analyzes this statement and understands that the user is seeking information about the weather. The analysis unit can also analyze spoken statements using speech recognition technology. Speech recognition technology converts spoken data into text data and performs analysis based on that text data. Furthermore, the analysis unit can also analyze the emotions contained in a statement using sentiment analysis technology. Sentiment analysis technology analyzes the tone of the statement, word choice, context, etc., to understand the user's emotional state. For example, if a user says, "I'm very tired today," the analysis unit understands from this statement that the user is tired and extracts information to generate an appropriate response. The analysis unit combines these technologies to analyze the content of the user's statements from multiple angles and provides the basic information necessary to generate the optimal response. This allows the analysis unit to accurately understand the user's statements and improve the overall response accuracy of the system.

[0070] The generation unit generates responses based on the utterances analyzed by the analysis unit. Generation is performed using, for example, a generative AI, but is not limited to such examples. Specifically, the generative AI uses algorithms to understand the user's utterances and generate appropriate responses. For example, if a user says, "What's the weather like today?", the generative AI searches for information about the weather and generates a response such as, "It's sunny today." Text generation AI is used for the generative AI, and these models are trained on large amounts of data and possess advanced natural language generation capabilities. The generative AI can understand the user's utterances and generate responses based on relevant information. Furthermore, the generative AI can also generate emotional responses based on the user's utterances. For example, if a user says, "I'm very tired today," the generative AI generates an emotional response such as, "You must be tired. Please rest well." Using these generative AIs, the generation unit can generate appropriate and emotional responses to the user's utterances. This allows the generation unit to achieve natural dialogue with the user and improve user satisfaction.

[0071] The emotion-adding unit adds emotions to the responses generated by the generation unit. Emotion addition is performed, for example, using emotion analysis techniques, but is not limited to such examples. Specifically, the emotion-adding unit adds emotions to the generated responses based on the user's emotional state. For example, if a user says, "I'm very tired today," and the generation unit generates the response, "You must be tired. Please rest well," the emotion-adding unit will add feelings of kindness and encouragement to this response. The emotion-adding unit can also add the intensity of emotion to the generated response. For example, if the user is very sad, the emotion-adding unit will add a strong feeling of empathy to the response. Furthermore, the emotion-adding unit can also add the type of emotion to the generated response. For example, if the user is happy, the emotion-adding unit will add a feeling of joy to the response. By using these emotion-adding techniques, the emotion-adding unit can add appropriate emotions to the generated responses, making the interaction with the user more natural and emotionally rich. In this way, the emotion-adding unit can provide responses that are attentive to the user's emotions and improve user satisfaction.

[0072] The speaking unit utters responses to which emotions have been imbued by the emotion-imparting unit. Speech is performed using, for example, speech synthesis technology, but is not limited to such examples. Specifically, speech synthesis technology converts text data into speech data and utters emotionally imbued responses as natural speech. Speech synthesis technology includes functions to adjust the tone, pitch, and speed of the voice, allowing for accurate expression of emotional nuances. For example, it can speak slowly and in a soft tone to express kindness. The speaking unit can also display emotionally imbued responses as text. Text display technology uses displays or screens to visually display emotionally imbued responses. This allows users to confirm the content of the response even in environments where speech is difficult to hear. Furthermore, the speaking unit can also express emotionally imbued responses as gestures. Gesture recognition technology controls the robot's movements and facial expressions to visually express emotions. For example, the robot can convey emotions by waving its hand or making a smile. As a result, the speaking unit can communicate emotionally imbued responses to the user in a variety of ways using voice, text, and gestures. As a result, the automated conversational robot system according to this embodiment can cheer up the user by analyzing the user's statements and uttering emotionally charged responses.

[0073] The generation unit can analyze the user's statements using a generation AI and generate an appropriate response. For example, the generation unit can analyze the user's statements using a generation AI and generate an appropriate response. The generation unit can also, for example, understand the user's statements using a generation AI and generate a response based on relevant information. The generation unit can also, for example, generate an emotional response based on the user's statements using a generation AI. In this way, by using a generation AI, it is possible to generate an appropriate response based on the user's statements. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's statements into the generation AI, and the generation AI generates an appropriate response. The generation AI analyzes the user's statements and generates a response based on relevant information. The generation AI can generate an emotional response based on the user's statements.

[0074] The emotion-assigning unit can assign appropriate emotions to the generated responses. For example, the emotion-assigning unit assigns emotions to the generated responses based on the user's emotional state. The emotion-assigning unit can also assign emotions to the generated responses with adjustments to their intensity. The emotion-assigning unit can also assign emotions to the generated responses with adjustments to their type. This allows the user to feel a sense of familiarity by assigning emotions to the generated responses. Some or all of the above processing in the emotion-assigning unit is performed using AI. For example, the emotion-assigning unit inputs the generated responses into the AI, and the AI ​​assigns appropriate emotions. The AI ​​assigns emotions to the generated responses based on the user's emotional state. The AI ​​assigns emotions to the generated responses with adjustments to their intensity. The AI ​​assigns emotions to the generated responses with adjustments to their type.

[0075] The speech unit allows the robot to utter emotionally charged responses. The speech unit can, for example, use speech synthesis technology to utter emotionally charged responses as voice. The speech unit can also, for example, display emotionally charged responses as text. The speech unit can also, for example, express emotionally charged responses as gestures. This allows the robot to cheer up the user by uttering emotionally charged responses. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs an emotionally charged response to the AI, and the AI ​​makes an appropriate utterance. The AI ​​utters the emotionally charged response as voice. The AI ​​displays the emotionally charged response as text. The AI ​​expresses the emotionally charged response as gestures.

[0076] The reception unit can estimate the user's emotions and adjust the timing of receiving their statements based on the estimated emotions. For example, if the user is sad, the reception unit can immediately receive their statements and generate a comforting response. If the user is excited, the reception unit can allow them to calm down a bit before receiving their statements. If the user is tired, the reception unit can allow them to relax before receiving their statements. By adjusting the timing of receiving statements according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts the timing of receiving statements based on the user's emotions. If the user is sad, the AI ​​immediately receives their statements and generates a comforting response. If the AI ​​is excited, it will allow the user to calm down a bit before accepting their comments. If the AI ​​is tired, it will allow the user to relax before accepting their comments. By adjusting the timing of comments according to the user's emotions, it can generate more appropriate responses.

[0077] The reception desk can analyze the user's past communication history and select the optimal reception method. For example, the reception desk can prioritize receiving phrases that the user has frequently used in the past. The reception desk can also analyze the user's past communication patterns and receive messages at the appropriate time. The reception desk can also prioritize receiving topics that the user has preferred to discuss in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past communication history. Some or all of the above processing in the reception desk is performed using AI. For example, the reception desk inputs the user's past communication history into the AI, and the AI ​​selects the optimal reception method. The AI ​​analyzes the user's past communication history and prioritizes receiving frequently used phrases. The AI ​​analyzes the user's past communication patterns and receives messages at the appropriate time. The AI ​​prioritizes receiving topics that the user has preferred to discuss in the past. This allows the reception desk to select the optimal reception method by analyzing the user's past communication history.

[0078] The reception unit can filter messages based on the user's current situation and areas of interest when receiving them. For example, the reception unit can prioritize receiving messages related to the user's current situation. The reception unit can also filter and receive relevant messages based on the user's areas of interest. The reception unit can also prioritize receiving messages related to the user's current activities. This allows for the generation of more relevant responses by filtering messages based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit inputs the user's current situation and areas of interest into the AI, and the AI ​​filters relevant messages. The AI ​​prioritizes receiving messages related to the user's current situation. The AI ​​filters and receives relevant messages based on the user's areas of interest. The AI ​​prioritizes receiving messages related to the user's current activities. This allows for the generation of more relevant responses by filtering messages based on the user's current situation and areas of interest.

[0079] The reception unit can estimate the user's emotions and determine the priority of messages to receive based on the estimated emotions. For example, if the user is sad, the reception unit will prioritize comforting messages. For example, if the user is excited, the reception unit may also prioritize calming messages. For example, if the user is tired, the reception unit may also prioritize relaxing messages. This allows for the generation of more appropriate responses by prioritizing messages according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit is performed using AI. For example, the reception unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​determines the priority of messages based on the user's emotions. If the user is sad, the AI ​​will prioritize comforting messages. When the user is agitated, the AI ​​prioritizes calming remarks. When the user is tired, the AI ​​prioritizes relaxing remarks. By prioritizing remarks according to the user's emotions, it can generate more appropriate responses.

[0080] The reception system can prioritize receiving messages based on the user's geographical location. For example, if the user is in a specific location, the reception system will prioritize messages related to that location. If the user is traveling, the reception system can also prioritize messages related to their travel destination. If the user is at home, the reception system can also prioritize messages related to their home. By prioritizing messages based on the user's geographical location, more relevant responses can be generated. Some or all of the above processing in the reception system is performed using AI. For example, the reception system inputs the user's geographical location into the AI, which then prioritizes receiving relevant messages. If the user is in a specific location, the AI ​​will prioritize messages related to that location. If the user is traveling, the AI ​​will prioritize messages related to their travel destination. If the user is at home, the AI ​​will prioritize messages related to their home. By prioritizing messages based on the user's geographical location, more relevant responses can be generated.

[0081] The reception desk can analyze a user's social media activity when receiving a message and accept relevant messages. For example, the reception desk can prioritize receiving messages on topics the user is discussing on social media. The reception desk can also analyze the content of a user's social media posts and accept relevant messages. The reception desk can also prioritize receiving messages related to accounts the user follows on social media. In this way, relevant messages can be received by analyzing the user's social media activity. Some or all of the above processing in the reception desk is performed using AI. For example, the reception desk inputs the user's social media activity into the AI, and the AI ​​accepts relevant messages. The AI ​​prioritizes receiving messages on topics the user is discussing on social media. The AI ​​analyzes the content of a user's social media posts and accepts relevant messages. The AI ​​prioritizes receiving messages related to accounts the user follows on social media. In this way, relevant messages can be received by analyzing the user's social media activity.

[0082] The analysis unit can estimate the user's emotions and adjust the utterance analysis method based on the estimated user emotions. For example, if the user is sad, the analysis unit can apply a comforting analysis method. For example, if the user is excited, the analysis unit can also apply a calming analysis method. For example, if the user is tired, the analysis unit can also apply a relaxing analysis method. By adjusting the utterance analysis method according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts the utterance analysis method based on the user's emotions. If the user is sad, the AI ​​applies a comforting analysis method. The AI ​​applies a calming analysis method when the user is excited. It applies a relaxing analysis method when the user is tired. This allows the AI ​​to adjust its analysis of utterances according to the user's emotions, thereby generating more appropriate responses.

[0083] The analysis unit can adjust the level of detail in its analysis based on the importance of the statement. For example, the analysis unit performs a detailed analysis for important statements. For example, the analysis unit can perform a simplified analysis for general statements. For example, the analysis unit can perform a rapid, detailed analysis for urgent statements. By adjusting the level of detail in the analysis based on the importance of the statement, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the importance of the statement to the AI, and the AI ​​adjusts the level of detail in the analysis. The AI ​​performs a detailed analysis for important statements. The AI ​​performs a simplified analysis for general statements. The AI ​​performs a rapid, detailed analysis for urgent statements. By adjusting the level of detail in the analysis based on the importance of the statement, a more appropriate response can be generated.

[0084] The analysis unit can apply different analysis algorithms depending on the category of the statement when analyzing it. For example, the analysis unit applies an emotion analysis algorithm to emotional statements. The analysis unit can also apply a fact-checking algorithm to fact-based statements. The analysis unit can also apply a question-answering algorithm to question-type statements. By applying different analysis algorithms depending on the category of the statement, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the category of the statement to the AI, and the AI ​​applies an appropriate analysis algorithm. The AI ​​applies an emotion analysis algorithm to emotional statements. The AI ​​applies a fact-checking algorithm to fact-based statements. The AI ​​applies a question-answering algorithm to question-type statements. By applying different analysis algorithms depending on the category of the statement, a more appropriate response can be generated.

[0085] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is sad, the analysis unit will prioritize analyzing comforting statements. For example, if the user is excited, the analysis unit may also prioritize analyzing calming statements. For example, if the user is tired, the analysis unit may also prioritize analyzing relaxing statements. By determining the priority of analysis according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​determines the priority of analysis based on the user's emotions. If the user is sad, the AI ​​will prioritize analyzing comforting statements. When the user is agitated, the AI ​​prioritizes analyzing calming statements. When the user is tired, the AI ​​prioritizes analyzing relaxing statements. By prioritizing analysis according to the user's emotions, it can generate more appropriate responses.

[0086] The analysis unit can determine the priority of analysis based on when the statements were submitted. For example, the analysis unit may prioritize analyzing recent statements. The analysis unit may also prioritize analyzing statements of high urgency. The analysis unit may also prioritize analyzing statements made by the user during a specific time period. By determining the priority of analysis based on when the statements were submitted, it is possible to generate more appropriate responses. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the submission date of the statements to the AI, and the AI ​​determines the priority of analysis. The AI ​​prioritizes analyzing recent statements. The AI ​​prioritizes analyzing statements of high urgency. The AI ​​prioritizes analyzing statements made by the user during a specific time period. By determining the priority of analysis based on when the statements were submitted, it is possible to generate more appropriate responses.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the statements. For example, the analysis unit may prioritize analyzing statements that are highly relevant. The analysis unit may also prioritize analyzing statements that are relevant to the user's current situation. The analysis unit may also prioritize analyzing statements that are relevant to the user's past statements. By adjusting the order of analysis based on the relevance of the statements, a more appropriate response can be generated. Some or all of the above processing in the analysis unit is performed using AI. For example, the analysis unit inputs the relevance of the statements to the AI, and the AI ​​adjusts the order of analysis. The AI ​​prioritizes analyzing statements that are highly relevant. The AI ​​prioritizes analyzing statements that are relevant to the user's current situation. The AI ​​prioritizes analyzing statements that are relevant to the user's past statements. By adjusting the order of analysis based on the relevance of the statements, a more appropriate response can be generated.

[0088] The generation unit can estimate the user's emotions and adjust the response generation method based on the estimated user emotions. For example, if the user is sad, the generation unit can generate a comforting response. For example, if the user is excited, the generation unit can also generate a calming response. For example, if the user is tired, the generation unit can also generate a relaxing response. In this way, by adjusting the response generation method according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The generation AI takes the user's facial expression data as input and estimates the emotions. The generation AI adjusts the response generation method based on the user's emotions. If the user is sad, the generation AI generates a comforting response. The generative AI generates calming responses when the user is excited. It generates relaxing responses when the user is tired. This allows for more appropriate responses by adjusting the response generation method according to the user's emotions.

[0089] The generation unit can adjust the level of detail in responses based on the importance of the statements when generating responses. For example, the generation unit generates detailed responses for important statements. The generation unit can also generate simplified responses for general statements. The generation unit can also quickly generate detailed responses for urgent statements. By adjusting the level of detail in responses based on the importance of the statements, more appropriate responses can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the importance of the statements to the generation AI, and the generation AI adjusts the level of detail in the responses. The generation AI generates detailed responses for important statements. The generation AI generates simplified responses for general statements. The generation AI quickly generates detailed responses for urgent statements. By adjusting the level of detail in responses based on the importance of the statements, more appropriate responses can be generated.

[0090] The generation unit can apply different generation algorithms depending on the category of the statement when generating a response. For example, the generation unit applies an emotional response algorithm to emotional statements. The generation unit can also apply a factual response algorithm to factual statements. The generation unit can also apply a question-answering algorithm to question-type statements. By applying different generation algorithms depending on the category of the statement, a more appropriate response can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the category of the statement to the generation AI, and the generation AI applies an appropriate generation algorithm. The generation AI applies an emotional response algorithm to emotional statements. The generation AI applies a factual response algorithm to factual statements. The generation AI applies a question-answering algorithm to question-type statements. By applying different generation algorithms depending on the category of the statement, a more appropriate response can be generated.

[0091] The generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is sad, the generation unit can generate a longer, comforting response. For example, if the user is excited, the generation unit can also generate a shorter, calming response. For example, if the user is tired, the generation unit can generate a moderately long, relaxing response. By adjusting the length of the response according to the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The generation AI takes the user's facial expression data as input and estimates the emotions. The generation AI adjusts the length of the response based on the user's emotions. If the user is sad, the generation AI generates a longer, comforting response. The generative AI generates a short, calming response when the user is agitated. It also generates a moderately long, relaxing response when the user is tired. This allows for the generation of more appropriate responses by adjusting the response length according to the user's emotions.

[0092] The generation unit can determine the priority of responses based on when the statements were submitted. For example, the generation unit can prioritize responses to recent statements. The generation unit can also prioritize responses to urgent statements. The generation unit can also prioritize responses to statements made by users within a specific time period. This allows for the generation of more appropriate responses by determining the priority of responses based on when the statements were submitted. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the submission date of the statement to the generation AI, and the generation AI determines the priority of responses. The generation AI prioritizes responses to recent statements. The generation AI prioritizes responses to urgent statements. The generation AI prioritizes responses to statements made by users within a specific time period. This allows for the generation of more appropriate responses by determining the priority of responses based on when the statements were submitted.

[0093] The generation unit can adjust the order of responses based on the relevance of the statements when generating responses. For example, the generation unit can prioritize generating responses to highly relevant statements. The generation unit can also prioritize generating responses to statements related to the user's current situation. The generation unit can also prioritize generating responses to statements related to the user's past statements. By adjusting the order of responses based on the relevance of the statements, more appropriate responses can be generated. Some or all of the above processing in the generation unit is performed using a generation AI. For example, the generation unit inputs the relevance of statements to the generation AI, and the generation AI adjusts the order of responses. The generation AI prioritizes generating responses to highly relevant statements. The generation AI prioritizes generating responses to statements related to the user's current situation. The generation AI prioritizes generating responses to statements related to the user's past statements. By adjusting the order of responses based on the relevance of the statements, more appropriate responses can be generated.

[0094] The emotion-assigning unit can estimate the user's emotions and adjust the type of emotion assigned to the response based on the estimated user's emotions. For example, if the user is sad, the emotion-assigning unit may assign a comforting emotion to the response. For example, if the user is excited, the emotion-assigning unit may assign a calming emotion to the response. For example, if the user is tired, the emotion-assigning unit may assign a relaxing emotion to the response. In this way, by adjusting the type of emotion assigned to the response according to the user's emotions, a more appropriate emotion can be assigned. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the emotion-assigning unit is performed using AI. For example, the emotion-assigning unit analyzes the user's facial expressions using facial recognition technology in order to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts the type of emotion assigned to the response based on the user's emotions. The AI ​​will add comforting emotions to its responses if the user is sad. If the user is excited, the AI ​​will add calming emotions to its responses. If the user is tired, the AI ​​will add relaxing emotions to its responses. This allows the AI ​​to adjust the type of emotion added to its responses according to the user's emotions, thereby providing more appropriate responses.

[0095] The emotion-generating unit can adjust the intensity of emotion based on the content of the response when generating emotion. For example, the emotion-generating unit can generate strong emotion for important responses. For example, the emotion-generating unit can generate moderate emotion for general responses. For example, the emotion-generating unit can generate strong emotion quickly for urgent responses. By adjusting the intensity of emotion based on the content of the response, it is possible to generate more appropriate emotions. Some or all of the above processing in the emotion-generating unit is performed using AI. For example, the emotion-generating unit inputs the content of the response into the AI, and the AI ​​adjusts the intensity of the emotion. The AI ​​generates strong emotion for important responses. The AI ​​generates moderate emotion for general responses. The AI ​​generates strong emotion quickly for urgent responses. By adjusting the intensity of emotion based on the content of the response, it is possible to generate more appropriate emotions.

[0096] The emotion-assigning unit can apply different emotion-assigning algorithms depending on the category of the response when assigning emotions. For example, the emotion-assigning unit can apply a comforting emotion-assigning algorithm to a comforting response. For example, the emotion-assigning unit can also apply a calming emotion-assigning algorithm to a calming response. For example, the emotion-assigning unit can also apply a relaxation emotion-assigning algorithm to a relaxing response. By applying different emotion-assigning algorithms depending on the category of the response, more appropriate emotions can be assigned. Some or all of the above processing in the emotion-assigning unit is performed using AI. For example, the emotion-assigning unit inputs the category of the response to the AI, and the AI ​​applies an appropriate emotion-assigning algorithm. The AI ​​applies a comforting emotion-assigning algorithm to a comforting response. The AI ​​applies a calming emotion-assigning algorithm to a calming response. The AI ​​applies a relaxation emotion-assigning algorithm to a relaxing response. By applying different emotion-assigning algorithms depending on the category of the response, more appropriate emotions can be assigned.

[0097] The emotion assignment unit can estimate the user's emotions and adjust the method of assigning emotions based on the estimated user emotions. For example, if the user is sad, the emotion assignment unit will assign a gentle emotion. For example, if the user is excited, the emotion assignment unit can also assign a calm emotion. For example, if the user is tired, the emotion assignment unit can also assign a relaxed emotion. In this way, by adjusting the method of assigning emotions according to the user's emotions, more appropriate emotions can be assigned. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the emotion assignment unit is performed using AI. For example, the emotion assignment unit analyzes the user's facial expressions using facial recognition technology in order to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts the method of assigning emotions based on the user's emotions. If the user is sad, the AI ​​will assign a gentle emotion. The AI ​​will assign calm emotions to users who are excited, and relaxed emotions to users who are tired. By adjusting how emotions are assigned according to the user's mood, it is possible to assign more appropriate emotions.

[0098] The emotion assignment unit can determine the priority of emotions based on the timing of response submission when assigning emotions. For example, the emotion assignment unit may prioritize assigning emotions to recent responses. The emotion assignment unit may also prioritize assigning emotions to responses that are urgent. The emotion assignment unit may also prioritize assigning emotions to responses made by the user within a specific time period. This allows for the assignment of more appropriate emotions by determining the priority of emotions based on the timing of response submission. Some or all of the above processing in the emotion assignment unit is performed using AI. For example, the emotion assignment unit inputs the timing of response submission to the AI, and the AI ​​determines the priority of emotions. The AI ​​prioritizes assigning emotions to recent responses. The AI ​​prioritizes assigning emotions to responses that are urgent. The AI ​​prioritizes assigning emotions to responses made by the user within a specific time period. This allows for the assignment of more appropriate emotions by determining the priority of emotions based on the timing of response submission.

[0099] The emotion assignment unit can adjust the order of emotions based on the relevance of the responses when assigning emotions. For example, the emotion assignment unit can preferentially assign emotions to highly relevant responses. The emotion assignment unit can also preferentially assign emotions to responses related to the user's current situation. The emotion assignment unit can also preferentially assign emotions to responses related to the user's past statements. By adjusting the order of emotions based on the relevance of the responses, more appropriate emotions can be assigned. Some or all of the above processing in the emotion assignment unit is performed using AI. For example, the emotion assignment unit inputs the relevance of the responses to the AI, and the AI ​​adjusts the order of emotions. The AI ​​preferentially assigns emotions to highly relevant responses. The AI ​​preferentially assigns emotions to responses related to the user's current situation. The AI ​​preferentially assigns emotions to responses related to the user's past statements. By adjusting the order of emotions based on the relevance of the responses, more appropriate emotions can be assigned.

[0100] The speech unit can estimate the user's emotions and adjust its speech expression based on the estimated emotions. For example, if the user is sad, the speech unit will speak in a gentle voice. For example, if the user is excited, the speech unit can also speak in a calm voice. For example, if the user is tired, the speech unit can also speak in a relaxed voice. This allows for more appropriate speech by adjusting the speech expression according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts its speech expression based on the user's emotions. For example, if the user is sad, the AI ​​will speak in a gentle voice. The AI ​​will speak in a calm voice if the user is excited, and in a relaxed voice if the user is tired. By adjusting its speech expression according to the user's emotions, it can provide more appropriate responses.

[0101] The speech unit can adjust the level of detail in its utterances based on the importance of the response. For example, the speech unit will provide detailed utterances for important responses. For example, the speech unit can provide simplified utterances for general responses. For example, the speech unit can provide detailed utterances quickly for urgent responses. This allows for more appropriate utterances by adjusting the level of detail in utterances based on the importance of the response. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the importance of the response to the AI, and the AI ​​adjusts the level of detail in utterances. The AI ​​provides detailed utterances for important responses. The AI ​​provides simplified utterances for general responses. The AI ​​provides detailed utterances quickly for urgent responses. This allows for more appropriate utterances by adjusting the level of detail in utterances based on the importance of the response.

[0102] The speech unit can apply different speech algorithms depending on the category of the response when speaking. For example, the speech unit can apply a comforting speech algorithm to a comforting response. For example, the speech unit can also apply a calming speech algorithm to a soothing response. For example, the speech unit can also apply a relaxing speech algorithm to a relaxing response. This allows for more appropriate speech by applying different speech algorithms depending on the category of the response. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the category of the response to the AI, and the AI ​​applies an appropriate speech algorithm. The AI ​​applies a comforting speech algorithm to a comforting response. The AI ​​applies a calming speech algorithm to a soothing response. The AI ​​applies a relaxing speech algorithm to a relaxing response. This allows for more appropriate speech by applying different speech algorithms depending on the category of the response.

[0103] The speech unit can estimate the user's emotions and adjust the length of its speech based on the estimated emotions. For example, if the user is sad, the speech unit can make longer, comforting speeches. If the user is excited, the speech unit can also make shorter, calming speeches. If the user is tired, the speech unit can also make moderately long, relaxing speeches. By adjusting the length of speech according to the user's emotions, it is possible to make more appropriate speeches. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit analyzes the user's facial expressions using facial recognition technology to estimate the user's emotions. The AI ​​takes the user's facial expression data as input and estimates the emotions. The AI ​​adjusts the length of speech based on the user's emotions. The AI ​​will make longer, comforting remarks if the user is sad. If the user is agitated, the AI ​​will make shorter, calming remarks. If the user is tired, the AI ​​will make moderately long, relaxing remarks. By adjusting the length of remarks according to the user's emotions, the AI ​​can make more appropriate remarks.

[0104] The speech unit can determine the priority of utterances based on the timing of response submissions. For example, the speech unit may prioritize utterances to recent responses. The speech unit may also prioritize utterances to responses of high urgency. The speech unit may also prioritize utterances to responses made by the user within a specific time period. This allows for more appropriate utterances by determining the priority of utterances based on the timing of response submissions. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the timing of response submissions to the AI, and the AI ​​determines the priority of utterances. The AI ​​prioritizes utterances to recent responses. The AI ​​prioritizes utterances to responses of high urgency. The AI ​​prioritizes utterances to responses made by the user within a specific time period. This allows for more appropriate utterances by determining the priority of utterances based on the timing of response submissions.

[0105] The speech unit can adjust the order of utterances based on the relevance of the responses when uttering. For example, the speech unit can prioritize utterances for highly relevant responses. The speech unit can also prioritize utterances for responses related to the user's current situation. The speech unit can also prioritize utterances for responses related to the user's past statements. This allows for more appropriate utterances by adjusting the order of utterances based on the relevance of the responses. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the relevance of the responses to the AI, and the AI ​​adjusts the order of utterances. The AI ​​prioritizes utterances for highly relevant responses. The AI ​​prioritizes utterances for responses related to the user's current situation. The AI ​​prioritizes utterances for responses related to the user's past statements. This allows for more appropriate utterances by adjusting the order of utterances based on the relevance of the responses.

[0106] The speech unit can provide multilingual speech at the time of speaking, according to the user's language settings. The speech unit can, for example, automatically set the language of speech based on the language settings of the user's device. The speech unit can also, for example, provide a language switching function if the user uses multiple languages. The speech unit can also, for example, provide speech in a specific language if the user selects that language. This allows for more appropriate speech by providing multilingual speech according to the user's language settings. Some or all of the above processing in the speech unit is performed using AI. For example, the speech unit inputs the user's language settings into the AI, and the AI ​​provides multilingual speech. The AI ​​automatically sets the language of speech based on the language settings of the user's device. The AI ​​provides a language switching function if the user uses multiple languages. The AI ​​provides speech in a specific language if the user selects that language. This allows for more appropriate speech by providing multilingual speech according to the user's language settings.

[0107] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0108] An automated conversational robot system can estimate a user's health condition based on their statements and provide appropriate advice. For example, if a user says, "I haven't been sleeping well lately," the system can estimate the user's sleep patterns and offer advice on how to relax. If a user says, "My shoulder hurts," the system can estimate the user's physical condition and recommend stretching or rest. Furthermore, if a user says, "I have no appetite," the system can estimate the user's eating habits and suggest a nutritionally balanced meal. This allows the system to provide appropriate advice tailored to the user's health condition.

[0109] An automated conversational robot system can estimate a user's hobbies and interests based on what they say and provide relevant information. For example, if a user says, "I recently watched a movie," the system can estimate the user's movie preferences and provide information on related movies. Similarly, if a user says, "I want to try a new recipe," the system can estimate the user's interest in cooking and suggest recipes. Furthermore, if a user says, "I want to travel," the system can estimate the user's travel preferences and provide information on travel destinations. This allows the system to provide information tailored to the user's hobbies and interests.

[0110] An automated conversational robot system can estimate a user's learning needs based on their statements and provide appropriate learning resources. For example, if a user says, "I want to learn programming," the system can estimate the user's learning level and provide appropriate programming learning materials. Similarly, if a user says, "I want to study English," the system can estimate the user's English level and provide appropriate English learning resources. Furthermore, if a user says, "I want to learn more about history," the system can provide relevant historical information based on the user's interests. This allows the system to provide resources that meet the user's learning needs.

[0111] An automated conversational robot system can estimate a user's lifestyle based on their statements and provide advice for improvement. For example, if a user says, "I don't get enough exercise," the system can estimate the user's exercise habits and suggest an appropriate exercise plan. If a user says, "My diet is unhealthy," the system can estimate their eating habits and suggest a balanced diet. Furthermore, if a user says, "I'm stressed," the system can estimate their stress level and suggest relaxation methods. This allows the system to provide advice tailored to the user's lifestyle for improvement.

[0112] An automated conversational robot system can estimate a user's emotions based on what they say and provide appropriate music. For example, if a user says, "I'm tired today," the system can estimate the user's level of fatigue and provide relaxing music. If a user says, "Something good happened," the system can estimate the user's joy and provide cheerful music. Furthermore, if a user says, "I'm feeling sad," the system can estimate the user's sadness and provide comforting music. In this way, the system can provide music that is appropriate to the user's emotions.

[0113] The automated conversational robot system can estimate the user's emotions based on what the user says and suggest appropriate exercises. For example, if the user says, "I'm stressed," the system can estimate the user's stress level and suggest relaxation exercises. If the user says, "I'm not feeling well," the system can estimate the user's energy level and suggest exercises to boost energy. Furthermore, if the user says, "I'm not concentrating," the system can suggest exercises to improve the user's concentration. In this way, the system can suggest exercises that are appropriate to the user's emotions.

[0114] An automated conversational robot system can estimate a user's emotions based on their statements and provide an appropriate reading list. For example, if a user says, "I want to relax," the system can estimate the user's desire to relax and suggest a relaxing book. Similarly, if a user says, "I'm feeling down," the system can estimate the user's desire to cheer up and suggest a book that will lift their spirits. Furthermore, if a user says, "I want to be moved," the system can estimate the user's desire to be moved and suggest an emotionally moving book. This allows the system to provide an appropriate reading list tailored to the user's emotions.

[0115] An automated conversational robot system can estimate a user's emotions based on what they say and suggest an appropriate movie. For example, if a user says, "I'm feeling down today," the system can estimate the user's feelings of sadness and suggest a movie that will cheer them up. If a user says, "I want to feel happy," the system can estimate the user's desire to feel happy and suggest a comedy movie. Furthermore, if a user says, "I want to be moved," the system can estimate the user's desire to be moved and suggest a moving movie. In this way, the system can suggest a movie that is appropriate to the user's emotions.

[0116] An automated conversational robot system can estimate a user's emotions based on their statements and suggest appropriate travel destinations. For example, if a user says, "I want to refresh myself," the system can estimate the user's desire to refresh themselves and suggest a travel destination surrounded by nature. If a user says, "I want to have an adventure," the system can estimate the user's adventurous spirit and suggest an active travel destination. Furthermore, if a user says, "I want to relax," the system can estimate the user's desire to relax and suggest a resort destination. In this way, the system can suggest travel destinations that are appropriate to the user's emotions.

[0117] An automated conversational robot system can estimate a user's emotions based on their statements and suggest appropriate works of art. For example, if a user says, "I want inspiration," the system can estimate the user's desire for inspiration and suggest creative works of art. If a user says, "I want to relax," the system can estimate the user's desire for relaxation and suggest calming works of art. Furthermore, if a user says, "I want to be moved," the system can estimate the user's desire for emotion and suggest emotionally moving works of art. In this way, the system can suggest works of art that are appropriate to the user's emotions.

[0118] The following briefly describes the processing flow for example form 2.

[0119] Step 1: The reception desk receives information from the user. User information can include voice, text, and gestures. For example, voice recognition technology can be used to receive voice messages, text input via keyboard or touchscreen, and gesture recognition technology can be used to receive gesture messages. Step 2: The analysis unit analyzes the statements received by the reception unit. The analysis is performed using natural language processing technology, speech recognition technology, and sentiment analysis technology. For example, natural language processing technology is used to analyze the content of the statements, speech recognition technology is used to convert the audio data into text data, and sentiment analysis technology is used to analyze the emotions contained in the statements. Step 3: The generation unit generates a response based on the utterances analyzed by the analysis unit. Generation is performed using a generation AI to produce an appropriate response based on the user's utterances. For example, a text generation AI is used to generate a response, and the response is generated based on relevant information. Step 4: The emotion-adding unit adds emotions to the responses generated by the generation unit. Emotion addition is performed using emotion analysis technology to add appropriate emotions, emotional intensity, and types to the generated responses. For example, emotions based on the user's emotional state are added, and the emotional intensity and type are adjusted. Step 5: The utterance unit utters a response to which emotion has been added by the emotion-adding unit. The utterance is performed using speech synthesis technology, and the response to which emotion has been added is spoken as voice. Furthermore, it can also be displayed as text using text display technology, or expressed as a gesture using gesture recognition technology.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0122] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0123] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, emotion-adding unit, and speech unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives user statements using the microphone 38B or touch panel 38A of the smart device 14. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the user's statements. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an appropriate response using a generation AI. The emotion-adding unit is implemented by the specific processing unit 290 of the data processing unit 12 and adds emotion to the generated response. The speech unit speaks the emotion-added response using the speaker 40B of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0124] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0125] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0127] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0128] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0130] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0131] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0132] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0133] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0134] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0135] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0136] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0138] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0139] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, emotion-adding unit, and speech unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives the user's utterance using the microphone 238 of the smart glasses 214. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the user's utterance. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an appropriate response using a generation AI. The emotion-adding unit is implemented by the specific processing unit 290 of the data processing unit 12 and adds emotion to the generated response. The speech unit speaks the emotion-added response using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0140] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0141] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0143] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0144] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0146] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0147] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0148] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0149] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0150] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0151] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0152] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0153] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0154] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0155] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, emotion-adding unit, and speech unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives the user's statements using the microphone 238 of the headset terminal 314. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the user's statements. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an appropriate response using a generation AI. The emotion-adding unit is implemented by the specific processing unit 290 of the data processing unit 12 and adds emotion to the generated response. The speech unit speaks the emotion-added response using the speaker 240 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0156] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0157] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0159] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0160] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0162] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0163] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0164] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0165] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0166] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0167] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0168] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0171] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0172] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, emotion-adding unit, and speech unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives the user's utterance using the microphone 238 of the robot 414. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of the user's utterance. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an appropriate response using a generation AI. The emotion-adding unit is implemented by the specific processing unit 290 of the data processing unit 12 and adds emotion to the generated response. The speech unit speaks the emotion-added response using the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0173] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0174] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0175] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0176] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0177] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0178] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0180] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0181] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0182] 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.

[0183] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0184] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0185] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0186] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0187] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0188] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0189] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0190] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0191] (Note 1) A reception desk that receives comments from users, An analysis unit analyzes the statements received by the reception unit, A generation unit that generates a response based on the statement analyzed by the analysis unit, An emotion-adding unit that adds emotion to the response generated by the generation unit, The system comprises a speech unit that utters a response to which emotion has been imbued by the emotion imbuing unit. A system characterized by the following features. (Note 2) The generating unit is The AI ​​analyzes the user's statements and generates appropriate responses. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned emotion-generating unit, Add appropriate emotions to the generated responses. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned speech unit, The robot speaks responses imbued with emotion. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of receiving comments based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is Analyze the user's past communication history and select the most suitable method of receiving their message. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When receiving a message, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is It estimates the user's emotions and determines the priority of messages to accept based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving messages, the system prioritizes receiving messages that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving a comment, the system analyzes the user's social media activity and accepts relevant comments. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the analysis method of their statements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing statements, the level of detail in the analysis is adjusted based on the importance of the statement. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, When analyzing a statement, different analysis algorithms are applied depending on the category of the statement. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing statements, the priority of analysis is determined based on when the statements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, When analyzing statements, the order of analysis is adjusted based on the relevance of the statements. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the response generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating a response, adjust the level of detail in the response based on the importance of the statement. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating responses, different generation algorithms are applied depending on the category of the statement. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating responses, the priority of responses is determined based on when the statements were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating responses, the order of responses is adjusted based on the relevance of the statements. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned emotion-generating unit, It estimates the user's emotions and adjusts the type of emotion assigned to the response based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion-generating unit, When assigning an emotion, adjust the intensity of the emotion based on the content of the response. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion-generating unit, When assigning emotions, different emotion assignment algorithms are applied depending on the category of the response. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion-generating unit, It estimates the user's emotions and adjusts how emotions are assigned based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned emotion-generating unit, When assigning emotions, prioritize emotions based on when the response is submitted. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned emotion-generating unit, When assigning emotions, the order of emotions is adjusted based on the relevance of the response. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned speech unit, It estimates the user's emotions and adjusts the way utterances are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned speech unit, When speaking, adjust the level of detail in your speech based on the importance of the response. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned speech unit, When speaking, different speech algorithms are applied depending on the category of the response. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned speech unit, It estimates the user's emotions and adjusts the length of utterances based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned speech unit, When speaking, the priority of utterances is determined based on the timing of the response. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned speech unit, When speaking, adjust the order of utterances based on the relevance of the response. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned speech unit, When speaking, the system provides multilingual speech based on the user's language settings. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that receives comments from users, An analysis unit analyzes the statements received by the reception unit, A generation unit that generates a response based on the statement analyzed by the analysis unit, An emotion-adding unit that adds emotion to the response generated by the generation unit, The system comprises a speech unit that utters a response to which emotion has been imbued by the emotion imbuing unit. A system characterized by the following features.

2. The generating unit is The AI ​​generates responses by analyzing the user's statements. The system according to feature 1.

3. The aforementioned emotion-generating unit, Add appropriate emotions to the generated responses. The system according to feature 1.

4. The aforementioned speech unit, The robot speaks responses imbued with emotion. The system according to feature 1.

5. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of receiving comments based on those emotions. The system according to feature 1.

6. The aforementioned reception unit is Analyze the user's past communication history and select the most suitable method of receiving their message. The system according to feature 1.

7. The aforementioned reception unit is When receiving a message, filtering is performed based on the user's current situation and areas of interest. The system according to feature 1.

8. The aforementioned reception unit is It estimates the user's emotions and determines the priority of messages to accept based on the estimated emotions. The system according to feature 1.

9. The aforementioned reception unit is When receiving messages, the system prioritizes receiving messages that are highly relevant based on the user's geographical location. The system according to feature 1.

10. The aforementioned reception unit is When receiving a comment, the system analyzes the user's social media activity and accepts relevant comments. The system according to feature 1.

Images