system

Abstract

The system according to this embodiment aims to generate natural responses that take emotions into account in response to user questions and requests. [Solution] The system according to this embodiment comprises a reception unit, a recognition unit, a generation unit, and a provision unit. The reception unit receives questions or requests from the user. The recognition unit recognizes the user's facial expressions. The generation unit generates a response based on the information received by the reception unit and the recognition result from the recognition unit. The provision unit provides the response generated by the generation unit to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 conventional technology, natural responses considering emotions to user questions and demands have not been sufficiently generated, and there is room for improvement.

[0005] The system according to the embodiment aims to generate natural responses considering emotions to user questions and demands.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a recognition unit, a generation unit, and a provision unit. The reception unit receives questions or requests from the user. The recognition unit recognizes the user's facial expressions. The generation unit generates a response based on the information received by the reception unit and the recognition result from the recognition unit. The provision unit provides the response generated by the generation unit to the user. [Effects of the Invention]

[0007] The system according to this embodiment can generate natural responses that take emotions into account in response to user questions and requests. [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 manages communication between multiple computers. Examples of communication standards applicable 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) The AI ​​concierge system according to an embodiment of the present invention is a system that responds to user questions and requests in natural language while recognizing facial expressions. The AI ​​concierge system can respond to user questions and requests in natural language while recognizing facial expressions. Specifically, first, the user inputs a question or request. For example, the user inputs a request such as "I would like to reserve a meeting room." This information is entered into the reception department. Next, the AI ​​concierge system recognizes the user's facial expression. The recognition unit analyzes the user's facial expression and reads their emotions. For example, it recognizes whether the user is smiling or has a troubled expression. Then, based on the information received by the reception department and the recognition results from the recognition unit, it generates a response. The generation unit generates an appropriate response to the user's request or question. For example, it generates a response such as "Your meeting room reservation has been accepted." Finally, the generated response is provided to the user. The delivery unit conveys the generated response to the user. For example, the AI ​​concierge system can convey the response by voice. This mechanism enables efficient handling of reception work for corporations and public institutions, solving the problem of labor shortages. Furthermore, the AI ​​concierge system possesses features such as multilingual support, facial recognition, body gestures, navigation, information provision, and learning capabilities, enabling smarter and more diverse responses. This can improve the operational efficiency of corporations and public institutions, contributing to the development of society as a whole. As a result, the AI ​​concierge system can respond to user questions and requests in natural language while recognizing their facial expressions.

[0029] The AI ​​concierge system according to this embodiment comprises a reception unit, a recognition unit, a generation unit, and a provision unit. The reception unit receives questions or requests from the user. These questions or requests may include, but are not limited to, text format, voice format, etc. The reception unit may, for example, analyze text entered by the user and receive questions or requests. The reception unit may also analyze voice input and receive questions or requests. For example, it may use speech recognition technology to convert the user's voice into text and receive questions or requests. The recognition unit recognizes the user's facial expressions. The recognition unit may, for example, use a camera to photograph the user's face and analyze the facial expressions. For example, it may use a facial expression recognition algorithm to recognize the user's smile or troubled expression. The recognition unit may also read emotions from the user's voice. For example, it may use speech analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. The generation unit generates appropriate responses to user questions and requests, for example, using natural language generation technology. For example, it generates answers to user questions using generation AI. The generation unit can also perform template-based response generation. For example, it generates responses to user questions and requests based on pre-prepared response templates. The delivery unit provides the responses generated by the generation unit to the user. The delivery unit provides responses, for example, in voice. For example, it conveys the generated responses to the user in voice using speech synthesis technology. The delivery unit can also provide responses in text. For example, it displays the generated responses as text and provides them to the user. As a result, the AI ​​concierge system according to this embodiment can respond to user questions and requests in natural language while recognizing facial expressions.

[0030] The reception desk receives user questions or requests. User questions or requests may include, but are not limited to, text or voice input. The reception desk can, for example, analyze text entered by the user and receive questions or requests. The reception desk can also analyze voice input and receive questions or requests. For example, it can use speech recognition technology to convert the user's voice into text and receive questions or requests. Specifically, the speech recognition technology used is a deep learning-based speech recognition model. This model can learn from a large amount of voice data and convert user speech into text with high accuracy. Furthermore, the reception desk is equipped with natural language processing (NLP) technology to analyze the user's input. By using NLP technology, the intent of the user's questions or requests can be accurately understood and processed appropriately. For example, if a user enters "What's the weather like tomorrow?", the reception desk analyzes this question and starts processing to provide weather information. Also, in the case of voice input, since the user's speech may be affected by noise and background sounds, noise cancellation technology can be used to preprocess the voice data and improve recognition accuracy. This allows the reception desk to handle a variety of user input formats and receive questions and requests accurately and quickly.

[0031] The recognition unit recognizes the user's facial expressions. For example, the recognition unit uses a camera to capture the user's face and analyzes their expressions. For example, it uses a facial expression recognition algorithm to recognize the user's smile or troubled expression. The recognition unit can also read emotions from the user's voice. For example, it uses voice analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. Specifically, a model using a convolutional neural network (CNN) is used as the facial expression recognition algorithm. This model can extract facial feature points and classify emotions such as smiles, anger, and sadness with high accuracy. Furthermore, the recognition unit can also analyze the user's facial and eye movements to grasp their emotional state in more detail. For example, if the user frowns, it can be determined that they are showing confusion or dissatisfaction. As for voice analysis technology, the user's emotional state is estimated by analyzing features such as pitch, tone, speed, and intensity of the voice. For example, if the user's voice is high-pitched and fast, it can be determined that they are showing excitement or tension. This allows the recognition unit to read emotions from multiple angles based on the user's facial expressions and voice, and provide information to generate more natural and appropriate responses.

[0032] The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. The generation unit generates appropriate responses to user questions and requests, for example, using natural language generation technology. For example, it generates answers to user questions using generation AI. The generation unit can also perform template-based response generation. For example, it generates responses to user questions and requests based on pre-prepared response templates. Specifically, a large-scale language model (LLM) based on a transformer model is used as the generation AI. This model can learn from a large amount of text data and generate contextually natural responses to user questions. For example, if a user asks, "Tell me about nearby restaurants," the generation unit will generate a response that suggests appropriate restaurants, taking into account the user's current location and preferred cuisine. Furthermore, template-based response generation can provide quick and consistent responses by using pre-prepared response templates. For example, if a user asks, "Tell me the opening hours," the generation unit will generate a response based on a pre-prepared template regarding opening hours. This allows the generation unit to generate flexible and appropriate responses to user questions and requests.

[0033] The service provider delivers the response generated by the generation unit to the user. The service provider can deliver the response, for example, by voice. For example, it can use speech synthesis technology to deliver the generated response to the user by voice. The service provider can also deliver the response in text. For example, it can display the generated response as text and deliver it to the user. Specifically, text-to-speech (TTS) technology is used as the speech synthesis technology. This technology can convert the generated text into natural-sounding speech and deliver it to the user. For example, if the user asks, "What is the weather forecast?", the service provider can deliver the generated weather forecast response to the user by voice. In the case of text response delivery, the generated response is displayed on the user's device. For example, it can be displayed as text on the screen of a smartphone or tablet so that the user can visually confirm it. Furthermore, the service provider can select the format of the response according to the user's preference. For example, it can deliver a voice response to users who prefer voice responses and a text response to users who prefer text responses. This allows the service provider to deliver the response in the most optimal format for the user and improve the user experience.

[0034] The multilingual support unit can accept user questions or requests in multiple languages. For example, the multilingual support unit can support multiple languages ​​such as English, Japanese, and Spanish. For example, the multilingual support unit can automatically translate text entered by the user and accept questions or requests. Furthermore, the multilingual support unit can automatically translate voice input and accept questions or requests. For example, by combining speech recognition and translation technologies, it can convert the user's voice into text, and then translate it to accept questions or requests. This allows for support of a wider range of users by supporting multiple languages. Some or all of the above-described processes in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input user input data into a generating AI and have the generating AI perform the translation.

[0035] The body gesture unit can recognize the user's body gestures. For example, the body gesture unit can recognize the user's hand movements, head movements, and full-body movements. For example, the body gesture unit can capture the user's movements using a camera and analyze the body gestures. For example, it can use a gesture recognition algorithm to recognize the user's hand and head movements. The body gesture unit can also detect the user's movements using sensors. For example, it can use a motion sensor to recognize the user's full-body movements. This allows for more natural interaction by recognizing the user's body gestures. Some or all of the above processing in the body gesture unit may be performed using AI, or not. For example, the body gesture unit can input user movement data into a generating AI and have the generating AI perform gesture recognition.

[0036] The navigation unit can provide navigation information to the user. For example, the navigation unit can provide map information, directions, and destination information. For example, the navigation unit can obtain the user's current location and guide them to their destination. For example, it can use GPS data to identify the user's current location and guide them to the optimal route based on map information. The navigation unit can also provide information about the user's destination, such as the destination's business hours and contact information. This allows for smoother navigation by providing navigation information to the user. Some or all of the above-described processes in the navigation unit may be performed using AI, or without AI. For example, the navigation unit can input the user's current location data into a generating AI and have the generating AI execute the optimal route guidance.

[0037] The information provision unit can provide users with a variety of information. For example, it can provide news, weather forecasts, and traffic information. For example, the information provision unit can automatically collect the latest news and provide it to users. For example, it can analyze news feeds and extract and provide important news. The information provision unit can also provide weather forecasts. For example, it can analyze meteorological data and provide current weather and future forecasts. The information provision unit can also provide traffic information. For example, it can analyze traffic data and provide information on congestion and traffic accidents. By providing users with a variety of information, it makes it easier for them to obtain information. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input news feed data into a generating AI and have the generating AI extract important news.

[0038] The learning unit can learn through interaction with the user. For example, the learning unit can analyze the history of user questions and requests to improve the system's accuracy. The learning unit can learn user interaction data using machine learning algorithms, for example. For example, it can analyze patterns in user questions and requests to improve the system's response accuracy. The learning unit can also learn based on user feedback. For example, it can analyze user-provided feedback to identify areas for system improvement. In this way, the system's accuracy improves through learning via user interaction. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user interaction data into a generating AI and have the generating AI perform the learning.

[0039] The reception desk can analyze the user's past questions and requests and select the most suitable reception method. For example, the reception desk can automatically display questions and requests that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest questions and requests that will be used during specific time periods based on the user's past questions and requests. This enables more efficient reception by analyzing past history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input data on the user's past questions and requests into a generating AI and have the generating AI select the most suitable reception method.

[0040] The reception unit can filter questions and requests based on the user's current situation and areas of interest. For example, when a user enters their current situation, the reception unit prioritizes receiving questions and requests related to that situation. The reception unit can also filter and receive relevant questions and requests based on the user's areas of interest. Furthermore, the reception unit can exclude unnecessary questions and requests based on the user's current situation and areas of interest. This allows for the reception of more appropriate questions and requests by filtering based on the user's situation and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input data on the user's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0041] The reception desk can prioritize receiving questions and requests that are highly relevant, taking into account the user's geographical location. For example, if a user is in a specific region, the reception desk will prioritize receiving questions and requests related to that region. The reception desk can also filter and receive questions and requests that are highly relevant based on the user's geographical location. Furthermore, the reception desk can exclude unnecessary questions and requests based on the user's current location. In this way, by considering geographical location, highly relevant questions and requests can be prioritized. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location into a generating AI and have the generating AI perform the filtering of highly relevant questions and requests.

[0042] The reception desk can analyze a user's social media activity when receiving questions or requests and accept relevant questions or requests. For example, the reception desk can analyze a user's social media activity and prioritize accepting relevant questions and requests. The reception desk can also filter and accept questions and requests that are highly relevant based on the user's social media activity. Furthermore, the reception desk can exclude unnecessary questions and requests based on the user's social media activity. In this way, by analyzing social media activity, relevant questions and requests can be prioritized. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform the filtering of relevant questions and requests.

[0043] The recognition unit can improve recognition accuracy by referring to the user's past facial expression data during facial expression recognition. For example, the recognition unit can improve recognition accuracy by referring to the user's past facial expression data. The recognition unit can also recognize specific facial expressions more accurately based on the user's past facial expression data. Furthermore, the recognition unit can analyze the user's past facial expression data and optimize the recognition algorithm. This improves recognition accuracy by referring to past facial expression data. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's past facial expression data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0044] The recognition unit can perform facial recognition while considering the user's attribute information. For example, the recognition unit can perform facial recognition while considering the user's attribute information such as age and gender. The recognition unit can also perform facial recognition while considering the user's cultural background. Furthermore, the recognition unit can perform facial recognition based on the user's occupation and role. This allows for more accurate facial recognition by considering attribute information. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's attribute information into a generating AI and have the generating AI perform facial recognition.

[0045] The recognition unit can perform facial recognition while considering the user's geographical background. For example, the recognition unit can accurately recognize facial expressions from a specific region by considering the user's geographical background. The recognition unit can also perform facial recognition that takes cultural differences into account based on the user's geographical background. Furthermore, the recognition unit can analyze the user's geographical background and optimize the recognition algorithm. This makes it possible to perform more accurate facial recognition by considering the geographical background. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's geographical background data into a generating AI and have the generating AI perform facial recognition.

[0046] The recognition unit can improve recognition accuracy by referring to the user's relevant literature during facial expression recognition. For example, the recognition unit can refer to the user's relevant literature to recognize specific facial expressions more accurately. The recognition unit can also optimize the recognition algorithm based on the user's relevant literature. Furthermore, the recognition unit can analyze the user's relevant literature to improve recognition accuracy. Thus, recognition accuracy is improved by referring to relevant literature. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's relevant literature data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0047] The generation unit can generate the optimal response by referring to the user's past questions and requests when generating a response. For example, the generation unit can generate the optimal response based on questions and requests the user has made in the past. The generation unit can also generate responses that avoid congestion based on the user's past questions and requests. Furthermore, the generation unit can analyze the user's past questions and requests and generate the most efficient response. In this way, the optimal response is generated by referring to past questions and requests. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the user's past questions and requests into a generation AI and have the generation AI perform the generation of the optimal response.

[0048] The generation unit can customize responses by considering user attribute information during response generation. For example, the generation unit can customize responses by considering attribute information such as the user's age and gender. It can also customize responses by considering the user's cultural background. Furthermore, the generation unit can customize responses based on the user's occupation and role. This allows for the generation of more appropriate responses by considering attribute information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user attribute information into a generation AI and have the generation AI perform the response customization.

[0049] The generation unit can generate the optimal response by considering the user's geographical location information during response generation. For example, if the user is in a specific region, the generation unit will prioritize generating responses related to that region. The generation unit can also filter and generate highly relevant responses based on the user's geographical location information. Furthermore, the generation unit can exclude unnecessary responses based on the user's current location. This allows for the generation of highly relevant responses by considering geographical location information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's geographical location information into a generation AI and have the generation AI perform the generation of the optimal response.

[0050] The generation unit can generate responses by analyzing the user's social media activity during response generation. For example, the generation unit can analyze the user's social media activity and prioritize the generation of relevant responses. The generation unit can also filter and generate highly relevant responses based on the user's social media activity. Furthermore, the generation unit can exclude unnecessary responses based on the user's social media activity. This allows for the priority generation of relevant responses by analyzing social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's social media activity data into a generation AI and have the generation AI perform the response generation.

[0051] The service provider can select the optimal service method by referring to the user's past response history when providing a response. For example, the service provider can select the optimal service method based on the response methods the user has used in the past. The service provider can also predict and suggest a service method to be used during a specific time period based on the user's past response history. Furthermore, the service provider can analyze the user's past response history and select the most efficient service method. In this way, the optimal service method is selected by referring to past response history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past response history data into a generating AI and have the generating AI perform the selection of the optimal service method.

[0052] The service provider can provide responses while considering the user's attribute information. For example, the service provider can provide responses while considering the user's attribute information such as age and gender. The service provider can also provide responses while considering the user's cultural background. Furthermore, the service provider can provide responses based on the user's occupation and role. By considering attribute information, a more appropriate response can be provided. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's attribute information into a generating AI and have the generating AI perform the task of providing responses.

[0053] The service provider can select the optimal service delivery method when providing a response, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a service delivery method that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a service delivery method optimized for a larger screen. Additionally, if the user is using a smartwatch, the service provider can provide a concise and highly visible service delivery method. Thus, the optimal service delivery method is selected by considering the device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal service delivery method.

[0054] The service provider can analyze the user's social media activity when providing responses. For example, the service provider can analyze the user's social media activity and prioritize providing relevant responses. The service provider can also filter and provide highly relevant responses based on the user's social media activity. Furthermore, the service provider can exclude unnecessary responses based on the user's social media activity. This allows the service provider to prioritize providing relevant responses by analyzing social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI perform the task of providing responses.

[0055] The multilingual support unit can select the optimal support method by referring to the user's past language usage history when providing multilingual support. For example, the multilingual support unit can select the optimal support method based on the languages ​​the user has used in the past. The multilingual support unit can also predict and suggest the languages ​​the user will use at a specific time based on their past language usage history. Furthermore, the multilingual support unit can analyze the user's past language usage history and select the most efficient support method. In this way, the optimal support method is selected by referring to past language usage history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the user's past language usage history data into a generating AI and have the generating AI perform the selection of the optimal support method.

[0056] The multilingual support unit can select the optimal support method by considering the user's geographical location information when providing multilingual support. For example, if the user is in a specific region, the multilingual support unit will prioritize supporting languages ​​related to that region. The multilingual support unit can also filter and support highly relevant languages ​​based on the user's geographical location information. Furthermore, the multilingual support unit can exclude unnecessary languages ​​based on the user's current location. This allows for prioritization of highly relevant languages ​​by considering geographical location information. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal support method.

[0057] The body gesture unit can improve recognition accuracy by referring to the user's past gesture data during body gesture recognition. For example, the body gesture unit can improve recognition accuracy by referring to the user's past gesture data. The body gesture unit can also recognize specific gestures more accurately based on the user's past gesture data. Furthermore, the body gesture unit can analyze the user's past gesture data and optimize the recognition algorithm. This improves recognition accuracy by referring to past gesture data. Some or all of the above processing in the body gesture unit may be performed using AI, for example, or without AI. For example, the body gesture unit can input the user's past gesture data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0058] The body gesture unit can perform recognition while considering the user's geographical background. For example, the body gesture unit can accurately recognize gestures from a specific region by considering the user's geographical background. Furthermore, the body gesture unit can perform gesture recognition that takes cultural differences into account based on the user's geographical background. In addition, the body gesture unit can analyze the user's geographical background and optimize the recognition algorithm. This enables more accurate body gesture recognition by considering geographical background. Some or all of the above processing in the body gesture unit may be performed using AI, for example, or without AI. For example, the body gesture unit can input the user's geographical background data into a generating AI and have the generating AI perform gesture recognition.

[0059] The navigation unit can provide optimal information by referring to the user's past travel history when providing navigation information. For example, the navigation unit can provide optimal navigation information based on routes previously used by the user. The navigation unit can also provide navigation information that avoids congestion based on the user's past travel history. Furthermore, the navigation unit can analyze the user's past travel history and provide the most efficient navigation information. In this way, optimal navigation information is provided by referring to past travel history. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the user's past travel history data into a generating AI and have the generating AI perform the task of providing optimal navigation information.

[0060] The navigation unit can provide optimal information by considering the user's device information when providing navigation information. For example, if the user is using a smartphone, the navigation unit can provide navigation information that is adapted to the screen size. Furthermore, if the user is using a tablet, the navigation unit can provide navigation information optimized for a larger screen. Additionally, if the user is using a smartwatch, the navigation unit can provide concise and highly visible navigation information. In this way, optimal navigation information is provided by considering device information. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the user's device information into a generating AI and have the generating AI perform the task of providing optimal navigation information.

[0061] The information provision unit can provide optimal information by referring to the user's past information acquisition history when providing information. For example, the information provision unit can provide optimal information based on information the user has acquired in the past. The information provision unit can also provide highly relevant information from the user's past information acquisition history. Furthermore, the information provision unit can analyze the user's past information acquisition history and provide the most efficient information. In this way, optimal information is provided by referring to the past information acquisition history. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input the user's past information acquisition history data into a generating AI and have the generating AI perform the task of providing optimal information.

[0062] The information provision unit can provide optimal information by considering the user's device information when providing information. For example, if the user is using a smartphone, the information provision unit can provide information that is adapted to the screen size. Furthermore, if the user is using a tablet, the information provision unit can provide information optimized for a larger screen. In addition, if the user is using a smartwatch, the information provision unit can provide concise and highly visible information. This ensures that optimal information is provided by considering device information. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input the user's device information into a generating AI and have the generating AI perform the task of providing optimal information.

[0063] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit can also reflect specific patterns in the learning algorithm based on past learning data. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. In this way, the learning algorithm is optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0064] The learning unit can weight the training data during training based on when users submit questions and requests. For example, the learning unit weights the training data based on when users submit questions and requests. The learning unit can also adjust the weighting of the training data based on the frequency of user questions and requests. Furthermore, the learning unit can optimize the weighting of the training data based on the content of user questions and requests. This improves the accuracy of training by weighting the training data based on submission timing. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user question and request submission timing data into a generating AI and have the generating AI perform the weighting of the training data.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The AI ​​concierge system can also be equipped with a health management unit that monitors the user's health status. This unit monitors vital signs such as the user's heart rate, blood pressure, and body temperature. This allows for responses tailored to the user's health condition. For example, if the user's heart rate is high, it can provide advice on how to relax. Similarly, if the user's body temperature is high, it can encourage them to rest. Furthermore, the health management unit can record the user's health data over the long term and track changes in their health status. This allows for more effective health management of the user.

[0067] The AI ​​concierge system can also be equipped with a hobby learning unit that learns the user's hobbies and interests. For example, the hobby learning unit analyzes the user's past searches and purchase history to learn their hobbies and interests. This enables more personalized suggestions. For instance, if the user is interested in music, it can provide information on new album releases. Similarly, if the user is interested in travel, it can provide recommendations for travel destinations. Furthermore, the hobby learning unit can track changes in the user's hobbies and interests, providing the latest information. This allows for information tailored to the user's interests.

[0068] The AI ​​concierge system can also be equipped with a behavioral analysis unit that analyzes user behavior patterns. This unit, for example, analyzes the user's travel history and schedule to learn their behavioral patterns. This enables the system to provide suggestions tailored to the user's behavior. For instance, if a user jogs every morning, the system can provide weather forecasts and optimal routes. It can also provide information related to a specific location if the user visits that location on a specific day of the week. Furthermore, the behavioral analysis unit can track changes in the user's behavior patterns and provide appropriate advice, enabling the system to provide information tailored to the user's actions.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The reception desk receives user questions or requests. These questions or requests may be in text or voice format. For example, it may analyze text entered by the user to receive questions or requests. Alternatively, it may use speech recognition technology to convert the user's voice into text to receive questions or requests. Step 2: The recognition unit recognizes the user's facial expressions. For example, it uses a camera to capture the user's face and uses a facial expression recognition algorithm to recognize the user's smile or troubled expression. It can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. Step 3: The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. For example, it can use natural language generation technology to generate appropriate responses to user questions and requests. It can also generate responses to user questions and requests based on generation AI or pre-prepared response templates. Step 4: The providing unit provides the user with the response generated by the generating unit. For example, it may convey the response to the user by voice using speech synthesis technology. Alternatively, it may display the generated response as text and provide it to the user.

[0071] (Example of form 2) The AI ​​concierge system according to an embodiment of the present invention is a system that responds to user questions and requests in natural language while recognizing facial expressions. The AI ​​concierge system can respond to user questions and requests in natural language while recognizing facial expressions. Specifically, first, the user inputs a question or request. For example, the user inputs a request such as "I would like to reserve a meeting room." This information is entered into the reception department. Next, the AI ​​concierge system recognizes the user's facial expression. The recognition unit analyzes the user's facial expression and reads their emotions. For example, it recognizes whether the user is smiling or has a troubled expression. Then, based on the information received by the reception department and the recognition results from the recognition unit, it generates a response. The generation unit generates an appropriate response to the user's request or question. For example, it generates a response such as "Your meeting room reservation has been accepted." Finally, the generated response is provided to the user. The delivery unit conveys the generated response to the user. For example, the AI ​​concierge system can convey the response by voice. This mechanism enables efficient handling of reception work for corporations and public institutions, solving the problem of labor shortages. Furthermore, the AI ​​concierge system possesses features such as multilingual support, facial recognition, body gestures, navigation, information provision, and learning capabilities, enabling smarter and more diverse responses. This can improve the operational efficiency of corporations and public institutions, contributing to the development of society as a whole. As a result, the AI ​​concierge system can respond to user questions and requests in natural language while recognizing their facial expressions.

[0072] The AI ​​concierge system according to this embodiment comprises a reception unit, a recognition unit, a generation unit, and a provision unit. The reception unit receives questions or requests from the user. These questions or requests may include, but are not limited to, text format, voice format, etc. The reception unit may, for example, analyze text entered by the user and receive questions or requests. The reception unit may also analyze voice input and receive questions or requests. For example, it may use speech recognition technology to convert the user's voice into text and receive questions or requests. The recognition unit recognizes the user's facial expressions. The recognition unit may, for example, use a camera to photograph the user's face and analyze the facial expressions. For example, it may use a facial expression recognition algorithm to recognize the user's smile or troubled expression. The recognition unit may also read emotions from the user's voice. For example, it may use speech analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. The generation unit generates appropriate responses to user questions and requests, for example, using natural language generation technology. For example, it generates answers to user questions using generation AI. The generation unit can also perform template-based response generation. For example, it generates responses to user questions and requests based on pre-prepared response templates. The delivery unit provides the responses generated by the generation unit to the user. The delivery unit provides responses, for example, in voice. For example, it conveys the generated responses to the user in voice using speech synthesis technology. The delivery unit can also provide responses in text. For example, it displays the generated responses as text and provides them to the user. As a result, the AI ​​concierge system according to this embodiment can respond to user questions and requests in natural language while recognizing facial expressions.

[0073] The reception desk receives user questions or requests. User questions or requests may include, but are not limited to, text or voice input. The reception desk can, for example, analyze text entered by the user and receive questions or requests. The reception desk can also analyze voice input and receive questions or requests. For example, it can use speech recognition technology to convert the user's voice into text and receive questions or requests. Specifically, the speech recognition technology used is a deep learning-based speech recognition model. This model can learn from a large amount of voice data and convert user speech into text with high accuracy. Furthermore, the reception desk is equipped with natural language processing (NLP) technology to analyze the user's input. By using NLP technology, the intent of the user's questions or requests can be accurately understood and processed appropriately. For example, if a user enters "What's the weather like tomorrow?", the reception desk analyzes this question and starts processing to provide weather information. Also, in the case of voice input, since the user's speech may be affected by noise and background sounds, noise cancellation technology can be used to preprocess the voice data and improve recognition accuracy. This allows the reception desk to handle a variety of user input formats and receive questions and requests accurately and quickly.

[0074] The recognition unit recognizes the user's facial expressions. For example, the recognition unit uses a camera to capture the user's face and analyzes their expressions. For example, it uses a facial expression recognition algorithm to recognize the user's smile or troubled expression. The recognition unit can also read emotions from the user's voice. For example, it uses voice analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. Specifically, a model using a convolutional neural network (CNN) is used as the facial expression recognition algorithm. This model can extract facial feature points and classify emotions such as smiles, anger, and sadness with high accuracy. Furthermore, the recognition unit can also analyze the user's facial and eye movements to grasp their emotional state in more detail. For example, if the user frowns, it can be determined that they are showing confusion or dissatisfaction. As for voice analysis technology, the user's emotional state is estimated by analyzing features such as pitch, tone, speed, and intensity of the voice. For example, if the user's voice is high-pitched and fast, it can be determined that they are showing excitement or tension. This allows the recognition unit to read emotions from multiple angles based on the user's facial expressions and voice, and provide information to generate more natural and appropriate responses.

[0075] The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. The generation unit generates appropriate responses to user questions and requests, for example, using natural language generation technology. For example, it generates answers to user questions using generation AI. The generation unit can also perform template-based response generation. For example, it generates responses to user questions and requests based on pre-prepared response templates. Specifically, a large-scale language model (LLM) based on a transformer model is used as the generation AI. This model can learn from a large amount of text data and generate contextually natural responses to user questions. For example, if a user asks, "Tell me about nearby restaurants," the generation unit will generate a response that suggests appropriate restaurants, taking into account the user's current location and preferred cuisine. Furthermore, template-based response generation can provide quick and consistent responses by using pre-prepared response templates. For example, if a user asks, "Tell me the opening hours," the generation unit will generate a response based on a pre-prepared template regarding opening hours. This allows the generation unit to generate flexible and appropriate responses to user questions and requests.

[0076] The service provider delivers the response generated by the generation unit to the user. The service provider can deliver the response, for example, by voice. For example, it can use speech synthesis technology to deliver the generated response to the user by voice. The service provider can also deliver the response in text. For example, it can display the generated response as text and deliver it to the user. Specifically, text-to-speech (TTS) technology is used as the speech synthesis technology. This technology can convert the generated text into natural-sounding speech and deliver it to the user. For example, if the user asks, "What is the weather forecast?", the service provider can deliver the generated weather forecast response to the user by voice. In the case of text response delivery, the generated response is displayed on the user's device. For example, it can be displayed as text on the screen of a smartphone or tablet so that the user can visually confirm it. Furthermore, the service provider can select the format of the response according to the user's preference. For example, it can deliver a voice response to users who prefer voice responses and a text response to users who prefer text responses. This allows the service provider to deliver the response in the most optimal format for the user and improve the user experience.

[0077] The multilingual support unit can accept user questions or requests in multiple languages. For example, the multilingual support unit can support multiple languages ​​such as English, Japanese, and Spanish. For example, the multilingual support unit can automatically translate text entered by the user and accept questions or requests. Furthermore, the multilingual support unit can automatically translate voice input and accept questions or requests. For example, by combining speech recognition and translation technologies, it can convert the user's voice into text, and then translate it to accept questions or requests. This allows for support of a wider range of users by supporting multiple languages. Some or all of the above-described processes in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input user input data into a generating AI and have the generating AI perform the translation.

[0078] The body gesture unit can recognize the user's body gestures. For example, the body gesture unit can recognize the user's hand movements, head movements, and full-body movements. For example, the body gesture unit can capture the user's movements using a camera and analyze the body gestures. For example, it can use a gesture recognition algorithm to recognize the user's hand and head movements. The body gesture unit can also detect the user's movements using sensors. For example, it can use a motion sensor to recognize the user's full-body movements. This allows for more natural interaction by recognizing the user's body gestures. Some or all of the above processing in the body gesture unit may be performed using AI, or not. For example, the body gesture unit can input user movement data into a generating AI and have the generating AI perform gesture recognition.

[0079] The navigation unit can provide navigation information to the user. For example, the navigation unit can provide map information, directions, and destination information. For example, the navigation unit can obtain the user's current location and guide them to their destination. For example, it can use GPS data to identify the user's current location and guide them to the optimal route based on map information. The navigation unit can also provide information about the user's destination, such as the destination's business hours and contact information. This allows for smoother navigation by providing navigation information to the user. Some or all of the above-described processes in the navigation unit may be performed using AI, or without AI. For example, the navigation unit can input the user's current location data into a generating AI and have the generating AI execute the optimal route guidance.

[0080] The information provision unit can provide users with a variety of information. For example, it can provide news, weather forecasts, and traffic information. For example, the information provision unit can automatically collect the latest news and provide it to users. For example, it can analyze news feeds and extract and provide important news. The information provision unit can also provide weather forecasts. For example, it can analyze meteorological data and provide current weather and future forecasts. The information provision unit can also provide traffic information. For example, it can analyze traffic data and provide information on congestion and traffic accidents. By providing users with a variety of information, it makes it easier for them to obtain information. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input news feed data into a generating AI and have the generating AI extract important news.

[0081] The learning unit can learn through interaction with the user. For example, the learning unit can analyze the history of user questions and requests to improve the system's accuracy. The learning unit can learn user interaction data using machine learning algorithms, for example. For example, it can analyze patterns in user questions and requests to improve the system's response accuracy. The learning unit can also learn based on user feedback. For example, it can analyze user-provided feedback to identify areas for system improvement. In this way, the system's accuracy improves through learning via user interaction. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user interaction data into a generating AI and have the generating AI perform the learning.

[0082] The reception desk can estimate the user's emotions and adjust how questions and requests are received based on the estimated emotions. For example, if the user is stressed, the reception desk can provide a simple interface and minimize the input steps. If the user is relaxed, the reception desk can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception desk can prioritize voice input to allow for quick input of questions and requests. This allows for more appropriate responses by adjusting the reception method according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines 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 desk may be performed using AI or not. For example, the reception desk can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0083] The reception desk can analyze the user's past questions and requests and select the most suitable reception method. For example, the reception desk can automatically display questions and requests that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest questions and requests that will be used during specific time periods based on the user's past questions and requests. This enables more efficient reception by analyzing past history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input data on the user's past questions and requests into a generating AI and have the generating AI select the most suitable reception method.

[0084] The reception unit can filter questions and requests based on the user's current situation and areas of interest. For example, when a user enters their current situation, the reception unit prioritizes receiving questions and requests related to that situation. The reception unit can also filter and receive relevant questions and requests based on the user's areas of interest. Furthermore, the reception unit can exclude unnecessary questions and requests based on the user's current situation and areas of interest. This allows for the reception of more appropriate questions and requests by filtering based on the user's situation and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input data on the user's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0085] The reception desk can estimate the user's emotions and determine the priority of questions and requests to be received based on the estimated emotions. For example, if the user is nervous, the reception desk can prioritize important questions and requests. If the user is relaxed, the reception desk can also prioritize detailed questions and requests. Furthermore, if the user is in a hurry, the reception desk can prioritize questions and requests that require a quick response. In this way, important questions and requests can be prioritized by determining priorities based on the user's emotions. 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 reception desk may be performed using AI, or not using AI. For example, the reception desk can input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0086] The reception desk can prioritize receiving questions and requests that are highly relevant, taking into account the user's geographical location. For example, if a user is in a specific region, the reception desk will prioritize receiving questions and requests related to that region. The reception desk can also filter and receive questions and requests that are highly relevant based on the user's geographical location. Furthermore, the reception desk can exclude unnecessary questions and requests based on the user's current location. In this way, by considering geographical location, highly relevant questions and requests can be prioritized. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's geographical location into a generating AI and have the generating AI perform the filtering of highly relevant questions and requests.

[0087] The reception desk can analyze a user's social media activity when receiving questions or requests and accept relevant questions or requests. For example, the reception desk can analyze a user's social media activity and prioritize accepting relevant questions and requests. The reception desk can also filter and accept questions and requests that are highly relevant based on the user's social media activity. Furthermore, the reception desk can exclude unnecessary questions and requests based on the user's social media activity. In this way, by analyzing social media activity, relevant questions and requests can be prioritized. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity data into a generating AI and have the generating AI perform the filtering of relevant questions and requests.

[0088] The recognition unit can estimate the user's emotions and adjust the accuracy of facial recognition based on the estimated emotions. For example, if the user is tense, the recognition unit performs a detailed analysis to improve the accuracy of facial recognition. The recognition unit can also adjust the accuracy of facial recognition to recognize natural expressions if the user is relaxed. Furthermore, if the user is in a hurry, the recognition unit can adjust the accuracy to quickly recognize expressions. This allows for more accurate facial recognition by adjusting the accuracy of facial recognition based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recognition unit may be performed using AI, or not. For example, the recognition unit can input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0089] The recognition unit can improve recognition accuracy by referring to the user's past facial expression data during facial expression recognition. For example, the recognition unit can improve recognition accuracy by referring to the user's past facial expression data. The recognition unit can also recognize specific facial expressions more accurately based on the user's past facial expression data. Furthermore, the recognition unit can analyze the user's past facial expression data and optimize the recognition algorithm. This improves recognition accuracy by referring to past facial expression data. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's past facial expression data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0090] The recognition unit can perform facial recognition while considering the user's attribute information. For example, the recognition unit can perform facial recognition while considering the user's attribute information such as age and gender. The recognition unit can also perform facial recognition while considering the user's cultural background. Furthermore, the recognition unit can perform facial recognition based on the user's occupation and role. This allows for more accurate facial recognition by considering attribute information. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's attribute information into a generating AI and have the generating AI perform facial recognition.

[0091] The recognition unit can estimate the user's emotions and adjust the display method of the recognition results based on the estimated emotions. For example, if the user is tense, the recognition unit can provide a simple and highly visible display method. If the user is relaxed, the recognition unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the recognition unit can provide a concise display method. By adjusting the display method based on the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0092] The recognition unit can perform facial recognition while considering the user's geographical background. For example, the recognition unit can accurately recognize facial expressions from a specific region by considering the user's geographical background. The recognition unit can also perform facial recognition that takes cultural differences into account based on the user's geographical background. Furthermore, the recognition unit can analyze the user's geographical background and optimize the recognition algorithm. This makes it possible to perform more accurate facial recognition by considering the geographical background. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's geographical background data into a generating AI and have the generating AI perform facial recognition.

[0093] The recognition unit can improve recognition accuracy by referring to the user's relevant literature during facial expression recognition. For example, the recognition unit can refer to the user's relevant literature to recognize specific facial expressions more accurately. The recognition unit can also optimize the recognition algorithm based on the user's relevant literature. Furthermore, the recognition unit can analyze the user's relevant literature to improve recognition accuracy. Thus, recognition accuracy is improved by referring to relevant literature. Some or all of the above processing in the recognition unit may be performed using AI, for example, or without AI. For example, the recognition unit can input the user's relevant literature data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0094] 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 relaxed, the generation unit can generate a response that proceeds at a leisurely pace. If the user is in a hurry, the generation unit can also generate a response that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can generate a response with visually stimulating effects. In this way, by adjusting the response generation method based on the user's emotions, a more appropriate response is generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into a generation AI and have the generation AI perform the generation of responses.

[0095] The generation unit can generate the optimal response by referring to the user's past questions and requests when generating a response. For example, the generation unit can generate the optimal response based on questions and requests the user has made in the past. The generation unit can also generate responses that avoid congestion based on the user's past questions and requests. Furthermore, the generation unit can analyze the user's past questions and requests and generate the most efficient response. In this way, the optimal response is generated by referring to past questions and requests. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on the user's past questions and requests into a generation AI and have the generation AI perform the generation of the optimal response.

[0096] The generation unit can customize responses by considering user attribute information during response generation. For example, the generation unit can customize responses by considering attribute information such as the user's age and gender. It can also customize responses by considering the user's cultural background. Furthermore, the generation unit can customize responses based on the user's occupation and role. This allows for the generation of more appropriate responses by considering attribute information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user attribute information into a generation AI and have the generation AI perform the response customization.

[0097] The generation unit can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is tense, the generation unit will prioritize generating important responses. It can also prioritize generating detailed responses if the user is relaxed. Furthermore, if the user is in a hurry, the generation unit can prioritize generating responses that require a quick response. This allows for the prioritization of important responses by determining the priority of responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not. For example, the generation unit can input user emotion data into a generative AI and have the generative AI determine the priority of responses.

[0098] The generation unit can generate the optimal response by considering the user's geographical location information during response generation. For example, if the user is in a specific region, the generation unit will prioritize generating responses related to that region. The generation unit can also filter and generate highly relevant responses based on the user's geographical location information. Furthermore, the generation unit can exclude unnecessary responses based on the user's current location. This allows for the generation of highly relevant responses by considering geographical location information. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's geographical location information into a generation AI and have the generation AI perform the generation of the optimal response.

[0099] The generation unit can generate responses by analyzing the user's social media activity during response generation. For example, the generation unit can analyze the user's social media activity and prioritize the generation of relevant responses. The generation unit can also filter and generate highly relevant responses based on the user's social media activity. Furthermore, the generation unit can exclude unnecessary responses based on the user's social media activity. This allows for the priority generation of relevant responses by analyzing social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's social media activity data into a generation AI and have the generation AI perform the response generation.

[0100] The service provider can estimate the user's emotions and adjust the way it delivers responses based on those emotions. For example, if the user is nervous, the service provider can deliver a response in a calm voice. If the user is relaxed, the service provider can deliver a response in a cheerful voice. Furthermore, if the user is in a hurry, the service provider can deliver a quick and concise response. By adjusting the delivery method based on the user's emotions, a more appropriate response is provided. 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 service provider may be performed using AI or not. For example, the service provider can input user emotion data into a generative AI and have the generative AI adjust the way it delivers responses.

[0101] The service provider can select the optimal service method by referring to the user's past response history when providing a response. For example, the service provider can select the optimal service method based on the response methods the user has used in the past. The service provider can also predict and suggest a service method to be used during a specific time period based on the user's past response history. Furthermore, the service provider can analyze the user's past response history and select the most efficient service method. In this way, the optimal service method is selected by referring to past response history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past response history data into a generating AI and have the generating AI perform the selection of the optimal service method.

[0102] The service provider can provide responses while considering the user's attribute information. For example, the service provider can provide responses while considering the user's attribute information such as age and gender. The service provider can also provide responses while considering the user's cultural background. Furthermore, the service provider can provide responses based on the user's occupation and role. By considering attribute information, a more appropriate response can be provided. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's attribute information into a generating AI and have the generating AI perform the task of providing responses.

[0103] The service provider can estimate the user's emotions and determine the order in which responses are provided based on the estimated emotions. For example, if the user is tense, the service provider may prioritize providing important responses. Similarly, if the user is relaxed, the service provider may prioritize providing detailed responses. Furthermore, if the user is in a hurry, the service provider may prioritize providing responses that require immediate attention. This allows for the prioritization of important responses by determining the order of responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the service provider may be performed using AI, or not. For example, the service provider can input user emotion data into a generative AI and have the generative AI determine the order in which responses are provided.

[0104] The service provider can select the optimal service delivery method when providing a response, taking into account the user's device information. For example, if the user is using a smartphone, the service provider can provide a service delivery method that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a service delivery method optimized for a larger screen. Additionally, if the user is using a smartwatch, the service provider can provide a concise and highly visible service delivery method. Thus, the optimal service delivery method is selected by considering the device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal service delivery method.

[0105] The service provider can analyze the user's social media activity when providing responses. For example, the service provider can analyze the user's social media activity and prioritize providing relevant responses. The service provider can also filter and provide highly relevant responses based on the user's social media activity. Furthermore, the service provider can exclude unnecessary responses based on the user's social media activity. This allows the service provider to prioritize providing relevant responses by analyzing social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity data into a generating AI and have the generating AI perform the task of providing responses.

[0106] The multilingual support unit can estimate the user's emotions and adjust the multilingual support method based on the estimated emotions. For example, if the user is nervous, the multilingual support unit can provide a simple and highly visible multilingual support method. If the user is relaxed, it can also provide a multilingual support method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a concise multilingual support method. By adjusting the multilingual support method based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 multilingual support unit may be performed using AI, for example, or not using AI. For example, the multilingual support unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the multilingual support method.

[0107] The multilingual support unit can select the optimal support method by referring to the user's past language usage history when providing multilingual support. For example, the multilingual support unit can select the optimal support method based on the languages ​​the user has used in the past. The multilingual support unit can also predict and suggest the languages ​​the user will use at a specific time based on their past language usage history. Furthermore, the multilingual support unit can analyze the user's past language usage history and select the most efficient support method. In this way, the optimal support method is selected by referring to past language usage history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the user's past language usage history data into a generating AI and have the generating AI perform the selection of the optimal support method.

[0108] The multilingual support unit can estimate the user's emotions and determine the priority of multilingual support based on the estimated emotions. For example, if the user is stressed, the multilingual support unit can prioritize the multilingual support of important information. Furthermore, if the user is relaxed, the multilingual support unit can prioritize the multilingual support of detailed information. Additionally, if the user is in a hurry, the multilingual support unit can prioritize the multilingual support of information requiring a quick response. This allows for the prioritization of important information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the multilingual support unit may be performed using AI, or not. For example, the multilingual support unit can input user emotion data into a generative AI and have the generative AI determine the priority of multilingual support.

[0109] The multilingual support unit can select the optimal support method by considering the user's geographical location information when providing multilingual support. For example, if the user is in a specific region, the multilingual support unit will prioritize supporting languages ​​related to that region. The multilingual support unit can also filter and support highly relevant languages ​​based on the user's geographical location information. Furthermore, the multilingual support unit can exclude unnecessary languages ​​based on the user's current location. This allows for prioritization of highly relevant languages ​​by considering geographical location information. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the user's geographical location information into a generating AI and have the generating AI select the optimal support method.

[0110] The body gesture unit can estimate the user's emotions and adjust the method of recognizing body gestures based on the estimated emotions. For example, if the user is nervous, the body gesture unit can perform a detailed analysis to improve the accuracy of body gesture recognition. It can also adjust the accuracy to recognize natural body gestures if the user is relaxed. Furthermore, if the user is in a hurry, the body gesture unit can adjust the accuracy to recognize body gestures quickly. This allows for more accurate body gesture recognition by adjusting the recognition method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the body gesture unit may be performed using AI, or not. For example, the body gesture unit can input user emotion data into the generative AI and have the generative AI adjust the method of recognizing body gestures.

[0111] The body gesture unit can improve recognition accuracy by referring to the user's past gesture data during body gesture recognition. For example, the body gesture unit can improve recognition accuracy by referring to the user's past gesture data. The body gesture unit can also recognize specific gestures more accurately based on the user's past gesture data. Furthermore, the body gesture unit can analyze the user's past gesture data and optimize the recognition algorithm. This improves recognition accuracy by referring to past gesture data. Some or all of the above processing in the body gesture unit may be performed using AI, for example, or without AI. For example, the body gesture unit can input the user's past gesture data into a generating AI and have the generating AI perform the improvement of recognition accuracy.

[0112] The body gesture unit can estimate the user's emotions and adjust the display method of body gestures based on the estimated emotions. For example, if the user is nervous, the body gesture unit can provide a simple and highly visible display method. If the user is relaxed, the body gesture unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the body gesture unit can provide a display method that gets straight to the point. By adjusting the display method based on the user's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 body gesture unit may be performed using AI, for example, or without AI. For example, the body gesture unit can input user emotion data into the generative AI and have the generative AI adjust the display method of body gestures.

[0113] The body gesture unit can perform recognition while considering the user's geographical background. For example, the body gesture unit can accurately recognize gestures from a specific region by considering the user's geographical background. Furthermore, the body gesture unit can perform gesture recognition that takes cultural differences into account based on the user's geographical background. In addition, the body gesture unit can analyze the user's geographical background and optimize the recognition algorithm. This enables more accurate body gesture recognition by considering geographical background. Some or all of the above processing in the body gesture unit may be performed using AI, for example, or without AI. For example, the body gesture unit can input the user's geographical background data into a generating AI and have the generating AI perform gesture recognition.

[0114] The navigation unit can estimate the user's emotions and adjust how navigation information is provided based on the estimated emotions. For example, if the user is tense, the navigation unit can provide simple and easily visible navigation information. If the user is relaxed, the navigation unit can also provide navigation information that includes detailed information. Furthermore, if the user is in a hurry, the navigation unit can provide concise navigation information. By adjusting the delivery method based on the user's emotions, more appropriate navigation information is provided. 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 navigation unit may be performed using AI, or not using AI. For example, the navigation unit can input user emotion data into the generative AI and have the generative AI adjust how navigation information is provided.

[0115] The navigation unit can provide optimal information by referring to the user's past travel history when providing navigation information. For example, the navigation unit can provide optimal navigation information based on routes previously used by the user. The navigation unit can also provide navigation information that avoids congestion based on the user's past travel history. Furthermore, the navigation unit can analyze the user's past travel history and provide the most efficient navigation information. In this way, optimal navigation information is provided by referring to past travel history. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the user's past travel history data into a generating AI and have the generating AI perform the task of providing optimal navigation information.

[0116] The navigation unit can estimate the user's emotions and prioritize navigation information based on the estimated emotions. For example, if the user is stressed, the navigation unit can prioritize important navigation information. It can also prioritize detailed navigation information if the user is relaxed. Furthermore, if the user is in a hurry, the navigation unit can prioritize navigation information requiring immediate attention. This allows for the prioritization of important navigation information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the navigation unit may be performed using AI or not. For example, the navigation unit can input user emotion data into a generative AI and have the generative AI determine the priority of navigation information.

[0117] The navigation unit can provide optimal information by considering the user's device information when providing navigation information. For example, if the user is using a smartphone, the navigation unit can provide navigation information that is adapted to the screen size. Furthermore, if the user is using a tablet, the navigation unit can provide navigation information optimized for a larger screen. Additionally, if the user is using a smartwatch, the navigation unit can provide concise and highly visible navigation information. In this way, optimal navigation information is provided by considering device information. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the user's device information into a generating AI and have the generating AI perform the task of providing optimal navigation information.

[0118] The information delivery unit can estimate the user's emotions and adjust the method of information delivery based on the estimated emotions. For example, if the user is nervous, the information delivery unit can provide a simple and highly visible method of information delivery. If the user is relaxed, the information delivery unit can also provide a method of information delivery that includes detailed information. Furthermore, if the user is in a hurry, the information delivery unit can provide a concise method of information delivery. In this way, more appropriate information is provided by adjusting the method of information delivery based on the user's emotions. 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 information delivery unit may be performed using AI, for example, or not using AI. For example, the information delivery unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the method of information delivery.

[0119] The information provision unit can provide optimal information by referring to the user's past information acquisition history when providing information. For example, the information provision unit can provide optimal information based on information the user has acquired in the past. The information provision unit can also provide highly relevant information from the user's past information acquisition history. Furthermore, the information provision unit can analyze the user's past information acquisition history and provide the most efficient information. In this way, optimal information is provided by referring to the past information acquisition history. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input the user's past information acquisition history data into a generating AI and have the generating AI perform the task of providing optimal information.

[0120] The information provision unit can estimate the user's emotions and determine the priority of information provision based on the estimated emotions. For example, if the user is stressed, the information provision unit can prioritize providing important information. It can also prioritize providing detailed information if the user is relaxed. Furthermore, if the user is in a hurry, the information provision unit can prioritize providing information that requires immediate attention. This allows for the priority provision of important information by determining priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information provision unit may be performed using AI, or not. For example, the information provision unit can input user emotion data into a generative AI and have the generative AI determine the priority of information provision.

[0121] The information provision unit can provide optimal information by considering the user's device information when providing information. For example, if the user is using a smartphone, the information provision unit can provide information that is adapted to the screen size. Furthermore, if the user is using a tablet, the information provision unit can provide information optimized for a larger screen. In addition, if the user is using a smartwatch, the information provision unit can provide concise and highly visible information. This ensures that optimal information is provided by considering device information. Some or all of the above processing in the information provision unit may be performed using AI, for example, or without AI. For example, the information provision unit can input the user's device information into a generating AI and have the generating AI perform the task of providing optimal information.

[0122] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit can select detailed training data. If the user is in a hurry, the learning unit can also select concise training data. Furthermore, if the user is excited, the learning unit can select visually stimulating training data. This allows for more effective learning by selecting training data based on the user's emotions. 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 learning unit may be performed using AI, or not using AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0123] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit can also reflect specific patterns in the learning algorithm based on past learning data. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. In this way, the learning algorithm is optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0124] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can increase the learning frequency when the user is relaxed. It can also decrease the learning frequency when the user is in a hurry. Furthermore, if the user is excited, the learning unit can adjust the learning frequency to achieve optimal learning. This allows for more effective learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into the generative AI and have the generative AI adjust the learning frequency.

[0125] The learning unit can weight the training data during training based on when users submit questions and requests. For example, the learning unit weights the training data based on when users submit questions and requests. The learning unit can also adjust the weighting of the training data based on the frequency of user questions and requests. Furthermore, the learning unit can optimize the weighting of the training data based on the content of user questions and requests. This improves the accuracy of training by weighting the training data based on submission timing. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user question and request submission timing data into a generating AI and have the generating AI perform the weighting of the training data.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] The AI ​​concierge system can also be equipped with a health management unit that monitors the user's health status. This unit monitors vital signs such as the user's heart rate, blood pressure, and body temperature. This allows for responses tailored to the user's health condition. For example, if the user's heart rate is high, it can provide advice on how to relax. Similarly, if the user's body temperature is high, it can encourage them to rest. Furthermore, the health management unit can record the user's health data over the long term and track changes in their health status. This allows for more effective health management of the user.

[0128] The AI ​​concierge system can also be equipped with a hobby learning unit that learns the user's hobbies and interests. For example, the hobby learning unit analyzes the user's past searches and purchase history to learn their hobbies and interests. This enables more personalized suggestions. For instance, if the user is interested in music, it can provide information on new album releases. Similarly, if the user is interested in travel, it can provide recommendations for travel destinations. Furthermore, the hobby learning unit can track changes in the user's hobbies and interests, providing the latest information. This allows for information tailored to the user's interests.

[0129] The AI ​​concierge system can also be equipped with a behavioral analysis unit that analyzes user behavior patterns. This unit, for example, analyzes the user's travel history and schedule to learn their behavioral patterns. This enables the system to provide suggestions tailored to the user's behavior. For instance, if a user jogs every morning, the system can provide weather forecasts and optimal routes. It can also provide information related to a specific location if the user visits that location on a specific day of the week. Furthermore, the behavioral analysis unit can track changes in the user's behavior patterns and provide appropriate advice, enabling the system to provide information tailored to the user's actions.

[0130] The AI ​​concierge system may further include a music recommendation unit that estimates the user's emotions and recommends music based on those emotions. For example, if the user is relaxed, the music recommendation unit may recommend relaxing music. If the user is stressed, it may also recommend stress-relieving music. Furthermore, if the user is excited, it may recommend energetic music. This enables music recommendations that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processing in the music recommendation unit may be performed using AI, or not using AI.

[0131] The AI ​​concierge system may further include an exercise suggestion unit that estimates the user's emotions and suggests exercises based on those emotions. For example, if the user is relaxed, the exercise suggestion unit may suggest light stretching. If the user is stressed, it may also suggest stress-relieving exercises. Furthermore, if the user is excited, it may suggest energetic exercises. This enables exercise suggestions that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processing in the exercise suggestion unit may be performed using AI, or not using AI.

[0132] The AI ​​concierge system may further include a meal suggestion unit that estimates the user's emotions and suggests meals based on those emotions. For example, if the user is relaxed, the meal suggestion unit may suggest a relaxing meal. If the user is stressed, it may also suggest a stress-relieving meal. Furthermore, if the user is excited, it may suggest an energetic meal. This enables meal suggestions tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processing in the meal suggestion unit may be performed using AI, or not using AI.

[0133] The AI ​​concierge system may further include a relaxation suggestion unit that estimates the user's emotions and proposes relaxation methods based on the estimated emotions. For example, if the user is relaxed, the relaxation suggestion unit may suggest ways to relax. If the user is stressed, it may also suggest relaxation methods to relieve stress. Furthermore, if the user is excited, it may also suggest energetic relaxation methods. This enables relaxation suggestions that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Some or all of the above-described processing in the relaxation suggestion unit may be performed using AI, or not using AI.

[0134] The AI ​​concierge system may further include a travel suggestion unit that estimates the user's emotions and proposes travel plans based on those emotions. For example, if the user is relaxed, the travel suggestion unit may propose a relaxing travel plan. If the user is stressed, it may also propose a stress-relieving travel plan. Furthermore, if the user is excited, it may propose an energetic travel plan. This enables travel suggestions tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processing in the travel suggestion unit may be performed using AI, or not using AI.

[0135] The AI ​​concierge system may further include a reading recommendation section that estimates the user's emotions and recommends books based on those emotions. For example, if the user is relaxed, the reading recommendation section may recommend relaxing books. If the user is stressed, it may recommend books that reduce stress. Furthermore, if the user is excited, it may recommend energetic books. This enables reading recommendations that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processes in the reading recommendation section may be performed using AI, or they may not be performed using AI.

[0136] The AI ​​concierge system may further include a movie recommendation section that estimates the user's emotions and recommends movies based on those emotions. For example, if the user is relaxed, the movie recommendation section may recommend relaxing movies. If the user is stressed, it may recommend movies that reduce stress. Furthermore, if the user is excited, it may recommend energetic movies. This enables movie recommendations that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Some or all of the above-described processes in the movie recommendation section may be performed using AI, or they may not be performed using AI.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The reception desk receives user questions or requests. These questions or requests may be in text or voice format. For example, it may analyze text entered by the user to receive questions or requests. Alternatively, it may use speech recognition technology to convert the user's voice into text to receive questions or requests. Step 2: The recognition unit recognizes the user's facial expressions. For example, it uses a camera to capture the user's face and uses a facial expression recognition algorithm to recognize the user's smile or troubled expression. It can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate their emotions. Step 3: The generation unit generates a response based on the information received by the reception unit and the recognition results from the recognition unit. For example, it can use natural language generation technology to generate appropriate responses to user questions and requests. It can also generate responses to user questions and requests based on generation AI or pre-prepared response templates. Step 4: The providing unit provides the user with the response generated by the generating unit. For example, it may convey the response to the user by voice using speech synthesis technology. Alternatively, it may display the generated response as text and provide it to the user.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] For example, the reception unit is implemented by the reception device 38 of the smart device 14 and receives user questions and requests. For example, the recognition unit is implemented by the camera 42 and control unit 46A of the smart device 14 and recognizes the user's facial expressions. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates responses to user questions and requests. For example, the provision unit is implemented by the output device 40 of the smart device 14 and provides the generated responses to the user. For example, the multilingual support unit is implemented by the specific processing unit 290 of the data processing device 12 and supports multiple languages. For example, the body gesture unit is implemented by the camera 42 and control unit 46A of the smart device 14 and recognizes the user's body gestures. For example, the navigation unit is implemented by the specific processing unit 290 of the data processing device 12 and provides navigation information to the user. For example, the information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides various information to the user. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12, and learns through interaction with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and receives user questions and requests. For example, the recognition unit is implemented by the camera 42 and control unit 46A of the smart glasses 214 and recognizes the user's facial expressions. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates responses to user questions and requests. For example, the provision unit is implemented by the speaker 240 of the smart glasses 214 and provides the generated responses to the user. For example, the multilingual support unit is implemented by the specific processing unit 290 of the data processing device 12 and supports multiple languages. For example, the body gesture unit is implemented by the camera 42 and control unit 46A of the smart glasses 214 and recognizes the user's body gestures. For example, the navigation unit is implemented by the specific processing unit 290 of the data processing device 12 and provides navigation information to the user. For example, the information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides various information to the user. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12, and learns through interaction with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and receives user questions and requests. For example, the recognition unit is implemented by the camera 42 and control unit 46A of the headset terminal 314 and recognizes the user's facial expressions. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates responses to user questions and requests. For example, the provision unit is implemented by the speaker 240 of the headset terminal 314 and provides the generated responses to the user. For example, the multilingual support unit is implemented by the specific processing unit 290 of the data processing device 12 and supports multiple languages. For example, the body gesture unit is implemented by the camera 42 and control unit 46A of the headset terminal 314 and recognizes the user's body gestures. For example, the navigation unit is implemented by the specific processing unit 290 of the data processing device 12 and provides navigation information to the user. For example, the information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides various information to the user. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12, and learns through interaction with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.).

[0188] 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.

[0189] 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.

[0190] 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.

[0191] For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives user questions and requests. For example, the recognition unit is implemented by the camera 42 and control unit 46A of the robot 414 and recognizes the user's facial expressions. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates responses to user questions and requests. For example, the provision unit is implemented by the speaker 240 of the robot 414 and provides the generated responses to the user. For example, the multilingual support unit is implemented by the specific processing unit 290 of the data processing device 12 and supports multiple languages. For example, the body gesture unit is implemented by the camera 42 and control unit 46A of the robot 414 and recognizes the user's body gestures. For example, the navigation unit is implemented by the specific processing unit 290 of the data processing device 12 and provides navigation information to the user. For example, the information provision unit is implemented by the specific processing unit 290 of the data processing device 12 and provides various information to the user. For example, the learning unit is implemented by the specific processing unit 290 of the data processing device 12, and learns through interaction with the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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."

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] (Note 1) A reception desk that accepts user questions or requests, The recognition unit recognizes the user's facial expression, A generation unit generates a response based on the information received by the reception unit and the recognition result by the recognition unit, The system includes a providing unit that provides the response generated by the generating unit to the user. A system characterized by the following features. (Note 2) It features a multilingual support section that accepts user questions or requests in multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a body gesture unit that recognizes the user's body gestures. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a navigation unit that provides navigation information to the user. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes an information provision unit that provides users with multiple pieces of information. The system described in Appendix 1, characterized by the features described herein. (Note 6) It features a learning unit that learns through interaction with the user. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is We estimate the user's emotions and adjust how we receive questions and requests based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past questions and requests to select the most suitable method of handling them. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving questions or requests, 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 10) The aforementioned reception unit is It estimates the user's emotions and prioritizes the questions and requests it receives based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving questions and requests, the system prioritizes those that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving questions or requests, the system analyzes the user's social media activity and selects relevant questions or requests. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned recognition unit, It estimates the user's emotions and adjusts the accuracy of facial recognition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned recognition unit, When recognizing facial expressions, the system improves recognition accuracy by referencing the user's past facial expression data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned recognition unit, When recognizing facial expressions, the recognition process takes into account the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned recognition unit, It estimates the user's emotions and adjusts how the recognition results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned recognition unit, When recognizing facial expressions, the recognition process takes into account the user's geographical background. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned recognition unit, During facial recognition, the system improves recognition accuracy by referencing relevant literature from the user. The system described in Appendix 1, characterized by the features described herein. (Note 19) 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 20) The generating unit is When generating a response, the system refers to the user's past questions and requests to generate the most appropriate response. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating a response, customize the response by taking into account the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and determines the priority of responses based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating a response, the system takes the user's geographical location into consideration to generate the optimal response. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating a response, the system analyzes the user's social media activity to generate the response. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way responses are delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing a response, the system will refer to the user's past response history to select the most suitable method of delivery. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing a response, the response will be provided taking into account the user's attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, The system estimates the user's emotions and determines the order in which responses are provided based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing a response, the optimal delivery method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing a response, the system analyzes the user's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned multilingual support unit is It estimates the user's emotions and adjusts the multilingual support method based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned multilingual support unit is When implementing multilingual support, the system selects the optimal support method by referring to the user's past language usage history. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned multilingual support unit is It estimates user sentiment and determines the priority of multilingual support based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned multilingual support unit is When providing multilingual support, the optimal support method is selected by considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 35) The body gesture unit is It estimates the user's emotions and adjusts the body gesture recognition method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The body gesture unit is When recognizing body gestures, the system improves recognition accuracy by referencing the user's past gesture data. The system described in Appendix 3, characterized by the features described herein. (Note 37) The body gesture unit is It estimates the user's emotions and adjusts how body gestures are displayed based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The body gesture unit is When recognizing body gestures, the recognition process takes into account the user's geographical background. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned navigation unit is It estimates the user's emotions and adjusts how navigation information is provided based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned navigation unit is When providing navigation information, the system refers to the user's past travel history to provide the most suitable information. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned navigation unit is It estimates the user's emotions and prioritizes navigation information based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned navigation unit is When providing navigation information, we will provide the most suitable information by taking into account the user's device information. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned information provision unit, It estimates the user's emotions and adjusts the way information is provided based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned information provision unit, When providing information, we refer to the user's past information acquisition history to provide the most relevant information. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned information provision unit, The system estimates the user's emotions and prioritizes information provision based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned information provision unit, When providing information, we will provide the most relevant information by taking into account the user's device information. The system described in Appendix 5, characterized by the features described herein. (Note 47) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 48) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 6, characterized by the features described herein. (Note 49) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 6, characterized by the features described herein. (Note 50) The aforementioned learning unit, During training, the training data is weighted based on when users submitted their questions and requests. The system described in Appendix 6, characterized by the features described herein. [Explanation of symbols]

[0211] 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 accepts user questions or requests, The recognition unit recognizes the user's facial expression, A generation unit generates a response based on the information received by the reception unit and the recognition result by the recognition unit, The system includes a providing unit that provides the response generated by the generating unit to the user. A system characterized by the following features.

2. It includes a multilingual support unit that accepts user questions or requests in multiple languages. The system according to feature 1.

3. The system includes a body gesture unit that recognizes the user's body gestures. The system according to feature 1.

4. The system includes a navigation unit that provides navigation information to the user. The system according to feature 1.

5. The system includes an information provision unit that provides multiple pieces of information to the aforementioned user. The system according to feature 1.

6. It includes a learning unit that learns through interaction with the user. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the user's emotions and adjusts the method of receiving questions and requests based on the estimated user emotions. The system according to feature 1.

8. The aforementioned reception unit is The system analyzes the user's past questions and requests to select the most appropriate method of handling them. The system according to feature 1.

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

Images