system

Abstract

The system according to the embodiment aims to evaluate safety by analyzing the face, facial expression, and voice quality of visitors and calculating a risk index. [Solution] A system according to an embodiment includes a face recognition unit, an expression analysis unit, a voice quality analysis unit, and a risk calculation unit. The face recognition unit recognizes the face of a visitor. The expression analysis unit analyzes the facial expression recognized by the face recognition unit. The voice quality analysis unit analyzes the voice quality based on the expression analyzed by the expression analysis unit. The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to quickly and accurately assess the safety of visitors, and ensuring safety is particularly problematic when only children are present at home.

[0005] The system according to the embodiment aims to evaluate safety by analyzing the face, facial expression, and voice quality of visitors and calculating a risk index. [Means for solving the problem]

[0006] The system according to the embodiment includes a face recognition unit, an expression analysis unit, a voice quality analysis unit, and a risk calculation unit. The face recognition unit recognizes the face of a visitor. The expression analysis unit analyzes the expression of the face recognized by the face recognition unit. The voice quality analysis unit analyzes the voice quality based on the expression analyzed by the expression analysis unit. The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can evaluate safety by analyzing the face, facial expression, and voice quality of visitors and calculating a risk index. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A home intercom system according to an embodiment of the present invention displays a risk index based on a visitor's face, facial expression, and voice quality. This system captures the visitor's face with a camera and identifies the visitor using facial recognition technology. Next, the system analyzes the visitor's facial expression using facial expression analysis technology to determine their emotional state. Furthermore, the system analyzes the visitor's voice using voice quality analysis technology to evaluate their tone and nervousness. Based on this information, a risk index is calculated and displayed on a monitor. Safety is also assessed based on past visitor history and national crime case data. For example, if the same visitor has visited multiple times in the past or if the visitor is from a nationally high-crime area, a warning is displayed if the risk is deemed high. Furthermore, by linking with a smartphone, the system can detect danger even when the user is out. For example, if a visitor arrives while the user is out, a notification is sent to the user's smartphone, allowing the user to confirm the visitor's face and voice. This allows the user to ensure the safety of their home even when the user is out. This system allows the user to grasp the risk level of visitors in advance and take measures when a problem occurs. This system can particularly enhance safety when only children are at home, allowing the user to feel more secure even when the user is out. For example, a visitor's face is photographed with a camera and identified using facial recognition technology. Next, facial expression analysis technology is used to analyze the visitor's facial expression and determine their emotional state. Furthermore, voice quality analysis technology is used to analyze the visitor's voice and evaluate their tone and level of tension. Based on this information, a risk index is calculated and displayed on the monitor. Safety is also assessed based on past visitor history and national crime case data. For example, if the same visitor has visited multiple times in the past or if the visitor is from a nationally high-crime area, a warning is displayed if the risk is deemed high. Furthermore, by linking with a smartphone, danger can be detected even when the user is out. For example, if a visitor arrives while the user is out, a notification is sent to the user's smartphone, allowing the user to confirm the visitor's face and voice. This allows the user to ensure the safety of their home even when the user is out. This system allows the user to grasp the visitor's risk level in advance and take measures if a problem occurs. This system can particularly enhance safety when children are at home alone, allowing the user to feel more secure even when the user is out.This allows the home intercom system to grasp the danger level of visitors in advance and evaluate their safety.

[0029] The home intercom system according to the embodiment includes a face recognition unit, an expression analysis unit, a voice quality analysis unit, and a risk level calculation unit. The face recognition unit recognizes the face of a visitor. The face recognition unit recognizes the face using, for example, deep learning technology. The face recognition unit can also recognize the face using pattern matching technology. The face recognition unit can also extract facial feature points and recognize the face based on the extracted feature points. For example, the face recognition unit uses deep learning technology to recognize the face of a visitor with high accuracy. The face recognition unit can also use pattern matching technology to determine whether the face matches pre-registered facial data. The face recognition unit can also extract facial feature points and recognize the face based on the extracted feature points. The expression analysis unit analyzes the facial expression of the face recognized by the face recognition unit. The expression analysis unit analyzes the facial expression using, for example, an expression recognition algorithm. The expression analysis unit can also determine the type of expression. The expression analysis unit can also analyze changes in facial expression. For example, the expression analysis unit analyzes the facial expression of the visitor using an expression recognition algorithm. The facial expression analysis unit can also determine the type of facial expression and estimate the emotional state of the visitor. The facial expression analysis unit can also analyze changes in facial expressions and grasp changes in the visitor's emotions. The voice quality analysis unit analyzes voice quality based on the facial expression analyzed by the facial expression analysis unit. The voice quality analysis unit analyzes voice quality using, for example, a voice feature extraction algorithm. The voice quality analysis unit can also evaluate voice tone and tension. The voice quality analysis unit can also analyze voice changes. For example, the voice quality analysis unit analyzes the voice quality of the visitor using a voice feature extraction algorithm. The voice quality analysis unit can also evaluate voice tone and tension and estimate the visitor's emotional state. The voice quality analysis unit can also analyze voice changes and grasp changes in the visitor's emotions. The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit. The risk calculation unit calculates the risk index using, for example, a scoring algorithm. The risk calculation unit can also evaluate the risk based on evaluation criteria. Furthermore, the risk calculation unit can also evaluate the risk by referring to past data.For example, the danger level calculation unit calculates a danger level index of a visitor using a scoring algorithm. The danger level calculation unit can also evaluate the danger level of a visitor based on evaluation criteria. Furthermore, the danger level calculation unit can evaluate the danger level of a visitor by referring to past data. As a result, the home intercom system according to the embodiment can grasp the danger level of a visitor in advance and evaluate safety by analyzing the face, expression, and voice quality of the visitor and calculating a danger level index.

[0030] The acquisition unit can acquire past visit history. The acquisition unit, for example, records the visit date and time of the visitor. The acquisition unit can also record the number of visits by the visitor. Furthermore, the acquisition unit can also record the purpose of the visit by the visitor. For example, the acquisition unit records the visit date and time of the visitor and manages the past visit history. The acquisition unit can also record the number of visits by the visitor and identify frequent visitors. Furthermore, the acquisition unit can record the purpose of the visit by the visitor and understand the behavioral patterns of the visitor. In this way, by acquiring the past visit history, reference information can be provided when evaluating the safety of the visitor. Some or all of the above-mentioned processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the visit date and time of the visitor to AI and have the AI ​​analyze the number of visits and the purpose of the visit.

[0031] The acquisition unit can acquire nationwide crime case data. The acquisition unit acquires data, for example, from a crime case database. The acquisition unit can also acquire crime case data from public police data. Furthermore, the acquisition unit can collect crime case data from news articles and reports. For example, the acquisition unit acquires data from a crime case database and manages nationwide crime cases. The acquisition unit can also acquire crime case data from public police data to grasp the latest crime information. Furthermore, the acquisition unit can collect crime case data from news articles and reports and analyze local crime trends. In this way, acquiring nationwide crime case data can provide reference information for evaluating visitor safety. Some or all of the above-mentioned processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input data acquired from the crime case database into AI and have the AI ​​analyze crime trends.

[0032] The evaluation unit can evaluate safety based on the data acquired by the acquisition unit. The evaluation unit can evaluate safety based on, for example, the visitor's past visit history. The evaluation unit can also evaluate safety based on nationwide crime case data. The evaluation unit can also evaluate safety based on the visitor's behavioral patterns. For example, the evaluation unit can evaluate the safety of frequent visitors based on the visitor's past visit history. The evaluation unit can also evaluate the safety of visitors from high-crime areas based on nationwide crime case data. The evaluation unit can also evaluate the safety of visitors exhibiting abnormal behavior based on the visitor's behavioral patterns. In this way, evaluating safety based on the acquired data can more accurately determine the visitor's risk level. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can input the visitor's past visit history and crime case data into AI and have the AI ​​perform a safety evaluation.

[0033] The notification unit can send a notification to the smartphone when a visitor arrives while the user is out. For example, the notification unit can send a notification to the smartphone when the visitor presses the intercom. The notification unit can also send a notification to the smartphone when the visitor is captured on camera. The notification unit can also send a notification to the smartphone when the visitor makes a sound. For example, the notification unit can send a push notification to the smartphone when the visitor presses the intercom. The notification unit can also send a notification with an image to the smartphone when the visitor is captured on camera. The notification unit can also send a notification with audio to the smartphone when the visitor makes a sound. This allows the user to check visitor information on their smartphone even when they are out, thereby ensuring the safety of their home. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the visitor's behavior into AI and have the AI ​​determine the timing and content of the notification.

[0034] The notification unit can display the visitor's face and voice on the smartphone. For example, the notification unit can capture the visitor's face with a camera and stream the video to the smartphone. The notification unit can also record the visitor's voice with a microphone and stream the audio to the smartphone. Furthermore, the notification unit can simultaneously display the visitor's face and voice on the smartphone. For example, the notification unit can capture the visitor's face with a camera and stream the video to the smartphone in real time. The notification unit can also record the visitor's voice with a microphone and stream the audio to the smartphone in real time. Furthermore, the notification unit can simultaneously display the visitor's face and voice on the smartphone, allowing detailed visitor information to be confirmed. This allows the visitor's information to be confirmed even when the visitor is out by displaying the visitor's face and voice on the smartphone. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the visitor's face and voice data into AI and have the AI ​​optimize the streaming.

[0035] When recognizing a face, the face recognition unit can determine the recognition priority by referring to the visitor's past visit history. For example, the face recognition unit may prioritize recognition of visitors who have visited frequently in the past. The face recognition unit may also prioritize recognition of visitors who have caused problems in the past. Furthermore, the face recognition unit may also prioritize recognition of visitors who have never visited before. For example, the face recognition unit may prioritize recognition of visitors who have visited frequently in the past to quickly identify important visitors. The face recognition unit may also prioritize recognition of visitors who have caused problems in the past to strengthen vigilance. Furthermore, the face recognition unit may prioritize recognition of visitors who have never visited before to identify new visitors. In this way, by referring to the past visit history, important visitors can be prioritized. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI, or may be performed without AI. For example, the face recognition unit may input visitor's past visit history data into AI and have the AI ​​determine the recognition priority.

[0036] The face recognition unit can adjust the recognition algorithm based on the visitor's age and gender during face recognition. For example, the face recognition unit optimizes the face recognition algorithm for older visitors. The face recognition unit can also optimize the face recognition algorithm for younger visitors. Furthermore, the face recognition unit can optimize the face recognition algorithm according to gender. For example, the face recognition unit optimizes the face recognition algorithm for older visitors to improve recognition accuracy. The face recognition unit can also optimize the face recognition algorithm for younger visitors to improve recognition accuracy. Furthermore, the face recognition unit can optimize the face recognition algorithm according to gender to improve recognition accuracy. In this way, optimizing the recognition algorithm according to the visitor's age and gender improves the accuracy of face recognition. Some or all of the above-described processing in the face recognition unit may be performed using, or without, AI. For example, the face recognition unit can input the visitor's age and gender data into AI and have the AI ​​adjust the recognition algorithm.

[0037] The face recognition unit can improve the accuracy of face recognition by taking into account the geographical location information of a visitor. For example, if a visitor comes from a specific area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a distant location, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a nearby area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. For example, if a visitor comes from a specific area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a distant location, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a nearby area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. In this way, the accuracy of face recognition is improved by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI or without using AI. For example, the facial recognition unit can input the visitor's geographic location information into the AI, allowing the AI ​​to improve the accuracy of facial recognition.

[0038] The face recognition unit can improve the accuracy of face recognition based on the visitor's clothing and belongings. The face recognition unit can improve the accuracy of face recognition, for example, by analyzing the color and design of the visitor's clothing. The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's belongings (such as a bag or umbrella). The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's accessories (such as glasses or a hat). For example, the face recognition unit can improve the accuracy of face recognition by analyzing the color and design of the visitor's clothing. The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's belongings (such as a bag or umbrella). The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's accessories (such as glasses or a hat). In this way, the accuracy of face recognition is improved by analyzing the visitor's clothing and belongings. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the facial recognition unit can input data on visitors' clothing and belongings into the AI, allowing the AI ​​to improve the accuracy of recognition.

[0039] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from previous visits by the same visitor. The facial expression analysis unit can also improve the accuracy of the analysis by referring to facial expression data from visitors who have caused problems in the past. Furthermore, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from visitors who have never visited before. For example, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from previous visits by the same visitor. The facial expression analysis unit can also improve the accuracy of the analysis by referring to facial expression data from visitors who have caused problems in the past. Furthermore, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from visitors who have never visited before. In this way, the accuracy of the facial expression analysis is improved by referring to past facial expression data. Some or all of the above-described processing in the facial expression analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the facial expression analysis unit can input the visitor's past facial expression data into AI and have the AI ​​improve the accuracy of the analysis.

[0040] The facial expression analysis unit can adjust the analysis algorithm based on the visitor's cultural background when analyzing facial expressions. The facial expression analysis unit can optimize the facial expression analysis algorithm based on, for example, the visitor's cultural background. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's nationality or region. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's religion or customs. For example, the facial expression analysis unit can optimize the facial expression analysis algorithm based on the visitor's cultural background to improve analysis accuracy. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's nationality or region to improve analysis accuracy. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's religion or customs to improve analysis accuracy. This improves the accuracy of facial expression analysis by taking the visitor's cultural background into consideration. Some or all of the above-described processing in the facial expression analysis unit can be performed using, for example, AI, or without AI. For example, the facial expression analysis unit can input the visitor's cultural background data into AI and have the AI ​​adjust the analysis algorithm.

[0041] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's body temperature and heart rate during facial expression analysis. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's body temperature. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's heart rate. Furthermore, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to both the visitor's body temperature and heart rate. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's body temperature. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's heart rate. Furthermore, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to both the visitor's body temperature and heart rate. In this way, by referring to the visitor's body temperature and heart rate, the accuracy of the facial expression analysis is improved. Some or all of the above-described processing in the facial expression analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the facial expression analysis unit can input the visitor's body temperature and heart rate data into AI and have the AI ​​improve the accuracy of the analysis.

[0042] The facial expression analysis unit can also analyze the visitor's tone of voice and level of tension when analyzing the facial expression. The facial expression analysis unit can, for example, improve the accuracy of the facial expression analysis by referring to the visitor's tone of voice. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's level of tension. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to both the visitor's tone of voice and level of tension. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's tone of voice. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's level of tension. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to both the visitor's tone of voice and level of tension. In this way, by analyzing the visitor's tone of voice and level of tension together, the accuracy of the facial expression analysis is improved. Some or all of the above-mentioned processing in the facial expression analysis unit may be performed, for example, using AI or without using AI. For example, the facial expression analysis unit can input the visitor's tone of voice and level of tension data into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0043] The voice quality analysis unit can improve the accuracy of the analysis by referring to past voice data of the visitor during voice quality analysis. For example, the voice quality analysis unit can improve the accuracy of the analysis by referring to voice data from when the same visitor visited in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data from visitors who caused problems in the past. Furthermore, the voice quality analysis unit can improve the accuracy of the analysis by referring to voice data from visitors who have never visited in the past. For example, the voice quality analysis unit can improve the accuracy of the analysis by referring to voice data from when the same visitor visited in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data from visitors who caused problems in the past. Furthermore, the voice quality analysis unit can improve the accuracy of the analysis by referring to voice data from visitors who have never visited in the past. In this way, by referring to past voice data, the accuracy of the voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without using AI. For example, the voice quality analysis unit can input a visitor's past voice data into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0044] The voice quality analysis unit can optimize the analysis algorithm by taking into account the language and dialect of the visitor when analyzing voice quality. The voice quality analysis unit optimizes the voice quality analysis algorithm based on, for example, the language of the visitor. The voice quality analysis unit can also optimize the voice quality analysis algorithm based on the dialect of the visitor. Furthermore, the voice quality analysis unit can optimize the voice quality analysis algorithm based on the accent of the visitor. For example, the voice quality analysis unit optimizes the voice quality analysis algorithm based on the language of the visitor to improve analysis accuracy. The voice quality analysis unit can also optimize the voice quality analysis algorithm based on the dialect of the visitor to improve analysis accuracy. Furthermore, the voice quality analysis unit can optimize the voice quality analysis algorithm based on the accent of the visitor to improve analysis accuracy. In this way, by taking into account the language and dialect of the visitor, the accuracy of voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without using AI. For example, the voice quality analysis unit can input the visitor's language and dialect data into the AI ​​and have the AI ​​optimize the analysis algorithm.

[0045] The voice quality analysis unit can improve the accuracy of the analysis by referring to the breathing pattern of the visitor during voice quality analysis. The voice quality analysis unit can improve the accuracy of the voice quality analysis by, for example, referring to the breathing pattern of the visitor. The voice quality analysis unit can also improve the accuracy of the voice quality analysis by referring to the breathing rhythm of the visitor. Furthermore, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the depth of breathing of the visitor. For example, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the breathing pattern of the visitor. The voice quality analysis unit can also improve the accuracy of the voice quality analysis by referring to the breathing rhythm of the visitor. Furthermore, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the depth of breathing of the visitor. In this way, by referring to the breathing pattern of the visitor, the accuracy of the voice quality analysis is improved. Some or all of the above-described processing in the voice quality analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice quality analysis unit can input the breathing pattern data of the visitor into AI and cause the AI ​​to improve the accuracy of the analysis.

[0046] The voice quality analysis unit can analyze the background sound of the visitor during voice quality analysis to improve the accuracy of the analysis. The voice quality analysis unit can, for example, analyze the background sound of the visitor to improve the accuracy of the voice quality analysis. The voice quality analysis unit can also analyze the noise around the visitor to improve the accuracy of the voice quality analysis. Furthermore, the voice quality analysis unit can analyze the background sound of the visitor and the ambient noise together to improve the accuracy of the voice quality analysis. For example, the voice quality analysis unit analyzes the background sound of the visitor to improve the accuracy of the voice quality analysis. The voice quality analysis unit can also analyze the noise around the visitor to improve the accuracy of the voice quality analysis. Furthermore, the voice quality analysis unit can analyze the background sound of the visitor and the ambient noise together to improve the accuracy of the voice quality analysis. In this way, by analyzing the background sound of the visitor, the accuracy of the voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without using AI. For example, the voice quality analysis unit can input background sound data of visitors into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0047] The risk calculation unit can improve the accuracy of the risk calculation by referring to the visitor's past behavioral history when calculating the risk level. For example, the risk calculation unit calculates the risk level by referring to the behavioral history of the same visitor when he or she visited in the past. The risk calculation unit can also calculate the risk level by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the risk calculation unit can calculate the risk level by referring to the behavioral history of visitors who have never visited before. For example, the risk calculation unit calculates the risk level by referring to the behavioral history of the same visitor when he or she visited in the past. The risk calculation unit can also calculate the risk level by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the risk calculation unit can calculate the risk level by referring to the behavioral history of visitors who have never visited before. In this way, referring to the past behavioral history improves the accuracy of the risk calculation. Some or all of the above-described processing in the risk calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the risk calculation unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the calculation.

[0048] The risk calculation unit can evaluate the visitor's current behavior and attitude in real time when calculating the risk level. For example, the risk calculation unit calculates the risk level by evaluating the visitor's current behavior (e.g., hand movements and posture) in real time. The risk calculation unit can also calculate the risk level by evaluating the visitor's current attitude (e.g., gaze and facial expression) in real time. The risk calculation unit can also calculate the risk level by evaluating the visitor's current behavior and attitude together in real time. For example, the risk calculation unit evaluates the visitor's current behavior (e.g., hand movements and posture) in real time and calculates the risk level. The risk calculation unit can also evaluate the visitor's current attitude (e.g., gaze and facial expression) in real time and calculate the risk level. The risk calculation unit can also evaluate the visitor's current behavior and attitude together in real time and calculate the risk level. In this way, by evaluating the visitor's current behavior and attitude in real time, the accuracy of the risk level calculation is improved. Some or all of the above-described processing in the risk calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk calculation unit may input data on the visitor's current behavior and attitude into AI and have the AI ​​perform a real-time evaluation.

[0049] The risk calculation unit can improve the accuracy of the risk calculation by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the risk calculation unit calculates the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the risk calculation unit calculates the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the risk calculation is improved. Some or all of the above-mentioned processing in the risk calculation unit may be performed, for example, using AI or without using AI. For example, the risk calculation unit can input the visitor's geographical location information into the AI ​​and allow the AI ​​to improve the accuracy of the calculation.

[0050] When calculating the risk level, the risk level calculation unit can improve the accuracy of the calculation by referring to the visitor's past criminal history and police data. The risk level calculation unit, for example, calculates the risk level by referring to the visitor's past criminal history. The risk level calculation unit can also calculate the risk level by referring to the visitor's police data. The risk level calculation unit can also calculate the risk level by referring to the visitor's past criminal history and police data together. For example, the risk level calculation unit calculates the risk level by referring to the visitor's past criminal history. The risk level calculation unit can also calculate the risk level by referring to the visitor's police data. The risk level calculation unit can also calculate the risk level by referring to the visitor's past criminal history and police data together. In this way, by referring to the visitor's past criminal history and police data, the accuracy of the risk level calculation is improved. Some or all of the above-mentioned processing in the risk level calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk level calculation unit can input the visitor's past criminal history and police data into AI and cause the AI ​​to improve the accuracy of the calculation.

[0051] When acquiring a visit history, the acquisition unit can improve the accuracy of the acquisition by referring to the visitor's past behavioral patterns. For example, the acquisition unit acquires the visit history by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire the visit history by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire the visit history by referring to the behavioral patterns of visitors who have never visited in the past. For example, the acquisition unit acquires the visit history by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire the visit history by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire the visit history by referring to the behavioral patterns of visitors who have never visited in the past. In this way, by referring to the past behavioral patterns, the accuracy of the visit history acquisition is improved. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the visitor's past behavioral patterns into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0052] When acquiring a visit history, the acquisition unit can improve the accuracy of the acquisition by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the acquisition unit acquires the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the acquisition unit acquires the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the visit history acquisition is improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0053] When acquiring crime case data, the acquisition unit can improve the accuracy of the acquisition by referring to the visitor's past behavioral patterns. For example, the acquisition unit acquires crime case data by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire crime case data by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire crime case data by referring to the behavioral patterns of visitors who have never visited before. For example, the acquisition unit acquires crime case data by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire crime case data by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire crime case data by referring to the behavioral patterns of visitors who have never visited before. In this way, referring to past behavioral patterns improves the accuracy of the crime case data acquisition. Some or all of the above-described processing by the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the visitor's past behavioral pattern data into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0054] When acquiring crime case data, the acquisition unit can improve the accuracy of the acquisition by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the acquisition unit acquires crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the acquisition unit acquires crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the acquisition of crime case data is improved. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0055] During safety evaluation, the evaluation unit can improve the accuracy of the evaluation by referring to the visitor's past behavioral history. For example, the evaluation unit evaluates safety by referring to the behavioral history of the same visitor when he or she visited in the past. The evaluation unit can also evaluate safety by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the evaluation unit can evaluate safety by referring to the behavioral history of visitors who have never visited before. For example, the evaluation unit evaluates safety by referring to the behavioral history of the same visitor when he or she visited in the past. The evaluation unit can also evaluate safety by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the evaluation unit can evaluate safety by referring to the behavioral history of visitors who have never visited before. In this way, referring to the past behavioral history improves the accuracy of the safety evaluation. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the evaluation.

[0056] The evaluation unit can improve the accuracy of the safety evaluation by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the safety evaluation is improved. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the evaluation.

[0057] The notification unit can improve the accuracy of the notification by referring to the visitor's past behavioral history when making a notification. For example, the notification unit can improve the accuracy of the notification by referring to the behavioral history of the same visitor when they visited in the past. The notification unit can also improve the accuracy of the notification by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the notification unit can improve the accuracy of the notification by referring to the behavioral history of visitors who have never visited before. For example, the notification unit can improve the accuracy of the notification by referring to the behavioral history of the same visitor when they visited in the past. The notification unit can also improve the accuracy of the notification by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the notification unit can improve the accuracy of the notification by referring to the behavioral history of visitors who have never visited before. In this way, the accuracy of the notification is improved by referring to the past behavioral history. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the notification.

[0058] The notification unit can improve the accuracy of the notification by taking into account the geographical location information of the visitor when making a notification. For example, if the visitor comes from a specific area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. In this way, the accuracy of the notification is improved by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the notification.

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

[0060] When recognizing a visitor's face, the face recognition unit can improve the accuracy of recognition based on the visitor's clothing and belongings. For example, the accuracy of face recognition can be improved by analyzing the color and design of the visitor's clothing. The accuracy of face recognition can also be improved by analyzing the visitor's belongings (bags, umbrellas, etc.). The accuracy of face recognition can also be improved by analyzing the visitor's accessories (glasses, hats, etc.). In this way, the accuracy of face recognition can be improved by analyzing the visitor's clothing and belongings.

[0061] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's body temperature and heart rate. For example, the accuracy of facial expression analysis can be improved by referring to the visitor's body temperature. The accuracy of facial expression analysis can also be improved by referring to the visitor's heart rate. Furthermore, the accuracy of facial expression analysis can also be improved by referring to both the visitor's body temperature and heart rate. In this way, the accuracy of facial expression analysis is improved by referring to the visitor's body temperature and heart rate.

[0062] The voice quality analysis unit can improve the accuracy of analysis by referring to the breathing pattern of the visitor. For example, the accuracy of voice quality analysis can be improved by referring to the breathing pattern of the visitor. The accuracy of voice quality analysis can also be improved by referring to the breathing rhythm of the visitor. Furthermore, the accuracy of voice quality analysis can also be improved by referring to the depth of breathing of the visitor. In this way, by referring to the breathing pattern of the visitor, the accuracy of voice quality analysis is improved.

[0063] The risk level calculation unit can evaluate the visitor's current behavior and attitude in real time. For example, the risk level can be calculated by evaluating the visitor's current behavior (e.g., hand movements and posture) in real time. The risk level can also be calculated by evaluating the visitor's current attitude (e.g., line of sight and facial expression) in real time. Furthermore, the risk level can be calculated by evaluating the visitor's current behavior and attitude together in real time. In this way, the accuracy of the risk level calculation is improved by evaluating the visitor's current behavior and attitude in real time.

[0064] The notification unit can improve the accuracy of the notification by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the accuracy of the notification can be improved by taking into account the characteristics of that area. Also, if the visitor comes from a distant location, the accuracy of the notification can be improved by taking into account the characteristics of that area. Furthermore, if the visitor comes from a nearby area, the accuracy of the notification can be improved by taking into account the characteristics of that area. In this way, the accuracy of the notification can be improved by taking into account the geographical location information of the visitor.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The face recognition unit recognizes the visitor's face. The face recognition unit can recognize faces using, for example, deep learning technology or pattern matching technology. It can also extract facial feature points and recognize faces based on those. Step 2: The facial expression analysis unit analyzes the facial expression recognized by the face recognition unit. The facial expression analysis unit can analyze the facial expression using, for example, a facial expression recognition algorithm and determine the type and changes of the facial expression. Step 3: The voice quality analysis unit analyzes the voice quality based on the facial expression analyzed by the facial expression analysis unit. The voice quality analysis unit can analyze the voice quality using, for example, an algorithm for extracting voice features, and evaluate the tone and tension of the voice. Step 4: The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit. The risk calculation unit can calculate the risk index using, for example, a scoring algorithm and evaluate the risk by referring to evaluation criteria and past data.

[0067] (Example 2) A home intercom system according to an embodiment of the present invention displays a risk index based on a visitor's face, facial expression, and voice quality. This system captures the visitor's face with a camera and identifies the visitor using facial recognition technology. Next, the system analyzes the visitor's facial expression using facial expression analysis technology to determine their emotional state. Furthermore, the system analyzes the visitor's voice using voice quality analysis technology to evaluate their tone and nervousness. Based on this information, a risk index is calculated and displayed on a monitor. Safety is also assessed based on past visitor history and national crime case data. For example, if the same visitor has visited multiple times in the past or if the visitor is from a nationally high-crime area, a warning is displayed if the risk is deemed high. Furthermore, by linking with a smartphone, the system can detect danger even when the user is out. For example, if a visitor arrives while the user is out, a notification is sent to the user's smartphone, allowing the user to confirm the visitor's face and voice. This allows the user to ensure the safety of their home even when the user is out. This system allows the user to grasp the risk level of visitors in advance and take measures when a problem occurs. This system can particularly enhance safety when only children are at home, allowing the user to feel more secure even when the user is out. For example, a visitor's face is photographed with a camera and identified using facial recognition technology. Next, facial expression analysis technology is used to analyze the visitor's facial expression and determine their emotional state. Furthermore, voice quality analysis technology is used to analyze the visitor's voice and evaluate their tone and level of tension. Based on this information, a risk index is calculated and displayed on the monitor. Safety is also assessed based on past visitor history and national crime case data. For example, if the same visitor has visited multiple times in the past or if the visitor is from a nationally high-crime area, a warning is displayed if the risk is deemed high. Furthermore, by linking with a smartphone, danger can be detected even when the user is out. For example, if a visitor arrives while the user is out, a notification is sent to the user's smartphone, allowing the user to confirm the visitor's face and voice. This allows the user to ensure the safety of their home even when the user is out. This system allows the user to grasp the visitor's risk level in advance and take measures if a problem occurs. This system can particularly enhance safety when children are at home alone, allowing the user to feel more secure even when the user is out.This allows the home intercom system to grasp the danger level of visitors in advance and evaluate their safety.

[0068] The home intercom system according to the embodiment includes a face recognition unit, an expression analysis unit, a voice quality analysis unit, and a risk level calculation unit. The face recognition unit recognizes the face of a visitor. The face recognition unit recognizes the face using, for example, deep learning technology. The face recognition unit can also recognize the face using pattern matching technology. The face recognition unit can also extract facial feature points and recognize the face based on the extracted feature points. For example, the face recognition unit uses deep learning technology to recognize the face of a visitor with high accuracy. The face recognition unit can also use pattern matching technology to determine whether the face matches pre-registered facial data. The face recognition unit can also extract facial feature points and recognize the face based on the extracted feature points. The expression analysis unit analyzes the facial expression of the face recognized by the face recognition unit. The expression analysis unit analyzes the facial expression using, for example, an expression recognition algorithm. The expression analysis unit can also determine the type of expression. The expression analysis unit can also analyze changes in facial expression. For example, the expression analysis unit analyzes the facial expression of the visitor using an expression recognition algorithm. The facial expression analysis unit can also determine the type of facial expression and estimate the emotional state of the visitor. The facial expression analysis unit can also analyze changes in facial expressions and grasp changes in the visitor's emotions. The voice quality analysis unit analyzes voice quality based on the facial expression analyzed by the facial expression analysis unit. The voice quality analysis unit analyzes voice quality using, for example, a voice feature extraction algorithm. The voice quality analysis unit can also evaluate voice tone and tension. The voice quality analysis unit can also analyze voice changes. For example, the voice quality analysis unit analyzes the voice quality of the visitor using a voice feature extraction algorithm. The voice quality analysis unit can also evaluate voice tone and tension and estimate the visitor's emotional state. The voice quality analysis unit can also analyze voice changes and grasp changes in the visitor's emotions. The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit. The risk calculation unit calculates the risk index using, for example, a scoring algorithm. The risk calculation unit can also evaluate the risk based on evaluation criteria. Furthermore, the risk calculation unit can also evaluate the risk by referring to past data.For example, the danger level calculation unit calculates a danger level index of a visitor using a scoring algorithm. The danger level calculation unit can also evaluate the danger level of a visitor based on evaluation criteria. Furthermore, the danger level calculation unit can evaluate the danger level of a visitor by referring to past data. As a result, the home intercom system according to the embodiment can grasp the danger level of a visitor in advance and evaluate safety by analyzing the face, expression, and voice quality of the visitor and calculating a danger level index.

[0069] The acquisition unit can acquire past visit history. The acquisition unit, for example, records the visit date and time of the visitor. The acquisition unit can also record the number of visits by the visitor. Furthermore, the acquisition unit can also record the purpose of the visit by the visitor. For example, the acquisition unit records the visit date and time of the visitor and manages the past visit history. The acquisition unit can also record the number of visits by the visitor and identify frequent visitors. Furthermore, the acquisition unit can record the purpose of the visit by the visitor and understand the behavioral patterns of the visitor. In this way, by acquiring the past visit history, reference information can be provided when evaluating the safety of the visitor. Some or all of the above-mentioned processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the visit date and time of the visitor to AI and have the AI ​​analyze the number of visits and the purpose of the visit.

[0070] The acquisition unit can acquire nationwide crime case data. The acquisition unit acquires data, for example, from a crime case database. The acquisition unit can also acquire crime case data from public police data. Furthermore, the acquisition unit can collect crime case data from news articles and reports. For example, the acquisition unit acquires data from a crime case database and manages nationwide crime cases. The acquisition unit can also acquire crime case data from public police data to grasp the latest crime information. Furthermore, the acquisition unit can collect crime case data from news articles and reports and analyze local crime trends. In this way, acquiring nationwide crime case data can provide reference information for evaluating visitor safety. Some or all of the above-mentioned processing by the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input data acquired from the crime case database into AI and have the AI ​​analyze crime trends.

[0071] The evaluation unit can evaluate safety based on the data acquired by the acquisition unit. The evaluation unit can evaluate safety based on, for example, the visitor's past visit history. The evaluation unit can also evaluate safety based on nationwide crime case data. The evaluation unit can also evaluate safety based on the visitor's behavioral patterns. For example, the evaluation unit can evaluate the safety of frequent visitors based on the visitor's past visit history. The evaluation unit can also evaluate the safety of visitors from high-crime areas based on nationwide crime case data. The evaluation unit can also evaluate the safety of visitors exhibiting abnormal behavior based on the visitor's behavioral patterns. In this way, evaluating safety based on the acquired data can more accurately determine the visitor's risk level. Some or all of the above-described processing in the evaluation unit can be performed using, for example, AI, or without AI. For example, the evaluation unit can input the visitor's past visit history and crime case data into AI and have the AI ​​perform a safety evaluation.

[0072] The notification unit can send a notification to the smartphone when a visitor arrives while the user is out. For example, the notification unit can send a notification to the smartphone when the visitor presses the intercom. The notification unit can also send a notification to the smartphone when the visitor is captured on camera. The notification unit can also send a notification to the smartphone when the visitor makes a sound. For example, the notification unit can send a push notification to the smartphone when the visitor presses the intercom. The notification unit can also send a notification with an image to the smartphone when the visitor is captured on camera. The notification unit can also send a notification with audio to the smartphone when the visitor makes a sound. This allows the user to check visitor information on their smartphone even when they are out, thereby ensuring the safety of their home. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the visitor's behavior into AI and have the AI ​​determine the timing and content of the notification.

[0073] The notification unit can display the visitor's face and voice on the smartphone. For example, the notification unit can capture the visitor's face with a camera and stream the video to the smartphone. The notification unit can also record the visitor's voice with a microphone and stream the audio to the smartphone. Furthermore, the notification unit can simultaneously display the visitor's face and voice on the smartphone. For example, the notification unit can capture the visitor's face with a camera and stream the video to the smartphone in real time. The notification unit can also record the visitor's voice with a microphone and stream the audio to the smartphone in real time. Furthermore, the notification unit can simultaneously display the visitor's face and voice on the smartphone, allowing detailed visitor information to be confirmed. This allows the visitor's information to be confirmed even when the visitor is out by displaying the visitor's face and voice on the smartphone. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the visitor's face and voice data into AI and have the AI ​​optimize the streaming.

[0074] The face recognition unit can estimate the emotion of the visitor and adjust the accuracy of face recognition based on the estimated emotion of the visitor. For example, if the visitor is nervous, the face recognition unit adjusts the face recognition algorithm to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the face recognition unit can adjust the face recognition algorithm to one suitable for a relaxed state. Furthermore, if the visitor is angry, the face recognition unit can adjust the face recognition algorithm to one suitable for an angry state. For example, if the visitor is nervous, the face recognition unit adjusts the face recognition algorithm to one suitable for a nervous state, thereby improving the accuracy of face recognition. Furthermore, if the visitor is relaxed, the face recognition unit can adjust the face recognition algorithm to one suitable for a relaxed state, thereby improving the accuracy of face recognition. Furthermore, if the visitor is angry, the face recognition unit can adjust the face recognition algorithm to one suitable for an angry state, thereby improving the accuracy of face recognition. In this way, by adjusting the accuracy of face recognition based on the emotion of the visitor, more accurate face recognition is possible. Some or all of the above-described processing in the face recognition unit may be performed using AI, for example, or may be performed without using AI. For example, the face recognition unit may input visitor emotion data into AI and have the AI ​​adjust the face recognition algorithm.

[0075] When recognizing a face, the face recognition unit can determine the recognition priority by referring to the visitor's past visit history. For example, the face recognition unit may prioritize recognition of visitors who have visited frequently in the past. The face recognition unit may also prioritize recognition of visitors who have caused problems in the past. Furthermore, the face recognition unit may also prioritize recognition of visitors who have never visited before. For example, the face recognition unit may prioritize recognition of visitors who have visited frequently in the past to quickly identify important visitors. The face recognition unit may also prioritize recognition of visitors who have caused problems in the past to strengthen vigilance. Furthermore, the face recognition unit may prioritize recognition of visitors who have never visited before to identify new visitors. In this way, by referring to the past visit history, important visitors can be prioritized. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI, or may be performed without AI. For example, the face recognition unit may input visitor's past visit history data into AI and have the AI ​​determine the recognition priority.

[0076] The face recognition unit can adjust the recognition algorithm based on the visitor's age and gender during face recognition. For example, the face recognition unit optimizes the face recognition algorithm for older visitors. The face recognition unit can also optimize the face recognition algorithm for younger visitors. Furthermore, the face recognition unit can optimize the face recognition algorithm according to gender. For example, the face recognition unit optimizes the face recognition algorithm for older visitors to improve recognition accuracy. The face recognition unit can also optimize the face recognition algorithm for younger visitors to improve recognition accuracy. Furthermore, the face recognition unit can optimize the face recognition algorithm according to gender to improve recognition accuracy. In this way, optimizing the recognition algorithm according to the visitor's age and gender improves the accuracy of face recognition. Some or all of the above-described processing in the face recognition unit may be performed using, or without, AI. For example, the face recognition unit can input the visitor's age and gender data into AI and have the AI ​​adjust the recognition algorithm.

[0077] The face recognition unit can estimate the emotion of the visitor and adjust the timing of face recognition based on the estimated emotion of the visitor. For example, if the visitor is nervous, the face recognition unit can delay the timing of face recognition. Also, if the visitor is relaxed, the face recognition unit can advance the timing of face recognition. Furthermore, if the visitor is angry, the face recognition unit can adjust the timing of face recognition. For example, if the visitor is nervous, the face recognition unit can delay the timing of face recognition to improve recognition accuracy. Also, if the visitor is relaxed, the face recognition unit can advance the timing of face recognition to improve recognition accuracy. Furthermore, if the visitor is angry, the face recognition unit can adjust the timing of face recognition to improve recognition accuracy. In this way, by adjusting the timing of face recognition based on the emotion of the visitor, face recognition can be performed at a more appropriate timing. Some or all of the above-mentioned processing in the face recognition unit may be performed, for example, using AI or without using AI. For example, the facial recognition unit can input the visitor's emotional data into the AI ​​and have the AI ​​adjust the timing of facial recognition.

[0078] The face recognition unit can improve the accuracy of face recognition by taking into account the geographical location information of a visitor. For example, if a visitor comes from a specific area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a distant location, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a nearby area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. For example, if a visitor comes from a specific area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a distant location, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. Furthermore, if a visitor comes from a nearby area, the face recognition unit can improve the accuracy of face recognition by taking into account the characteristics of the area. In this way, the accuracy of face recognition is improved by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI or without using AI. For example, the facial recognition unit can input the visitor's geographic location information into the AI, allowing the AI ​​to improve the accuracy of facial recognition.

[0079] The face recognition unit can improve the accuracy of face recognition based on the visitor's clothing and belongings. The face recognition unit can improve the accuracy of face recognition, for example, by analyzing the color and design of the visitor's clothing. The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's belongings (such as a bag or umbrella). The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's accessories (such as glasses or a hat). For example, the face recognition unit can improve the accuracy of face recognition by analyzing the color and design of the visitor's clothing. The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's belongings (such as a bag or umbrella). The face recognition unit can also improve the accuracy of face recognition by analyzing the visitor's accessories (such as glasses or a hat). In this way, the accuracy of face recognition is improved by analyzing the visitor's clothing and belongings. Some or all of the above-described processing in the face recognition unit may be performed, for example, using AI, or may be performed without using AI. For example, the facial recognition unit can input data on visitors' clothing and belongings into the AI, allowing the AI ​​to improve the accuracy of recognition.

[0080] The facial expression analysis unit can estimate the visitor's emotions and adjust the facial expression analysis algorithm based on the estimated visitor's emotions. For example, if the visitor is nervous, the facial expression analysis unit adjusts the facial expression analysis algorithm to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the facial expression analysis unit can also adjust the facial expression analysis algorithm to one suitable for a relaxed state. Furthermore, if the visitor is angry, the facial expression analysis unit can also adjust the facial expression analysis algorithm to one suitable for an angry state. For example, if the visitor is nervous, the facial expression analysis unit adjusts the facial expression analysis algorithm to one suitable for a nervous state, thereby improving analysis accuracy. Furthermore, if the visitor is relaxed, the facial expression analysis unit can also adjust the facial expression analysis algorithm to one suitable for an angry state, thereby improving analysis accuracy. Thus, adjusting the facial expression analysis algorithm based on the visitor's emotions enables more accurate facial expression analysis. Some or all of the above-described processing in the facial expression analysis unit may be performed, for example, using AI or without AI. For example, the facial expression analysis unit can input the visitor's emotional data into the AI ​​and have the AI ​​adjust the facial expression analysis algorithm.

[0081] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's past facial expression data during facial expression analysis. For example, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from previous visits by the same visitor. The facial expression analysis unit can also improve the accuracy of the analysis by referring to facial expression data from visitors who have caused problems in the past. Furthermore, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from visitors who have never visited before. For example, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from previous visits by the same visitor. The facial expression analysis unit can also improve the accuracy of the analysis by referring to facial expression data from visitors who have caused problems in the past. Furthermore, the facial expression analysis unit can improve the accuracy of the analysis by referring to facial expression data from visitors who have never visited before. In this way, the accuracy of the facial expression analysis is improved by referring to past facial expression data. Some or all of the above-described processing in the facial expression analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the facial expression analysis unit can input the visitor's past facial expression data into AI and have the AI ​​improve the accuracy of the analysis.

[0082] The facial expression analysis unit can adjust the analysis algorithm based on the visitor's cultural background when analyzing facial expressions. The facial expression analysis unit can optimize the facial expression analysis algorithm based on, for example, the visitor's cultural background. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's nationality or region. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's religion or customs. For example, the facial expression analysis unit can optimize the facial expression analysis algorithm based on the visitor's cultural background to improve analysis accuracy. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's nationality or region to improve analysis accuracy. The facial expression analysis unit can also optimize the facial expression analysis algorithm based on the visitor's religion or customs to improve analysis accuracy. This improves the accuracy of facial expression analysis by taking the visitor's cultural background into consideration. Some or all of the above-described processing in the facial expression analysis unit can be performed using, for example, AI, or without AI. For example, the facial expression analysis unit can input the visitor's cultural background data into AI and have the AI ​​adjust the analysis algorithm.

[0083] The facial expression analysis unit can estimate the emotion of the visitor and adjust the timing of facial expression analysis based on the estimated emotion of the visitor. For example, if the visitor is nervous, the facial expression analysis unit can delay the timing of facial expression analysis. Furthermore, if the visitor is relaxed, the facial expression analysis unit can advance the timing of facial expression analysis. Furthermore, if the visitor is angry, the facial expression analysis unit can adjust the timing of facial expression analysis. For example, if the visitor is nervous, the facial expression analysis unit can delay the timing of facial expression analysis to improve analysis accuracy. Furthermore, if the visitor is relaxed, the facial expression analysis unit can advance the timing of facial expression analysis to improve analysis accuracy. Furthermore, if the visitor is angry, the facial expression analysis unit can adjust the timing of facial expression analysis to improve analysis accuracy. In this way, by adjusting the timing of facial expression analysis based on the emotion of the visitor, facial expression analysis can be performed at a more appropriate timing. Some or all of the above-mentioned processing in the facial expression analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the facial expression analysis unit can input the visitor's emotional data into the AI ​​and have the AI ​​adjust the timing of facial expression analysis.

[0084] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's body temperature and heart rate during facial expression analysis. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's body temperature. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's heart rate. Furthermore, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to both the visitor's body temperature and heart rate. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's body temperature. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's heart rate. Furthermore, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to both the visitor's body temperature and heart rate. In this way, by referring to the visitor's body temperature and heart rate, the accuracy of the facial expression analysis is improved. Some or all of the above-described processing in the facial expression analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the facial expression analysis unit can input the visitor's body temperature and heart rate data into AI and have the AI ​​improve the accuracy of the analysis.

[0085] The facial expression analysis unit can also analyze the visitor's tone of voice and level of tension when analyzing the facial expression. The facial expression analysis unit can, for example, improve the accuracy of the facial expression analysis by referring to the visitor's tone of voice. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's level of tension. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to both the visitor's tone of voice and level of tension. For example, the facial expression analysis unit can improve the accuracy of the facial expression analysis by referring to the visitor's tone of voice. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to the visitor's level of tension. The facial expression analysis unit can also improve the accuracy of the facial expression analysis by referring to both the visitor's tone of voice and level of tension. In this way, by analyzing the visitor's tone of voice and level of tension together, the accuracy of the facial expression analysis is improved. Some or all of the above-mentioned processing in the facial expression analysis unit may be performed, for example, using AI or without using AI. For example, the facial expression analysis unit can input the visitor's tone of voice and level of tension data into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0086] The voice quality analysis unit can estimate the visitor's emotions and adjust the voice quality analysis algorithm based on the estimated visitor's emotions. For example, if the visitor is nervous, the voice quality analysis unit adjusts the voice quality analysis algorithm to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the voice quality analysis unit can also adjust the voice quality analysis algorithm to one suitable for a relaxed state. Furthermore, if the visitor is angry, the voice quality analysis unit can also adjust the voice quality analysis algorithm to one suitable for an angry state. For example, if the visitor is nervous, the voice quality analysis unit adjusts the voice quality analysis algorithm to one suitable for a nervous state, thereby improving analysis accuracy. Furthermore, if the visitor is relaxed, the voice quality analysis unit can also adjust the voice quality analysis algorithm to one suitable for an angry state, thereby improving analysis accuracy. In this way, by adjusting the voice quality analysis algorithm based on the visitor's emotions, more accurate voice quality analysis is possible. Some or all of the above-described processing in the voice quality analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice quality analysis unit may input emotional data of the visitor into AI and have the AI ​​adjust the voice quality analysis algorithm.

[0087] The voice quality analysis unit can improve the accuracy of the analysis by referring to past voice data of the visitor during voice quality analysis. The voice quality analysis unit can improve the accuracy of the analysis by, for example, referring to voice data from when the same visitor visited in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data of visitors who caused problems in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data of visitors who have never visited in the past. For example, the voice quality analysis unit can improve the accuracy of the analysis by referring to voice data from when the same visitor visited in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data of visitors who caused problems in the past. The voice quality analysis unit can also improve the accuracy of the analysis by referring to voice data of visitors who have never visited in the past. In this way, by referring to past voice data, the accuracy of the voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without AI. For example, the voice quality analysis unit can input a visitor's past voice data into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0088] The voice quality analysis unit can optimize the analysis algorithm by taking into account the language and dialect of the visitor when analyzing voice quality. The voice quality analysis unit optimizes the voice quality analysis algorithm based on, for example, the language of the visitor. The voice quality analysis unit can also optimize the voice quality analysis algorithm based on the dialect of the visitor. Furthermore, the voice quality analysis unit can optimize the voice quality analysis algorithm based on the accent of the visitor. For example, the voice quality analysis unit optimizes the voice quality analysis algorithm based on the language of the visitor to improve analysis accuracy. The voice quality analysis unit can also optimize the voice quality analysis algorithm based on the dialect of the visitor to improve analysis accuracy. Furthermore, the voice quality analysis unit can optimize the voice quality analysis algorithm based on the accent of the visitor to improve analysis accuracy. In this way, by taking into account the language and dialect of the visitor, the accuracy of voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without using AI. For example, the voice quality analysis unit can input the visitor's language and dialect data into the AI ​​and have the AI ​​optimize the analysis algorithm.

[0089] The voice quality analysis unit can estimate the visitor's emotions and adjust the timing of voice quality analysis based on the estimated emotions of the visitor. For example, if the visitor is nervous, the voice quality analysis unit can delay the timing of voice quality analysis. Furthermore, if the visitor is relaxed, the voice quality analysis unit can advance the timing of voice quality analysis. Furthermore, if the visitor is angry, the voice quality analysis unit can adjust the timing of voice quality analysis. For example, if the visitor is nervous, the voice quality analysis unit can delay the timing of voice quality analysis to improve analysis accuracy. Furthermore, if the visitor is relaxed, the voice quality analysis unit can advance the timing of voice quality analysis to improve analysis accuracy. Furthermore, if the visitor is angry, the voice quality analysis unit can adjust the timing of voice quality analysis to improve analysis accuracy. In this way, by adjusting the timing of voice quality analysis based on the visitor's emotions, voice quality analysis can be performed at a more appropriate timing. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed using, for example, AI, or without AI. For example, the voice quality analysis unit can input the visitor's emotional data into the AI ​​and have the AI ​​adjust the timing of voice quality analysis.

[0090] The voice quality analysis unit can improve the accuracy of the analysis by referring to the breathing pattern of the visitor during voice quality analysis. The voice quality analysis unit can improve the accuracy of the voice quality analysis by, for example, referring to the breathing pattern of the visitor. The voice quality analysis unit can also improve the accuracy of the voice quality analysis by referring to the breathing rhythm of the visitor. Furthermore, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the depth of breathing of the visitor. For example, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the breathing pattern of the visitor. The voice quality analysis unit can also improve the accuracy of the voice quality analysis by referring to the breathing rhythm of the visitor. Furthermore, the voice quality analysis unit can improve the accuracy of the voice quality analysis by referring to the depth of breathing of the visitor. In this way, by referring to the breathing pattern of the visitor, the accuracy of the voice quality analysis is improved. Some or all of the above-described processing in the voice quality analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice quality analysis unit can input the breathing pattern data of the visitor into AI and cause the AI ​​to improve the accuracy of the analysis.

[0091] The voice quality analysis unit can analyze the background sound of the visitor during voice quality analysis to improve the accuracy of the analysis. The voice quality analysis unit can, for example, analyze the background sound of the visitor to improve the accuracy of the voice quality analysis. The voice quality analysis unit can also analyze the noise around the visitor to improve the accuracy of the voice quality analysis. Furthermore, the voice quality analysis unit can analyze the background sound of the visitor and the ambient noise together to improve the accuracy of the voice quality analysis. For example, the voice quality analysis unit analyzes the background sound of the visitor to improve the accuracy of the voice quality analysis. The voice quality analysis unit can also analyze the noise around the visitor to improve the accuracy of the voice quality analysis. Furthermore, the voice quality analysis unit can analyze the background sound of the visitor and the ambient noise together to improve the accuracy of the voice quality analysis. In this way, by analyzing the background sound of the visitor, the accuracy of the voice quality analysis is improved. Some or all of the above-mentioned processing in the voice quality analysis unit may be performed, for example, using AI or without using AI. For example, the voice quality analysis unit can input background sound data of visitors into the AI, allowing the AI ​​to improve the accuracy of the analysis.

[0092] The risk calculation unit can estimate the visitor's emotions and adjust the risk index calculation method based on the estimated visitor's emotions. For example, if the visitor is nervous, the risk calculation unit adjusts the risk index calculation method to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the risk calculation unit can adjust the risk index calculation method to one suitable for a relaxed state. Furthermore, if the visitor is angry, the risk calculation unit can adjust the risk index calculation method to one suitable for an angry state. For example, if the visitor is nervous, the risk calculation unit adjusts the risk index calculation method to one suitable for a nervous state, thereby improving the calculation accuracy. Furthermore, if the visitor is relaxed, the risk calculation unit can adjust the risk index calculation method to one suitable for a relaxed state, thereby improving the calculation accuracy. Furthermore, if the visitor is angry, the risk calculation unit can adjust the risk index calculation method to one suitable for an angry state, thereby improving the calculation accuracy. Thus, by adjusting the risk index calculation method based on the visitor's emotions, a more accurate risk assessment is possible. Some or all of the above-described processing in the risk calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk calculation unit may input visitor emotion data into AI and have the AI ​​adjust the method for calculating the risk index.

[0093] The risk calculation unit can improve the accuracy of the risk calculation by referring to the visitor's past behavioral history when calculating the risk level. For example, the risk calculation unit calculates the risk level by referring to the behavioral history of the same visitor when he or she visited in the past. The risk calculation unit can also calculate the risk level by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the risk calculation unit can calculate the risk level by referring to the behavioral history of visitors who have never visited before. For example, the risk calculation unit calculates the risk level by referring to the behavioral history of the same visitor when he or she visited in the past. The risk calculation unit can also calculate the risk level by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the risk calculation unit can calculate the risk level by referring to the behavioral history of visitors who have never visited before. In this way, referring to the past behavioral history improves the accuracy of the risk calculation. Some or all of the above-described processing in the risk calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the risk calculation unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the calculation.

[0094] The risk level calculation unit can evaluate the visitor's current behavior and attitude in real time when calculating the risk level. For example, the risk level calculation unit calculates the risk level by evaluating the visitor's current behavior (e.g., hand movements and posture) in real time. The risk level calculation unit can also calculate the risk level by evaluating the visitor's current attitude (e.g., gaze and facial expression) in real time. Furthermore, the risk level calculation unit can calculate the risk level by evaluating the visitor's current behavior and attitude together in real time. For example, the risk level calculation unit evaluates the visitor's current behavior (e.g., hand movements and posture) in real time and calculates the risk level. The risk level calculation unit can also evaluate the visitor's current attitude (e.g., gaze and facial expression) in real time and calculate the risk level. Furthermore, the risk level calculation unit can evaluate the visitor's current behavior and attitude together in real time and calculate the risk level. In this way, by evaluating the visitor's current behavior and attitude in real time, the accuracy of the risk level calculation is improved. Some or all of the above-described processing in the risk calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk calculation unit may input data on the visitor's current behavior and attitude into AI and have the AI ​​perform a real-time evaluation.

[0095] The risk calculation unit can estimate the visitor's emotions and adjust the display method of the risk index based on the estimated visitor's emotions. For example, if the visitor is nervous, the risk calculation unit adjusts the display method of the risk index to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the risk calculation unit can adjust the display method of the risk index to one suitable for a relaxed state. Furthermore, if the visitor is angry, the risk calculation unit can adjust the display method of the risk index to one suitable for an angry state. For example, if the visitor is nervous, the risk calculation unit adjusts the display method of the risk index to one suitable for a nervous state, thereby improving the accuracy of the display. Furthermore, if the visitor is relaxed, the risk calculation unit can adjust the display method of the risk index to one suitable for a relaxed state, thereby improving the accuracy of the display. Furthermore, if the visitor is angry, the risk calculation unit can adjust the display method of the risk index to one suitable for an angry state, thereby improving the accuracy of the display. As a result, by adjusting the display method of the risk index based on the visitor's emotions, a more appropriate display is possible. Some or all of the above-described processing in the risk level calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk level calculation unit may input visitor emotion data into AI and have the AI ​​adjust the display method.

[0096] The risk calculation unit can improve the accuracy of the risk calculation by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the risk calculation unit calculates the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the risk calculation unit calculates the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the risk calculation unit can calculate the risk by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the risk calculation is improved. Some or all of the above-mentioned processing in the risk calculation unit may be performed, for example, using AI or without using AI. For example, the risk calculation unit can input the visitor's geographical location information into the AI ​​and allow the AI ​​to improve the accuracy of the calculation.

[0097] When calculating the risk level, the risk level calculation unit can improve the accuracy of the calculation by referring to the visitor's past criminal history and police data. The risk level calculation unit, for example, calculates the risk level by referring to the visitor's past criminal history. The risk level calculation unit can also calculate the risk level by referring to the visitor's police data. The risk level calculation unit can also calculate the risk level by referring to the visitor's past criminal history and police data together. For example, the risk level calculation unit calculates the risk level by referring to the visitor's past criminal history. The risk level calculation unit can also calculate the risk level by referring to the visitor's police data. The risk level calculation unit can also calculate the risk level by referring to the visitor's past criminal history and police data together. In this way, by referring to the visitor's past criminal history and police data, the accuracy of the risk level calculation is improved. Some or all of the above-mentioned processing in the risk level calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the risk level calculation unit can input the visitor's past criminal history and police data into AI and have the AI ​​improve the accuracy of the calculation.

[0098] The acquisition unit can estimate the visitor's emotions and adjust the visit history acquisition method based on the estimated visitor's emotions. For example, if the visitor is nervous, the acquisition unit adjusts the visit history acquisition method to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the acquisition unit can also adjust the visit history acquisition method to one suitable for a relaxed state. Furthermore, if the visitor is angry, the acquisition unit can also adjust the visit history acquisition method to one suitable for an angry state. For example, if the visitor is nervous, the acquisition unit adjusts the visit history acquisition method to one suitable for a nervous state, thereby improving the acquisition accuracy. Furthermore, if the visitor is relaxed, the acquisition unit can also adjust the visit history acquisition method to one suitable for a relaxed state, thereby improving the acquisition accuracy. Furthermore, if the visitor is angry, the acquisition unit can adjust the visit history acquisition method to one suitable for an angry state, thereby improving the acquisition accuracy. In this way, by adjusting the visit history acquisition method based on the visitor's emotions, it is possible to acquire a visit history more accurately. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input visitor emotion data into AI and have the AI ​​adjust the method for acquiring visit history.

[0099] When acquiring a visit history, the acquisition unit can improve the accuracy of the acquisition by referring to the visitor's past behavioral patterns. For example, the acquisition unit acquires the visit history by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire the visit history by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire the visit history by referring to the behavioral patterns of visitors who have never visited in the past. For example, the acquisition unit acquires the visit history by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire the visit history by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire the visit history by referring to the behavioral patterns of visitors who have never visited in the past. In this way, by referring to the past behavioral patterns, the accuracy of the visit history acquisition is improved. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the visitor's past behavioral patterns into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0100] The acquisition unit can estimate the visitor's emotions and determine the priority of the visit history based on the estimated visitor's emotions. For example, if the visitor is nervous, the acquisition unit can determine the priority of the visit history to be appropriate for a nervous state. Furthermore, if the visitor is relaxed, the acquisition unit can also determine the priority of the visit history to be appropriate for a relaxed state. Furthermore, if the visitor is angry, the acquisition unit can also determine the priority of the visit history to be appropriate for an angry state. For example, if the visitor is nervous, the acquisition unit can determine the priority of the visit history to be appropriate for a nervous state and prioritize acquiring important visit history. Furthermore, if the visitor is relaxed, the acquisition unit can determine the priority of the visit history to be appropriate for a relaxed state and prioritize acquiring important visit history. Furthermore, if the visitor is angry, the acquisition unit can determine the priority of the visit history to be appropriate for an angry state and prioritize acquiring important visit history. In this way, by determining the priority of the visit history based on the visitor's emotions, important visit history can be prioritized. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input visitor emotion data into AI and have the AI ​​determine the priority of visit history.

[0101] When acquiring a visit history, the acquisition unit can improve the accuracy of the acquisition by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the acquisition unit acquires the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the acquisition unit acquires the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire the visit history by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the visit history acquisition is improved. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0102] The acquisition unit can estimate the visitor's emotions and adjust the method for acquiring crime case data based on the estimated visitor's emotions. For example, if the visitor is nervous, the acquisition unit can adjust the method for acquiring crime case data to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the acquisition unit can adjust the method for acquiring crime case data to one suitable for a relaxed state. Furthermore, if the visitor is angry, the acquisition unit can adjust the method for acquiring crime case data to one suitable for an angry state. For example, if the visitor is nervous, the acquisition unit can adjust the method for acquiring crime case data to one suitable for a nervous state, thereby improving acquisition accuracy. Furthermore, if the visitor is relaxed, the acquisition unit can adjust the method for acquiring crime case data to one suitable for a relaxed state, thereby improving acquisition accuracy. Furthermore, if the visitor is angry, the acquisition unit can adjust the method for acquiring crime case data to one suitable for an angry state, thereby improving acquisition accuracy. In this way, adjusting the method for acquiring crime case data based on the visitor's emotions enables more accurate acquisition of crime case data. Some or all of the above-described processing by the acquisition unit may be performed, for example, using AI or without AI. For example, the acquisition unit can input visitor emotional data into the AI ​​and have the AI ​​adjust the method of acquiring crime case data.

[0103] When acquiring crime case data, the acquisition unit can improve the accuracy of the acquisition by referring to the visitor's past behavioral patterns. For example, the acquisition unit acquires crime case data by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire crime case data by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire crime case data by referring to the behavioral patterns of visitors who have never visited before. For example, the acquisition unit acquires crime case data by referring to the behavioral patterns of the same visitor when he or she visited in the past. The acquisition unit can also acquire crime case data by referring to the behavioral patterns of visitors who have caused problems in the past. Furthermore, the acquisition unit can acquire crime case data by referring to the behavioral patterns of visitors who have never visited before. In this way, referring to past behavioral patterns improves the accuracy of the crime case data acquisition. Some or all of the above-described processing by the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the visitor's past behavioral pattern data into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0104] The acquisition unit can estimate the visitor's emotions and prioritize the crime case data based on the estimated visitor's emotions. For example, if the visitor is nervous, the acquisition unit can prioritize the crime case data to be appropriate for a nervous state. Furthermore, if the visitor is relaxed, the acquisition unit can also prioritize the crime case data to be appropriate for a relaxed state. Furthermore, if the visitor is angry, the acquisition unit can also prioritize the crime case data to be appropriate for an angry state. For example, if the visitor is nervous, the acquisition unit can prioritize the crime case data to be appropriate for a nervous state and prioritize acquiring important crime case data. Furthermore, if the visitor is relaxed, the acquisition unit can prioritize the crime case data to be appropriate for a relaxed state and prioritize acquiring important crime case data. Furthermore, if the visitor is angry, the acquisition unit can prioritize the crime case data to be appropriate for an angry state and prioritize acquiring important crime case data. In this way, by prioritizing the crime case data based on the visitor's emotions, important crime case data can be prioritized. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input visitor emotion data into AI and have the AI ​​determine the priority of crime case data.

[0105] When acquiring crime case data, the acquisition unit can improve the accuracy of the acquisition by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the acquisition unit acquires crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the acquisition unit acquires crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the acquisition unit can also acquire crime case data taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the acquisition of crime case data is improved. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the acquisition.

[0106] The evaluation unit can estimate the visitor's emotions and adjust the safety assessment method based on the estimated visitor's emotions. For example, if the visitor is nervous, the evaluation unit can adjust the safety assessment method to one suitable for a nervous state. Furthermore, if the visitor is relaxed, the evaluation unit can also adjust the safety assessment method to one suitable for a relaxed state. Furthermore, if the visitor is angry, the evaluation unit can also adjust the safety assessment method to one suitable for an angry state. For example, if the visitor is nervous, the evaluation unit can adjust the safety assessment method to one suitable for a nervous state, thereby improving the evaluation accuracy. Furthermore, if the visitor is relaxed, the evaluation unit can also adjust the safety assessment method to one suitable for a relaxed state, thereby improving the evaluation accuracy. Furthermore, if the visitor is angry, the evaluation unit can also adjust the safety assessment method to one suitable for an angry state, thereby improving the evaluation accuracy. Thus, adjusting the safety assessment method based on the visitor's emotions enables more accurate safety assessment. Some or all of the above-described processing in the evaluation unit may be performed, for example, using AI or without AI. For example, the evaluation unit can input visitor emotional data into the AI ​​and have the AI ​​adjust the safety evaluation method.

[0107] During safety evaluation, the evaluation unit can improve the accuracy of the evaluation by referring to the visitor's past behavioral history. For example, the evaluation unit evaluates safety by referring to the behavioral history of the same visitor when he or she visited in the past. The evaluation unit can also evaluate safety by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the evaluation unit can evaluate safety by referring to the behavioral history of visitors who have never visited before. For example, the evaluation unit evaluates safety by referring to the behavioral history of the same visitor when he or she visited in the past. The evaluation unit can also evaluate safety by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the evaluation unit can evaluate safety by referring to the behavioral history of visitors who have never visited before. In this way, referring to the past behavioral history improves the accuracy of the safety evaluation. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the evaluation.

[0108] The evaluation unit can estimate the visitor's emotions and determine the priority of safety assessments based on the estimated visitor's emotions. For example, if the visitor is nervous, the evaluation unit determines the priority of safety assessments to be appropriate for a nervous state. Furthermore, if the visitor is relaxed, the evaluation unit can also determine the priority of safety assessments to be appropriate for a relaxed state. Furthermore, if the visitor is angry, the evaluation unit can also determine the priority of safety assessments to be appropriate for an angry state. For example, if the visitor is nervous, the evaluation unit can determine the priority of safety assessments to be appropriate for a nervous state and prioritize important safety assessments. Furthermore, if the visitor is relaxed, the evaluation unit can determine the priority of safety assessments to be appropriate for a relaxed state and prioritize important safety assessments. Furthermore, if the visitor is angry, the evaluation unit can determine the priority of safety assessments to be appropriate for an angry state and prioritize important safety assessments. In this way, by determining the priority of safety assessments based on the visitor's emotions, important safety assessments can be prioritized. Some or all of the above-described processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit may input visitor emotion data into AI and have the AI ​​determine the priority of safety evaluations.

[0109] The evaluation unit can improve the accuracy of the safety evaluation by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the evaluation unit can evaluate safety by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the evaluation unit can evaluate safety by taking into account the characteristics of the area. In this way, by taking into account the geographical location information of the visitor, the accuracy of the safety evaluation is improved. Some or all of the above-mentioned processing in the evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the evaluation unit can input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the evaluation.

[0110] The notification unit can estimate the visitor's emotions and adjust the content of the notification based on the estimated visitor's emotions. For example, if the visitor is nervous, the notification unit can adjust the content of the notification to be appropriate for a nervous state. Furthermore, if the visitor is relaxed, the notification unit can adjust the content of the notification to be appropriate for a relaxed state. Furthermore, if the visitor is angry, the notification unit can adjust the content of the notification to be appropriate for an angry state. For example, if the visitor is nervous, the notification unit can adjust the content of the notification to be appropriate for a nervous state, thereby improving the accuracy of the notification. Furthermore, if the visitor is relaxed, the notification unit can adjust the content of the notification to be appropriate for a relaxed state, thereby improving the accuracy of the notification. Furthermore, if the visitor is angry, the notification unit can adjust the content of the notification to be appropriate for an angry state, thereby improving the accuracy of the notification. Thus, adjusting the content of the notification based on the visitor's emotions enables more appropriate notification. Some or all of the above-described processing in the notification unit may be performed, for example, using AI or without using AI. For example, the notification unit can input the visitor's emotional data into the AI ​​and have the AI ​​adjust the content of the notification.

[0111] The notification unit can improve the accuracy of the notification by referring to the visitor's past behavioral history when making a notification. For example, the notification unit can improve the accuracy of the notification by referring to the behavioral history of the same visitor when they visited in the past. The notification unit can also improve the accuracy of the notification by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the notification unit can improve the accuracy of the notification by referring to the behavioral history of visitors who have never visited before. For example, the notification unit can improve the accuracy of the notification by referring to the behavioral history of the same visitor when they visited in the past. The notification unit can also improve the accuracy of the notification by referring to the behavioral history of visitors who have caused problems in the past. Furthermore, the notification unit can improve the accuracy of the notification by referring to the behavioral history of visitors who have never visited before. In this way, the accuracy of the notification is improved by referring to the past behavioral history. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the visitor's past behavioral history data into AI and have the AI ​​improve the accuracy of the notification.

[0112] The notification unit can estimate the visitor's emotions and adjust the timing of the notification based on the estimated visitor's emotions. For example, if the visitor is nervous, the notification unit can delay the timing of the notification. Furthermore, if the visitor is relaxed, the notification unit can also advance the timing of the notification. Furthermore, if the visitor is angry, the notification unit can adjust the timing of the notification. For example, if the visitor is nervous, the notification unit can delay the timing of the notification to improve the accuracy of the notification. Furthermore, if the visitor is relaxed, the notification unit can also advance the timing of the notification to improve the accuracy of the notification. Furthermore, if the visitor is angry, the notification unit can adjust the timing of the notification to improve the accuracy of the notification. Thus, by adjusting the timing of the notification based on the visitor's emotions, the notification can be made at a more appropriate time. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input visitor emotion data into AI and have the AI ​​adjust the timing of the notification.

[0113] The notification unit can improve the accuracy of the notification by taking into account the geographical location information of the visitor when making a notification. For example, if the visitor comes from a specific area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. For example, if the visitor comes from a specific area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a distant location, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. Furthermore, if the visitor comes from a nearby area, the notification unit can improve the accuracy of the notification by taking into account the characteristics of the area. In this way, the accuracy of the notification is improved by taking into account the geographical location information of the visitor. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the geographical location information of the visitor into AI and cause the AI ​​to improve the accuracy of the notification. === Hard Collateral 1-1 === Each of the multiple elements, including the face recognition unit, facial expression analysis unit, voice quality analysis unit, and risk calculation unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the face recognition unit photographs the visitor's face using the camera 42 of the smart device 14 and executes facial recognition technology using the specific processing unit 290 of the data processing device 12. For example, the facial expression analysis unit executes facial expression analysis technology using the specific processing unit 290 of the data processing device 12 to determine the visitor's emotional state. For example, the voice quality analysis unit collects the visitor's voice using the microphone 38B of the smart device 14 and executes voice quality analysis technology using the specific processing unit 290 of the data processing device 12. For example, the risk calculation unit calculates a risk index using the specific processing unit 290 of the data processing device 12 and displays it on the display 40A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the face recognition unit, facial expression analysis unit, voice quality analysis unit, and risk calculation unit described above is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the face recognition unit photographs the visitor's face using the camera 42 of the smart glasses 214 and executes a facial recognition technique using the specific processing unit 290 of the data processing device 12. For example, the facial expression analysis unit executes a facial expression analysis technique using the specific processing unit 290 of the data processing device 12 to determine the visitor's emotional state. For example, the voice quality analysis unit collects the visitor's voice using the microphone 238 of the smart glasses 214 and executes a voice quality analysis technique using the specific processing unit 290 of the data processing device 12. For example, the risk calculation unit calculates a risk index using the specific processing unit 290 of the data processing device 12 and displays it on the display of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the face recognition unit, facial expression analysis unit, voice quality analysis unit, and risk calculation unit described above is realized, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the face recognition unit photographs the face of the visitor using the camera 42 of the headset terminal 314, and executes facial recognition technology using the specific processing unit 290 of the data processing device 12. For example, the facial expression analysis unit executes facial expression analysis technology using the specific processing unit 290 of the data processing device 12 to determine the emotional state of the visitor. For example, the voice quality analysis unit collects the voice of the visitor using the microphone 238 of the headset terminal 314, and executes voice quality analysis technology using the specific processing unit 290 of the data processing device 12. For example, the risk calculation unit calculates a risk index using the specific processing unit 290 of the data processing device 12, and displays it on the display 343 of the headset terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the face recognition unit, facial expression analysis unit, voice quality analysis unit, and danger level calculation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the face recognition unit photographs the face of the visitor using the camera 42 of the robot 414 and executes a facial recognition technique using the specific processing unit 290 of the data processing device 12. For example, the facial expression analysis unit executes a facial expression analysis technique using the specific processing unit 290 of the data processing device 12 to determine the emotional state of the visitor. For example, the voice quality analysis unit collects the voice of the visitor using the microphone 238 of the robot 414 and executes a voice quality analysis technique using the specific processing unit 290 of the data processing device 12. For example, the danger level calculation unit calculates a danger level index using the specific processing unit 290 of the data processing device 12 and displays it on the display of the robot 414.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] When recognizing a visitor's face, the face recognition unit can improve the accuracy of recognition based on the visitor's clothing and belongings. For example, the accuracy of face recognition can be improved by analyzing the color and design of the visitor's clothing. The accuracy of face recognition can also be improved by analyzing the visitor's belongings (bags, umbrellas, etc.). The accuracy of face recognition can also be improved by analyzing the visitor's accessories (glasses, hats, etc.). In this way, the accuracy of face recognition can be improved by analyzing the visitor's clothing and belongings.

[0116] The facial expression analysis unit can improve the accuracy of the analysis by referring to the visitor's body temperature and heart rate. For example, the accuracy of facial expression analysis can be improved by referring to the visitor's body temperature. The accuracy of facial expression analysis can also be improved by referring to the visitor's heart rate. Furthermore, the accuracy of facial expression analysis can also be improved by referring to both the visitor's body temperature and heart rate. In this way, the accuracy of facial expression analysis is improved by referring to the visitor's body temperature and heart rate.

[0117] The voice quality analysis unit can improve the accuracy of analysis by referring to the breathing pattern of the visitor. For example, the accuracy of voice quality analysis can be improved by referring to the breathing pattern of the visitor. The accuracy of voice quality analysis can also be improved by referring to the breathing rhythm of the visitor. Furthermore, the accuracy of voice quality analysis can also be improved by referring to the depth of breathing of the visitor. In this way, by referring to the breathing pattern of the visitor, the accuracy of voice quality analysis is improved.

[0118] The risk level calculation unit can evaluate the visitor's current behavior and attitude in real time. For example, the risk level can be calculated by evaluating the visitor's current behavior (e.g., hand movements and posture) in real time. The risk level can also be calculated by evaluating the visitor's current attitude (e.g., line of sight and facial expression) in real time. Furthermore, the risk level can be calculated by evaluating the visitor's current behavior and attitude together in real time. In this way, the accuracy of the risk level calculation is improved by evaluating the visitor's current behavior and attitude in real time.

[0119] The notification unit can improve the accuracy of the notification by taking into account the geographical location information of the visitor. For example, if the visitor comes from a specific area, the accuracy of the notification can be improved by taking into account the characteristics of that area. Also, if the visitor comes from a distant location, the accuracy of the notification can be improved by taking into account the characteristics of that area. Furthermore, if the visitor comes from a nearby area, the accuracy of the notification can be improved by taking into account the characteristics of that area. In this way, the accuracy of the notification can be improved by taking into account the geographical location information of the visitor.

[0120] The face recognition unit can estimate the emotion of the visitor and adjust the accuracy of face recognition based on the estimated emotion of the visitor. For example, if the visitor is nervous, the face recognition algorithm can be adjusted to one suitable for a nervous state. Also, if the visitor is relaxed, the face recognition algorithm can be adjusted to one suitable for a relaxed state. Furthermore, if the visitor is angry, the face recognition algorithm can be adjusted to one suitable for an angry state. In this way, adjusting the accuracy of face recognition based on the emotion of the visitor enables more accurate face recognition.

[0121] The facial expression analysis unit can estimate the emotion of the visitor and adjust the facial expression analysis algorithm based on the estimated emotion of the visitor. For example, if the visitor is nervous, the facial expression analysis algorithm can be adjusted to one suitable for a nervous state. Also, if the visitor is relaxed, the facial expression analysis algorithm can be adjusted to one suitable for a relaxed state. Furthermore, if the visitor is angry, the facial expression analysis algorithm can be adjusted to one suitable for an angry state. In this way, by adjusting the facial expression analysis algorithm based on the emotion of the visitor, more accurate facial expression analysis is possible.

[0122] The voice quality analysis unit can estimate the visitor's emotions and adjust the voice quality analysis algorithm based on the estimated visitor's emotions. For example, if the visitor is nervous, the voice quality analysis algorithm can be adjusted to one suitable for a nervous state. Also, if the visitor is relaxed, the voice quality analysis algorithm can be adjusted to one suitable for a relaxed state. Furthermore, if the visitor is angry, the voice quality analysis algorithm can be adjusted to one suitable for an angry state. In this way, adjusting the voice quality analysis algorithm based on the visitor's emotions enables more accurate voice quality analysis.

[0123] The risk calculation unit can estimate the visitor's emotions and adjust the risk index calculation method based on the estimated visitor's emotions. For example, if the visitor is nervous, the risk index calculation method can be adjusted to one suitable for a nervous state. Also, if the visitor is relaxed, the risk index calculation method can be adjusted to one suitable for a relaxed state. Furthermore, if the visitor is angry, the risk index calculation method can be adjusted to one suitable for an angry state. In this way, adjusting the risk index calculation method based on the visitor's emotions enables more accurate risk assessment.

[0124] The notification unit can estimate the visitor's emotions and adjust the content of the notification based on the estimated visitor's emotions. For example, if the visitor is nervous, the notification content can be adjusted to be appropriate for a nervous state. Also, if the visitor is relaxed, the notification content can be adjusted to be appropriate for a relaxed state. Furthermore, if the visitor is angry, the notification content can be adjusted to be appropriate for an angry state. In this way, by adjusting the content of the notification based on the visitor's emotions, more appropriate notifications can be provided.

[0125] The processing flow of the second embodiment will be briefly explained below.

[0126] Step 1: The face recognition unit recognizes the visitor's face. The face recognition unit can recognize faces using, for example, deep learning technology or pattern matching technology. It can also extract facial feature points and recognize faces based on those. Step 2: The facial expression analysis unit analyzes the facial expression recognized by the face recognition unit. The facial expression analysis unit can analyze the facial expression using, for example, a facial expression recognition algorithm and determine the type and changes of the facial expression. Step 3: The voice quality analysis unit analyzes the voice quality based on the facial expression analyzed by the facial expression analysis unit. The voice quality analysis unit can analyze the voice quality using, for example, an algorithm for extracting voice features, and evaluate the tone and tension of the voice. Step 4: The risk calculation unit calculates a risk index based on the voice quality analyzed by the voice quality analysis unit. The risk calculation unit can calculate the risk index using, for example, a scoring algorithm and evaluate the risk by referring to evaluation criteria and past data.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0129] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0141] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0170] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0171] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0172] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0173] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0174] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0175] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0177] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0182] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0183] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0184] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0188] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0189] 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.

[0190] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0191] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0192] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0193] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0195] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0196] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0197] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0198] [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a face recognition unit that recognizes the face of a visitor; an expression analysis unit that analyzes facial expressions recognized by the face recognition unit; a voice quality analysis unit that analyzes voice quality based on the facial expression analyzed by the facial expression analysis unit; a risk calculation unit that calculates a risk index based on the voice quality analyzed by the voice quality analysis unit; Equipped with A system characterized by:

2. Equipped with an acquisition unit that acquires past visit history The system of claim 1 .

3. Equipped with an acquisition unit that collects crime case data from across the country The system of claim 1 .

4. an evaluation unit that evaluates safety based on the data acquired by the acquisition unit; 4. The system of claim 3.

5. Equipped with a notification function that sends a notification to your smartphone if a visitor arrives while you are out The system of claim 1 .

6. The notification unit Displaying visitors' faces and voices on your smartphone 6. The system of claim 5.

7. The face recognition unit Estimate the visitor's emotions and adjust the accuracy of facial recognition based on the estimated emotions of the visitor. The system of claim 1 .

8. The face recognition unit When recognizing faces, the system determines the priority of recognition by referring to the visitor's past visit history. The system of claim 1 .

9. The face recognition unit When recognizing faces, the recognition algorithm is adjusted based on the visitor's age and gender. The system of claim 1 .

Images