System

Abstract

An object of a system according to an embodiment is to automate handling of a suicide prevention dial and to perform quick and appropriate handling.SOLUTION: A system includes a voice recognition unit, an analysis unit, and a reporting unit. In the AI recognition unit, the generated speech automatically responds when a phone call is made to the suicide prevention dial. The analysis unit analyzes the call content acquired by the voice recognition unit in real time, and grasps the feeling and situation of the other party. The reporting unit reports to an emergency contact destination when the analysis unit determines that there is an emergency.SELECTED DRAWING: Figure 1

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, suicide prevention hotlines were dependent on human intervention, which meant that responses could be delayed.

[0005] The system according to the embodiment aims to automate responses to suicide prevention hotlines and provide prompt and appropriate responses. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice recognition unit, an analysis unit, and a reporting unit. The voice recognition unit uses a generation AI to automatically respond when a call is made to the suicide prevention hotline. The analysis unit analyzes the content of the call acquired by the voice recognition unit in real time to understand the emotions and situation of the other party. The reporting unit notifies an emergency contact if the analysis unit determines that the call is an emergency. [Effects of the Invention]

[0007] The system according to the embodiment automates responses to suicide prevention hotlines, enabling prompt and appropriate responses. [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) The AI ​​suicide prevention hotline system according to an embodiment of the present invention is a system that uses generation AI to automate suicide prevention hotline responses and provide prompt and appropriate support. This enables the AI ​​suicide prevention hotline system to provide prompt and appropriate support.

[0029] An AI-enabled suicide prevention hotline system according to an embodiment includes a generation AI, a voice recognition unit, an analysis unit, and a reporting unit. The generation AI automatically answers calls to the suicide prevention hotline. For example, the generation AI responds by saying, "Hello, this is the suicide prevention hotline. We'd like to hear from you." The voice recognition unit uses voice recognition technology to understand what the caller is saying when the generation AI automatically responds. For example, the voice recognition unit converts the caller's speech into text data. The analysis unit analyzes the call content acquired by the voice recognition unit in real time to understand the caller's emotions and situation. For example, if the caller says, "There's no point in living anymore," the analysis unit analyzes the statement and suggests an appropriate response. The reporting unit notifies an emergency contact if the analysis unit determines that the call is an emergency. For example, if the caller expresses an intention to attempt suicide, the reporting unit immediately notifies an emergency contact. As a result, the AI-enabled suicide prevention hotline system according to an embodiment automates suicide prevention hotline responses and provides prompt and appropriate assistance.

[0030] The voice recognition unit can refer to the other party's past call history when a call starts and provide individualized support. For example, the generation AI can refer to the other party's past call history when a call starts and provide individualized support based on the content of the previous conversation. For example, it can remember what was said in the previous call and proceed with the conversation based on that. In addition, the voice recognition unit can analyze the other party's past call history when a call starts and follow up on specific problems or concerns. For example, it can check the progress of solutions proposed in the previous call. In addition, the voice recognition unit can refer to the other party's past call history and provide individualized support. For example, it can provide appropriate advice or support based on what the other party previously said. This makes it possible to provide individualized support based on past call history.

[0031] The speech recognition unit can be equipped with a multilingual support function so that it can handle different languages ​​and dialects. For example, the speech recognition unit can equip the generation AI with a multilingual support function to handle different languages ​​and dialects. For example, it can receive calls in multiple languages ​​such as English, Spanish, and Chinese. The speech recognition unit can also enable the generation AI, which handles the initial call reception, to handle different dialects. For example, it can handle regional dialects such as the Kansai dialect and Tohoku dialect of Japanese. The speech recognition unit can also equip the generation AI with a multilingual support function to handle different languages ​​and dialects. For example, it can use an automatic translation function during a call to respond in a language that is appropriate for the other party. This makes it possible to handle different languages ​​and dialects.

[0032] The voice recognition unit also analyzes background and environmental sounds when receiving a call, allowing for a more detailed understanding of the other party's situation. For example, when the generation AI receives a call, the voice recognition unit analyzes background and environmental sounds to understand the other party's situation. For example, it can infer that the other party is out from the traffic sounds and crowd sounds heard during the call. The voice recognition unit also analyzes background sounds during the call to understand the other party's situation. For example, it can infer that the other party is at home from the sounds of the television and music heard during the call. The voice recognition unit also analyzes environmental sounds when the generation AI receives a call to understand the other party's situation. For example, it can infer that the other party is outside from the sound of the wind and birds chirping heard during the call. In this way, by analyzing background and environmental sounds, the other party's situation can be understood in more detail.

[0033] When analyzing the content of a call, the analysis unit can identify potential problems or trauma behind the other party's words and suggest an appropriate response. For example, the generation AI analyzes the content of a call to identify potential problems or trauma behind the other party's words. For example, if the other party talks about past trauma, the analysis unit suggests an appropriate response to that problem. The generation AI also analyzes the other party's words during a call to identify potential problems or trauma. For example, if the other party talks about a past failure, the analysis unit provides appropriate advice for that problem. The generation AI also analyzes the content of a call to identify potential problems or trauma behind the other party's words. For example, if the other party talks about a past experience, the analysis unit provides appropriate support for that problem. This makes it possible to identify the other party's potential problems or trauma and suggest an appropriate response.

[0034] The analysis unit can build a system in which the analysis results of the call content are shared with other support organizations and experts, and a collaborative response is possible. For example, the analysis unit builds a system in which the generation AI analyzes the call content and shares the results with other support organizations and experts. For example, it contacts an appropriate expert depending on the other party's situation. The analysis unit also builds a system in which the analysis results of the call content are shared with other support organizations and experts, and a collaborative response is possible. For example, if the other party has a specific problem, it will collaborate with an expert who is knowledgeable about that problem. The analysis unit also builds a system in which the generation AI analyzes the call content and shares the results with other support organizations and experts. For example, it will contact an appropriate support organization depending on the other party's situation. This allows the analysis results of the call content to be shared with other support organizations and experts, and a collaborative response is possible.

[0035] The reporting unit can automatically obtain the location information of the other party during an emergency response and notify the nearest emergency contact. For example, the generation AI can automatically obtain the location information of the other party during a call and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will immediately contact the police or an ambulance. Furthermore, in an emergency response, the generation AI can obtain the location information of the other party and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will respond quickly. Furthermore, the generation AI can automatically obtain the location information of the other party during a call and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will immediately notify the emergency contact. This allows the other party's location information to be automatically obtained and notified the nearest emergency contact.

[0036] When responding to an emergency, the reporting unit can refer to the other party's past health information and medical history to suggest the optimal response. For example, when the generation AI responds to an emergency, the reporting unit can refer to the other party's past health information and medical history to suggest the optimal response. For example, if the other party has a specific medical history, the reporting unit can take an appropriate response based on that information. Also, when responding to an emergency, the generation AI can refer to the other party's medical history to suggest the optimal response. For example, if the other party has attempted suicide in the past, the reporting unit can take an appropriate response based on that information. Also, when responding to an emergency, the reporting unit can refer to the other party's health information to suggest the optimal response. For example, if the other party is taking a specific medication, the reporting unit can take an appropriate response based on that information. This allows the reporting unit to refer to the other party's past health information and medical history to suggest the optimal response.

[0037] The reporting unit can be made multifunctional so that it can respond to different emergency situations. For example, the reporting unit can make the generating AI multifunctional so that it can respond to different emergency situations. For example, it can issue evacuation orders in the event of a natural disaster, and notify the police in the event of a crime. The reporting unit also enables the generating AI that responds to emergencies to respond to different emergency situations. For example, it can notify the fire department in the event of a fire, and contact ambulances in the event of a medical emergency. The reporting unit can also make the generating AI multifunctional so that it can respond to different emergency situations. For example, it can provide information on evacuation sites in the event of an earthquake, and notify the police in the event of a crime. This makes it possible to respond to different emergency situations.

[0038] The reporting unit can automatically contact the other party's family and friends to request assistance in an emergency. For example, when the generating AI responds to an emergency, the reporting unit automatically contacts the other party's family and friends to request assistance. For example, if the other party expresses an intention to attempt suicide, it will contact their family and friends. The reporting unit can also automatically contact the other party's family and friends to request assistance in an emergency. For example, if the other party is in a dangerous situation, it will contact their family and friends. The reporting unit can also automatically contact the other party's family and friends to request assistance in an emergency. For example, if the other party expresses an intention to attempt suicide, it will contact their family and friends. This allows the other party's family and friends to automatically contact the other party's family and friends to request assistance in an emergency.

[0039] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0040] The AI ​​suicide prevention hotline system can also be equipped with a health management unit that monitors the user's health status. For example, if a user complains of feeling unwell during a call, the health management unit will record that information and contact the appropriate medical institution. The health management unit can also refer to the user's past health data and provide appropriate advice. For example, if the user has had heart disease in the past, the health management unit can take appropriate action based on that information. Furthermore, the health management unit can monitor the user's health status in real time and issue an alert if an abnormality is detected. This allows for comprehensive management of the user's health status and enables prompt and appropriate action.

[0041] The AI ​​suicide prevention hotline system can also be equipped with a social background analysis unit that takes into account the user's social background. For example, if a user complains of work stress during a call, the social background analysis unit will analyze that information and suggest appropriate counseling. The social background analysis unit can also provide appropriate support measures by taking into account the user's family environment and financial situation. For example, if the user is experiencing financial difficulties, the unit will contact an appropriate support organization based on that information. Furthermore, the social background analysis unit can comprehensively analyze the user's social background and create a long-term support plan. This makes it possible to provide comprehensive support that takes into account the user's social background.

[0042] The AI ​​suicide prevention hotline system can also be equipped with a hobby analysis unit that takes into account the user's hobbies and interests. For example, if a user talks about their hobbies during a call, the hobby analysis unit can record that information and provide appropriate topics. The hobby analysis unit can also suggest relaxing activities based on the user's hobbies and interests. For example, if the user likes music, the unit can suggest relaxing music based on that information. Furthermore, the hobby analysis unit can comprehensively analyze the user's hobbies and interests and create a long-term support plan. This makes it possible to provide comprehensive support that takes the user's hobbies and interests into consideration.

[0043] The AI-based suicide prevention hotline system can also be equipped with a lifestyle analysis unit that monitors the user's lifestyle. For example, if a user complains about lack of sleep during a call, the lifestyle analysis unit can record that information and provide appropriate advice. The lifestyle analysis unit can also take into account the user's eating and exercise habits to suggest healthy lifestyle habits. For example, if a user has irregular eating habits, the unit can suggest an appropriate meal plan based on that information. Furthermore, the lifestyle analysis unit can comprehensively analyze the user's lifestyle and create a long-term health management plan. This makes it possible to provide comprehensive support that takes into account the user's lifestyle.

[0044] The processing flow of the first embodiment will be briefly explained below.

[0045] Step 1: When a call comes in to the suicide prevention hotline, the generation AI automatically responds. For example, the generation AI responds by saying something like, "Hello, this is the suicide prevention hotline. We'd like to hear from you," and uses speech recognition technology to understand what the caller is saying. The speech recognition unit then converts what the caller is saying into text data. Step 2: The analysis unit analyzes the call content acquired by the voice recognition unit in real time to understand the other person's emotions and situation. For example, if the other person says, "There's no point in living anymore," the analysis unit analyzes that statement and suggests an appropriate response. Step 3: If the analysis unit determines that the situation is urgent, the reporting unit notifies the emergency contacts. For example, if the other person expresses an intention to attempt suicide, the reporting unit immediately notifies the emergency contacts.

[0046] (Example 2) The AI ​​suicide prevention hotline system according to an embodiment of the present invention is a system that uses generation AI to automate suicide prevention hotline responses and provide prompt and appropriate support. This enables the AI ​​suicide prevention hotline system to provide prompt and appropriate support.

[0047] An AI-enabled suicide prevention hotline system according to an embodiment includes a generation AI, a voice recognition unit, an analysis unit, and a reporting unit. The generation AI automatically answers calls to the suicide prevention hotline. For example, the generation AI responds by saying, "Hello, this is the suicide prevention hotline. We'd like to hear from you." The voice recognition unit uses voice recognition technology to understand what the caller is saying when the generation AI automatically responds. For example, the voice recognition unit converts the caller's speech into text data. The analysis unit analyzes the call content acquired by the voice recognition unit in real time to understand the caller's emotions and situation. For example, if the caller says, "There's no point in living anymore," the analysis unit analyzes the statement and suggests an appropriate response. The reporting unit notifies an emergency contact if the analysis unit determines that the call is an emergency. For example, if the caller expresses an intention to attempt suicide, the reporting unit immediately notifies an emergency contact. As a result, the AI-enabled suicide prevention hotline system according to an embodiment automates suicide prevention hotline responses and provides prompt and appropriate assistance.

[0048] The voice recognition unit analyzes the other party's tone of voice and speaking patterns to infer their emotional state and adjust the response accordingly. For example, when the generation AI answers a call, it analyzes the other party's tone of voice and speaking patterns to infer their emotional state. For example, if the other party sounds sad, the generation AI will respond in a gentle tone. The voice recognition unit also analyzes the other party's tone of voice in real time during a call to infer their emotional state. For example, if the other party sounds angry, the generation AI will respond in a calm tone. The voice recognition unit also analyzes the other party's speaking patterns to infer their emotional state. For example, if the other party is nervous, the generation AI will say words to relax them. This makes it possible to respond appropriately according to the other party's emotional state.

[0049] The voice recognition unit can refer to the other party's past call history when a call starts and provide individualized support. For example, the generation AI can refer to the other party's past call history when a call starts and provide individualized support based on the content of the previous conversation. For example, it can remember what was said in the previous call and proceed with the conversation based on that. In addition, the voice recognition unit can analyze the other party's past call history when a call starts and follow up on specific problems or concerns. For example, it can check the progress of solutions proposed in the previous call. In addition, the voice recognition unit can refer to the other party's past call history and provide individualized support. For example, it can provide appropriate advice or support based on what the other party previously said. This makes it possible to provide individualized support based on past call history.

[0050] The speech recognition unit uses the emotion estimation function to monitor the other party's emotional state in real time and can offer reassuring words at the appropriate time. For example, the generation AI in the speech recognition unit can monitor the other party's emotional state in real time during a call and offer reassuring words at the appropriate time. For example, if the other party is feeling anxious, it can say, "It's okay, we're listening to you here." The speech recognition unit also uses the emotion estimation function to monitor the other party's emotional state in real time and offer encouraging words at the appropriate time. For example, if the other party is feeling down, it can say, "You're not alone." The speech recognition unit also uses the generation AI to monitor the other party's emotional state in real time and offer reassuring words at the appropriate time. For example, if the other party is nervous, it can say, "Please relax and talk." This makes it possible to offer reassuring words at the appropriate time according to the other party's emotional state.

[0051] The speech recognition unit can be equipped with a multilingual support function so that it can handle different languages ​​and dialects. For example, the speech recognition unit can equip the generation AI with a multilingual support function to handle different languages ​​and dialects. For example, it can receive calls in multiple languages ​​such as English, Spanish, and Chinese. The speech recognition unit can also enable the generation AI, which handles the initial call reception, to handle different dialects. For example, it can handle regional dialects such as the Kansai dialect and Tohoku dialect of Japanese. The speech recognition unit can also equip the generation AI with a multilingual support function to handle different languages ​​and dialects. For example, it can use an automatic translation function during a call to respond in a language that is appropriate for the other party. This makes it possible to handle different languages ​​and dialects.

[0052] The voice recognition unit also analyzes background and environmental sounds when receiving a call, allowing for a more detailed understanding of the other party's situation. For example, when the generation AI receives a call, the voice recognition unit analyzes background and environmental sounds to understand the other party's situation. For example, it can infer that the other party is out from the traffic sounds and crowd sounds heard during the call. The voice recognition unit also analyzes background sounds during the call to understand the other party's situation. For example, it can infer that the other party is at home from the sounds of the television and music heard during the call. The voice recognition unit also analyzes environmental sounds when the generation AI receives a call to understand the other party's situation. For example, it can infer that the other party is outside from the sound of the wind and birds chirping heard during the call. In this way, by analyzing background and environmental sounds, the other party's situation can be understood in more detail.

[0053] The voice recognition unit can use the emotion estimation function to adjust voice feedback during a call to provide an environment where the other party feels comfortable speaking. The voice recognition unit, for example, uses the emotion estimation function to adjust voice feedback during a call to provide an environment where the other party feels comfortable speaking. For example, if the other party feels nervous, the generation AI speaks in a calm tone. The voice recognition unit also monitors the emotional state of the other party during a call and adjusts the voice feedback. For example, if the other party feels anxious, the generation AI speaks at a slower pace. The voice recognition unit also uses the emotion estimation function to adjust voice feedback during a call to provide an environment where the other party feels comfortable speaking. For example, if the other party feels angry, the generation AI speaks in a calm tone. This allows the voice feedback to be adjusted to provide an environment where the other party feels comfortable speaking.

[0054] When analyzing the content of a call, the analysis unit can identify potential problems or trauma behind the other party's words and suggest an appropriate response. For example, the generation AI analyzes the content of a call to identify potential problems or trauma behind the other party's words. For example, if the other party talks about past trauma, the analysis unit suggests an appropriate response to that problem. The generation AI also analyzes the other party's words during a call to identify potential problems or trauma. For example, if the other party talks about a past failure, the analysis unit provides appropriate advice for that problem. The generation AI also analyzes the content of a call to identify potential problems or trauma behind the other party's words. For example, if the other party talks about a past experience, the analysis unit provides appropriate support for that problem. This makes it possible to identify the other party's potential problems or trauma and suggest an appropriate response.

[0055] The analysis unit can also take into account the other party's non-verbal signs when analyzing the content of a call and adjust its response accordingly. For example, when the generation AI analyzes the content of a call, the analysis unit also takes into account the other party's non-verbal signs. For example, if the other party sighs, the analysis unit estimates their emotional state and responds appropriately. The analysis unit also allows the generation AI to analyze the other party's non-verbal signs during a call and adjust its response accordingly. For example, if the other party is silent, the analysis unit infers the reason and responds appropriately. The analysis unit also takes into account the other party's non-verbal signs when the generation AI analyzes the content of a call. For example, if the other party's voice is trembling, the analysis unit estimates their emotional state and provides appropriate support. This allows the analysis unit to take into account the other party's non-verbal signs and adjust its response accordingly.

[0056] The analysis unit uses the emotion estimation function to track changes in the other person's emotions in real time and provide words of encouragement or comfort at the appropriate time. For example, the analysis unit uses the emotion estimation function to track changes in the other person's emotions in real time and provide words of encouragement at the appropriate time. For example, if the other person is feeling down, the analysis unit may say something like, "You are important." The analysis unit also uses the generation AI to track changes in the other person's emotions in real time during a call and provide words of comfort at the appropriate time. For example, if the other person is feeling sad, the analysis unit may say something like, "Let's get through this together." The analysis unit also uses the emotion estimation function to track changes in the other person's emotions in real time and provide words of encouragement or comfort at the appropriate time. For example, if the other person is feeling anxious, the analysis unit may say something like, "You are not alone." This makes it possible to track changes in the other person's emotions in real time and provide words of encouragement or comfort at the appropriate time.

[0057] The analysis unit can build a system in which the analysis results of the call content are shared with other support organizations and experts, and a collaborative response is possible. For example, the analysis unit builds a system in which the generation AI analyzes the call content and shares the results with other support organizations and experts. For example, it contacts an appropriate expert depending on the other party's situation. The analysis unit also builds a system in which the analysis results of the call content are shared with other support organizations and experts, and a collaborative response is possible. For example, if the other party has a specific problem, it will collaborate with an expert who is knowledgeable about that problem. The analysis unit also builds a system in which the generation AI analyzes the call content and shares the results with other support organizations and experts. For example, it will contact an appropriate support organization depending on the other party's situation. This allows the analysis results of the call content to be shared with other support organizations and experts, and a collaborative response is possible.

[0058] The analysis unit can use the emotion estimation function to suggest music or relaxation techniques that match the emotional state of the other party. For example, the analysis unit can use the emotion estimation function to suggest music that matches the emotional state of the other party. For example, if the other party is feeling anxious, it can suggest relaxing music. The analysis unit also monitors the emotional state of the other party during a call using the generation AI and suggests relaxation techniques. For example, if the other party is nervous, it can teach them how to take deep breaths. The analysis unit also uses the emotion estimation function to suggest relaxation techniques that match the emotional state of the other party. For example, if the other party is feeling stressed, it can teach them how to meditate. This makes it possible to suggest music or relaxation techniques that match the emotional state of the other party.

[0059] The reporting unit can automatically obtain the location information of the other party during an emergency response and notify the nearest emergency contact. For example, the generation AI can automatically obtain the location information of the other party during a call and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will immediately contact the police or an ambulance. Furthermore, in an emergency response, the generation AI can obtain the location information of the other party and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will respond quickly. Furthermore, the generation AI can automatically obtain the location information of the other party during a call and notify the nearest emergency contact. For example, if the other party indicates an intention to attempt suicide, the reporting unit will immediately notify the emergency contact. This allows the other party's location information to be automatically obtained and notified the nearest emergency contact.

[0060] When responding to an emergency, the reporting unit can refer to the other party's past health information and medical history to suggest the optimal response. For example, when the generation AI responds to an emergency, the reporting unit can refer to the other party's past health information and medical history to suggest the optimal response. For example, if the other party has a specific medical history, the reporting unit can take an appropriate response based on that information. Also, when responding to an emergency, the generation AI can refer to the other party's medical history to suggest the optimal response. For example, if the other party has attempted suicide in the past, the reporting unit can take an appropriate response based on that information. Also, when responding to an emergency, the reporting unit can refer to the other party's health information to suggest the optimal response. For example, if the other party is taking a specific medication, the reporting unit can take an appropriate response based on that information. This allows the reporting unit to refer to the other party's past health information and medical history to suggest the optimal response.

[0061] The reporting department can use the emotion estimation function to monitor the emotional state of the other party in an emergency in real time and provide appropriate reassurance. For example, the reporting department can use the emotion estimation function to monitor the emotional state of the other party in an emergency in real time and provide appropriate reassurance. For example, if the other party is panicking, the reporting department can say, "Please stay calm, we will call for help immediately." In addition, when the generation AI responds to an emergency, the reporting department can monitor the other party's emotional state in real time and provide appropriate reassurance. For example, if the other party is feeling scared, the reporting department can say, "It's okay, we're listening here." In addition, the reporting department can use the emotion estimation function to monitor the other party's emotional state in an emergency in real time and provide appropriate reassurance. For example, if the other party is feeling anxious, the reporting department can say, "You are not alone." In this way, the reporting department can monitor the other party's emotional state in an emergency in real time and provide appropriate reassurance.

[0062] The reporting unit can be made multifunctional so that it can respond to different emergency situations. For example, the reporting unit can make the generating AI multifunctional so that it can respond to different emergency situations. For example, it can issue evacuation orders in the event of a natural disaster, and notify the police in the event of a crime. The reporting unit also enables the generating AI that responds to emergencies to respond to different emergency situations. For example, it can notify the fire department in the event of a fire, and contact ambulances in the event of a medical emergency. The reporting unit can also make the generating AI multifunctional so that it can respond to different emergency situations. For example, it can provide information on evacuation sites in the event of an earthquake, and notify the police in the event of a crime. This makes it possible to respond to different emergency situations.

[0063] The reporting unit can automatically contact the other party's family and friends to request assistance in an emergency. For example, when the generating AI responds to an emergency, the reporting unit automatically contacts the other party's family and friends to request assistance. For example, if the other party expresses an intention to attempt suicide, it will contact their family and friends. The reporting unit can also automatically contact the other party's family and friends to request assistance in an emergency. For example, if the other party is in a dangerous situation, it will contact their family and friends. The reporting unit can also automatically contact the other party's family and friends to request assistance in an emergency. For example, if the other party expresses an intention to attempt suicide, it will contact their family and friends. This allows the other party's family and friends to automatically contact the other party's family and friends to request assistance in an emergency.

[0064] The reporting unit can use the emotion estimation function to suggest relaxation techniques and breathing techniques that correspond to the other party's emotional state in an emergency. For example, the reporting unit uses the emotion estimation function to suggest relaxation techniques that correspond to the other party's emotional state in an emergency. For example, if the other party is in a panic, it teaches them how to take deep breaths. In addition, when the generation AI responds to an emergency, the reporting unit suggests relaxation techniques that correspond to the other party's emotional state. For example, if the other party is nervous, it teaches them how to meditate to relax. In addition, the reporting unit uses the emotion estimation function to suggest relaxation techniques and breathing techniques that correspond to the other party's emotional state in an emergency. For example, if the other party is feeling stressed, it teaches them breathing techniques to relax. In this way, it is possible to suggest relaxation techniques and breathing techniques that correspond to the other party's emotional state in an emergency.

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

[0066] The AI ​​suicide prevention hotline system can also be equipped with a health management unit that monitors the user's health status. For example, if a user complains of feeling unwell during a call, the health management unit will record that information and contact the appropriate medical institution. The health management unit can also refer to the user's past health data and provide appropriate advice. For example, if the user has had heart disease in the past, the health management unit can take appropriate action based on that information. Furthermore, the health management unit can monitor the user's health status in real time and issue an alert if an abnormality is detected. This allows for comprehensive management of the user's health status and enables prompt and appropriate action.

[0067] The AI ​​suicide prevention hotline system can also be equipped with a social background analysis unit that takes into account the user's social background. For example, if a user complains of work stress during a call, the social background analysis unit will analyze that information and suggest appropriate counseling. The social background analysis unit can also provide appropriate support measures by taking into account the user's family environment and financial situation. For example, if the user is experiencing financial difficulties, the unit will contact an appropriate support organization based on that information. Furthermore, the social background analysis unit can comprehensively analyze the user's social background and create a long-term support plan. This makes it possible to provide comprehensive support that takes into account the user's social background.

[0068] The AI ​​suicide prevention hotline system can also be equipped with a hobby analysis unit that takes into account the user's hobbies and interests. For example, if a user talks about their hobbies during a call, the hobby analysis unit can record that information and provide appropriate topics. The hobby analysis unit can also suggest relaxing activities based on the user's hobbies and interests. For example, if the user likes music, the unit can suggest relaxing music based on that information. Furthermore, the hobby analysis unit can comprehensively analyze the user's hobbies and interests and create a long-term support plan. This makes it possible to provide comprehensive support that takes the user's hobbies and interests into consideration.

[0069] The AI-based suicide prevention hotline system can also be equipped with a lifestyle analysis unit that monitors the user's lifestyle. For example, if a user complains about lack of sleep during a call, the lifestyle analysis unit can record that information and provide appropriate advice. The lifestyle analysis unit can also take into account the user's eating and exercise habits to suggest healthy lifestyle habits. For example, if a user has irregular eating habits, the unit can suggest an appropriate meal plan based on that information. Furthermore, the lifestyle analysis unit can comprehensively analyze the user's lifestyle and create a long-term health management plan. This makes it possible to provide comprehensive support that takes into account the user's lifestyle.

[0070] The AI ​​suicide prevention hotline system can also be equipped with a relaxation suggestion unit that estimates the user's emotional state and suggests appropriate relaxation techniques. For example, if the user feels stressed during a call, the relaxation suggestion unit can suggest deep breathing or meditation techniques based on that information. The relaxation suggestion unit can also suggest relaxing music or aromatherapy based on the user's emotional state. For example, if the user feels anxious, the relaxation suggestion unit can suggest relaxing music based on that information. Furthermore, the relaxation suggestion unit can comprehensively analyze the user's emotional state and create a long-term relaxation plan. This enables comprehensive relaxation support that takes the user's emotional state into consideration.

[0071] The AI-based suicide prevention hotline system can also be equipped with an encouragement suggestion unit that estimates the user's emotional state and provides appropriate words of encouragement. For example, if the user feels depressed during a call, the encouragement suggestion unit can use that information to say something like, "You are important." The encouragement suggestion unit can also provide appropriate words of encouragement based on the user's emotional state. For example, if the user feels anxious, the encouragement suggestion unit can use that information to say something like, "You are not alone." Furthermore, the encouragement suggestion unit can comprehensively analyze the user's emotional state and create a long-term encouragement plan. This enables comprehensive encouragement support that takes the user's emotional state into consideration.

[0072] The AI ​​suicide prevention hotline system can further include a counseling suggestion unit that estimates the user's emotional state and suggests appropriate counseling techniques. For example, if the user talks about past trauma during a call, the counseling suggestion unit can suggest appropriate counseling techniques based on that information. The counseling suggestion unit can also provide appropriate counseling techniques depending on the user's emotional state. For example, if the user is feeling stressed, it can suggest stress management methods based on that information. Furthermore, the counseling suggestion unit can comprehensively analyze the user's emotional state and create a long-term counseling plan. This makes it possible to provide comprehensive counseling support that takes the user's emotional state into consideration.

[0073] The AI ​​suicide prevention hotline system can further include a support group suggestion unit that estimates the user's emotional state and suggests an appropriate support group. For example, if the user feels lonely during a call, the support group suggestion unit will suggest an appropriate support group based on that information. The support group suggestion unit can also provide an appropriate support group based on the user's emotional state. For example, if the user feels anxious, the support group suggestion unit will suggest a support group with which the user can share their anxiety based on that information. Furthermore, the support group suggestion unit can comprehensively analyze the user's emotional state and create a long-term support group plan. This enables comprehensive support group support that takes the user's emotional state into consideration.

[0074] The AI ​​suicide prevention hotline system can also be equipped with a mental health resource suggestion unit that estimates the user's emotional state and suggests appropriate mental health resources. For example, if a user mentions a mental health problem during a call, the mental health resource suggestion unit can suggest appropriate resources based on that information. The mental health resource suggestion unit can also provide appropriate mental health resources based on the user's emotional state. For example, if the user is feeling stressed, it can suggest stress management resources based on that information. Furthermore, the mental health resource suggestion unit can comprehensively analyze the user's emotional state and create a long-term mental health resource plan. This enables comprehensive mental health resource support that takes the user's emotional state into consideration.

[0075] The AI ​​suicide prevention hotline system can also be equipped with a feedback suggestion unit that estimates the user's emotional state and provides appropriate feedback. For example, if the user becomes emotional during a call, the feedback suggestion unit can provide feedback such as "I understand how you feel" based on that information. The feedback suggestion unit can also provide appropriate feedback depending on the user's emotional state. For example, if the user is feeling anxious, the feedback suggestion unit can provide feedback such as "You are not alone" based on that information. Furthermore, the feedback suggestion unit can comprehensively analyze the user's emotional state and create a long-term feedback plan. This enables comprehensive feedback support that takes the user's emotional state into consideration.

[0076] The processing flow of the second embodiment will be briefly explained below.

[0077] Step 1: When a call comes in to the suicide prevention hotline, the generation AI automatically responds. For example, the generation AI responds by saying something like, "Hello, this is the suicide prevention hotline. We'd like to hear from you," and uses speech recognition technology to understand what the caller is saying. The speech recognition unit then converts what the caller is saying into text data. Step 2: The analysis unit analyzes the call content acquired by the voice recognition unit in real time to understand the other person's emotions and situation. For example, if the other person says, "There's no point in living anymore," the analysis unit analyzes that statement and suggests an appropriate response. Step 3: If the analysis unit determines that the situation is urgent, the reporting unit notifies the emergency contacts. For example, if the other person expresses an intention to attempt suicide, the reporting unit immediately notifies the emergency contacts.

[0078] 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.

[0079] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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 a data format such as voice data and text data. 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0080] 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.

[0081] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0082] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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).

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0095] 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.

[0096] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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).

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0107] 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.

[0108] 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.

[0109] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] 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.

[0111] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0112] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0123] 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.

[0124] 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.

[0125] 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 containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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 a data format such as voice data and text 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 model 58 includes AI 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 can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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."

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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. [Explanation of symbols]

[0145] 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 system that uses generative AI to automate responses to suicide prevention hotlines. A voice recognition unit that automatically responds when a call is made to the suicide prevention hotline, and an analysis unit that analyzes the call content acquired by the voice recognition unit in real time and grasps the emotions and situation of the other party; a reporting unit that reports to an emergency contact when the analysis unit determines that the event is an emergency. A system characterized by:

2. The voice recognition unit Analyze the other person's tone of voice and speaking patterns to estimate their emotional state and adjust the response accordingly 2. The system of claim 1.

3. The voice recognition unit When starting a call, check the other party's past call history and respond individually 2. The system of claim 1.

4. The voice recognition unit Monitor the other person's emotional state in real time and provide reassurance at the appropriate time 2. The system of claim 1.

5. The voice recognition unit Equipped with multilingual capabilities to accommodate different languages ​​and dialects 2. The system of claim 1.

Images