System

Abstract

To cause the elderly living far away to delay dementia through conversations with a family.SOLUTION: A system according to an embodiment comprises: an acquisition unit; a generation unit; and a dialogue unit. The acquisition unit is configured to acquire voice data on a family of an elderly. The generation unit is configured to, on the basis of the voice data acquired by the acquisition unit, generate a model of a voice of the family, using a model generated by the generation unit. The dialogue unit is configured to perform a dialogue with the elderly using the model generated by the generation unit.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult for elderly people who lived far away to slow down the onset of dementia through conversations with their families.

[0005] The system of the embodiment aims to slow down dementia in elderly people who live far away through conversations with their families. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, a generation unit, and a dialogue unit. The acquisition unit acquires voice data of a family member of an elderly person. The generation unit generates a model of the family member's voice based on the voice data acquired by the acquisition unit. The dialogue unit uses the model generated by the generation unit to dialogue with the elderly person. Effect of the Invention

[0007] The system according to the embodiment enables elderly people who live far away to delay dementia through conversations with their families. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed 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 and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a system that emphasizes "conversation" as a measure to delay dementia. This system is particularly effective when an elderly person lives far away and does not talk much with his / her family. The system uses AI to recognize the voices of family members and creates a space where the elderly person talks to their family members even when they are far away. In addition, the system can grasp the health condition of the elderly person by collecting conversation data and submitting it to the family or medical institution. For example, the system includes an acquisition unit that acquires voice data of the elderly person's family members. This acquisition unit may include AI processing. For example, the family members record voices using a smartphone or microphone and transmit the data to the acquisition unit. Next, the system includes a generation unit that generates a model of the family member's voice based on the voice data acquired by the acquisition unit. This generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the features of the family member's voice to generate a model. The system includes a dialogue unit that uses the generated model to dialogue with the elderly person. This dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks to the system, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are having a conversation with a family member. Furthermore, the system includes a notification unit that notifies the family or medical institution of the data of the dialogue between the dialogue unit and the elderly person. This notification unit may include AI processing. For example, the content and frequency of the dialogue may be digitized and transmitted to the family or medical institution. This makes it possible to grasp the health condition of the elderly person and take necessary measures. This system allows the elderly person to enjoy conversations even when they are away from their family, which is expected to have the effect of slowing the progression of dementia. In addition, it becomes easier for the family and medical institution to grasp the health condition of the elderly person and provide appropriate care. This allows the system to grasp the health condition of the elderly person and provide appropriate care.

[0029] The system according to the embodiment includes an acquisition unit, a generation unit, and a dialogue unit. The acquisition unit acquires voice data of the elderly family member. For example, the family member can record voice using a smartphone or a microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. The generation unit generates a model of the family member's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the features of the family member's voice to generate a model. The generation unit can extract the features of the family member's voice using, for example, voice recognition technology and generate a model based on the extracted features. The dialogue unit uses the model generated by the generation unit to engage in dialogue with the elderly person. The dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks to the dialogue unit, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are talking to a family member. The dialogue unit can analyze the elderly person's remarks using, for example, natural language processing technology and generate an appropriate response. As a result, the system according to the embodiment creates a space where elderly people feel as if they are talking with their families, which is expected to have the effect of slowing down the progression of dementia.

[0030] The acquisition unit acquires voice data of the elderly family member. For example, the family member can record voice using a smartphone or microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. Specifically, the acquisition unit receives the voice data transmitted from the smartphone or microphone in real time and stores it in a database. It is recommended that the voice data be recorded with high quality in order to accurately capture the characteristics of the family member's voice. The acquisition unit can use noise reduction technology to remove background noise from the recorded voice data and generate clear voice data. In addition, the acquisition unit can perform format conversion and compression of the voice data and efficiently manage the data. Furthermore, the acquisition unit can evaluate the quality of the voice data using AI and prompt the family member to re-record as necessary. For example, if the voice data contains a lot of noise or the volume is low, the acquisition unit sends a notification to the family member and requests them to re-record. This allows the acquisition unit to always collect high-quality voice data and enable the generation unit and dialogue unit to accurately process it. The acquisition unit can flexibly set the frequency and timing of collection of voice data, making it possible to efficiently collect data according to the family member's schedule.

[0031] The generation unit generates a model of the family's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data, learns the features of the family's voice, and generates a model. The generation unit can extract the features of the family's voice using, for example, voice recognition technology, and generate a model based on the features. Specifically, the generation unit extracts voice features such as phonemes, pitch, intonation, and rhythm from the voice data, and integrates these features to build a model of the family's voice. The generation AI uses deep learning technology to analyze the voice data with a multi-layered neural network, and learns the features of the family's voice with high accuracy. The generation unit evaluates the accuracy of the model using a learning dataset, and adjusts the parameters of the model as necessary. Furthermore, the generation unit tests the generated model and checks whether there is any incongruity by comparing it with the family's voice. The generation unit can reproduce the family's voice based on the generated model using voice synthesis technology. For example, when text is input, the generation unit generates voice data that reads the text in the family's voice. This enables the generation unit to reproduce the voices of family members with a high degree of accuracy, providing the elderly person with the experience of conversing with their family members.

[0032] The dialogue unit uses the model generated by the generation unit to dialogue with the elderly person. The dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are talking to their family member. The dialogue unit can, for example, analyze the elderly person's speech using natural language processing technology and generate an appropriate response. Specifically, the dialogue unit converts the elderly person's speech into text using voice recognition technology and analyzes the text using natural language processing technology. Based on the analysis result, the dialogue unit generates an appropriate response and responds in the family member's voice using the model of the generation unit. The dialogue unit can understand the context of the dialogue and generate a consistent response by referring to the past conversation history. Furthermore, the dialogue unit can analyze the elderly person's emotions and intentions and generate a response according to the emotions. For example, if the elderly person speaks in a sad voice, the dialogue unit generates a comforting response. The dialogue unit responds at an appropriate time to keep the flow of the dialogue smooth and realize a natural conversation. This allows the dialogue unit to provide the elderly with a sense of security, as if they were talking to a family member, and is expected to have the effect of slowing down the progression of dementia. The dialogue unit can periodically evaluate the content of the dialogue and update the model to improve the accuracy and naturalness of responses.

[0033] The device may include a notification unit that notifies a family or a medical institution of data of a dialogue between the dialogue unit and the elderly person. The notification unit notifies a family or a medical institution of data of a dialogue between the dialogue unit and the elderly person. The notification unit may include AI processing. For example, the content and frequency of the dialogue can be digitized and transmitted to the family or the medical institution. The notification unit can transmit the data by using, for example, an email notification or an app notification. This makes it easier for the family or the medical institution to grasp the health condition of the elderly person. For example, the notification unit can save the content of the dialogue as text data and transmit it to the family or the medical institution. In addition, the notification unit can record the frequency and time of the dialogue and evaluate the health condition of the elderly person based on the data. This allows the notification unit to grasp the health condition of the elderly person in detail and take appropriate measures.

[0034] The acquisition unit can analyze the past voice data of the family and select the optimal acquisition method. The acquisition unit, for example, selects voice data that allows the most natural conversation from the past voice data of the family. The acquisition unit may include AI processing. For example, the past voice data can be analyzed and data with good sound quality can be preferentially acquired. The acquisition unit can select data with rich emotional expression from the past voice data of the family. As a result, the acquisition unit acquires optimal voice data, enabling more natural conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input past voice data to a generation AI and cause the generation AI to select an optimal acquisition method.

[0035] The acquisition unit can filter the voice data based on the current living situation and areas of interest of the family when acquiring the voice data. For example, the acquisition unit preferentially acquires voice data related to topics in which the family has recently taken an interest. The acquisition unit may include AI processing. For example, voice data of an appropriate topic can be selected according to the living situation of the family. The acquisition unit can filter and acquire highly relevant voice data based on the areas of interest of the family. As a result, the acquisition unit can acquire voice data based on the interests of the family, thereby enabling a more relevant conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data related to the areas of interest of the family to the generation AI and cause the generation AI to execute filtering.

[0036] When acquiring voice data, the acquisition unit can preferentially acquire highly relevant voice data in consideration of the geographical location information of the family. For example, the acquisition unit preferentially acquires voice data on topics related to the location where the family is currently located. The acquisition unit may include AI processing. For example, based on the geographical location information of the family, the acquisition unit can acquire voice data related to local news and events. For example, when the family is traveling, the acquisition unit can preferentially acquire voice data related to the travel destination. As a result, the acquisition unit acquires voice data based on the geographical location information of the family, thereby enabling a more relevant conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the geographical location information of the family to the generation AI and cause the generation AI to select highly relevant voice data.

[0037] The acquisition unit can analyze the social media activities of the family when acquiring the voice data and acquire related voice data. The acquisition unit can acquire, for example, voice data related to topics shared by the family on social media. The acquisition unit may include AI processing. For example, the content of the family's social media posts can be analyzed to acquire voice data on topics of interest. The acquisition unit can acquire related voice data based on, for example, the content of accounts that the family follows on social media. As a result, the acquisition unit acquires voice data based on the family's social media activities, enabling more relevant conversations. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the family's social media activity data to the generation AI and cause the generation AI to select related voice data.

[0038] The generation unit can adjust the level of detail of the model based on the importance of the family's voice when generating the voice model. For example, when the family's voice is important to the elderly, the generation unit generates a detailed voice model. The generation unit may include AI processing or generation AI processing. For example, the importance of the voice can be evaluated and the level of detail of the model can be adjusted based on the result. For example, when the family's voice is a daily conversation, the generation unit can generate a simplified voice model. In addition, when the family's voice is related to a specific event, the generation unit can generate a voice model specialized for the event. Thereby, the generation unit generates a detailed model according to the importance of the family's voice, thereby enabling more natural dialogue. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to adjust the level of detail of the model.

[0039] The generation unit can apply different generation algorithms according to the category of the family's voice when generating a voice model. For example, when the family's voice is emotional, the generation unit applies a generation algorithm specialized for emotional expression. The generation unit may include AI processing or generation AI processing. For example, the category of the voice can be evaluated and different generation algorithms can be applied based on the result. For example, when the family's voice is informational, the generation unit can apply a generation algorithm that emphasizes the accuracy of the information. Also, when the family's voice is entertainment, the generation unit can apply a generation algorithm that emphasizes fun. Thereby, the generation unit can generate a more appropriate model by applying a generation algorithm according to the category of the family's voice. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to apply a generation algorithm according to the category.

[0040] The generation unit can determine the priority of the models based on the time of submission of the family member's voice when generating the voice model. For example, if the family member's voice has been submitted recently, the generation unit preferentially models the voice. The generation unit may include AI processing or generation AI processing. For example, the generation unit can evaluate the time of submission of the voice and determine the priority of the models based on the result. For example, if the family member's voice is related to a specific event, the generation unit can preferentially model the voice close to the event. In addition, if the family member's voice is submitted periodically, the generation unit can preferentially model the latest voice. This allows the generation unit to generate a model based on the time of submission of the family member's voice, thereby enabling more appropriate dialogue. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the family member's voice data to the generation AI and cause the generation AI to execute the determination of the priority of the models based on the time of submission.

[0041] The generation unit can adjust the order of models based on the relevance of the family's voices when generating a voice model. For example, if the family's voice is important to an elderly person, the generation unit preferentially models the voice. The generation unit may include AI processing or generation AI processing. For example, the generation unit can evaluate the relevance of the voices and adjust the order of models based on the result. For example, if the family's voice is a daily conversation, the generation unit can model it later. In addition, if the family's voice is related to a specific topic, the generation unit can preferentially model the voice related to the topic. Thereby, the generation unit generates a model based on the relevance of the family's voice, thereby enabling more appropriate dialogue. Part or all of the above-mentioned processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to adjust the order of models based on the relevance.

[0042] The dialogue unit can select an optimal dialogue method by referring to the elderly person's past dialogue history during dialogue. The dialogue unit, for example, conducts dialogue based on topics that the elderly person liked in the past. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can analyze the past dialogue history and select an optimal dialogue method based on the result. The dialogue unit can select a dialogue method that is most relaxing from the elderly person's past dialogue history. In addition, the dialogue unit can conduct dialogue while avoiding topics that the elderly person avoided in the past. As a result, the dialogue unit can select a dialogue method based on the elderly person's past dialogue history, thereby enabling a more appropriate dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's past dialogue history data to the generation AI and cause the generation AI to select an optimal dialogue method.

[0043] The dialogue unit can customize the content of the dialogue based on the elderly person's current living situation during the dialogue. The dialogue unit, for example, conducts a dialogue based on an event in which the elderly person has recently participated. The dialogue unit includes AI processing or generation AI processing. For example, the current living situation can be evaluated and the content of the dialogue can be customized based on the result. The dialogue unit can select an appropriate topic according to the elderly person's current health condition, for example. In addition, the dialogue unit can select a related topic based on the elderly person's current living environment. As a result, the dialogue unit customizes the dialogue content based on the elderly person's current living situation, thereby enabling a more relevant dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's current living situation data to the generation AI and cause the generation AI to customize the dialogue content.

[0044] The dialogue unit can select an optimal dialogue method in consideration of the geographical location information of the elderly person during dialogue. For example, when the elderly person is at home, the dialogue unit selects a relaxed dialogue method. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can evaluate geographical location information and select an optimal dialogue method based on the result. For example, when the elderly person is out, the dialogue unit can select a simple and to the point dialogue method. In addition, when the elderly person is in a specific location, the dialogue unit can conduct a dialogue on a topic related to the location. As a result, the dialogue unit can select a dialogue method based on the geographical location information of the elderly person, thereby enabling a more appropriate dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the geographical location information data of the elderly person to the generation AI and cause the generation AI to select the optimal dialogue method.

[0045] The dialogue unit can analyze the social media activity of the elderly person and suggest the content of the dialogue during the dialogue. The dialogue unit, for example, conducts a dialogue based on topics shared by the elderly person on social media. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can evaluate social media activities and suggest the content of the dialogue based on the results. The dialogue unit can analyze the content of the elderly person's social media posts and conduct a dialogue on topics of interest. The dialogue unit can also conduct a dialogue on related topics based on the content of accounts that the elderly person follows on social media. This allows the dialogue unit to propose dialogue content based on the elderly person's social media activity, thereby enabling a more relevant dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's social media activity data to the generation AI and cause the generation AI to execute the proposal of dialogue content.

[0046] The notification unit can select the optimal notification method by referring to the elderly person's past health data at the time of notification. The notification unit transmits a notification at an appropriate timing, for example, based on the elderly person's past health data. The notification unit may include AI processing. For example, the past health data can be evaluated, and the optimal notification method can be selected based on the result. The notification unit can customize the content of the notification, for example, according to the elderly person's health condition. In addition, the notification unit can transmit a notification including health advice based on the elderly person's past health data. As a result, the notification unit can select a notification method based on the elderly person's past health data, thereby enabling more appropriate notification. Part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the elderly person's past health data into the generation AI and cause the generation AI to select the optimal notification method.

[0047] The notification unit can select the optimal notification method in consideration of the geographical location information of the elderly person at the time of notification. For example, when the elderly person is at home, the notification unit transmits a notification with relaxing content. The notification unit may include AI processing. For example, the geographical location information can be evaluated and the optimal notification method can be selected based on the result. For example, when the elderly person is out, the notification unit can transmit a concise and to the point notification. In addition, when the elderly person is in a specific location, the notification unit can transmit a notification including information related to the location. Thereby, the notification unit can select a notification method based on the geographical location information of the elderly person, thereby enabling more appropriate notification. Part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the geographical location information data of the elderly person to the generation AI and cause the generation AI to select the optimal notification method.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] When generating a voice model based on the voice data of family members, the generation unit can generate the model by taking into consideration not only the voice characteristics of the family members but also the family members' speaking style and language. For example, the generation unit can learn phrases and expressions that are frequently used by family members and reflect them in the model. In addition, by reproducing the rhythm and tempo of the family members' speaking style, more natural conversations are possible. Furthermore, by reproducing the intonation and strength of the family members' voices, a model with rich emotional expression can be generated. This allows the generation unit to generate a voice model that takes into consideration the family members' speaking style and language.

[0050] When engaging in a dialogue with an elderly person, the dialogue unit can select an optimal dialogue method by referring to the elderly person's past dialogue history. For example, the dialogue can be conducted based on topics that the elderly person liked in the past. Also, the dialogue can be conducted while avoiding topics that the elderly person avoided in the past. Furthermore, the dialogue method that makes the elderly person feel most relaxed can be selected from the elderly person's past dialogue history. This allows the dialogue unit to select a dialogue method based on the elderly person's past dialogue history, thereby enabling a more appropriate dialogue.

[0051] When acquiring the voice data, the acquisition unit can perform filtering based on the current living situation and areas of interest of the family. For example, voice data related to topics that the family has recently been interested in can be preferentially acquired. Also, voice data of appropriate topics can be selected according to the living situation of the family. Furthermore, based on the areas of interest of the family, highly relevant voice data can be filtered and acquired. In this way, the acquisition unit can acquire voice data based on the interests of the family, thereby enabling more relevant conversations.

[0052] The dialogue unit can customize the content of the dialogue based on the current living situation of the elderly person during the dialogue. For example, the dialogue is based on an event that the elderly person recently participated in. Also, an appropriate topic can be selected according to the current health condition of the elderly person. Furthermore, a related topic can be selected based on the current living environment of the elderly person. This allows the dialogue unit to customize the content of the dialogue based on the current living situation of the elderly person, thereby enabling a more relevant dialogue.

[0053] At the time of notification, the notification unit can select the optimal notification method by referring to the elderly person's past health data. For example, a notification is sent at an appropriate time based on the elderly person's past health data. The content of the notification can be customized according to the elderly person's health condition. Furthermore, a notification including health advice can be sent based on the elderly person's past health data. This allows the notification unit to select a notification method based on the elderly person's past health data, enabling more appropriate notification.

[0054] When acquiring voice data, the acquisition unit can prioritize acquiring highly relevant voice data in consideration of the geographical location information of family members. For example, voice data on topics related to the location where the family members are currently located can be acquired preferentially. Also, based on the geographical location information of the family members, voice data related to local news and events can be acquired. Furthermore, if the family members are traveling, voice data related to the travel destination can be acquired preferentially. In this way, the acquisition unit can acquire voice data based on the geographical location information of the family members, thereby enabling more relevant conversations.

[0055] The process flow of the first embodiment will be briefly described below.

[0056] Step 1: The acquisition unit acquires voice data of the elderly person's family. For example, the family can record voice using a smartphone or microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. Step 2: The generation unit generates a model of the family member's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the characteristics of the family member's voice to generate a model. The generation unit can extract the characteristics of the family member's voice using voice recognition technology, for example, and generate a model based on the extracted characteristics. Step 3: The dialogue unit uses the model generated by the generation unit to dialogue with the elderly person. The dialogue unit includes AI processing or generative AI processing. For example, when the elderly person speaks to the elderly person, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are conversing with a family member. The dialogue unit can, for example, use natural language processing technology to analyze the elderly person's utterances and generate an appropriate response.

[0057] (Example 2) The system according to the embodiment of the present invention is a system that emphasizes "conversation" as a measure to delay dementia. This system is particularly effective when an elderly person lives far away and does not talk much with his / her family. The system uses AI to recognize the voices of family members and creates a space where the elderly person talks to their family members even when they are far away. In addition, the system can grasp the health condition of the elderly person by collecting conversation data and submitting it to the family or medical institution. For example, the system includes an acquisition unit that acquires voice data of the elderly person's family members. This acquisition unit may include AI processing. For example, the family members record voices using a smartphone or microphone and transmit the data to the acquisition unit. Next, the system includes a generation unit that generates a model of the family member's voice based on the voice data acquired by the acquisition unit. This generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the features of the family member's voice to generate a model. The system includes a dialogue unit that uses the generated model to dialogue with the elderly person. This dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks to the system, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are having a conversation with a family member. Furthermore, the system includes a notification unit that notifies the family or medical institution of the data of the dialogue between the dialogue unit and the elderly person. This notification unit may include AI processing. For example, the content and frequency of the dialogue may be digitized and transmitted to the family or medical institution. This makes it possible to grasp the health condition of the elderly person and take necessary measures. This system allows the elderly person to enjoy conversations even when they are away from their family, which is expected to have the effect of slowing the progression of dementia. In addition, it becomes easier for the family and medical institution to grasp the health condition of the elderly person and provide appropriate care. This allows the system to grasp the health condition of the elderly person and provide appropriate care.

[0058] The system according to the embodiment includes an acquisition unit, a generation unit, and a dialogue unit. The acquisition unit acquires voice data of the elderly family member. For example, the family member can record voice using a smartphone or a microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. The generation unit generates a model of the family member's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the features of the family member's voice to generate a model. The generation unit can extract the features of the family member's voice using, for example, voice recognition technology and generate a model based on the extracted features. The dialogue unit uses the model generated by the generation unit to engage in dialogue with the elderly person. The dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks to the dialogue unit, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are talking to a family member. The dialogue unit can analyze the elderly person's remarks using, for example, natural language processing technology and generate an appropriate response. As a result, the system according to the embodiment creates a space where elderly people feel as if they are talking with their families, which is expected to have the effect of slowing down the progression of dementia.

[0059] The acquisition unit acquires voice data of the elderly family member. For example, the family member can record voice using a smartphone or microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. Specifically, the acquisition unit receives the voice data transmitted from the smartphone or microphone in real time and stores it in a database. It is recommended that the voice data be recorded with high quality in order to accurately capture the characteristics of the family member's voice. The acquisition unit can use noise reduction technology to remove background noise from the recorded voice data and generate clear voice data. In addition, the acquisition unit can perform format conversion and compression of the voice data and efficiently manage the data. Furthermore, the acquisition unit can evaluate the quality of the voice data using AI and prompt the family member to re-record as necessary. For example, if the voice data contains a lot of noise or the volume is low, the acquisition unit sends a notification to the family member and requests them to re-record. This allows the acquisition unit to always collect high-quality voice data and enable the generation unit and dialogue unit to accurately process it. The acquisition unit can flexibly set the frequency and timing of collection of voice data, making it possible to efficiently collect data according to the family member's schedule.

[0060] The generation unit generates a model of the family's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data, learns the features of the family's voice, and generates a model. The generation unit can extract the features of the family's voice using, for example, voice recognition technology, and generate a model based on the features. Specifically, the generation unit extracts voice features such as phonemes, pitch, intonation, and rhythm from the voice data, and integrates these features to build a model of the family's voice. The generation AI uses deep learning technology to analyze the voice data with a multi-layered neural network, and learns the features of the family's voice with high accuracy. The generation unit evaluates the accuracy of the model using a learning dataset, and adjusts the parameters of the model as necessary. Furthermore, the generation unit tests the generated model and checks whether there is any incongruity by comparing it with the family's voice. The generation unit can reproduce the family's voice based on the generated model using voice synthesis technology. For example, when text is input, the generation unit generates voice data that reads the text in the family's voice. This enables the generation unit to reproduce the voices of family members with a high degree of accuracy, providing the elderly person with the experience of conversing with their family members.

[0061] The dialogue unit uses the model generated by the generation unit to dialogue with the elderly person. The dialogue unit includes AI processing or generation AI processing. For example, when the elderly person speaks, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are talking to their family member. The dialogue unit can, for example, analyze the elderly person's speech using natural language processing technology and generate an appropriate response. Specifically, the dialogue unit converts the elderly person's speech into text using voice recognition technology and analyzes the text using natural language processing technology. Based on the analysis result, the dialogue unit generates an appropriate response and responds in the family member's voice using the model of the generation unit. The dialogue unit can understand the context of the dialogue and generate a consistent response by referring to the past conversation history. Furthermore, the dialogue unit can analyze the elderly person's emotions and intentions and generate a response according to the emotions. For example, if the elderly person speaks in a sad voice, the dialogue unit generates a comforting response. The dialogue unit responds at an appropriate time to keep the flow of the dialogue smooth and realize a natural conversation. This allows the dialogue unit to provide the elderly with a sense of security, as if they were talking to a family member, and is expected to have the effect of slowing down the progression of dementia. The dialogue unit can periodically evaluate the content of the dialogue and update the model to improve the accuracy and naturalness of responses.

[0062] The device may include a notification unit that notifies a family or a medical institution of data of a dialogue between the dialogue unit and the elderly person. The notification unit notifies a family or a medical institution of data of a dialogue between the dialogue unit and the elderly person. The notification unit may include AI processing. For example, the content and frequency of the dialogue can be digitized and transmitted to the family or the medical institution. The notification unit can transmit the data by using, for example, an email notification or an app notification. This makes it easier for the family or the medical institution to grasp the health condition of the elderly person. For example, the notification unit can save the content of the dialogue as text data and transmit it to the family or the medical institution. In addition, the notification unit can record the frequency and time of the dialogue and evaluate the health condition of the elderly person based on the data. This allows the notification unit to grasp the health condition of the elderly person in detail and take appropriate measures.

[0063] The acquisition unit can estimate the emotion of the elderly person and adjust the timing of acquiring the voice data based on the estimated emotion of the elderly person. The acquisition unit selects the timing of acquiring the voice data of the family member, for example, when the elderly person is relaxed. The acquisition unit may include AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm, and the timing of acquiring the voice data can be adjusted based on the result. For example, the acquisition unit can adjust to refrain from acquiring the voice data when the elderly person is stressed. In addition, the acquisition unit can temporarily suspend the acquisition of the voice data when the elderly person is excited, and resume it when the elderly person has calmed down. This allows the acquisition unit to acquire the voice data at an appropriate timing according to the emotion of the elderly person. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the acquisition unit can input emotion data of an elderly person to the generation AI and have the generation AI perform emotion estimation.

[0064] The acquisition unit can analyze the past voice data of the family and select the optimal acquisition method. The acquisition unit, for example, selects voice data that allows the most natural conversation from the past voice data of the family. The acquisition unit may include AI processing. For example, the past voice data can be analyzed and data with good sound quality can be preferentially acquired. The acquisition unit can select data with rich emotional expression from the past voice data of the family. As a result, the acquisition unit acquires optimal voice data, enabling more natural conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input past voice data to a generation AI and cause the generation AI to select an optimal acquisition method.

[0065] The acquisition unit can filter the voice data based on the current living situation and areas of interest of the family when acquiring the voice data. For example, the acquisition unit preferentially acquires voice data related to topics in which the family has recently taken an interest. The acquisition unit may include AI processing. For example, voice data of an appropriate topic can be selected according to the living situation of the family. The acquisition unit can filter and acquire highly relevant voice data based on the areas of interest of the family. As a result, the acquisition unit can acquire voice data based on the interests of the family, thereby enabling a more relevant conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data related to the areas of interest of the family to the generation AI and cause the generation AI to execute filtering.

[0066] The acquisition unit can estimate the emotion of the elderly person and determine the priority of the voice data to be acquired based on the estimated emotion of the elderly person. For example, when the elderly person feels lonely, the acquisition unit preferentially acquires voice data of the voice of the family. The acquisition unit may include AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm and the priority of the voice data can be determined based on the result. For example, when the elderly person is happy, the acquisition unit can preferentially acquire voice data on a fun topic. Also, when the elderly person feels anxious, the acquisition unit can preferentially acquire voice data that gives a sense of security. This allows the acquisition unit to preferentially acquire appropriate voice data according to the emotion of the elderly person. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the emotion data of the elderly person to the generation AI and cause the generation AI to execute emotion estimation.

[0067] When acquiring voice data, the acquisition unit can preferentially acquire highly relevant voice data in consideration of the geographical location information of the family. For example, the acquisition unit preferentially acquires voice data on topics related to the location where the family is currently located. The acquisition unit may include AI processing. For example, based on the geographical location information of the family, the acquisition unit can acquire voice data related to local news and events. For example, when the family is traveling, the acquisition unit can preferentially acquire voice data related to the travel destination. As a result, the acquisition unit acquires voice data based on the geographical location information of the family, thereby enabling a more relevant conversation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the geographical location information of the family to the generation AI and cause the generation AI to select highly relevant voice data.

[0068] The acquisition unit can analyze the social media activities of the family when acquiring the voice data and acquire related voice data. The acquisition unit can acquire, for example, voice data related to topics shared by the family on social media. The acquisition unit may include AI processing. For example, the content of the family's social media posts can be analyzed to acquire voice data on topics of interest. The acquisition unit can acquire related voice data based on, for example, the content of accounts that the family follows on social media. As a result, the acquisition unit acquires voice data based on the family's social media activities, enabling more relevant conversations. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the family's social media activity data to the generation AI and cause the generation AI to select related voice data.

[0069] The generation unit can estimate the emotion of the elderly person and adjust the generation method of the voice model based on the estimated emotion of the elderly person. For example, when the elderly person is relaxed, the generation unit generates a calm voice model. The generation unit may include AI processing or generation AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm, and the generation method of the voice model can be adjusted based on the result. For example, when the elderly person is excited, the generation unit can generate a lively voice model. Also, when the elderly person is feeling anxious, the generation unit can generate a voice model that gives a sense of security. Thereby, the generation unit generates a voice model according to the emotion of the elderly person, thereby enabling a more natural dialogue. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input emotion data of the elderly person to the generation AI and cause the generation AI to execute emotion estimation.

[0070] The generation unit can adjust the level of detail of the model based on the importance of the family's voice when generating the voice model. For example, when the family's voice is important to the elderly, the generation unit generates a detailed voice model. The generation unit may include AI processing or generation AI processing. For example, the importance of the voice can be evaluated and the level of detail of the model can be adjusted based on the result. For example, when the family's voice is a daily conversation, the generation unit can generate a simplified voice model. In addition, when the family's voice is related to a specific event, the generation unit can generate a voice model specialized for the event. Thereby, the generation unit generates a detailed model according to the importance of the family's voice, thereby enabling more natural dialogue. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to adjust the level of detail of the model.

[0071] The generation unit can apply different generation algorithms according to the category of the family's voice when generating a voice model. For example, when the family's voice is emotional, the generation unit applies a generation algorithm specialized for emotional expression. The generation unit may include AI processing or generation AI processing. For example, the category of the voice can be evaluated and different generation algorithms can be applied based on the result. For example, when the family's voice is informational, the generation unit can apply a generation algorithm that emphasizes the accuracy of the information. Also, when the family's voice is entertainment, the generation unit can apply a generation algorithm that emphasizes fun. Thereby, the generation unit can generate a more appropriate model by applying a generation algorithm according to the category of the family's voice. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to apply a generation algorithm according to the category.

[0072] The generation unit can estimate the emotion of the elderly person and adjust the generation frequency of the voice model based on the estimated emotion of the elderly person. For example, when the elderly person feels lonely, the generation unit generates the voice model frequently. The generation unit may include AI processing or generation AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm, and the generation frequency of the voice model can be adjusted based on the result. For example, when the elderly person is relaxed, the generation unit can generate the voice model at a moderate frequency. Also, when the elderly person feels stressed, the generation unit can reduce the generation frequency of the voice model. Thereby, the generation unit generates the voice model at a frequency according to the emotion of the elderly person, thereby enabling a more natural dialogue. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input emotion data of an elderly person to the generation AI and have the generation AI perform emotion estimation.

[0073] The generation unit can determine the priority of the models based on the time of submission of the family member's voice when generating the voice model. For example, if the family member's voice has been submitted recently, the generation unit preferentially models the voice. The generation unit may include AI processing or generation AI processing. For example, the generation unit can evaluate the time of submission of the voice and determine the priority of the models based on the result. For example, if the family member's voice is related to a specific event, the generation unit can preferentially model the voice close to the event. In addition, if the family member's voice is submitted periodically, the generation unit can preferentially model the latest voice. This allows the generation unit to generate a model based on the time of submission of the family member's voice, thereby enabling more appropriate dialogue. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using AI or may be performed without using AI. For example, the generation unit can input the family member's voice data to the generation AI and cause the generation AI to execute the determination of the priority of the models based on the time of submission.

[0074] The generation unit can adjust the order of models based on the relevance of the family's voices when generating a voice model. For example, if the family's voice is important to an elderly person, the generation unit preferentially models the voice. The generation unit may include AI processing or generation AI processing. For example, the generation unit can evaluate the relevance of the voices and adjust the order of models based on the result. For example, if the family's voice is a daily conversation, the generation unit can model it later. In addition, if the family's voice is related to a specific topic, the generation unit can preferentially model the voice related to the topic. Thereby, the generation unit generates a model based on the relevance of the family's voice, thereby enabling more appropriate dialogue. Part or all of the above-mentioned processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit can input the family's voice data to the generation AI and cause the generation AI to adjust the order of models based on the relevance.

[0075] The dialogue unit can estimate the emotion of the elderly person and adjust the way of expressing the dialogue based on the estimated emotion of the elderly person. For example, when the elderly person is relaxed, the dialogue unit conducts the dialogue in a calm tone. The dialogue unit includes AI processing or generation AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm, and the way of expressing the dialogue can be adjusted based on the result. For example, when the elderly person is excited, the dialogue unit can conduct the dialogue in a lively tone. Also, when the elderly person is feeling anxious, the dialogue unit can conduct the dialogue in a tone that gives a sense of security. This allows the dialogue unit to adjust the way of expressing the dialogue according to the emotion of the elderly person, thereby enabling a more natural dialogue. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the dialogue unit can input the emotion data of the elderly person to the generation AI and cause the generation AI to execute the emotion estimation.

[0076] The dialogue unit can select an optimal dialogue method by referring to the elderly person's past dialogue history during dialogue. The dialogue unit, for example, conducts dialogue based on topics that the elderly person liked in the past. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can analyze the past dialogue history and select an optimal dialogue method based on the result. The dialogue unit can select a dialogue method that is most relaxing from the elderly person's past dialogue history. In addition, the dialogue unit can conduct dialogue while avoiding topics that the elderly person avoided in the past. As a result, the dialogue unit can select a dialogue method based on the elderly person's past dialogue history, thereby enabling a more appropriate dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's past dialogue history data to the generation AI and cause the generation AI to select an optimal dialogue method.

[0077] The dialogue unit can customize the content of the dialogue based on the elderly person's current living situation during the dialogue. The dialogue unit, for example, conducts a dialogue based on an event in which the elderly person has recently participated. The dialogue unit includes AI processing or generation AI processing. For example, the current living situation can be evaluated and the content of the dialogue can be customized based on the result. The dialogue unit can select an appropriate topic according to the elderly person's current health condition, for example. In addition, the dialogue unit can select a related topic based on the elderly person's current living environment. As a result, the dialogue unit customizes the dialogue content based on the elderly person's current living situation, thereby enabling a more relevant dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's current living situation data to the generation AI and cause the generation AI to customize the dialogue content.

[0078] The dialogue unit can estimate the emotion of the elderly person and determine the priority of the dialogue based on the estimated emotion of the elderly person. For example, when the elderly person feels lonely, the dialogue unit increases the frequency of the dialogue. The dialogue unit includes AI processing or generation AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm and the priority of the dialogue can be determined based on the result. For example, when the elderly person is relaxed, the dialogue unit can conduct dialogue at a moderate frequency. In addition, when the elderly person feels stressed, the dialogue unit can reduce the frequency of the dialogue. As a result, the dialogue unit can determine the priority of the dialogue according to the emotion of the elderly person, thereby enabling the dialogue at a more appropriate time. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the dialogue unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the dialogue unit can input emotion data of the elderly person to the generation AI and cause the generation AI to execute emotion estimation.

[0079] The dialogue unit can select an optimal dialogue method in consideration of the geographical location information of the elderly person during dialogue. For example, when the elderly person is at home, the dialogue unit selects a relaxed dialogue method. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can evaluate geographical location information and select an optimal dialogue method based on the result. For example, when the elderly person is out, the dialogue unit can select a simple and to the point dialogue method. In addition, when the elderly person is in a specific location, the dialogue unit can conduct a dialogue on a topic related to the location. As a result, the dialogue unit can select a dialogue method based on the geographical location information of the elderly person, thereby enabling a more appropriate dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the geographical location information data of the elderly person to the generation AI and cause the generation AI to select the optimal dialogue method.

[0080] The dialogue unit can analyze the social media activity of the elderly person and suggest the content of the dialogue during the dialogue. The dialogue unit, for example, conducts a dialogue based on topics shared by the elderly person on social media. The dialogue unit includes AI processing or generation AI processing. For example, the dialogue unit can evaluate social media activities and suggest the content of the dialogue based on the results. The dialogue unit can analyze the content of the elderly person's social media posts and conduct a dialogue on topics of interest. The dialogue unit can also conduct a dialogue on related topics based on the content of accounts that the elderly person follows on social media. This allows the dialogue unit to propose dialogue content based on the elderly person's social media activity, thereby enabling a more relevant dialogue. Part or all of the above-mentioned processing in the dialogue unit may be performed, for example, using AI or may be performed without using AI. For example, the dialogue unit can input the elderly person's social media activity data to the generation AI and cause the generation AI to execute the proposal of dialogue content.

[0081] The notification unit can estimate the emotion of the elderly person and adjust the content of the notification based on the estimated emotion of the elderly person. For example, when the elderly person is relaxed, the notification unit transmits a notification with calm content. The notification unit may include AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm, and the content of the notification can be adjusted based on the result. For example, when the elderly person is excited, the notification unit can transmit a notification with lively content. Also, when the elderly person is feeling anxious, the notification unit can transmit a notification with content that gives a sense of security. Thereby, the notification unit can adjust the notification content according to the emotion of the elderly person, thereby enabling a more appropriate notification. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the emotion data of the elderly person to the generation AI and cause the generation AI to execute the emotion estimation.

[0082] The notification unit can select the optimal notification method by referring to the elderly person's past health data at the time of notification. The notification unit transmits a notification at an appropriate timing, for example, based on the elderly person's past health data. The notification unit may include AI processing. For example, the past health data can be evaluated, and the optimal notification method can be selected based on the result. The notification unit can customize the content of the notification, for example, according to the elderly person's health condition. In addition, the notification unit can transmit a notification including health advice based on the elderly person's past health data. As a result, the notification unit can select a notification method based on the elderly person's past health data, thereby enabling more appropriate notification. Part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the elderly person's past health data into the generation AI and cause the generation AI to select the optimal notification method.

[0083] The notification unit can estimate the emotion of the elderly person and determine the priority of notifications based on the estimated emotion of the elderly person. For example, when the elderly person feels lonely, the notification unit preferentially transmits important notifications. The notification unit may include AI processing. For example, the emotion of the elderly person can be estimated using an emotion estimation algorithm and the priority of notifications can be determined based on the result. For example, when the elderly person is relaxed, the notification unit can transmit normal notifications at a moderate frequency. Also, when the elderly person feels stressed, the notification unit can reduce the frequency of notifications. Thereby, the notification unit can determine the priority of notifications according to the emotion of the elderly person, thereby enabling notifications at a more appropriate time. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the notification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the notification unit can input the emotion data of the elderly person to the generation AI and cause the generation AI to execute emotion estimation.

[0084] The notification unit can select the optimal notification method in consideration of the geographical location information of the elderly person at the time of notification. For example, when the elderly person is at home, the notification unit transmits a notification with relaxing content. The notification unit may include AI processing. For example, the geographical location information can be evaluated and the optimal notification method can be selected based on the result. For example, when the elderly person is out, the notification unit can transmit a concise and to the point notification. In addition, when the elderly person is in a specific location, the notification unit can transmit a notification including information related to the location. Thereby, the notification unit can select a notification method based on the geographical location information of the elderly person, thereby enabling more appropriate notification. Part or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can input the geographical location information data of the elderly person to the generation AI and cause the generation AI to select the optimal notification method.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] When acquiring voice data of family members, the acquisition unit can analyze the tone of the family members' voices and emotional expressions, and select voice data that allows the most natural conversation. For example, if the family members' voices are calm and relaxed, that voice data can be acquired preferentially. Also, if the family members' voices are excited, that voice data can be avoided. Furthermore, by selecting data in which the family members' voices are rich in emotional expressions, more natural conversations can be made. This allows the acquisition unit to acquire optimal voice data based on the tone of the family members' voices and emotional expressions.

[0087] When generating a voice model based on the voice data of family members, the generation unit can generate the model by taking into consideration not only the voice characteristics of the family members but also the family members' speaking style and language. For example, the generation unit can learn phrases and expressions that are frequently used by family members and reflect them in the model. In addition, by reproducing the rhythm and tempo of the family members' speaking style, more natural conversations are possible. Furthermore, by reproducing the intonation and strength of the family members' voices, a model with rich emotional expression can be generated. This allows the generation unit to generate a voice model that takes into consideration the family members' speaking style and language.

[0088] When engaging in a dialogue with an elderly person, the dialogue unit can select an optimal dialogue method by referring to the elderly person's past dialogue history. For example, the dialogue can be conducted based on topics that the elderly person liked in the past. Also, the dialogue can be conducted while avoiding topics that the elderly person avoided in the past. Furthermore, the dialogue method that makes the elderly person feel most relaxed can be selected from the elderly person's past dialogue history. This allows the dialogue unit to select a dialogue method based on the elderly person's past dialogue history, thereby enabling a more appropriate dialogue.

[0089] The notification unit can estimate the emotion of the elderly person and adjust the content of the notification based on the estimated emotion of the elderly person. For example, if the elderly person is relaxed, a notification with calm content can be sent. If the elderly person is excited, a notification with lively content can be sent. Furthermore, if the elderly person is feeling anxious, a notification with content that gives a sense of security can be sent. In this way, the notification unit can adjust the notification content according to the emotion of the elderly person to provide a more appropriate notification.

[0090] When acquiring the voice data, the acquisition unit can perform filtering based on the current living situation and areas of interest of the family. For example, voice data related to topics that the family has recently been interested in can be preferentially acquired. Also, voice data of appropriate topics can be selected according to the living situation of the family. Furthermore, based on the areas of interest of the family, highly relevant voice data can be filtered and acquired. In this way, the acquisition unit can acquire voice data based on the interests of the family, thereby enabling more relevant conversations.

[0091] The generation unit can estimate the emotion of the elderly person and adjust the generation method of the voice model based on the estimated emotion of the elderly person. For example, when the elderly person is relaxed, a calm voice model can be generated. When the elderly person is excited, a lively voice model can be generated. Furthermore, when the elderly person is anxious, a voice model that gives a sense of security can be generated. In this way, the generation unit can generate a voice model according to the emotion of the elderly person, thereby enabling more natural dialogue.

[0092] The dialogue unit can customize the content of the dialogue based on the current living situation of the elderly person during the dialogue. For example, the dialogue is based on an event that the elderly person recently participated in. Also, an appropriate topic can be selected according to the current health condition of the elderly person. Furthermore, a related topic can be selected based on the current living environment of the elderly person. This allows the dialogue unit to customize the content of the dialogue based on the current living situation of the elderly person, thereby enabling a more relevant dialogue.

[0093] At the time of notification, the notification unit can select the optimal notification method by referring to the elderly person's past health data. For example, a notification is sent at an appropriate time based on the elderly person's past health data. The content of the notification can be customized according to the elderly person's health condition. Furthermore, a notification including health advice can be sent based on the elderly person's past health data. This allows the notification unit to select a notification method based on the elderly person's past health data, enabling more appropriate notification.

[0094] The dialogue unit can estimate the emotion of the elderly person and determine the priority of dialogue based on the estimated emotion of the elderly person. For example, if the elderly person feels lonely, the frequency of dialogue can be increased. Also, if the elderly person feels relaxed, dialogue can be performed at an appropriate frequency. Furthermore, if the elderly person feels stressed, the frequency of dialogue can be reduced. In this way, the dialogue unit can determine the priority of dialogue according to the emotion of the elderly person, thereby enabling dialogue at a more appropriate time.

[0095] When acquiring voice data, the acquisition unit can prioritize acquiring highly relevant voice data in consideration of the geographical location information of family members. For example, voice data on topics related to the location where the family members are currently located can be acquired preferentially. Also, based on the geographical location information of the family members, voice data related to local news and events can be acquired. Furthermore, if the family members are traveling, voice data related to the travel destination can be acquired preferentially. In this way, the acquisition unit can acquire voice data based on the geographical location information of the family members, thereby enabling more relevant conversations.

[0096] The process flow of the second embodiment will be briefly described below.

[0097] Step 1: The acquisition unit acquires voice data of the elderly person's family. For example, the family can record voice using a smartphone or microphone and transmit the data to the acquisition unit. The acquisition unit may include AI processing. Step 2: The generation unit generates a model of the family member's voice based on the voice data acquired by the acquisition unit. The generation unit may include AI processing or generation AI processing. For example, the generation AI analyzes the voice data and learns the characteristics of the family member's voice to generate a model. The generation unit can extract the characteristics of the family member's voice using voice recognition technology, for example, and generate a model based on the extracted characteristics. Step 3: The dialogue unit uses the model generated by the generation unit to dialogue with the elderly person. The dialogue unit includes AI processing or generative AI processing. For example, when the elderly person speaks to the elderly person, the dialogue unit responds using a model of the family member's voice. This allows the elderly person to feel as if they are conversing with a family member. The dialogue unit can, for example, use natural language processing technology to analyze the elderly person's utterances and generate an appropriate response.

[0098] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0100] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0101] For example, the acquisition unit acquires voice data of the family members using the camera 42 and microphone 38B of the smart device 14, and the data is processed by the specific processing unit 290 of the data processing device 12. The generation unit generates a model of the family members' voices, for example, by the specific processing unit 290 of the data processing device 12. The dialogue unit dialogues with the elderly person, for example, by using the model generated by the control unit 46A of the smart device 14. The notification unit transmits dialogue data to the family members or medical institutions, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 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.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0105] 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.

[0106] 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 the voice according to instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0108] 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 performed in a secure state.

[0109] Fig. 4 shows an example of 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.

[0110] 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.

[0111] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0113] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0114] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0115] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0116] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0117] For example, the acquisition unit acquires voice data of the family members using the camera 42 and microphone 238 of the smart glasses 214, and the data is processed by the specific processing unit 290 of the data processing device 12. The generation unit generates a model of the family members' voices, for example, by the specific processing unit 290 of the data processing device 12. The dialogue unit dialogues with the elderly person, for example, by using the model generated by the control unit 46A of the smart glasses 214. The notification unit transmits dialogue data to the family members or medical institutions, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 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.

[0120] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0121] 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.

[0122] 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 the voice according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0124] 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 performed in a secure state.

[0125] 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.

[0126] 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.

[0127] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0128] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0129] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0130] 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 voice indicating a user input for 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.

[0131] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0132] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0133] For example, the acquisition unit acquires voice data of the family members using the camera 42 and microphone 238 of the headset type terminal 314, and the data is processed by the specific processing unit 290 of the data processing device 12. The generation unit generates a model of the family members' voices, for example, by the specific processing unit 290 of the data processing device 12. The dialogue unit dialogues with the elderly person, for example, by using the model generated by the control unit 46A of the headset type terminal 314. The notification unit transmits dialogue data to the family members or medical institutions, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0137] 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.

[0138] 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 the voice according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0140] 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 performed in a secure state.

[0141] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0142] 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.

[0143] 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.

[0144] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0145] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0146] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0147] 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 a voice indicating a user input for 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.

[0148] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0149] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0150] For example, the acquisition unit acquires voice data of the family members using the camera 42 and microphone 238 of the robot 414, and the data is processed by the specific processing unit 290 of the data processing device 12. The generation unit generates a model of the family members' voices, for example, by the specific processing unit 290 of the data processing device 12. The dialogue unit dialogues with the elderly person, for example, by using the model generated by the control unit 46A of the robot 414. The notification unit transmits dialogue data to the family members or medical institutions, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0151] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0152] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0153] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0154] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0155] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0156] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0158] 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.

[0159] 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 Universal Serial Bus (USB) 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.

[0160] In addition, 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 upon request from the data processing device 12.

[0161] 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.

[0162] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0163] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0164] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0165] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0166] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0167] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0168] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0169] (Appendix 1) A system comprising: an acquisition unit that acquires voice data of an elderly person's family; a generation unit that generates a model of the family's voice based on the voice data acquired by the acquisition unit; and a dialogue unit that engages in a dialogue with the elderly person using the model generated by the generation unit. (Appendix 2) The system described in Appendix 1, further comprising a notification unit that notifies a family member or a medical institution of data of the dialogue between the dialogue unit and the elderly person. (Appendix 3) The acquisition unit is Estimating the emotions of the elderly and adjusting the timing of voice data acquisition based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 4) The system described in Appendix 1, wherein the acquisition unit analyzes past voice data of family members and selects the optimal acquisition method. (Appendix 5) The system described in Appendix 1, characterized in that the acquisition unit performs filtering based on the family's current living situation and areas of interest when acquiring voice data. (Appendix 6) The acquisition unit is Estimating the emotions of the elderly and determining the priority of voice data to be acquired based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 7) The system described in Appendix 1, characterized in that, when acquiring voice data, the acquisition unit takes into consideration geographical location information of family members and preferentially acquires highly relevant voice data. (Appendix 8) The acquisition unit is When voice data is acquired, the family's social media activity is analyzed to acquire relevant voice data. 2. The system of claim 1, (Appendix 9) The generation unit is Estimating the emotions of the elderly and adjusting the method of generating a voice model based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 10) The generation unit is When generating a voice model, adjust the model detail based on the importance of family members' voices 2. The system of claim 1, (Appendix 11) The generation unit is When generating voice models, different generation algorithms are applied depending on the family's voice category. 2. The system of claim 1, (Appendix 12) The generation unit is Estimating the emotion of the elderly person and adjusting the frequency of voice model generation based on the estimated emotion of the elderly person 2. The system of claim 1, (Appendix 13) The generation unit is When generating voice models, prioritize models based on when family members' voices were submitted 2. The system of claim 1, (Appendix 14) The generation unit is When generating voice models, adjust the order of models based on the relevance of family members' voices 2. The system of claim 1, (Appendix 15) The dialogue unit includes: Estimate the emotions of the elderly and adjust the way dialogue is expressed based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 16) The dialogue unit includes: When engaging in dialogue, the system selects the most appropriate dialogue method by referring to the elderly person's past dialogue history. 2. The system of claim 1, (Appendix 17) The dialogue unit includes: During the conversation, the content of the conversation is customized based on the senior's current living situation. 2. The system of claim 1, (Appendix 18) The dialogue unit includes: Estimating the emotions of the elderly and determining the priority of dialogue based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 19) The dialogue unit includes: When communicating, the system selects the optimal communication method by taking into account the elderly person's geographic location information. 2. The system of claim 1, (Appendix 20) The dialogue unit includes: During conversations, the system analyzes the social media activity of seniors to suggest conversation content 2. The system of claim 1, (Appendix 21) The notification unit is Estimating the emotions of the elderly and adjusting the content of notifications based on the estimated emotions of the elderly 3. The system of claim 2, (Appendix 22) The notification unit is When notifying the elderly, the system will select the optimal notification method by referring to the elderly person's past health data. 3. The system of claim 2, (Appendix 23) The notification unit is Estimate the emotions of the elderly and prioritize notifications based on the estimated emotions of the elderly 3. The system of claim 2, (Appendix 24) The notification unit is When notifying the elderly, the optimal notification method is selected taking into account the elderly person's geographic location information. 3. The system of claim 2, [Explanation of symbols]

[0170] 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. An acquisition unit for acquiring voice data of an elderly person's family member; A generation unit that generates a model of the voice of the family member based on the voice data acquired by the acquisition unit; A dialogue unit that uses the model generated by the generation unit to dialogue with the elderly person. A system characterized by:

2. A notification unit that notifies the family or a medical institution of data of the dialogue between the elderly person and the dialogue unit.

2. The system of claim 1 .

3. The acquisition unit is A feeling of the elderly person is estimated, and a timing for acquiring the voice data is adjusted based on the estimated feeling of the elderly person.

2. The system of claim 1 .

4. The acquisition unit is Analyze the past voice data of the family member and select the optimal acquisition method.

2. The system of claim 1 .

5. The acquisition unit is When acquiring the voice data, filtering is performed based on the current living situation and areas of interest of the family.

2. The system of claim 1 .

6. The acquisition unit is Estimating the emotion of the elderly person, and determining a priority order of the voice data to be acquired based on the estimated emotion of the elderly person.

2. The system of claim 1 .

7. The system according to claim 1 , wherein the acquisition unit, when acquiring the voice data, takes into consideration geographical location information of the family members and preferentially acquires highly relevant voice data.

8. The acquisition unit is Upon acquisition of the voice data, analyzing social media activity of the family member to acquire relevant voice data.

2. The system of claim 1 .

9. The generation unit is The emotion of the elderly person is estimated, and a method for generating a voice model is adjusted based on the estimated emotion of the elderly person.

2. The system of claim 1 .

10. The generation unit is When generating a voice model, the level of detail of the model is adjusted based on the importance of the voice of the family member.

2. The system of claim 1 .

Images