system

Abstract

To provide a system for enabling persons who remain following the death of a decedent, to mitigate their feelings of loss and to recover their mental health.SOLUTION: A system includes a learning part, an incorporating part, an instruction part, an interactive part, and a stop part. The learning part generates AI having learned a user's voice, way of speaking, and personality. The incorporating part incorporates the AI generated by the learning part in a tablet terminal. The instruction part instructs delivery of a tablet terminal to a person specified by a user, after the death of the user. The interactive part interacts with a person specified by the user, by using the AI incorporated in the tablet terminal. The stop part stops services according to AI after the lapse of a predetermined period after the death of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately provide adequate means for those left behind to ease the sense of loss after the death of a deceased person, and there is room for improvement.

[0005] The system of the embodiment aims to help those left behind after the death of a deceased person to ease their sense of loss and regain their mental health. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an embedding unit, an instruction unit, a dialogue unit, and a stopping unit. The learning unit generates AI that has learned the user's voice, speaking style, and personality. The embedding unit embeds the AI ​​generated by the learning unit into a tablet device. The instruction unit instructs delivery of the tablet device to a person designated by the user after the user's death. The dialogue unit uses the AI ​​embedded in the tablet device to dialogue with the person designated by the user. The stopping unit stops the AI's services a predetermined period of time after the user's death. [Effects of the Invention]

[0007] The system according to the embodiment can help those left behind after the death of a deceased person to ease their sense of loss and regain their mental health. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention allows a user to create their own AI on a dedicated tablet while they are still alive, and then deliver the tablet to a designated person after their death. This system aims to ease their sense of loss and restore their mental health by interacting with the deceased's AI. This system generates an AI that learns the user's voice, speaking style, and personality, embeds the generated AI in a tablet device, and delivers it to the designated person after the user's death. Once the tablet device arrives at the designated person's home, a dialogue is conducted using the AI, giving the user the sensation of conversing with the deceased. This is expected to ease their sense of loss and restore their mental health. Furthermore, after a predetermined period (e.g., 49 days) has passed since the user's death, the AI ​​service is terminated. After this period, the tablet device stops providing service, and interaction with the AI ​​is no longer possible. When the service is terminated, the system also has a function to request the return of the tablet device. For example, returning the tablet device allows for reuse or appropriate disposal. Furthermore, a function to delete data when the service is terminated protects privacy. Thus, the present invention provides a system aimed at easing their sense of loss and restoring their mental health by interacting with the deceased's AI. By generating AI that learns the user's voice, speaking style, and personality and incorporating it into a tablet device, the user can feel as if they are conversing with the deceased. The system also includes functions for terminating the service, returning the tablet device, and deleting data, ensuring privacy and appropriate handling. This allows the system to ease the sense of loss and restore mental health by interacting with the deceased's AI.

[0029] The system according to the embodiment includes a learning unit, an embedding unit, an instruction unit, a dialogue unit, and a stopping unit. The learning unit generates an AI that has learned the user's voice, speaking style, and personality. The user's voice includes, for example, but is not limited to, a method for collecting voice samples and voice features. The learning unit, for example, records the user's voice and extracts voice features using voice recognition technology. The learning unit also analyzes the user's speaking style. The speaking style includes, for example, but is not limited to, speech rate, intonation, and accent. The learning unit, for example, records the user's speaking style and analyzes the speaking style features using natural language processing technology. The learning unit also evaluates the user's personality. The personality includes, for example, but is not limited to, a personality diagnostic test and an analysis of behavioral patterns. The learning unit, for example, administers a personality diagnostic test to the user and evaluates the personality based on the results. The embedding unit embeds the AI ​​generated by the learning unit into a tablet device. The embedding includes, for example, but is not limited to, software installation procedures and hardware configuration methods. The embedding unit, for example, installs AI software on the tablet device and performs the necessary settings. The instruction unit instructs delivery of the tablet device to a person designated by the user after the user's death. Examples of delivery include, but are not limited to, selecting a delivery company and setting a delivery schedule. The instruction unit, for example, confirms the address of the person designated by the user, selects an appropriate delivery company, and instructs delivery. The dialogue unit uses AI to engage in a dialogue with the designated person when the tablet device arrives. Examples of dialogue include, but are not limited to, a dialogue scenario and a natural language processing technology to be used. Examples of dialogue unit include, but are not limited to, the AI ​​reproducing the voice and speaking style of the deceased person and engaging in a dialogue with the designated person. The stopping unit stops the AI-provided service a predetermined period of time after the user's death. Examples of service stopping include, but are not limited to, trigger conditions for stopping the service and post-stop processing. For example, 49 days after the user's death, the stopping unit stops the service and requests the user to return the tablet device. As a result, the system of the embodiment uses AI that has learned the user's voice, speaking style, and personality to provide the feeling of interacting with the deceased, thereby easing the sense of loss.

[0030] The learning unit generates an AI that has learned the user's voice, speaking style, and personality. The user's voice includes, but is not limited to, a method for collecting voice samples and voice features. The learning unit, for example, records the user's voice and extracts voice features using voice recognition technology. Specifically, the user's voice is recorded using a high-quality microphone and the voice data is analyzed using digital signal processing technology. Voice features include fundamental frequency, formants, and spectral energy distribution. These features are important for expressing the individuality of the user's voice. The learning unit also analyzes the user's speaking style. Examples of speaking style include, but are not limited to, speech rate, intonation, and accent. The learning unit, for example, records the user's speaking style and analyzes the speaking style features using natural language processing technology. Specifically, the recording data of the user's speaking style is converted into text and the text data is analyzed to extract patterns of speaking rate and intonation. The learning unit also evaluates the user's personality. Examples of personality evaluation include, but are not limited to, a personality diagnostic test and an analysis of behavioral patterns. The learning unit, for example, administers a personality test to the user and evaluates the personality based on the results. Specifically, the results of the personality test are quantified and the numerical data is input into the AI ​​model to evaluate the personality. This allows the learning unit to comprehensively learn the user's voice, speaking style, and personality, and generate an AI that resembles the user.

[0031] The embedding unit embeds the AI ​​generated by the learning unit into the tablet device. Embedding includes, but is not limited to, software installation procedures and hardware configuration methods. Specifically, first, the AI ​​software is downloaded to the tablet device and installed. After installation, the necessary settings are made to ensure the AI ​​software operates properly. For example, the compatibility of the tablet device's operating system with the AI ​​software is confirmed, and necessary drivers and libraries are installed. The audio output device and microphone are also configured so that the AI ​​software can reproduce the user's voice and speaking style. Furthermore, the tablet device's network settings are configured to enable the AI ​​software to communicate with a cloud server. This allows the AI ​​software to access a database on the cloud and obtain necessary data. The embedding unit reliably executes these procedures and verifies that the AI ​​software operates properly on the tablet device. The embedding unit can then embed the AI ​​generated by the learning unit into the tablet device and provide it to the user.

[0032] The instruction unit instructs the delivery of a tablet device to a person designated by the user after the user's death. Delivery includes, for example, selecting a delivery company and setting a delivery schedule, but is not limited to these examples. Specifically, the unit first confirms the address of the person designated by the user and selects a company that can deliver to that address. The selected company is then given detailed instructions on how to handle the tablet device and the delivery schedule. For example, appropriate packaging materials are used to prevent damage to the tablet device and shock during delivery is minimized. Regarding the delivery schedule, the unit also adjusts a date and time when the designated person can reliably receive the tablet device and instructs the delivery company. Furthermore, the instruction unit tracks the delivery status in real time and notifies the designated person of the delivery status. This allows the designated person to know the expected date and time of arrival of the tablet device and to prepare for receipt. The instruction unit reliably executes these procedures to ensure that the tablet device is delivered to the designated person after the user's death. This allows the instruction unit to respect the user's wishes and smoothly deliver the tablet device.

[0033] When the tablet device is delivered to the designated person, the dialogue unit uses AI to engage in a dialogue. The dialogue may include, but is not limited to, a dialogue scenario and the natural language processing technology used. Specifically, the AI ​​recreates the deceased's voice and speaking style and engages in a dialogue with the designated person. The dialogue scenario is created based on the user's settings. For example, it may include messages the deceased wanted to convey and dialogue content tailored to specific situations. The AI ​​uses natural language processing technology to engage in a natural dialogue based on these scenarios. Specifically, the AI ​​converts the designated person's utterances into text using speech recognition technology, analyzes the text, and generates an appropriate response. The generated response is played back in the deceased's voice using speech synthesis technology. This allows the designated person to feel as if they are conversing with the deceased. Furthermore, the dialogue unit can flexibly change the AI's response depending on the content and situation of the dialogue. For example, if the designated person shows an emotional reaction, the AI ​​generates a response appropriate to that emotion and continues the dialogue. This allows the dialogue unit to provide the designated person with support to ease their sense of loss through dialogue with the deceased.

[0034] The termination unit terminates the AI-based service a predetermined period after the user's death. The termination of the service includes, but is not limited to, trigger conditions and post-termination processes. Specifically, the service is terminated 49 days after the user's death and the tablet device is requested to be returned. Trigger conditions for the termination include the submission of a death certificate for the user and notification from a designated person. When these conditions are met, the termination unit initiates procedures to terminate the AI-based service. Specifically, the termination unit first terminates the AI ​​software on the tablet device and terminates the provision of the service. Next, the termination unit requests the designated person to return the tablet device and notifies them of the details of the return procedure. The return procedure includes, for example, providing packaging materials for return and notifying the designated person of the return address. Furthermore, the termination unit erases data on the returned tablet device and takes measures to protect privacy. This allows the termination unit to terminate the AI-based service at an appropriate time after the user's death and ensure the tablet device is returned. This allows the termination unit to respect the user's wishes and appropriately terminate the provision of the service.

[0035] The tablet device includes a request unit that requests the return of the tablet device when the AI-based service is stopped by the stopping unit. The request unit requests the return of the tablet device when the service is stopped. The return request includes, for example, a method for notifying the user of the return request and a return deadline, but is not limited to these examples. The request unit may, for example, display a return request message on the screen of the tablet device and notify the user of the return deadline. The request unit may also send the return request notification by email or SMS. For example, the request unit may send the return request notification based on contact information of a person designated by the user. The request unit may also send the return request notification by mail. For example, the request unit may send the return request notification by mail and specify the return deadline. This allows the tablet device to be reused or appropriately disposed of by requesting its return after the service is stopped.

[0036] The tablet device includes a deletion unit that deletes data when the AI-based service is stopped by the stopping unit. The deletion unit deletes data when the service is stopped. Data deletion includes, for example, the type of data to be deleted and the deletion procedure, but is not limited to these examples. The deletion unit deletes, for example, user data and interaction history in the tablet device. The deletion unit can also automate the data deletion procedure. For example, the deletion unit automatically deletes data when the service is stopped. Furthermore, the deletion unit can also confirm the data deletion. For example, the deletion unit displays a confirmation message before deleting the data and executes the deletion only after obtaining the user's consent. This protects privacy by deleting data after the service is stopped.

[0037] The learning unit analyzes the user's past dialogue history and selects an appropriate learning algorithm. The learning unit analyzes the user's past dialogue history and selects an optimal learning algorithm. Dialogue history analysis includes, but is not limited to, natural language processing technology and analysis standards. The learning unit, for example, analyzes frequently used words and phrases by the user and adjusts the learning algorithm based on the analysis. The learning unit can also analyze the user's dialogue patterns and select an optimal learning algorithm. For example, the learning unit selects a learning algorithm corresponding to a specific emotional state from the user's dialogue history. Furthermore, the learning unit can customize the learning data based on the analysis results of the dialogue history. For example, the learning unit optimizes the learning data based on information obtained from the user's dialogue history. In this way, the optimal learning algorithm can be selected by analyzing the past dialogue history.

[0038] The learning unit customizes the learning data based on the user's lifestyle and hobbies. The learning unit customizes the learning data based on the user's lifestyle and hobbies. Lifestyles include, but are not limited to, daily behavioral patterns and health data. For example, the learning unit learns conversation data that takes place during a specific time period based on the user's lifestyle. The learning unit can also prioritize learning conversation data related to the user's hobbies. For example, the learning unit collects conversation data related to the user's hobbies and reflects it in the learning data. Furthermore, the learning unit can customize and learn related conversation data based on the user's interests. For example, the learning unit collects data related to topics that interest the user and incorporates it into the learning data. This allows for customizing the learning data based on the user's lifestyle and hobbies, thereby generating a more personalized AI.

[0039] The learning unit analyzes the user's social media activity and reflects it in the learning data. The learning unit analyzes the user's social media activity and reflects it in the learning data. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower information. The learning unit, for example, reflects words and phrases frequently used by the user on social media in the learning data. The learning unit can also analyze the user's social media activity patterns and reflect them in the learning data. For example, the learning unit analyzes the content of the user's posts and customizes the learning data based on the user's interests. Furthermore, the learning unit can optimize the learning data based on information shared by the user on social media. For example, the learning unit analyzes the reactions of the user's followers and reflects them in the learning data. In this way, by analyzing social media activity, more realistic learning data can be generated.

[0040] The learning unit incorporates regional language and culture into the training data based on the user's geographical location information. The learning unit incorporates regional language and culture into the training data taking into account the user's geographical location information. Collection of geographical location information includes, but is not limited to, collection of GPS data and location information analysis methods. The learning unit incorporates, for example, dialects and expressions of the region where the user lives into the training data. The learning unit can also reflect regional culture and customs into the training data based on the user's geographical location information. For example, the learning unit incorporates information about places frequently visited by the user into the training data. Furthermore, the learning unit can reflect information about regional events and ceremonies into the training data. For example, the learning unit collects data related to regional festivals and traditional events and incorporates it into the training data. In this way, by taking geographical location information into account, it is possible to generate AI that reflects regional language and culture.

[0041] The embedding unit generates AI optimized for the hardware characteristics of the tablet device. The embedding unit generates AI optimized for the hardware characteristics of the tablet device. Optimization of hardware characteristics includes, but is not limited to, CPU performance and memory capacity, for example. The embedding unit generates AI optimized for, for example, the processor performance of the tablet device. The embedding unit can also generate AI optimized for the memory capacity of the tablet device. For example, the embedding unit optimizes memory usage of the tablet device to achieve efficient operation. Furthermore, the embedding unit can generate AI optimized taking into account the battery life of the tablet device. For example, the embedding unit sets the AI ​​operation to a low power consumption mode to reduce battery consumption. This allows the device's performance to be maximized by generating AI optimized for the hardware characteristics of the tablet device.

[0042] The embedded unit customizes the AI's operating mode according to the user's usage environment. The embedded unit customizes the AI's operating mode according to the user's usage environment. Customization of the usage environment includes, but is not limited to, indoor and outdoor environments and the applications used. For example, the embedded unit provides an operating mode that reduces battery consumption when the user uses the device outdoors. The embedded unit can also provide a high-performance operating mode when the user uses the device indoors. For example, the embedded unit automatically adjusts the AI's operating mode according to the user's usage environment. Furthermore, the embedded unit can adjust the operating mode in real time when the user uses the device while on the move. For example, the embedded unit selects the optimal operating mode based on the user's location information. By customizing the operating mode according to the usage environment, it is possible to provide optimal operation according to the user's needs.

[0043] The embedded unit adjusts the operation of the AI ​​taking into account the battery life of the tablet device. The embedded unit adjusts the operation of the AI ​​taking into account the battery life of the tablet device. Optimization of battery life includes, but is not limited to, battery consumption patterns and power-saving modes, for example. For example, the embedded unit sets the operation of the AI ​​to a low-power consumption mode to reduce battery consumption. The embedded unit can also optimize the operation of the AI ​​to extend battery life. For example, the embedded unit automatically adjusts the operation mode of the AI ​​according to the remaining battery level. Furthermore, the embedded unit can analyze battery consumption patterns and select the optimal operation mode. For example, the embedded unit optimizes the operation of the AI ​​based on the battery consumption pattern. In this way, optimizing the operation of the AI ​​taking into account battery life can extend the usage time of the device.

[0044] The embedded unit incorporates additional functions for enhancing the security functions of the tablet device. The embedded unit incorporates additional functions for enhancing the security functions of the tablet device. Enhanced security functions include, but are not limited to, encryption technology and authentication methods, for example. The embedded unit enhances the security of the tablet device, for example, by incorporating an AI-based facial recognition function. The embedded unit can also incorporate an AI-based fingerprint authentication function. For example, the embedded unit can enhance access control of the tablet device using fingerprint authentication technology. The embedded unit can also incorporate an AI-based voice recognition function. For example, the embedded unit can enhance the security of the tablet device using voice recognition technology. This enhances the security functions, thereby improving the safety of the device.

[0045] The instruction unit issues a delivery instruction taking into consideration the time period when the designated person is available to receive the package. The instruction unit issues a delivery instruction taking into consideration the time period when the designated person is available to receive the package. Consideration of the available time period for receiving the package includes, but is not limited to, the designated time period and the date when the package is available to receive the package. For example, the instruction unit issues an optimal delivery time taking into consideration the time period when the designated person is available to receive the package. The instruction unit can also issue a delivery instruction for a time period when the designated person is available to receive the package by referring to the schedule of the designated person. For example, the instruction unit refers to the past receiving history of the designated person to indicate the optimal delivery time. Furthermore, the instruction unit can also optimize the delivery schedule based on the available time period for receiving the package. For example, the instruction unit issues instructions to the delivery company based on the available time period for receiving the package. In this way, by taking into consideration the available time period for receiving the package, the designated person can be sure to receive the package.

[0046] The instruction unit selects the optimal delivery method taking into consideration the geographical conditions of the delivery destination. The instruction unit selects the optimal delivery method taking into consideration the geographical conditions of the delivery destination. Consideration of geographical conditions includes, for example, the topography and traffic conditions of the delivery destination, but is not limited to these examples. For example, the instruction unit selects a rapid delivery method when the delivery destination is in an urban area. The instruction unit can also select an efficient delivery method when the delivery destination is in a suburban area. For example, the instruction unit selects the optimal delivery method when the delivery destination is in a remote area. Furthermore, the instruction unit can optimize the delivery schedule based on the geographical conditions. For example, the instruction unit issues instructions to the delivery company based on the geographical conditions of the delivery destination. In this way, efficient and rapid delivery is achieved by taking geographical conditions into consideration.

[0047] The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. Confirmed contact information includes, for example, a telephone number and an email address, but is not limited to these examples. The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. Furthermore, if the contact information of the designated person is changed, the instruction unit can automatically update the contact information and issue delivery instructions. For example, the instruction unit detects changes in the contact information in real time and updates the delivery instructions. Furthermore, the instruction unit can select an optimal delivery method based on the contact information. For example, the instruction unit selects an optimal delivery company by referring to the contact information of the designated person. In this way, accurate delivery instructions can be issued by automatically checking the contact information of the designated person.

[0048] The instruction unit adds a function for tracking the delivery status in real time. The instruction unit adds a function for tracking the delivery status in real time. Delivery status tracking includes, for example, GPS tracking and delivery status update methods, but is not limited to these examples. For example, the instruction unit tracks the delivery status in real time and notifies a designated person. The instruction unit can also track the delivery status in real time and notify a user. For example, the instruction unit monitors the progress of the delivery status in real time and notifies a user. Furthermore, the instruction unit can select an optimal delivery method based on the delivery status. For example, the instruction unit tracks the delivery status in real time and selects an optimal delivery company. In this way, the delivery progress can be confirmed by tracking the delivery status in real time.

[0049] The dialogue unit customizes the tone of the dialogue according to the current situation of the designated person. The dialogue unit customizes the tone of the dialogue according to the current situation of the designated person. Customization of the tone of the dialogue includes, but is not limited to, the atmosphere and the language used in the dialogue. For example, if the designated person is relaxed, the dialogue unit may use a calm tone. Furthermore, if the designated person is stressed, the dialogue unit may use an encouraging tone. For example, the dialogue unit dynamically adjusts the tone of the dialogue according to the emotional state of the designated person. Furthermore, if the designated person is excited, the dialogue unit may use a calming tone. For example, the dialogue unit monitors the emotional state of the designated person in real time and optimizes the tone of the dialogue. This allows the dialogue to be more appropriate by customizing the tone of the dialogue according to the situation of the designated person.

[0050] The dialogue unit analyzes the social media activity of the designated person and reflects it in the dialogue content. The dialogue unit analyzes the social media activity of the designated person and reflects it in the dialogue content. Analysis of social media activity includes, but is not limited to, analysis of posted content and analysis of followers, for example. The dialogue unit reflects, for example, words and phrases frequently used by the designated person on social media in the dialogue content. The dialogue unit can also analyze the designated person's social media activity patterns and reflect it in the dialogue content. For example, the dialogue unit analyzes the posted content of the designated person and customizes the dialogue content based on the designated person's interests and concerns. Furthermore, the dialogue unit can optimize the dialogue content based on information shared by the designated person on social media. For example, the dialogue unit analyzes the reactions of the designated person's followers and reflects them in the dialogue content. In this way, by analyzing social media activity, it is possible to provide dialogue content that is more in line with reality.

[0051] The dialogue unit provides a topic specific to a region by taking into account the geographical location information of the designated person. The dialogue unit provides a topic specific to a region by taking into account the geographical location information of the designated person. Examples of collecting geographical location information include, but are not limited to, collecting GPS data and analyzing location information. The dialogue unit, for example, reflects topics specific to the region where the designated person lives in the dialogue content. The dialogue unit can also reflect local culture and customs in the dialogue content based on the geographical location information of the designated person. For example, the dialogue unit incorporates information about places frequently visited by the designated person into the dialogue content. Furthermore, the dialogue unit can also reflect information about local events and ceremonies in the dialogue content. For example, the dialogue unit collects data about local festivals and traditional events and incorporates it into the dialogue content. In this way, local topics can be provided by taking into account the geographical location information.

[0052] The stop unit issues the stop notification taking into account the emotional state of the designated person. The stop unit issues the stop notification taking into account the emotional state of the designated person. Examples of consideration of the emotional state include, but are not limited to, emotion recognition technology and emotion evaluation criteria. For example, if the designated person is relaxed, the stop unit issues the stop notification in a calm tone. Furthermore, if the designated person is feeling stressed, the stop unit can also issue the stop notification in an encouraging tone. For example, the stop unit dynamically adjusts the tone of the stop notification according to the emotional state of the designated person. Furthermore, if the designated person is excited, the stop unit can also issue the stop notification in a calming tone. For example, the stop unit monitors the emotional state of the designated person in real time and optimizes the tone of the stop notification. In this way, the stop notification can be issued in a more appropriate tone by taking into account the emotional state of the designated person.

[0053] The stopping unit adds a function to safely back up data on the tablet device when the service is stopped. The stopping unit adds a function to safely back up data on the tablet device when the service is stopped. Data backup includes, for example, selection of backup frequency and backup destination, but is not limited to these examples. For example, the stopping unit backs up data on the tablet device to the cloud when the service is stopped. The stopping unit can also back up data on the tablet device to external storage when the service is stopped. For example, the stopping unit encrypts the data before backing it up. Furthermore, the stopping unit can automate the data backup procedure. For example, the stopping unit automatically performs data backup when the service is stopped. This ensures data protection by safely backing up the data.

[0054] The stop unit automatically checks the contact information of the designated person and issues a stop notification. The stop unit automatically checks the contact information of the designated person and issues a stop notification. Confirmation of the contact information includes, for example, a phone number and an email address, but is not limited to these examples. The stop unit automatically checks, for example, the contact information of the designated person and issues a stop notification. Furthermore, if the contact information of the designated person is changed, the stop unit can automatically update the contact information and issue a stop notification. For example, the stop unit detects changes in the contact information in real time and updates the stop notification. Furthermore, the stop unit can select an optimal stop notification method based on the contact information. For example, the stop unit selects an optimal notification method by referring to the contact information of the designated person. In this way, an accurate stop notification can be issued by automatically checking the contact information of the designated person.

[0055] The stopping unit incorporates an additional function for enhancing the security functions of the tablet device when stopped. The stopping unit incorporates an additional function for enhancing the security functions of the tablet device when stopped. Enhanced security functions include, for example, encryption technology and authentication methods, but are not limited to such examples. The stopping unit, for example, enhances the security of the tablet device by incorporating an AI facial recognition function. The stopping unit can also incorporate an AI fingerprint authentication function. For example, the stopping unit uses fingerprint authentication technology to enhance access control of the tablet device. Furthermore, the stopping unit can also incorporate an AI voice recognition function. For example, the stopping unit uses voice recognition technology to enhance the security of the tablet device. This enhances the security functions and improves the safety of the device.

[0056] The request unit makes a return request taking into consideration the time period during which the designated person can return the item. The request unit makes a return request taking into consideration the time period during which the designated person can return the item. Examples of the time period during which the designated person can return the item include, but are not limited to, the designated time period and the date on which the item can be returned. For example, the request unit requests the optimal return time taking into consideration the time period during which the designated person can return the item. The request unit can also make a return request during a time period during which the designated person can return the item by referring to the schedule of the designated person. For example, the request unit can request the optimal return time by referring to the past return history of the designated person. Furthermore, the request unit can optimize the return schedule based on the time period during which the designated person can return the item. For example, the request unit issues instructions to the return company based on the time period during which the designated person can return the item. In this way, by taking into consideration the time period during which the designated person can return the item, the designated person can be reliably returned.

[0057] The requesting unit automatically checks the contact information of the designated person and makes a return request. The requesting unit automatically checks the contact information of the designated person and makes a return request. Examples of confirmed contact information include, but are not limited to, a phone number and an email address. For example, the requesting unit automatically checks the contact information of the designated person and makes a return request. Furthermore, if the contact information of the designated person is changed, the requesting unit can automatically update the contact information and make a return request. For example, the requesting unit detects changes in the contact information in real time and updates the return request. Furthermore, the requesting unit can select an optimal return request method based on the contact information. For example, the requesting unit selects an optimal return request method by referring to the contact information of the designated person. In this way, an accurate return request can be made by automatically checking the contact information of the designated person.

[0058] The deletion unit issues a deletion notification taking into account the emotional state of the designated person. The deletion unit issues a deletion notification taking into account the emotional state of the designated person. Examples of consideration of the emotional state include, but are not limited to, emotion recognition technology and emotion evaluation criteria. For example, if the designated person is relaxed, the deletion unit issues a deletion notification in a calm tone. Furthermore, if the designated person is stressed, the deletion unit can also issue a deletion notification in an encouraging tone. For example, the deletion unit dynamically adjusts the tone of the deletion notification according to the emotional state of the designated person. Furthermore, if the designated person is excited, the deletion unit can also issue a deletion notification in a calming tone. For example, the deletion unit monitors the emotional state of the designated person in real time and optimizes the tone of the deletion notification. In this way, the deletion notification can be issued in a more appropriate tone by taking into account the emotional state of the designated person.

[0059] The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. Confirmation of the contact information includes, for example, a phone number and an email address, but is not limited to these examples. The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. Furthermore, if the contact information of the designated person is changed, the deletion unit can automatically update the contact information and issue a deletion notification. For example, the deletion unit detects changes in the contact information in real time and updates the deletion notification. Furthermore, the deletion unit can select an optimal deletion notification method based on the contact information. For example, the deletion unit selects an optimal notification method by referring to the contact information of the designated person. In this way, an accurate deletion notification can be issued by automatically checking the contact information of the designated person.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The request unit can also provide options for the return method when requesting the return of the tablet device. For example, if it is difficult for the person designated by the user to return the device by mail, the request unit can guide the user to a nearby return location. A return label can also be enclosed with the return request notice to make the return easier. Furthermore, detailed instructions on the return procedure can be included in the return request notice to enable the designated person to return the device smoothly. In this way, providing options for the return method makes it easier for the designated person to return the device.

[0062] The deletion unit may also have a function to temporarily back up data before deletion when deleting data. For example, the deletion unit may temporarily back up data in the tablet device to cloud storage before deleting the data. The deletion unit may also back up data to external storage before deleting the data. Furthermore, the deletion unit may ask the user for confirmation of backup before deleting the data and execute deletion only after obtaining consent. In this way, data protection is achieved by performing a temporary backup when deleting data.

[0063] The learning unit can also analyze the user's past dialogue history and select an appropriate learning algorithm. For example, it can analyze the words and phrases frequently used by the user and adjust the learning algorithm based on that. It can also analyze the user's dialogue patterns and select the optimal learning algorithm. Furthermore, it can customize the learning data based on the analysis results of the dialogue history. This makes it possible to select the optimal learning algorithm by analyzing the past dialogue history.

[0064] The learning unit can also customize learning data based on the user's lifestyle and hobbies. For example, it can learn conversation data that takes place during a specific time period based on the user's lifestyle. It can also prioritize learning conversation data related to the user's hobbies. Furthermore, it can customize and learn related conversation data based on the user's interests. This allows for the generation of more personalized AI by customizing learning data based on the user's lifestyle and hobbies.

[0065] The learning unit can also analyze a user's social media activity and reflect it in the learning data. For example, words and phrases frequently used by the user on social media can be reflected in the learning data. The learning unit can also analyze a user's social media activity patterns and reflect them in the learning data. Furthermore, the learning data can be optimized based on the information the user shares on social media. This makes it possible to generate learning data that is more in line with reality by analyzing social media activity.

[0066] The learning unit can also incorporate regional language and culture into the training data, taking into account the user's geographical location information. For example, the dialect and expressions of the region where the user lives can be incorporated into the training data. Regional culture and customs can also be reflected in the training data based on the user's geographical location information. Furthermore, information about regional events and ceremonies can also be reflected in the training data. In this way, by taking geographical location information into account, it is possible to generate AI that reflects regional language and culture.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The learning unit generates an AI that has learned the user's voice, speaking style, and personality. Specifically, the user's voice is recorded and speech features are extracted using speech recognition technology. The user's speaking style is also recorded and the characteristics of the speaking style are analyzed using natural language processing technology. The user is then given a personality assessment test and their personality is evaluated based on the results. Step 2: The embedding unit embeds the AI ​​generated by the learning unit into the tablet device. Specifically, it installs the AI ​​software on the tablet device and performs the necessary settings. Step 3: The instruction unit instructs the delivery of the tablet device to a person designated by the user after the user's death. Specifically, the instruction unit checks the address of the person designated by the user, selects an appropriate delivery company, and instructs the delivery. Step 4: When the tablet device is delivered to the designated person, the dialogue unit uses AI to carry out a dialogue. Specifically, the AI ​​reproduces the voice and speaking style of the deceased person and engages in a dialogue with the designated person. Step 5: The termination unit will terminate the AI-based service a predetermined period of time after the user's death. Specifically, the service will be terminated 49 days after the user's death and the tablet device will be requested to be returned.

[0069] (Example 2) A system according to an embodiment of the present invention allows a user to create their own AI on a dedicated tablet while they are still alive, and then deliver the tablet to a designated person after their death. This system aims to ease their sense of loss and restore their mental health by interacting with the deceased's AI. This system generates an AI that learns the user's voice, speaking style, and personality, embeds the generated AI in a tablet device, and delivers it to the designated person after the user's death. Once the tablet device arrives at the designated person's home, a dialogue is conducted using the AI, giving the user the sensation of conversing with the deceased. This is expected to ease their sense of loss and restore their mental health. Furthermore, after a predetermined period (e.g., 49 days) has passed since the user's death, the AI ​​service is terminated. After this period, the tablet device stops providing service, and interaction with the AI ​​is no longer possible. When the service is terminated, the system also has a function to request the return of the tablet device. For example, returning the tablet device allows for reuse or appropriate disposal. Furthermore, a function to delete data when the service is terminated protects privacy. Thus, the present invention provides a system aimed at easing their sense of loss and restoring their mental health by interacting with the deceased's AI. By generating AI that learns the user's voice, speaking style, and personality and incorporating it into a tablet device, the user can feel as if they are conversing with the deceased. The system also includes functions for terminating the service, returning the tablet device, and deleting data, ensuring privacy and appropriate handling. This allows the system to ease the sense of loss and restore mental health by interacting with the deceased's AI.

[0070] The system according to the embodiment includes a learning unit, an embedding unit, an instruction unit, a dialogue unit, and a stopping unit. The learning unit generates an AI that has learned the user's voice, speaking style, and personality. The user's voice includes, for example, but is not limited to, a method for collecting voice samples and voice features. The learning unit, for example, records the user's voice and extracts voice features using voice recognition technology. The learning unit also analyzes the user's speaking style. The speaking style includes, for example, but is not limited to, speech rate, intonation, and accent. The learning unit, for example, records the user's speaking style and analyzes the speaking style features using natural language processing technology. The learning unit also evaluates the user's personality. The personality includes, for example, but is not limited to, a personality diagnostic test and an analysis of behavioral patterns. The learning unit, for example, administers a personality diagnostic test to the user and evaluates the personality based on the results. The embedding unit embeds the AI ​​generated by the learning unit into a tablet device. The embedding includes, for example, but is not limited to, software installation procedures and hardware configuration methods. The embedding unit, for example, installs AI software on the tablet device and performs the necessary settings. The instruction unit instructs delivery of the tablet device to a person designated by the user after the user's death. Examples of delivery include, but are not limited to, selecting a delivery company and setting a delivery schedule. The instruction unit, for example, confirms the address of the person designated by the user, selects an appropriate delivery company, and instructs delivery. The dialogue unit uses AI to engage in a dialogue with the designated person when the tablet device arrives. Examples of dialogue include, but are not limited to, a dialogue scenario and a natural language processing technology to be used. Examples of dialogue unit include, but are not limited to, the AI ​​reproducing the voice and speaking style of the deceased person and engaging in a dialogue with the designated person. The stopping unit stops the AI-provided service a predetermined period of time after the user's death. Examples of service stopping include, but are not limited to, trigger conditions for stopping the service and post-stop processing. For example, 49 days after the user's death, the stopping unit stops the service and requests the user to return the tablet device. As a result, the system of the embodiment uses AI that has learned the user's voice, speaking style, and personality to provide the feeling of interacting with the deceased, thereby easing the sense of loss.

[0071] The learning unit generates an AI that has learned the user's voice, speaking style, and personality. The user's voice includes, but is not limited to, a method for collecting voice samples and voice features. The learning unit, for example, records the user's voice and extracts voice features using voice recognition technology. Specifically, the user's voice is recorded using a high-quality microphone and the voice data is analyzed using digital signal processing technology. Voice features include fundamental frequency, formants, and spectral energy distribution. These features are important for expressing the individuality of the user's voice. The learning unit also analyzes the user's speaking style. Examples of speaking style include, but are not limited to, speech rate, intonation, and accent. The learning unit, for example, records the user's speaking style and analyzes the speaking style features using natural language processing technology. Specifically, the recording data of the user's speaking style is converted into text and the text data is analyzed to extract patterns of speaking rate and intonation. The learning unit also evaluates the user's personality. Examples of personality evaluation include, but are not limited to, a personality diagnostic test and an analysis of behavioral patterns. The learning unit, for example, administers a personality test to the user and evaluates the personality based on the results. Specifically, the results of the personality test are quantified and the numerical data is input into the AI ​​model to evaluate the personality. This allows the learning unit to comprehensively learn the user's voice, speaking style, and personality, and generate an AI that resembles the user.

[0072] The embedding unit embeds the AI ​​generated by the learning unit into the tablet device. Embedding includes, but is not limited to, software installation procedures and hardware configuration methods. Specifically, first, the AI ​​software is downloaded to the tablet device and installed. After installation, the necessary settings are made to ensure the AI ​​software operates properly. For example, the compatibility of the tablet device's operating system with the AI ​​software is confirmed, and necessary drivers and libraries are installed. The audio output device and microphone are also configured so that the AI ​​software can reproduce the user's voice and speaking style. Furthermore, the tablet device's network settings are configured to enable the AI ​​software to communicate with a cloud server. This allows the AI ​​software to access a database on the cloud and obtain necessary data. The embedding unit reliably executes these procedures and verifies that the AI ​​software operates properly on the tablet device. The embedding unit can then embed the AI ​​generated by the learning unit into the tablet device and provide it to the user.

[0073] The instruction unit instructs the delivery of a tablet device to a person designated by the user after the user's death. Delivery includes, for example, selecting a delivery company and setting a delivery schedule, but is not limited to these examples. Specifically, the unit first confirms the address of the person designated by the user and selects a company that can deliver to that address. The selected company is then given detailed instructions on how to handle the tablet device and the delivery schedule. For example, appropriate packaging materials are used to prevent damage to the tablet device and shock during delivery is minimized. Regarding the delivery schedule, the unit also adjusts a date and time when the designated person can reliably receive the tablet device and instructs the delivery company. Furthermore, the instruction unit tracks the delivery status in real time and notifies the designated person of the delivery status. This allows the designated person to know the expected date and time of arrival of the tablet device and to prepare for receipt. The instruction unit reliably executes these procedures to ensure that the tablet device is delivered to the designated person after the user's death. This allows the instruction unit to respect the user's wishes and smoothly deliver the tablet device.

[0074] When the tablet device is delivered to the designated person, the dialogue unit uses AI to engage in a dialogue. The dialogue may include, but is not limited to, a dialogue scenario and the natural language processing technology used. Specifically, the AI ​​recreates the deceased's voice and speaking style and engages in a dialogue with the designated person. The dialogue scenario is created based on the user's settings. For example, it may include messages the deceased wanted to convey and dialogue content tailored to specific situations. The AI ​​uses natural language processing technology to engage in a natural dialogue based on these scenarios. Specifically, the AI ​​converts the designated person's utterances into text using speech recognition technology, analyzes the text, and generates an appropriate response. The generated response is played back in the deceased's voice using speech synthesis technology. This allows the designated person to feel as if they are conversing with the deceased. Furthermore, the dialogue unit can flexibly change the AI's response depending on the content and situation of the dialogue. For example, if the designated person shows an emotional reaction, the AI ​​generates a response appropriate to that emotion and continues the dialogue. This allows the dialogue unit to provide the designated person with support to ease their sense of loss through dialogue with the deceased.

[0075] The termination unit terminates the AI-based service a predetermined period after the user's death. The termination of the service includes, but is not limited to, trigger conditions and post-termination processes. Specifically, the service is terminated 49 days after the user's death and the tablet device is requested to be returned. Trigger conditions for the termination include the submission of a death certificate for the user and notification from a designated person. When these conditions are met, the termination unit initiates procedures to terminate the AI-based service. Specifically, the termination unit first terminates the AI ​​software on the tablet device and terminates the provision of the service. Next, the termination unit requests the designated person to return the tablet device and notifies them of the details of the return procedure. The return procedure includes, for example, providing packaging materials for return and notifying the designated person of the return address. Furthermore, the termination unit erases data on the returned tablet device and takes measures to protect privacy. This allows the termination unit to terminate the AI-based service at an appropriate time after the user's death and ensure the tablet device is returned. This allows the termination unit to respect the user's wishes and appropriately terminate the provision of the service.

[0076] The tablet device includes a request unit that requests the return of the tablet device when the AI-based service is stopped by the stopping unit. The request unit requests the return of the tablet device when the service is stopped. The return request includes, for example, a method for notifying the user of the return request and a return deadline, but is not limited to these examples. The request unit may, for example, display a return request message on the screen of the tablet device and notify the user of the return deadline. The request unit may also send the return request notification by email or SMS. For example, the request unit may send the return request notification based on contact information of a person designated by the user. The request unit may also send the return request notification by mail. For example, the request unit may send the return request notification by mail and specify the return deadline. This allows the tablet device to be reused or appropriately disposed of by requesting its return after the service is stopped.

[0077] The tablet device includes a deletion unit that deletes data when the AI-based service is stopped by the stopping unit. The deletion unit deletes data when the service is stopped. Data deletion includes, for example, the type of data to be deleted and the deletion procedure, but is not limited to these examples. The deletion unit deletes, for example, user data and interaction history in the tablet device. The deletion unit can also automate the data deletion procedure. For example, the deletion unit automatically deletes data when the service is stopped. Furthermore, the deletion unit can also confirm the data deletion. For example, the deletion unit displays a confirmation message before deleting the data and executes the deletion only after obtaining the user's consent. This protects privacy by deleting data after the service is stopped.

[0078] The learning unit estimates the user's emotions and selects training data based on the estimated user emotions. The learning unit estimates the user's emotions and selects training data based on the estimated emotions. Emotion estimation includes, but is not limited to, emotion recognition technology and the type of data used. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion recognition algorithm. The learning unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the learning unit analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, the learning unit can collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on heart rate fluctuations. This allows for the generation of more appropriate AI by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0079] The learning unit analyzes the user's past dialogue history and selects an appropriate learning algorithm. The learning unit analyzes the user's past dialogue history and selects an optimal learning algorithm. Dialogue history analysis includes, but is not limited to, natural language processing technology and analysis standards. The learning unit, for example, analyzes frequently used words and phrases by the user and adjusts the learning algorithm based on the analysis. The learning unit can also analyze the user's dialogue patterns and select an optimal learning algorithm. For example, the learning unit selects a learning algorithm corresponding to a specific emotional state from the user's dialogue history. Furthermore, the learning unit can customize the learning data based on the analysis results of the dialogue history. For example, the learning unit optimizes the learning data based on information obtained from the user's dialogue history. In this way, the optimal learning algorithm can be selected by analyzing the past dialogue history.

[0080] The learning unit customizes the learning data based on the user's lifestyle and hobbies. The learning unit customizes the learning data based on the user's lifestyle and hobbies. Lifestyles include, but are not limited to, daily behavioral patterns and health data. For example, the learning unit learns conversation data that takes place during a specific time period based on the user's lifestyle. The learning unit can also prioritize learning conversation data related to the user's hobbies. For example, the learning unit collects conversation data related to the user's hobbies and reflects it in the learning data. Furthermore, the learning unit can customize and learn related conversation data based on the user's interests. For example, the learning unit collects data related to topics that interest the user and incorporates it into the learning data. This allows for customizing the learning data based on the user's lifestyle and hobbies, thereby generating a more personalized AI.

[0081] The learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated emotions. Adjustments to the learning frequency include, but are not limited to, the learning interval and the learning data update frequency. For example, when the user is relaxed, the learning unit increases the learning frequency to collect data. Furthermore, when the user is stressed, the learning unit can reduce the learning frequency to reduce the burden on the user. For example, the learning unit dynamically adjusts the learning frequency according to the user's emotional state. Furthermore, when the user is excited, the learning unit can adjust the learning frequency to collect appropriate data. For example, the learning unit monitors the user's emotional state in real time and optimizes the learning frequency. By adjusting the learning frequency based on the user's emotions, appropriate data can be collected while reducing the burden on the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0082] The learning unit analyzes the user's social media activity and reflects it in the learning data. The learning unit analyzes the user's social media activity and reflects it in the learning data. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower information. The learning unit, for example, reflects words and phrases frequently used by the user on social media in the learning data. The learning unit can also analyze the user's social media activity patterns and reflect them in the learning data. For example, the learning unit analyzes the content of the user's posts and customizes the learning data based on the user's interests. Furthermore, the learning unit can optimize the learning data based on information shared by the user on social media. For example, the learning unit analyzes the reactions of the user's followers and reflects them in the learning data. In this way, by analyzing social media activity, more realistic learning data can be generated.

[0083] The learning unit incorporates regional language and culture into the training data based on the user's geographical location information. The learning unit incorporates regional language and culture into the training data taking into account the user's geographical location information. Collection of geographical location information includes, but is not limited to, collection of GPS data and location information analysis methods. The learning unit incorporates, for example, dialects and expressions of the region where the user lives into the training data. The learning unit can also reflect regional culture and customs into the training data based on the user's geographical location information. For example, the learning unit incorporates information about places frequently visited by the user into the training data. Furthermore, the learning unit can reflect information about regional events and ceremonies into the training data. For example, the learning unit collects data related to regional festivals and traditional events and incorporates it into the training data. In this way, by taking geographical location information into account, it is possible to generate AI that reflects regional language and culture.

[0084] The integration unit estimates the user's emotions and adjusts the timing of integration based on the estimated user emotions. The integration unit estimates the user's emotions and adjusts the timing of integration based on the estimated emotions. Examples of adjustments to the timing of integration include, but are not limited to, the user's schedule and the system's operating status. For example, the integration unit may advance the timing of integration when the user is relaxed. The integration unit may also delay the timing of integration when the user is stressed. For example, the integration unit dynamically adjusts the timing of integration according to the user's emotional state. Furthermore, if the user is excited, the integration unit may adjust the timing of integration to integrate the AI ​​at an appropriate timing. For example, the integration unit monitors the user's emotional state in real time and optimizes the timing of integration. This allows the AI ​​to be integrated at a more appropriate timing by adjusting the timing of integration based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] The embedding unit generates AI optimized for the hardware characteristics of the tablet device. The embedding unit generates AI optimized for the hardware characteristics of the tablet device. Optimization of hardware characteristics includes, but is not limited to, CPU performance and memory capacity, for example. The embedding unit generates AI optimized for, for example, the processor performance of the tablet device. The embedding unit can also generate AI optimized for the memory capacity of the tablet device. For example, the embedding unit optimizes memory usage of the tablet device to achieve efficient operation. Furthermore, the embedding unit can generate AI optimized taking into account the battery life of the tablet device. For example, the embedding unit sets the AI ​​operation to a low power consumption mode to reduce battery consumption. This allows the device's performance to be maximized by generating AI optimized for the hardware characteristics of the tablet device.

[0086] The embedded unit customizes the AI's operating mode according to the user's usage environment. The embedded unit customizes the AI's operating mode according to the user's usage environment. Customization of the usage environment includes, but is not limited to, indoor and outdoor environments and the applications used. For example, the embedded unit provides an operating mode that reduces battery consumption when the user uses the device outdoors. The embedded unit can also provide a high-performance operating mode when the user uses the device indoors. For example, the embedded unit automatically adjusts the AI's operating mode according to the user's usage environment. Furthermore, the embedded unit can adjust the operating mode in real time when the user uses the device while on the move. For example, the embedded unit selects the optimal operating mode based on the user's location information. By customizing the operating mode according to the usage environment, it is possible to provide optimal operation according to the user's needs.

[0087] The embedding unit estimates the user's emotions and determines the embedding priority based on the estimated user emotions. The embedding unit estimates the user's emotions and determines the embedding priority based on the estimated emotions. The embedding priority may be determined based on, for example, the importance and urgency of the task, but is not limited to, these examples. For example, the embedding unit may increase the embedding priority when the user is relaxed. The embedding unit may also decrease the embedding priority when the user is stressed. For example, the embedding unit dynamically adjusts the embedding priority according to the user's emotional state. Furthermore, when the user is excited, the embedding unit may adjust the embedding priority to embed the AI ​​at an appropriate time. For example, the embedding unit may monitor the user's emotional state in real time and optimize the embedding priority. By determining the embedding priority based on the user's emotions, more important embeddings can be prioritized. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0088] The embedded unit adjusts the operation of the AI ​​taking into account the battery life of the tablet device. The embedded unit adjusts the operation of the AI ​​taking into account the battery life of the tablet device. Optimization of battery life includes, but is not limited to, battery consumption patterns and power-saving modes, for example. For example, the embedded unit sets the operation of the AI ​​to a low-power consumption mode to reduce battery consumption. The embedded unit can also optimize the operation of the AI ​​to extend battery life. For example, the embedded unit automatically adjusts the operation mode of the AI ​​according to the remaining battery level. Furthermore, the embedded unit can analyze battery consumption patterns and select the optimal operation mode. For example, the embedded unit optimizes the operation of the AI ​​based on the battery consumption pattern. In this way, optimizing the operation of the AI ​​taking into account battery life can extend the usage time of the device.

[0089] The embedded unit incorporates additional functions for enhancing the security functions of the tablet device. The embedded unit incorporates additional functions for enhancing the security functions of the tablet device. Enhanced security functions include, but are not limited to, encryption technology and authentication methods, for example. The embedded unit enhances the security of the tablet device, for example, by incorporating an AI-based facial recognition function. The embedded unit can also incorporate an AI-based fingerprint authentication function. For example, the embedded unit can enhance access control of the tablet device using fingerprint authentication technology. The embedded unit can also incorporate an AI-based voice recognition function. For example, the embedded unit can enhance the security of the tablet device using voice recognition technology. This enhances the security functions, thereby improving the safety of the device.

[0090] The instruction unit estimates the user's emotions and adjusts the timing of the delivery instruction based on the estimated user emotions. The instruction unit estimates the user's emotions and adjusts the timing of the delivery instruction based on the estimated emotions. Examples of adjustments to the timing of the delivery instruction include, but are not limited to, a delivery schedule and a pickup time. For example, the instruction unit may advance the timing of the delivery instruction if the user is relaxed. The instruction unit may also delay the timing of the delivery instruction if the user is stressed. For example, the instruction unit dynamically adjusts the timing of the delivery instruction according to the user's emotional state. Furthermore, if the user is excited, the instruction unit may adjust the timing of the delivery instruction to perform delivery at an appropriate time. For example, the instruction unit monitors the user's emotional state in real time and optimizes the timing of the delivery instruction. By adjusting the timing of the delivery instruction based on the user's emotions, delivery can be performed at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0091] The instruction unit issues a delivery instruction taking into consideration the time period when the designated person is available to receive the package. The instruction unit issues a delivery instruction taking into consideration the time period when the designated person is available to receive the package. Consideration of the available time period for receiving the package includes, but is not limited to, the designated time period and the date when the package is available to receive the package. For example, the instruction unit issues an optimal delivery time taking into consideration the time period when the designated person is available to receive the package. The instruction unit can also issue a delivery instruction for a time period when the designated person is available to receive the package by referring to the schedule of the designated person. For example, the instruction unit refers to the past receiving history of the designated person to indicate the optimal delivery time. Furthermore, the instruction unit can also optimize the delivery schedule based on the available time period for receiving the package. For example, the instruction unit issues instructions to the delivery company based on the available time period for receiving the package. In this way, by taking into consideration the available time period for receiving the package, the designated person can be sure to receive the package.

[0092] The instruction unit selects the optimal delivery method taking into consideration the geographical conditions of the delivery destination. The instruction unit selects the optimal delivery method taking into consideration the geographical conditions of the delivery destination. Consideration of geographical conditions includes, for example, the topography and traffic conditions of the delivery destination, but is not limited to these examples. For example, the instruction unit selects a rapid delivery method when the delivery destination is in an urban area. The instruction unit can also select an efficient delivery method when the delivery destination is in a suburban area. For example, the instruction unit selects the optimal delivery method when the delivery destination is in a remote area. Furthermore, the instruction unit can optimize the delivery schedule based on the geographical conditions. For example, the instruction unit issues instructions to the delivery company based on the geographical conditions of the delivery destination. In this way, efficient and rapid delivery is achieved by taking geographical conditions into consideration.

[0093] The instruction unit estimates the user's emotions and determines the priority of delivery instructions based on the estimated user emotions. The instruction unit estimates the user's emotions and determines the priority of delivery instructions based on the estimated emotions. The determination of delivery instruction priorities includes, but is not limited to, the urgency and importance of delivery, for example. For example, the instruction unit increases the priority of delivery instructions when the user is relaxed. The instruction unit can also decrease the priority of delivery instructions when the user is stressed. For example, the instruction unit dynamically adjusts the priority of delivery instructions according to the user's emotional state. Furthermore, the instruction unit can adjust the priority of delivery instructions to deliver at an appropriate time when the user is excited. For example, the instruction unit monitors the user's emotional state in real time and optimizes the priority of delivery instructions. By determining the priority of delivery instructions based on the user's emotions, important deliveries can be prioritized. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0094] The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. Confirmed contact information includes, for example, a telephone number and an email address, but is not limited to these examples. The instruction unit automatically checks the contact information of the designated person and issues delivery instructions. Furthermore, if the contact information of the designated person is changed, the instruction unit can automatically update the contact information and issue delivery instructions. For example, the instruction unit detects changes in the contact information in real time and updates the delivery instructions. Furthermore, the instruction unit can select an optimal delivery method based on the contact information. For example, the instruction unit selects an optimal delivery company by referring to the contact information of the designated person. In this way, accurate delivery instructions can be issued by automatically checking the contact information of the designated person.

[0095] The instruction unit adds a function for tracking the delivery status in real time. The instruction unit adds a function for tracking the delivery status in real time. Delivery status tracking includes, for example, GPS tracking and delivery status update methods, but is not limited to these examples. For example, the instruction unit tracks the delivery status in real time and notifies a designated person. The instruction unit can also track the delivery status in real time and notify a user. For example, the instruction unit monitors the progress of the delivery status in real time and notifies a user. Furthermore, the instruction unit can select an optimal delivery method based on the delivery status. For example, the instruction unit tracks the delivery status in real time and selects an optimal delivery company. In this way, the delivery progress can be confirmed by tracking the delivery status in real time.

[0096] The dialogue unit estimates the user's emotions and adjusts the content of the dialogue based on the estimated user emotions. The dialogue unit estimates the user's emotions and adjusts the content of the dialogue based on the estimated emotions. Examples of dialogue content adjustment include, but are not limited to, the topic and tone of the dialogue. For example, if the user is relaxed, the dialogue unit provides a dialogue with relaxing content. Furthermore, if the user is stressed, the dialogue unit can also provide a dialogue with content that alleviates stress. For example, the dialogue unit dynamically adjusts the content of the dialogue according to the user's emotional state. Furthermore, if the user is excited, the dialogue unit can also provide a dialogue with content that alleviates excitement. For example, the dialogue unit monitors the user's emotional state in real time and optimizes the content of the dialogue. This allows for more appropriate dialogue by adjusting the content of the dialogue based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The dialogue unit customizes the tone of the dialogue according to the current situation of the designated person. The dialogue unit customizes the tone of the dialogue according to the current situation of the designated person. Customization of the tone of the dialogue includes, but is not limited to, the atmosphere and the language used in the dialogue. For example, if the designated person is relaxed, the dialogue unit may use a calm tone. Furthermore, if the designated person is stressed, the dialogue unit may use an encouraging tone. For example, the dialogue unit dynamically adjusts the tone of the dialogue according to the emotional state of the designated person. Furthermore, if the designated person is excited, the dialogue unit may use a calming tone. For example, the dialogue unit monitors the emotional state of the designated person in real time and optimizes the tone of the dialogue. This allows the dialogue to be more appropriate by customizing the tone of the dialogue according to the situation of the designated person.

[0098] The dialogue unit estimates the user's emotions and determines the priority of dialogues based on the estimated emotions. The dialogue unit estimates the user's emotions and determines the priority of dialogues based on the estimated emotions. The dialogue priority determination includes, but is not limited to, the importance and urgency of the dialogues. For example, the dialogue unit may increase the priority of a dialogue when the user is relaxed. The dialogue unit may also decrease the priority of a dialogue when the user is stressed. For example, the dialogue unit dynamically adjusts the priority of a dialogue according to the user's emotional state. Furthermore, when the user is excited, the dialogue unit may adjust the priority of a dialogue to conduct the dialogue at an appropriate time. For example, the dialogue unit monitors the user's emotional state in real time and optimizes the priority of the dialogues. By determining the priority of dialogues based on the user's emotions, important dialogues can be prioritized. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0099] The dialogue unit analyzes the social media activity of the designated person and reflects it in the dialogue content. The dialogue unit analyzes the social media activity of the designated person and reflects it in the dialogue content. Analysis of social media activity includes, but is not limited to, analysis of posted content and analysis of followers, for example. The dialogue unit reflects, for example, words and phrases frequently used by the designated person on social media in the dialogue content. The dialogue unit can also analyze the designated person's social media activity patterns and reflect it in the dialogue content. For example, the dialogue unit analyzes the posted content of the designated person and customizes the dialogue content based on the designated person's interests and concerns. Furthermore, the dialogue unit can optimize the dialogue content based on information shared by the designated person on social media. For example, the dialogue unit analyzes the reactions of the designated person's followers and reflects them in the dialogue content. In this way, by analyzing social media activity, it is possible to provide dialogue content that is more in line with reality.

[0100] The dialogue unit provides a topic specific to a region by taking into account the geographical location information of the designated person. The dialogue unit provides a topic specific to a region by taking into account the geographical location information of the designated person. Examples of collecting geographical location information include, but are not limited to, collecting GPS data and analyzing location information. The dialogue unit, for example, reflects topics specific to the region where the designated person lives in the dialogue content. The dialogue unit can also reflect local culture and customs in the dialogue content based on the geographical location information of the designated person. For example, the dialogue unit incorporates information about places frequently visited by the designated person into the dialogue content. Furthermore, the dialogue unit can also reflect information about local events and ceremonies in the dialogue content. For example, the dialogue unit collects data about local festivals and traditional events and incorporates it into the dialogue content. In this way, local topics can be provided by taking into account the geographical location information.

[0101] The stopping unit estimates the user's emotion and adjusts the timing of stopping the service based on the estimated emotion. The stopping unit estimates the user's emotion and adjusts the timing of stopping the service based on the estimated emotion. The adjustment of the timing of stopping the service includes, but is not limited to, trigger conditions for stopping the service and post-stop processing, for example. For example, the stopping unit may advance the timing of stopping the service if the user is relaxed. The stopping unit may also delay the timing of stopping the service if the user is stressed. For example, the stopping unit dynamically adjusts the timing of stopping the service according to the user's emotional state. Furthermore, the stopping unit may adjust the timing of stopping the service to stop the service at an appropriate time if the user is excited. For example, the stopping unit monitors the user's emotional state in real time and optimizes the timing of stopping the service. This allows the service to be stopped at a more appropriate time by adjusting the timing of stopping the service based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0102] The stop unit issues the stop notification taking into account the emotional state of the designated person. The stop unit issues the stop notification taking into account the emotional state of the designated person. Examples of consideration of the emotional state include, but are not limited to, emotion recognition technology and emotion evaluation criteria. For example, if the designated person is relaxed, the stop unit issues the stop notification in a calm tone. Furthermore, if the designated person is feeling stressed, the stop unit can also issue the stop notification in an encouraging tone. For example, the stop unit dynamically adjusts the tone of the stop notification according to the emotional state of the designated person. Furthermore, if the designated person is excited, the stop unit can also issue the stop notification in a calming tone. For example, the stop unit monitors the emotional state of the designated person in real time and optimizes the tone of the stop notification. In this way, the stop notification can be issued in a more appropriate tone by taking into account the emotional state of the designated person.

[0103] The stopping unit adds a function to safely back up data on the tablet device when the service is stopped. The stopping unit adds a function to safely back up data on the tablet device when the service is stopped. Data backup includes, for example, selection of backup frequency and backup destination, but is not limited to these examples. For example, the stopping unit backs up data on the tablet device to the cloud when the service is stopped. The stopping unit can also back up data on the tablet device to external storage when the service is stopped. For example, the stopping unit encrypts the data before backing it up. Furthermore, the stopping unit can automate the data backup procedure. For example, the stopping unit automatically performs data backup when the service is stopped. This ensures data protection by safely backing up the data.

[0104] The stopping unit estimates the user's emotions and determines the priority of service stop based on the estimated user emotions. The stopping unit estimates the user's emotions and determines the priority of service stop based on the estimated emotions. The determination of the service stop priority includes, for example, but is not limited to, the urgency and importance of the stop. For example, the stopping unit may increase the priority of service stop when the user is relaxed. The stopping unit may also decrease the priority of service stop when the user is stressed. For example, the stopping unit dynamically adjusts the priority of service stop according to the user's emotional state. Furthermore, the stopping unit may adjust the priority of service stop to stop the service at an appropriate time when the user is excited. For example, the stopping unit monitors the user's emotional state in real time and optimizes the priority of service stop. This allows important services to be stopped with priority by determining the priority of service stop based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0105] The stop unit automatically checks the contact information of the designated person and issues a stop notification. The stop unit automatically checks the contact information of the designated person and issues a stop notification. Confirmation of the contact information includes, for example, a phone number and an email address, but is not limited to these examples. The stop unit automatically checks, for example, the contact information of the designated person and issues a stop notification. Furthermore, if the contact information of the designated person is changed, the stop unit can automatically update the contact information and issue a stop notification. For example, the stop unit detects changes in the contact information in real time and updates the stop notification. Furthermore, the stop unit can select an optimal stop notification method based on the contact information. For example, the stop unit selects an optimal notification method by referring to the contact information of the designated person. In this way, an accurate stop notification can be issued by automatically checking the contact information of the designated person.

[0106] The stopping unit incorporates an additional function for enhancing the security functions of the tablet device when stopped. The stopping unit incorporates an additional function for enhancing the security functions of the tablet device when stopped. Enhanced security functions include, for example, encryption technology and authentication methods, but are not limited to such examples. The stopping unit, for example, enhances the security of the tablet device by incorporating an AI facial recognition function. The stopping unit can also incorporate an AI fingerprint authentication function. For example, the stopping unit uses fingerprint authentication technology to enhance access control of the tablet device. Furthermore, the stopping unit can also incorporate an AI voice recognition function. For example, the stopping unit uses voice recognition technology to enhance the security of the tablet device. This enhances the security functions and improves the safety of the device.

[0107] The request unit estimates the user's emotions and adjusts the timing of the return request based on the estimated user emotions. The request unit estimates the user's emotions and adjusts the timing of the return request based on the estimated emotions. Examples of adjustments to the timing of the return request include, but are not limited to, the method of notifying the user of the return request and the return deadline. For example, the request unit may advance the timing of the return request if the user is relaxed. The request unit may also delay the timing of the return request if the user is stressed. For example, the request unit dynamically adjusts the timing of the return request according to the user's emotional state. Furthermore, if the user is excited, the request unit may adjust the timing of the return request to make the return request at an appropriate time. For example, the request unit monitors the user's emotional state in real time and optimizes the timing of the return request. This allows the return request to be made at a more appropriate time by adjusting the timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0108] The request unit makes a return request taking into consideration the time period during which the designated person can return the item. The request unit makes a return request taking into consideration the time period during which the designated person can return the item. Examples of the time period during which the designated person can return the item include, but are not limited to, the designated time period and the date on which the item can be returned. For example, the request unit requests the optimal return time taking into consideration the time period during which the designated person can return the item. The request unit can also make a return request during a time period during which the designated person can return the item by referring to the schedule of the designated person. For example, the request unit can request the optimal return time by referring to the past return history of the designated person. Furthermore, the request unit can optimize the return schedule based on the time period during which the designated person can return the item. For example, the request unit issues instructions to the return company based on the time period during which the designated person can return the item. In this way, by taking into consideration the time period during which the designated person can return the item, the designated person can be reliably returned.

[0109] The request unit estimates the user's emotions and determines the priority of return requests based on the estimated user emotions. The request unit estimates the user's emotions and determines the priority of return requests based on the estimated emotions. The determination of the priority of return requests includes, but is not limited to, the urgency and importance of the return. For example, the request unit may increase the priority of the return request if the user is relaxed. The request unit may also decrease the priority of the return request if the user is stressed. For example, the request unit dynamically adjusts the priority of the return request according to the user's emotional state. Furthermore, if the user is excited, the request unit may adjust the priority of the return request to make the return request at an appropriate time. For example, the request unit may monitor the user's emotional state in real time and optimize the priority of the return request. By determining the priority of return requests based on the user's emotions, important return requests can be prioritized. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0110] The requesting unit automatically checks the contact information of the designated person and makes a return request. The requesting unit automatically checks the contact information of the designated person and makes a return request. Examples of confirmed contact information include, but are not limited to, a phone number and an email address. For example, the requesting unit automatically checks the contact information of the designated person and makes a return request. Furthermore, if the contact information of the designated person is changed, the requesting unit can automatically update the contact information and make a return request. For example, the requesting unit detects changes in the contact information in real time and updates the return request. Furthermore, the requesting unit can select an optimal return request method based on the contact information. For example, the requesting unit selects an optimal return request method by referring to the contact information of the designated person. In this way, an accurate return request can be made by automatically checking the contact information of the designated person.

[0111] The deletion unit estimates the user's emotions and adjusts the timing of data deletion based on the estimated user emotions. The deletion unit estimates the user's emotions and adjusts the timing of data deletion based on the estimated emotions. Examples of adjusting the timing of data deletion include, but are not limited to, trigger conditions for deletion and post-deletion processing. For example, the deletion unit may advance the timing of data deletion when the user is relaxed. The deletion unit may also delay the timing of data deletion when the user is stressed. For example, the deletion unit dynamically adjusts the timing of data deletion according to the user's emotional state. Furthermore, the deletion unit may adjust the timing of data deletion to delete data at an appropriate time when the user is excited. For example, the deletion unit monitors the user's emotional state in real time and optimizes the timing of data deletion. By adjusting the timing of data deletion based on the user's emotions, data can be deleted at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0112] The deletion unit issues a deletion notification taking into account the emotional state of the designated person. The deletion unit issues a deletion notification taking into account the emotional state of the designated person. Examples of consideration of the emotional state include, but are not limited to, emotion recognition technology and emotion evaluation criteria. For example, if the designated person is relaxed, the deletion unit issues a deletion notification in a calm tone. Furthermore, if the designated person is stressed, the deletion unit can also issue a deletion notification in an encouraging tone. For example, the deletion unit dynamically adjusts the tone of the deletion notification according to the emotional state of the designated person. Furthermore, if the designated person is excited, the deletion unit can also issue a deletion notification in a calming tone. For example, the deletion unit monitors the emotional state of the designated person in real time and optimizes the tone of the deletion notification. In this way, the deletion notification can be issued in a more appropriate tone by taking into account the emotional state of the designated person.

[0113] The deletion unit estimates the user's emotions and determines the priority of data deletion based on the estimated user emotions. The deletion unit estimates the user's emotions and determines the priority of data deletion based on the estimated emotions. The data deletion priority may be determined based on, for example, the urgency and importance of deletion, but is not limited to, examples. For example, the deletion unit may increase the priority of data deletion when the user is relaxed. The deletion unit may also decrease the priority of data deletion when the user is stressed. For example, the deletion unit dynamically adjusts the priority of data deletion according to the user's emotional state. Furthermore, the deletion unit may adjust the priority of data deletion when the user is excited, thereby deleting data at an appropriate time. For example, the deletion unit may monitor the user's emotional state in real time and optimize the priority of data deletion. By determining the priority of data deletion based on the user's emotions, important data can be deleted preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0114] The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. Confirmation of the contact information includes, for example, a phone number and an email address, but is not limited to these examples. The deletion unit automatically checks the contact information of the designated person and issues a deletion notification. Furthermore, if the contact information of the designated person is changed, the deletion unit can automatically update the contact information and issue a deletion notification. For example, the deletion unit detects changes in the contact information in real time and updates the deletion notification. Furthermore, the deletion unit can select an optimal deletion notification method based on the contact information. For example, the deletion unit selects an optimal notification method by referring to the contact information of the designated person. In this way, an accurate deletion notification can be issued by automatically checking the contact information of the designated person.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] The learning unit can also estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, it will prioritize learning data on the voice and speaking style in a relaxed state. Also, if the user is stressed, it can collect data on the voice and speaking style in a stressed state and reflect this in the training data. Furthermore, if the user is excited, it can collect data on the voice and speaking style in an excited state and incorporate it into the training data. In this way, by selecting training data based on the user's emotions, it is possible to generate more appropriate AI.

[0117] The request unit can also provide options for the return method when requesting the return of the tablet device. For example, if it is difficult for the person designated by the user to return the device by mail, the request unit can guide the user to a nearby return location. A return label can also be enclosed with the return request notice to make the return easier. Furthermore, detailed instructions on the return procedure can be included in the return request notice to enable the designated person to return the device smoothly. In this way, providing options for the return method makes it easier for the designated person to return the device.

[0118] The deletion unit may also have a function to temporarily back up data before deletion when deleting data. For example, the deletion unit may temporarily back up data in the tablet device to cloud storage before deleting the data. The deletion unit may also back up data to external storage before deleting the data. Furthermore, the deletion unit may ask the user for confirmation of backup before deleting the data and execute deletion only after obtaining consent. In this way, data protection is achieved by performing a temporary backup when deleting data.

[0119] The learning unit can also estimate the user's emotions and adjust the frequency of learning based on the estimated emotions. For example, if the user is relaxed, the learning frequency can be increased to collect data. Also, if the user is feeling stressed, the learning frequency can be decreased to reduce the burden on the user. Furthermore, if the user is excited, the learning frequency can be adjusted to collect appropriate data. In this way, by adjusting the learning frequency based on the user's emotions, appropriate data can be collected while reducing the burden on the user.

[0120] The learning unit can also analyze the user's past dialogue history and select an appropriate learning algorithm. For example, it can analyze the words and phrases frequently used by the user and adjust the learning algorithm based on that. It can also analyze the user's dialogue patterns and select the optimal learning algorithm. Furthermore, it can customize the learning data based on the analysis results of the dialogue history. This makes it possible to select the optimal learning algorithm by analyzing the past dialogue history.

[0121] The learning unit can also customize learning data based on the user's lifestyle and hobbies. For example, it can learn conversation data that takes place during a specific time period based on the user's lifestyle. It can also prioritize learning conversation data related to the user's hobbies. Furthermore, it can customize and learn related conversation data based on the user's interests. This allows for the generation of more personalized AI by customizing learning data based on the user's lifestyle and hobbies.

[0122] The learning unit can also estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, it will prioritize learning data on the voice and speaking style in a relaxed state. Also, if the user is stressed, it can collect data on the voice and speaking style in a stressed state and reflect this in the training data. Furthermore, if the user is excited, it can collect data on the voice and speaking style in an excited state and incorporate it into the training data. In this way, by selecting training data based on the user's emotions, it is possible to generate more appropriate AI.

[0123] The learning unit can also analyze a user's social media activity and reflect it in the learning data. For example, words and phrases frequently used by the user on social media can be reflected in the learning data. The learning unit can also analyze a user's social media activity patterns and reflect them in the learning data. Furthermore, the learning data can be optimized based on the information the user shares on social media. This makes it possible to generate learning data that is more in line with reality by analyzing social media activity.

[0124] The learning unit can also incorporate regional language and culture into the training data, taking into account the user's geographical location information. For example, the dialect and expressions of the region where the user lives can be incorporated into the training data. Regional culture and customs can also be reflected in the training data based on the user's geographical location information. Furthermore, information about regional events and ceremonies can also be reflected in the training data. In this way, by taking geographical location information into account, it is possible to generate AI that reflects regional language and culture.

[0125] The embedding unit can also estimate the user's emotions and adjust the timing of embedding based on the estimated emotions. For example, if the user is relaxed, the embedding timing can be advanced. Also, if the user is feeling stressed, the embedding timing can be delayed. Furthermore, if the user is excited, the embedding timing can be adjusted to embed the AI ​​at an appropriate time. In this way, by adjusting the embedding timing based on the user's emotions, it is possible to embed the AI ​​at a more appropriate time.

[0126] The processing flow of the second embodiment will be briefly explained below.

[0127] Step 1: The learning unit generates an AI that has learned the user's voice, speaking style, and personality. Specifically, the user's voice is recorded and speech features are extracted using speech recognition technology. The user's speaking style is also recorded and the characteristics of the speaking style are analyzed using natural language processing technology. The user is then given a personality assessment test and their personality is evaluated based on the results. Step 2: The embedding unit embeds the AI ​​generated by the learning unit into the tablet device. Specifically, it installs the AI ​​software on the tablet device and performs the necessary settings. Step 3: The instruction unit instructs the delivery of the tablet device to a person designated by the user after the user's death. Specifically, the instruction unit checks the address of the person designated by the user, selects an appropriate delivery company, and instructs the delivery. Step 4: When the tablet device is delivered to the designated person, the dialogue unit uses AI to carry out a dialogue. Specifically, the AI ​​reproduces the voice and speaking style of the deceased person and engages in a dialogue with the designated person. Step 5: The termination unit will terminate the AI-based service a predetermined period of time after the user's death. Specifically, the service will be terminated 49 days after the user's death and the tablet device will be requested to be returned.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats including 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. The AIs other than the generation AI are, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but are not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or in whole by AI, but are not limited to these 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.

[0130] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, processing for learning the user's voice, speaking style, and personality is performed by the specific processing unit 290 of the data processing device 12. The embedding unit is realized by, for example, the control unit 46A of the smart device 14, and embeds the generated AI into the tablet terminal. The instruction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and instructs the delivery of the tablet terminal after the user's death. The dialogue unit is realized by, for example, the control unit 46A of the smart device 14, and engages in dialogue with a designated person using AI. The stopping unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and stops the service when a predetermined period has elapsed after the user's death. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0132] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0133] 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.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] 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.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] 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.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0146] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, processing for learning the user's voice, speaking style, and personality is performed by the specific processing unit 290 of the data processing device 12. The embedding unit is realized by, for example, the control unit 46A of the smart glasses 214, and embeds the generated AI into the tablet terminal. The instruction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and instructs the delivery of the tablet terminal after the user's death. The dialogue unit is realized by, for example, the control unit 46A of the smart glasses 214, and engages in dialogue with a designated person using AI. The stopping unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and stops the service when a predetermined period of time has elapsed after the user's death. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0148] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0149] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] 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.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] 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.

[0156] 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.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0162] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, processing for learning the user's voice, speaking style, and personality is performed by the specific processing unit 290 of the data processing device 12. The embedding unit is realized by, for example, the control unit 46A of the headset-type terminal 314, and embeds the generated AI into the tablet terminal. The instruction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and instructs the delivery of the tablet terminal after the user's death. The dialogue unit is realized by, for example, the control unit 46A of the headset-type terminal 314, and engages in dialogue with a designated person using AI. The stopping unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and stops the service when a predetermined period of time has elapsed after the user's death. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0166] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0167] 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.

[0168] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0171] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0172] 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.

[0173] 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.

[0174] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0175] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0177] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in one or more data formats, such as 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 identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0180] For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, processing for learning the user's voice, speaking style, and personality is performed by the specific processing unit 290 of the data processing device 12. The embedding unit is realized by, for example, the control unit 46A of the robot 414, and embeds the generated AI into the tablet terminal. The instruction unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and instructs the delivery of the tablet terminal after the user's death. The dialogue unit is realized by, for example, the control unit 46A of the robot 414, and engages in dialogue with a designated person using AI. The stopping unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and stops the service when a predetermined period of time has elapsed after the user's death. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0181] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0182] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0183] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0184] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0185] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0186] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0187] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0188] 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.

[0189] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0190] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0191] 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.

[0192] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0193] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0194] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0195] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0196] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0197] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0198] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0199] (Appendix 1) A learning unit that generates AI that learns the user's voice, speaking style, and personality; an embedding unit that embeds the AI ​​generated by the learning unit into a tablet device; an instruction unit that instructs delivery of the tablet device to a person designated by the user after the user's death; The tablet terminal includes a dialogue unit that uses the AI ​​to dialogue with a person designated by the user; A system comprising: a stopping unit that stops the service provided by the AI ​​after a predetermined period of time has passed since the death of the user. (Appendix 2) The tablet terminal is and a request unit that requests the return of the tablet device when the service provided by the AI ​​is stopped by the stop unit. 2. The system of claim 1. (Appendix 3) The tablet terminal is a deletion unit that deletes data when the service provided by the AI ​​is stopped by the stop unit; 2. The system of claim 1. (Appendix 4) The learning unit Estimate the user's emotions and select training data based on the estimated user emotions. 2. The system of claim 1. (Appendix 5) The learning unit Analyze the user's past interaction history and select the appropriate learning algorithm 2. The system of claim 1. (Appendix 6) The learning unit Customize learning data based on the user's lifestyle and hobbies 2. The system of claim 1. (Appendix 7) The learning unit Estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1. (Appendix 8) The learning unit Analyze users' social media activity and incorporate it into learning data 2. The system of claim 1. (Appendix 9) The learning unit Incorporating local language and culture into training data based on the user's geographic location 2. The system of claim 1. (Appendix 10) The embedding portion is Estimate the user's emotions and adjust the timing of embedding based on the estimated user emotions. 2. The system of claim 1. (Appendix 11) The embedding portion is Generate AI optimized for the hardware characteristics of tablet devices 2. The system of claim 1. (Appendix 12) The embedding portion is Customize AI operation modes according to the user's environment 2. The system of claim 1. (Appendix 13) The embedding portion is Estimate user emotions and prioritize built-ins based on the estimated user emotions 2. The system of claim 1. (Appendix 14) The embedding portion is Adjusting AI behavior taking into account tablet device battery life 2. The system of claim 1. (Appendix 15) The embedding portion is Incorporating additional features to enhance the security of tablet devices 2. The system of claim 1. (Appendix 16) The instruction unit Estimates user emotions and adjusts delivery instruction timing based on the estimated user emotions. 2. The system of claim 1. (Appendix 17) The instruction unit Give delivery instructions taking into account the designated person's available time slot for receiving the item 2. The system of claim 1. (Appendix 18) The instruction unit Select the optimal delivery method taking into account the geographical location of the delivery destination 2. The system of claim 1. (Appendix 19) The instruction unit Estimate user emotions and prioritize delivery instructions based on the estimated user emotions 2. The system of claim 1. (Appendix 20) The instruction unit Automatically check the contact information of designated individuals and provide delivery instructions 2. The system of claim 1. (Appendix 21) The instruction unit Add real-time tracking of delivery status 2. The system of claim 1. (Appendix 22) The dialogue unit Estimate the user's emotions and adjust the content of the dialogue based on the estimated user emotions. 2. The system of claim 1. (Appendix 23) The dialogue unit Customize the tone of the conversation depending on the designated person's current situation 2. The system of claim 1. (Appendix 24) The dialogue unit Estimate the user's emotions and prioritize interactions based on the estimated user emotions. 2. The system of claim 1. (Appendix 25) The dialogue unit Analyze the social media activity of designated individuals and reflect it in the conversations 2. The system of claim 1. (Appendix 26) The dialogue unit Provides localized topics based on the geographic location of the designated person 2. The system of claim 1. (Appendix 27) The stop portion is Estimate user emotions and adjust the timing of service outages based on the estimated user emotions. 2. The system of claim 1. (Appendix 28) The stop portion is Consider the emotional state of the designated person when issuing a stop notification 2. The system of claim 1. (Appendix 29) The stop portion is Add a function to safely back up data on tablet devices when the device is stopped 2. The system of claim 1. (Appendix 30) The stop portion is Estimate user sentiment and prioritize service outages based on the estimated sentiment 2. The system of claim 1. (Appendix 31) The stop portion is Automatically verify contact information of designated individuals and notify them of the suspension 2. The system of claim 1. (Appendix 32) The stop portion is Incorporating additional features to enhance the security of tablet devices when they are down 2. The system of claim 1. (Appendix 33) The request unit: Estimate the user's emotions and adjust the timing of the return request based on the estimated user emotions. 3. The system of claim 2. (Appendix 34) The request unit: Requests for return are made taking into consideration the designated person's available time for return. 3. The system of claim 2. (Appendix 35) The request unit: Estimate the user's emotions and prioritize return requests based on the estimated user emotions. 3. The system of claim 2. (Appendix 36) The request unit: Automatically check the contact information of the designated person and request the return 3. The system of claim 2. (Appendix 37) The deletion unit Estimate user emotions and adjust the timing of data deletion based on the estimated user emotions 4. The system of claim 3. (Appendix 38) The deletion unit Consider the emotional state of the designated person when making a takedown notice 4. The system of claim 3. (Appendix 39) The deletion unit Estimate user sentiment and prioritize data deletion based on the estimated user sentiment 4. The system of claim 3. (Appendix 40) The deletion unit Automatically verify contact information for designated individuals and provide takedown notices 4. The system of claim 3. [Explanation of symbols]

[0200] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A learning unit that generates AI that has learned the user's voice, speaking style, and personality; an embedding unit that embeds the AI ​​generated by the learning unit into a tablet terminal; an instruction unit that instructs delivery of the tablet device to a person designated by the user after the user's death; The tablet terminal includes a dialogue unit that uses the AI ​​to dialogue with a person designated by the user; A stopping unit that stops the service provided by the AI ​​when a predetermined period of time has elapsed after the death of the user; A system including: a request unit that requests the return of the tablet terminal when the AI ​​service is stopped by the stop unit, The learning unit estimates the user's emotion based on at least one of the user's facial expression, voice, and biometric data, and when the estimated emotion of the user is relaxed, preferentially selects data of the voice and speaking style in a relaxed state as learning data. A system characterized by:

2. The tablet terminal is a deletion unit that deletes data when the service provided by the AI ​​is stopped by the stop unit; 2. The system of claim 1.

3. The system described in Claim 1, characterized in that the learning unit selects data of the voice and speaking style under stress as learning data when the estimated emotion of the user is stress.

4. The learning unit Analyzing the user's past interaction history and selecting an appropriate learning algorithm 2. The system of claim 1.

5. The learning unit Customize learning data based on the user's lifestyle and hobbies 2. The system of claim 1.

6. The learning unit Estimating the user's emotion and adjusting the frequency of learning based on the estimated user's emotion.

2. The system of claim 1.

7. The learning unit Analyzing the user's social media activity and reflecting it in the learning data 2. The system of claim 1.

8. The learning unit Incorporating local language and culture into the training data based on the user's geographic location.

2. The system of claim 1.

9. The embedding portion is Estimating the user's emotion and adjusting the timing of incorporation based on the estimated user's emotion.

2. The system of claim 1.

Images