system

Abstract

The system of the embodiment aims to utilize the user's personal data to generate AI prompts and provide appropriate answers. [Solution] A system according to an embodiment includes a collection unit, a generation unit, an input unit, and a provision unit. The collection unit collects personal data of a user. The generation unit generates a prompt based on the data collected by the collection unit. The input unit inputs the prompt generated by the generation unit to an AI. The provision unit provides the AI's answer.

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] Previous technologies had the problem of not effectively utilizing users' personal data to generate AI prompts and provide appropriate answers.

[0005] The system of the embodiment aims to utilize the user's personal data to generate AI prompts and provide appropriate answers. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a generation unit, an input unit, and a provision unit. The collection unit collects personal data of a user. The generation unit generates a prompt based on the data collected by the collection unit. The input unit inputs the prompt generated by the generation unit to the AI. The provision unit provides the AI's answer. [Effects of the Invention]

[0007] The system according to the embodiment can utilize the user's personal data to generate AI prompts and provide appropriate answers. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​Personal Prompter system according to an embodiment of the present invention utilizes a user's personal data to personalize AI responses. This system connects with data sources such as a smartwatch, a cashless app, and a calendar, automatically generating personalized prompts from those sources and inputting them into the AI. This eliminates the need for users to enter detailed information each time, allowing them to receive more appropriate answers and services. For example, the system collects the user's personal data, including health data from the smartwatch, purchase history from the cashless app, and schedule information from the calendar. Next, the AI ​​generates personalized prompts based on the collected data. These prompts are generated based on the user's current situation and past behavioral patterns. The generated prompts are input into the AI, which then provides the user with optimal answers and services. Furthermore, by utilizing the friend function, the AI ​​can automatically coordinate schedules with friends through inter-app collaboration. This allows users to communicate more smoothly with their friends. Furthermore, by employing MoE (Mixture of Experts), it is possible to derive even more accurate answers. This service does not rely on a specific AI generator, but acts as a hub connecting users with AI generators, which has the advantage of not limiting the AI ​​generators that can be used. This allows the AI ​​Personal Prompter system to use the user's personal data to personalize the AI's answers.

[0029] The AI ​​Personal Prompter system according to the embodiment includes a collection unit, a generation unit, an input unit, and a provision unit. The collection unit collects personal data of a user. The personal data of a user includes, but is not limited to, for example, a name, age, gender, location information, and browsing history. The collection unit collects, for example, health data from a smartwatch, purchase history from a cashless app, and schedule information from a calendar. The collection unit can also collect social media posts, email content, and location information. For example, the collection unit collects text, image, and video posts from social media, email subjects, email bodies, attachments, GPS data, Wi-Fi location information, and IP addresses. The generation unit generates prompts based on the data collected by the collection unit. Prompts may be in the form of questions, instructions, or information, for example, but are not limited to these. The generation unit generates prompts based on the user's current situation and past behavioral patterns. For example, the prompts are generated based on the user's current activity, current location, current mood, past purchase history, past search history, past travel history, and so on. The generation unit generates a prompt using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The input unit inputs the generated prompt to the AI. For example, the input unit inputs the generated prompt to the AI ​​and obtains the AI's answer. The provision unit provides the AI's answer to the user. For example, the provision unit provides the AI's answer to the user, allowing the user to receive an appropriate answer or service. As a result, the AI ​​Personal Prompter system according to the embodiment can personalize the AI's answer by utilizing the user's personal data.

[0030] The collection unit can collect the content of posts on SNS, the content of emails, and location information. The collection unit, for example, collects the content of posts on SNS. The content of posts on SNS includes text posts, image posts, video posts, etc. For example, the collection unit collects text, images, and videos posted by users on SNS. The collection unit can also collect the content of emails. The content of emails includes the subject, body, attachments, etc. For example, the collection unit collects the subject, body, and attachments of emails sent and received by users. The collection unit can also collect location information. Location information includes GPS data, Wi-Fi location information, IP address, etc. For example, the collection unit obtains the user's current location using GPS data, Wi-Fi location information, and IP address. By collecting the content of posts on SNS, the content of emails, and location information, a wider variety of data can be utilized. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the content of social media posts, email contents, and location information into the AI, allowing the AI ​​to automatically collect the data.

[0031] The generation unit can generate prompts based on the user's current situation or past behavioral patterns. The generation unit generates prompts based on, for example, the user's current situation. The current situation includes the user's current activity, current location, current mood, etc. For example, the generation unit generates prompts based on the user's current activity, current location, and current mood. The generation unit can also generate prompts based on the user's past behavioral patterns. Past behavioral patterns include the user's past purchase history, past search history, past travel history, etc. For example, the generation unit generates prompts based on the user's past purchases, search keywords, and travel locations. This allows the generation unit to generate prompts based on the user's current situation and past behavioral patterns, thereby providing more appropriate prompts. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's current situation and past behavioral patterns into the generation AI, which then automatically generates prompts.

[0032] The input unit can input the generated prompt to the AI. The input unit, for example, inputs the generated prompt to the AI. The generated prompt includes a question format, an instruction format, an information provision format, etc. For example, the input unit inputs the generated question format prompt to the AI ​​to obtain an answer from the AI. The input unit can also input the generated instruction format prompt to the AI ​​to obtain an instruction from the AI. The input unit can also input the generated information format prompt to the AI ​​to obtain information provided by the AI. In this way, by inputting the generated prompt to the AI, an answer from the AI ​​can be obtained. Some or all of the above-mentioned processing in the input unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the input unit can input the generated prompt to the AI, and the AI ​​can automatically generate an answer.

[0033] The providing unit can provide the AI's answer to the user. The providing unit, for example, provides the AI's answer to the user. The AI's answer can be in text format, audio format, image format, etc. For example, the providing unit can provide the AI's generated answer to the user in text format. The providing unit can also provide the AI's generated answer to the user in audio format. The providing unit can also provide the AI's generated answer to the user in image format. In this way, by providing the AI's answer to the user, the user can receive an appropriate answer or service. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide the AI's generated answer to the user, and the user can use the answer.

[0034] Furthermore, the AI ​​Personal Prompter system includes a linking unit that links the friend function. The linking unit links the friend function. For example, the linking unit acquires the user's friend list and coordinates schedules with friends. The linking unit coordinates schedules with friends based on the user's calendar information, for example. The linking unit can also acquire friends' calendar information and coordinate schedules with the user. In this way, by linking the friend function, the user can communicate smoothly with friends. Some or all of the above-described processing in the linking unit may be performed using AI, or may be performed without using AI. For example, the linking unit inputs the user's calendar information and friends' calendar information into AI, which can then automatically coordinate schedules.

[0035] Furthermore, the AI ​​Personal Prompter system includes an accuracy improvement unit that uses MoE to improve accuracy. The accuracy improvement unit uses MoE (Mixture of Experts) to improve accuracy. For example, the accuracy improvement unit combines multiple expert models to generate more accurate answers. For example, the accuracy improvement unit combines models from different fields of expertise to utilize the expertise of each field. The accuracy improvement unit can also integrate the output of each expert model to generate an optimal answer. In this way, by using MoE, even more accurate answers can be derived. Some or all of the above-described processing in the accuracy improvement unit may be performed using AI, or may be performed without using AI. For example, the accuracy improvement unit inputs the output of multiple expert models into AI, allowing the AI ​​to automatically generate an optimal answer.

[0036] The collection unit can analyze the user's past data collection history and select the optimal collection method. The collection unit, for example, analyzes the user's past data collection history. The data collection history includes the collection date and time, the type of collected data, and the collection frequency. For example, the collection unit analyzes the date, time, type, and frequency of data collected by the user in the past. Next, the collection unit selects the optimal collection method based on the analysis results. For example, the collection unit prioritizes collection of data sources that the user frequently used in the past. It is also possible to concentrate collection during specific time periods based on the user's past data collection history. It is also possible to select the most efficient collection method based on the user's past data collection history. In this way, the optimal collection method can be selected by analyzing the user's past data collection history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's past data collection history into AI, which can automatically select the optimal collection method.

[0037] The collection unit can filter data based on the user's current activity status and areas of interest when collecting data. For example, the collection unit takes into account the user's current activity status when collecting data. Activity status includes current work content, exercise status, rest, etc. For example, the collection unit can prioritize collecting health data when the user is exercising. Furthermore, the collection unit can prioritize collecting business-related data when the user is working. Furthermore, the collection unit can prioritize collecting data related to a hobby when the user is immersed in the hobby. Next, the collection unit filters data based on the user's areas of interest. Areas of interest include hobbies, topics of interest, and accounts followed. For example, the collection unit prioritizes collecting data related to a specific hobby. Furthermore, the collection unit can collect data related to topics in which the user is interested. Furthermore, the collection unit can collect data related to accounts followed by the user. In this way, by filtering data based on the user's current activity status and areas of interest, more relevant data can be collected. Some or all of the above-described processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection department can input the user's current activities and areas of interest into the AI, which can then automatically filter the data.

[0038] The collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information when collecting data. The collection unit, for example, considers the user's geographical location information when collecting data. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the collection unit can prioritize collecting data related to that area. Furthermore, if the user is traveling, the collection unit can prioritize collecting data related to the travel destination. Furthermore, if the user is at home, the collection unit can prioritize collecting data around the user's home. In this way, by taking the user's geographical location information into account, highly relevant data can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's geographical location information into AI, and the AI ​​can automatically collect highly relevant data preferentially.

[0039] The collection unit can analyze the user's social media activity and collect related data when collecting data. For example, the collection unit analyzes the user's social media activity when collecting data. Social media activity includes posted content, like history, follow relationships, etc. For example, if the user posts about a specific topic, the collection unit can collect data related to that topic. Also, if the user participates in a specific event, the collection unit can collect data related to that event. Also, if the user uses a specific hashtag, the collection unit can collect data related to that hashtag. In this way, related data can be collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input the user's social media activity into AI, and the AI ​​can automatically collect related data.

[0040] The generation unit can adjust the level of detail of the prompt based on important data of the user when generating the prompt. For example, the generation unit takes into account important data of the user when generating the prompt. Important data includes personal information, past purchase history, health data, etc. For example, the generation unit can generate a prompt including detailed health advice based on the user's health data. The generation unit can also generate a prompt including suggestions for related products based on the user's purchase history. The generation unit can also generate a prompt related to an appointment based on the user's calendar information. In this way, adjusting the level of detail of the prompt based on important data of the user can provide a more appropriate prompt. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input important data of the user into the generation AI, which can then automatically adjust the level of detail of the prompt.

[0041] The generation unit can apply different generation algorithms depending on the user's category when generating a prompt. The generation unit, for example, takes the user's category into consideration when generating a prompt. Categories include age group, interests, occupation, etc. For example, if the user belongs to the business category, the generation unit can apply a business-related algorithm to generate a prompt. Also, if the user belongs to the health category, the generation unit can apply a health-related algorithm to generate a prompt. Also, if the user belongs to the entertainment category, the generation unit can apply an entertainment-related algorithm to generate a prompt. In this way, by applying different generation algorithms depending on the user's category, more appropriate prompts can be provided. Some or all of the above-described processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's category into the generation AI, and the generation AI can automatically apply an appropriate algorithm to generate a prompt.

[0042] When generating prompts, the generation unit can determine the priority of prompts based on the time when the user collected data. For example, the generation unit considers the time when the user collected data when generating prompts. The time when data was collected includes the collection date and time, the collection frequency, and the collection period. For example, the generation unit can prioritize generating prompts based on data recently collected by the user. The generation unit can also adjust the priority of prompts based on data collected by the user in the past. The generation unit can also determine the priority of prompts based on data collected by the user during a specific time period. In this way, by determining the priority of prompts based on the time when the user collected data, more appropriate prompts can be provided. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the time when the user collected data into the generation AI, and the generation AI can automatically determine the priority of prompts.

[0043] The generation unit can adjust the order of prompts based on the user's relevance when generating prompts. For example, the generation unit considers the user's relevance when generating prompts. Relevance includes past behavioral history, degree of coincidence of interests, etc. For example, the generation unit prioritizes displaying prompts that are most relevant to the user's current situation. The generation unit can also adjust the order of prompts based on the user's past behavioral patterns. The generation unit can also optimize the order of prompts based on the user's areas of interest. In this way, adjusting the order of prompts based on the user's relevance can provide more appropriate prompts. Some or all of the above-described processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's relevance to the generation AI, and the generation AI can automatically adjust the order of prompts.

[0044] The input unit can select the optimal input method by analyzing the user's past input history when entering a prompt. The input unit, for example, analyzes the user's past input history when entering a prompt. The input history includes past input content, input frequency, input method, etc. For example, the input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The input unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The input unit can also select the most efficient input method based on the user's past input history. In this way, the optimal input method can be selected by analyzing the user's past input history. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's past input history into AI, which can then automatically select the optimal input method.

[0045] The input unit can customize the input means based on the user's current situation when inputting a prompt. For example, the input unit takes the user's current situation into consideration when inputting a prompt. The current situation includes the user's current activity, current location, current mood, etc. For example, the input unit can preferentially suggest voice input when the user is exercising. The input unit can also preferentially suggest text input when the user is working. The input unit can also suggest an input method related to a hobby when the user is immersed in that hobby. This allows for more appropriate input by customizing the input means based on the user's current situation. Some or all of the above-described processing in the input unit may be performed using, or without, AI. For example, the input unit can input the user's current situation to AI, and the AI ​​can automatically customize the input means.

[0046] The input unit can select the optimal input method by taking into account the user's geographical location information when inputting a prompt. The input unit, for example, considers the user's geographical location information when inputting a prompt. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the input unit can suggest an input method related to that area. Furthermore, if the user is traveling, the input unit can also suggest an input method related to the user's travel destination. Furthermore, if the user is at home, the input unit can also suggest an input method near the user's home. In this way, the optimal input method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's geographical location information to AI, and the AI ​​can automatically select the optimal input method.

[0047] The input unit can analyze the user's social media activity and suggest an input method when the user inputs a prompt. The input unit, for example, analyzes the user's social media activity when the user inputs a prompt. Social media activity includes the content of posts, like history, follow relationships, etc. For example, if the user posts about a specific topic, the input unit can suggest an input method related to the topic. Furthermore, if the user is participating in a specific event, the input unit can suggest an input method related to the event. Furthermore, if the user uses a specific hashtag, the input unit can suggest an input method related to the hashtag. In this way, the optimal input method can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the input unit may be performed, for example, using AI, or may be performed without using AI. For example, the input unit can input the user's social media activity into AI, which can then automatically suggest the optimal input method.

[0048] The providing unit can select the optimal display method by referring to the user's past answer history when providing an answer. The providing unit, for example, refers to the user's past answer history when providing an answer. The answer history includes past answer content, answer frequency, answer method, etc. For example, the providing unit preferentially provides display methods that the user has previously preferred. The providing unit can also select a display method suitable for a specific time period from the user's past answer history. The providing unit can also select the most efficient display method based on the user's past answer history. In this way, the optimal display method can be selected by referring to the user's past answer history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past answer history into AI, and the AI ​​can automatically select the optimal display method.

[0049] The providing unit can customize the answering method based on the user's current situation when providing an answer. For example, the providing unit takes the user's current situation into consideration when providing an answer. The current situation includes the user's current activity, current location, current mood, etc. For example, if the user is exercising, the providing unit can prioritize providing an audio answer. Also, if the user is at work, the providing unit can prioritize providing a text answer. Also, if the user is immersed in a hobby, the providing unit can provide an answering method related to that hobby. This allows for more appropriate answers by customizing the answering method based on the user's current situation. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input the user's current situation into AI, and the AI ​​can automatically customize the answering method.

[0050] The providing unit can select the optimal answering method by taking into account the user's geographical location information when providing an answer. For example, the providing unit can consider the user's geographical location information when providing an answer. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the providing unit can prioritize providing answers related to that area. Furthermore, if the user is traveling, the providing unit can prioritize providing answers related to the user's travel destination. Furthermore, if the user is at home, the providing unit can prioritize providing answers around the user's home. In this way, the optimal answering method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's geographical location information into AI, and the AI ​​can automatically select the optimal answering method.

[0051] When providing an answer, the providing unit can analyze the user's social media activity and suggest a means of answering. For example, the providing unit analyzes the user's social media activity when providing an answer. Social media activity includes the content of posts, like history, follow relationships, etc. For example, if the user posts about a specific topic, the providing unit can provide an answer related to that topic. Furthermore, if the user is participating in a specific event, the providing unit can also provide an answer related to that event. Furthermore, if the user uses a specific hashtag, the providing unit can also provide an answer related to that hashtag. In this way, by analyzing the user's social media activity, the optimal means of answering can be suggested. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity into AI, and the AI ​​can automatically suggest the optimal way of answering.

[0052] The collaboration unit can analyze the user's past collaboration history and select the optimal collaboration method at the time of collaboration. For example, the collaboration unit analyzes the user's past collaboration history at the time of collaboration. The collaboration history includes past collaboration content, collaboration frequency, collaboration method, etc. For example, the collaboration unit prioritizes suggesting collaboration methods that the user has frequently used in the past. The collaboration unit can also select a collaboration method suitable for a specific time period from the user's past collaboration history. The collaboration unit can also select the most efficient collaboration method based on the user's past collaboration history. In this way, the optimal collaboration method can be selected by analyzing the user's past collaboration history. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input the user's past collaboration history into AI, and the AI ​​can automatically select the optimal collaboration method.

[0053] The linking unit can select the optimal linking method by taking into account the user's geographical location information when linking. For example, the linking unit can consider the user's geographical location information when linking. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the linking unit can suggest a linking method related to that area. Furthermore, if the user is traveling, the linking unit can also suggest a linking method related to the user's travel destination. Furthermore, if the user is at home, the linking unit can suggest a linking method near the user's home. In this way, the optimal linking method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's geographical location information into AI, and the AI ​​can automatically select the optimal linking method.

[0054] The accuracy improvement unit can optimize the learning algorithm by referring to past learning data during learning. The accuracy improvement unit, for example, refers to past learning data during learning. The learning data includes past training data, labeled data, feedback data, etc. For example, the accuracy improvement unit selects an optimal algorithm based on the past learning data. The accuracy improvement unit can also extract specific patterns from the past learning data and optimize the algorithm. The accuracy improvement unit can also analyze the past learning data and adjust the parameters of the algorithm. In this way, the learning algorithm can be optimized by referring to the past learning data. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit can input past learning data into AI, and the AI ​​can automatically optimize the learning algorithm.

[0055] The accuracy improvement unit can weight the training data based on the time of data collection during training. For example, the accuracy improvement unit takes into account the time of data collection during training. The time of data collection includes the collection date and time, collection frequency, collection period, etc. For example, the accuracy improvement unit performs training by assigning a higher weight to recently collected data. The accuracy improvement unit can also perform training by assigning a lower weight to data collected in the past. The accuracy improvement unit can also perform weighting based on data collected during a specific time period. In this way, weighting the training data based on the time of data collection enables more appropriate training. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit can input the time of data collection into AI, and the AI ​​can automatically weight the training data.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] When collecting a user's personal data, the collection unit can adjust the frequency of data collection taking into account the remaining battery level of the user's device. For example, if the remaining battery level is low, the collection frequency can be reduced, and if the remaining battery level is sufficient, the collection frequency can be increased. The collection unit can also determine the priority of data collection based on the remaining battery level of the device. For example, if the remaining battery level is low, only highly important data can be collected with priority, and if the remaining battery level is sufficient, detailed data can be collected. This enables efficient data collection by taking into account the remaining battery level of the device.

[0058] When collecting user data, the collection unit can adjust the data collection method taking into account the user's internet connection status. For example, if the internet connection is unstable, the data can be stored locally and sent all at once when the connection is stable. The collection unit can also determine the priority of data collection based on the internet connection status. For example, if the connection is unstable, it can prioritize collecting only highly important data, and when the connection is stable, it can collect detailed data. This allows for efficient data collection by taking the internet connection status into account.

[0059] The generator may generate prompts taking into account the user's current weather information. For example, if it is raining, the generator may generate prompts related to indoor activities, and if it is sunny, the generator may generate prompts related to outdoor activities. The generator may also adjust the content of the prompts based on the weather information. For example, the generator may generate prompts related to hot drinks on cold days and prompts related to cold drinks on hot days. This allows the generator to provide more appropriate prompts by taking into account the weather information.

[0060] The input unit can adjust the prompt input method taking into account the user's device usage status. For example, if the user is using a smartphone, touch input can be prioritized, and if the user is using a personal computer, keyboard input can be prioritized. The input unit can also customize the input method based on the device usage status. For example, if the user is driving, voice input can be prioritized, and if the user is in a meeting, text input can be prioritized. This makes it possible to provide a more appropriate input method by taking into account the device usage status.

[0061] The providing unit can adjust the display method of the answer taking into account the screen size of the user's device. For example, a simple and highly visible display method can be provided on the small screen of a smartphone, and a display method including detailed information can be provided on the large screen of a personal computer. The providing unit can also customize the display content based on the screen size of the device. For example, important information can be displayed preferentially on a smartphone, and a display including detailed information can be provided on a personal computer. This makes it possible to provide a more appropriate display method by taking into account the screen size of the device.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The collection unit collects the user's personal data. The user's personal data includes name, age, gender, location information, browsing history, health data, purchase history, schedule information, social media posts, email content, and location information. For example, health data from a smartwatch, purchase history from a cashless app, schedule information from a calendar, text posts, image posts, video posts, email subjects, email bodies, attachments, GPS data, Wi-Fi location information, and IP addresses are collected. Step 2: The generator generates prompts based on the data collected by the collector. Prompts may be in the form of questions, instructions, or information, and are generated based on the user's current situation and past behavioral patterns. For example, they may be generated based on current activity, current location, current mood, past purchase history, past search history, past movement history, etc. The generator generates prompts using text generation AI (e.g., LLM) or multimodal generation AI. Step 3: The input unit inputs the generated prompt to the AI. The input unit inputs the generated prompt to the AI ​​and obtains the AI's answer. Step 4: The provider provides the AI's answer to the user. The provider provides the AI's answer to the user, and the user can receive an appropriate answer or service.

[0064] (Example 2) The AI ​​Personal Prompter system according to an embodiment of the present invention utilizes a user's personal data to personalize AI responses. This system connects with data sources such as a smartwatch, a cashless app, and a calendar, automatically generating personalized prompts from those sources and inputting them into the AI. This eliminates the need for users to enter detailed information each time, allowing them to receive more appropriate answers and services. For example, the system collects the user's personal data, including health data from the smartwatch, purchase history from the cashless app, and schedule information from the calendar. Next, the AI ​​generates personalized prompts based on the collected data. These prompts are generated based on the user's current situation and past behavioral patterns. The generated prompts are input into the AI, which then provides the user with optimal answers and services. Furthermore, by utilizing the friend function, the AI ​​can automatically coordinate schedules with friends through inter-app collaboration. This allows users to communicate more smoothly with their friends. Furthermore, by employing MoE (Mixture of Experts), it is possible to derive even more accurate answers. This service does not rely on a specific AI generator, but acts as a hub connecting users with AI generators, which has the advantage of not limiting the AI ​​generators that can be used. This allows the AI ​​Personal Prompter system to use the user's personal data to personalize the AI's answers.

[0065] The AI ​​Personal Prompter system according to the embodiment includes a collection unit, a generation unit, an input unit, and a provision unit. The collection unit collects personal data of a user. The personal data of a user includes, but is not limited to, for example, a name, age, gender, location information, and browsing history. The collection unit collects, for example, health data from a smartwatch, purchase history from a cashless app, and schedule information from a calendar. The collection unit can also collect social media posts, email content, and location information. For example, the collection unit collects text, image, and video posts from social media, email subjects, email bodies, attachments, GPS data, Wi-Fi location information, and IP addresses. The generation unit generates prompts based on the data collected by the collection unit. Prompts may be in the form of questions, instructions, or information, for example, but are not limited to these. The generation unit generates prompts based on the user's current situation and past behavioral patterns. For example, the prompts are generated based on the user's current activity, current location, current mood, past purchase history, past search history, past travel history, and so on. The generation unit generates a prompt using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The input unit inputs the generated prompt to the AI. For example, the input unit inputs the generated prompt to the AI ​​and obtains the AI's answer. The provision unit provides the AI's answer to the user. For example, the provision unit provides the AI's answer to the user, allowing the user to receive an appropriate answer or service. As a result, the AI ​​Personal Prompter system according to the embodiment can personalize the AI's answer by utilizing the user's personal data.

[0066] The collection unit can collect the content of posts on SNS, the content of emails, and location information. The collection unit, for example, collects the content of posts on SNS. The content of posts on SNS includes text posts, image posts, video posts, etc. For example, the collection unit collects text, images, and videos posted by users on SNS. The collection unit can also collect the content of emails. The content of emails includes the subject, body, attachments, etc. For example, the collection unit collects the subject, body, and attachments of emails sent and received by users. The collection unit can also collect location information. Location information includes GPS data, Wi-Fi location information, IP address, etc. For example, the collection unit obtains the user's current location using GPS data, Wi-Fi location information, and IP address. By collecting the content of posts on SNS, the content of emails, and location information, a wider variety of data can be utilized. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the content of social media posts, email contents, and location information into the AI, allowing the AI ​​to automatically collect the data.

[0067] The generation unit can generate prompts based on the user's current situation or past behavioral patterns. The generation unit generates prompts based on, for example, the user's current situation. The current situation includes the user's current activity, current location, current mood, etc. For example, the generation unit generates prompts based on the user's current activity, current location, and current mood. The generation unit can also generate prompts based on the user's past behavioral patterns. Past behavioral patterns include the user's past purchase history, past search history, past travel history, etc. For example, the generation unit generates prompts based on the user's past purchases, search keywords, and travel locations. This allows the generation unit to generate prompts based on the user's current situation and past behavioral patterns, thereby providing more appropriate prompts. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the user's current situation and past behavioral patterns into the generation AI, which then automatically generates prompts.

[0068] The input unit can input the generated prompt to the AI. The input unit, for example, inputs the generated prompt to the AI. The generated prompt includes a question format, an instruction format, an information provision format, etc. For example, the input unit inputs the generated question format prompt to the AI ​​to obtain an answer from the AI. The input unit can also input the generated instruction format prompt to the AI ​​to obtain an instruction from the AI. The input unit can also input the generated information format prompt to the AI ​​to obtain information provided by the AI. In this way, by inputting the generated prompt to the AI, an answer from the AI ​​can be obtained. Some or all of the above-mentioned processing in the input unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the input unit can input the generated prompt to the AI, and the AI ​​can automatically generate an answer.

[0069] The providing unit can provide the AI's answer to the user. The providing unit, for example, provides the AI's answer to the user. The AI's answer can be in text format, audio format, image format, etc. For example, the providing unit can provide the AI's generated answer to the user in text format. The providing unit can also provide the AI's generated answer to the user in audio format. The providing unit can also provide the AI's generated answer to the user in image format. In this way, by providing the AI's answer to the user, the user can receive an appropriate answer or service. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can provide the AI's generated answer to the user, and the user can use the answer.

[0070] Furthermore, the AI ​​Personal Prompter system includes a linking unit that links the friend function. The linking unit links the friend function. For example, the linking unit acquires the user's friend list and coordinates schedules with friends. The linking unit coordinates schedules with friends based on the user's calendar information, for example. The linking unit can also acquire friends' calendar information and coordinate schedules with the user. In this way, by linking the friend function, the user can communicate smoothly with friends. Some or all of the above-described processing in the linking unit may be performed using AI, or may be performed without using AI. For example, the linking unit inputs the user's calendar information and friends' calendar information into AI, which can then automatically coordinate schedules.

[0071] Furthermore, the AI ​​Personal Prompter system includes an accuracy improvement unit that uses MoE to improve accuracy. The accuracy improvement unit uses MoE (Mixture of Experts) to improve accuracy. For example, the accuracy improvement unit combines multiple expert models to generate more accurate answers. For example, the accuracy improvement unit combines models from different fields of expertise to utilize the expertise of each field. The accuracy improvement unit can also integrate the output of each expert model to generate an optimal answer. In this way, by using MoE, even more accurate answers can be derived. Some or all of the above-described processing in the accuracy improvement unit may be performed using AI, or may be performed without using AI. For example, the accuracy improvement unit inputs the output of multiple expert models into AI, allowing the AI ​​to automatically generate an optimal answer.

[0072] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. The collection unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotions using facial expression recognition technology. The collection unit can also record the user's voice and estimate the emotions using voice analysis technology. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions. For example, the collection unit estimates the emotions based on heart rate fluctuations. Next, the collection unit adjusts the timing of data collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit refrains from data collection and resumes collection when the user is relaxed. Also, if the user is relaxed, the collection unit can actively collect data to obtain detailed information. Also, if the user is in a hurry, the collection unit can quickly collect only the minimum amount of data necessary. This allows more appropriate data collection by adjusting the timing of data collection according to 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, or without, an AI. For example, the collection unit may input the user's emotion data into the AI, and the AI ​​may automatically adjust the timing of data collection.

[0073] The collection unit can analyze the user's past data collection history and select the optimal collection method. The collection unit, for example, analyzes the user's past data collection history. The data collection history includes the collection date and time, the type of collected data, and the collection frequency. For example, the collection unit analyzes the date, time, type, and frequency of data collected by the user in the past. Next, the collection unit selects the optimal collection method based on the analysis results. For example, the collection unit prioritizes collection of data sources that the user frequently used in the past. It is also possible to concentrate collection during specific time periods based on the user's past data collection history. It is also possible to select the most efficient collection method based on the user's past data collection history. In this way, the optimal collection method can be selected by analyzing the user's past data collection history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can input the user's past data collection history into AI, which can automatically select the optimal collection method.

[0074] The collection unit can filter data based on the user's current activity status and areas of interest when collecting data. For example, the collection unit takes into account the user's current activity status when collecting data. Activity status includes current work content, exercise status, rest, etc. For example, the collection unit can prioritize collecting health data when the user is exercising. Furthermore, the collection unit can prioritize collecting business-related data when the user is working. Furthermore, the collection unit can prioritize collecting data related to a hobby when the user is immersed in the hobby. Next, the collection unit filters data based on the user's areas of interest. Areas of interest include hobbies, topics of interest, and accounts followed. For example, the collection unit prioritizes collecting data related to a specific hobby. Furthermore, the collection unit can collect data related to topics in which the user is interested. Furthermore, the collection unit can collect data related to accounts followed by the user. In this way, by filtering data based on the user's current activity status and areas of interest, more relevant data can be collected. Some or all of the above-described processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection department can input the user's current activities and areas of interest into the AI, which can then automatically filter the data.

[0075] The collection unit can estimate the user's emotions and determine the priority of data to be collected based on the estimated user's emotions. The collection unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the collection unit captures the user's facial expressions with a camera and estimates the emotion using facial expression recognition technology. The collection unit can also record the user's voice and estimate the emotion using voice analysis technology. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the collection unit estimates the emotion based on heart rate fluctuations. Next, the collection unit determines the priority of data to be collected based on the estimated user's emotions. For example, if the user is feeling stressed, data related to relaxation can be prioritized. Also, if the user is relaxed, detailed health data can be prioritized. Also, if the user is in a hurry, the minimum necessary data can be prioritized. This enables more appropriate data collection by determining the priority of data to be collected according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, or without, an AI. For example, the collection unit may input the user's emotion data into an AI, and the AI ​​may automatically determine the priority of the data.

[0076] The collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information when collecting data. The collection unit, for example, considers the user's geographical location information when collecting data. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the collection unit can prioritize collecting data related to that area. Furthermore, if the user is traveling, the collection unit can prioritize collecting data related to the travel destination. Furthermore, if the user is at home, the collection unit can prioritize collecting data around the user's home. In this way, by taking the user's geographical location information into account, highly relevant data can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's geographical location information into AI, and the AI ​​can automatically collect highly relevant data preferentially.

[0077] The collection unit can analyze the user's social media activity and collect related data when collecting data. For example, the collection unit analyzes the user's social media activity when collecting data. Social media activity includes posted content, like history, follow relationships, etc. For example, if the user posts about a specific topic, the collection unit can collect data related to that topic. Also, if the user participates in a specific event, the collection unit can collect data related to that event. Also, if the user uses a specific hashtag, the collection unit can collect data related to that hashtag. In this way, related data can be collected by analyzing the user's social media activity. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input the user's social media activity into AI, and the AI ​​can automatically collect related data.

[0078] The generation unit can estimate the user's emotion and adjust the prompt expression based on the estimated user emotion. The generation unit, for example, estimates the user's emotion. Emotions include joy, sadness, anger, surprise, etc. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the generation unit estimates the emotion based on heart rate fluctuations. Next, the generation unit adjusts the prompt expression based on the estimated user emotion. For example, if the user is relaxed, the generation unit generates a prompt with a gentle expression. If the user is in a hurry, the generation unit can generate a concise and quick prompt. If the user is excited, the generation unit can generate a visually stimulating prompt. This allows the system to provide more appropriate prompts by adjusting the prompt expression based on the user's emotion. Emotion estimation is achieved 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. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without using AI. For example, the generation unit may input user emotion data into the AI, which may then automatically adjust the way the prompt is expressed.

[0079] The generation unit can adjust the level of detail of the prompt based on important data of the user when generating the prompt. For example, the generation unit takes into account important data of the user when generating the prompt. Important data includes personal information, past purchase history, health data, etc. For example, the generation unit can generate a prompt including detailed health advice based on the user's health data. The generation unit can also generate a prompt including suggestions for related products based on the user's purchase history. The generation unit can also generate a prompt related to an appointment based on the user's calendar information. In this way, adjusting the level of detail of the prompt based on important data of the user can provide a more appropriate prompt. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input important data of the user into the generation AI, which can then automatically adjust the level of detail of the prompt.

[0080] The generation unit can apply different generation algorithms depending on the user's category when generating a prompt. The generation unit, for example, takes the user's category into consideration when generating a prompt. Categories include age group, interests, occupation, etc. For example, if the user belongs to the business category, the generation unit can apply a business-related algorithm to generate a prompt. Also, if the user belongs to the health category, the generation unit can apply a health-related algorithm to generate a prompt. Also, if the user belongs to the entertainment category, the generation unit can apply an entertainment-related algorithm to generate a prompt. In this way, by applying different generation algorithms depending on the user's category, more appropriate prompts can be provided. Some or all of the above-described processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's category into the generation AI, and the generation AI can automatically apply an appropriate algorithm to generate a prompt.

[0081] The generation unit can estimate the user's emotion and adjust the length of the prompt based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion. Emotions include joy, sadness, anger, surprise, etc. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the generation unit estimates the emotion based on heart rate fluctuations. Next, the generation unit adjusts the length of the prompt based on the estimated user's emotion. For example, if the user is in a hurry, the generation unit generates a short, to-the-point prompt. If the user is relaxed, the generation unit can generate a longer prompt with detailed explanations. If the user is excited, the generation unit can generate a prompt with visually stimulating effects. This allows the generation unit to provide more appropriate prompts by adjusting the length of the prompt according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using 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. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit may input user emotion data into the generation AI, which may then automatically adjust the length of the prompt.

[0082] When generating prompts, the generation unit can determine the priority of prompts based on the time when the user collected data. For example, the generation unit considers the time when the user collected data when generating prompts. The time when data was collected includes the collection date and time, the collection frequency, and the collection period. For example, the generation unit can prioritize generating prompts based on data recently collected by the user. The generation unit can also adjust the priority of prompts based on data collected by the user in the past. The generation unit can also determine the priority of prompts based on data collected by the user during a specific time period. In this way, by determining the priority of prompts based on the time when the user collected data, more appropriate prompts can be provided. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the time when the user collected data into the generation AI, and the generation AI can automatically determine the priority of prompts.

[0083] The generation unit can adjust the order of prompts based on the user's relevance when generating prompts. For example, the generation unit considers the user's relevance when generating prompts. Relevance includes past behavioral history, degree of coincidence of interests, etc. For example, the generation unit prioritizes displaying prompts that are most relevant to the user's current situation. The generation unit can also adjust the order of prompts based on the user's past behavioral patterns. The generation unit can also optimize the order of prompts based on the user's areas of interest. In this way, adjusting the order of prompts based on the user's relevance can provide more appropriate prompts. Some or all of the above-described processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can input the user's relevance to the generation AI, and the generation AI can automatically adjust the order of prompts.

[0084] The input unit can estimate the user's emotions and adjust the timing of prompt input based on the estimated user emotions. The input unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the input unit captures the user's facial expressions with a camera and estimates the emotion using facial expression recognition technology. The input unit can also record the user's voice and estimate the emotion using voice analysis technology. The input unit can also estimate the emotion by collecting the user's biometric data (heart rate and electrodermal activity) with a sensor. For example, the input unit estimates the emotion based on heart rate fluctuations. Next, the input unit adjusts the timing of prompt input based on the estimated user emotions. For example, if the user is feeling stressed, the input timing can be delayed to encourage the user to input in a relaxed state. Also, if the user is relaxed, the input can be actively encouraged. Also, if the user is in a hurry, the input can be encouraged quickly. This allows for more appropriate input by adjusting the timing of prompt input according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the input unit may input user emotion data to the generation AI, and the generation AI may automatically adjust the input timing of the prompt.

[0085] The input unit can select the optimal input method by analyzing the user's past input history when entering a prompt. The input unit, for example, analyzes the user's past input history when entering a prompt. The input history includes past input content, input frequency, input method, etc. For example, the input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The input unit can also predict and suggest an input method to be used during a specific time period based on the user's past input history. The input unit can also select the most efficient input method based on the user's past input history. In this way, the optimal input method can be selected by analyzing the user's past input history. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's past input history into AI, which can then automatically select the optimal input method.

[0086] The input unit can customize the input means based on the user's current situation when inputting a prompt. For example, the input unit takes the user's current situation into consideration when inputting a prompt. The current situation includes the user's current activity, current location, current mood, etc. For example, the input unit can preferentially suggest voice input when the user is exercising. The input unit can also preferentially suggest text input when the user is working. The input unit can also suggest an input method related to a hobby when the user is immersed in that hobby. This allows for more appropriate input by customizing the input means based on the user's current situation. Some or all of the above-described processing in the input unit may be performed using, or without, AI. For example, the input unit can input the user's current situation to AI, and the AI ​​can automatically customize the input means.

[0087] The input unit can estimate the user's emotion and determine the priority of prompts to be input based on the estimated user's emotion. The input unit estimates the user's emotion, for example. Emotions include joy, sadness, anger, surprise, etc. For example, the input unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The input unit can also record the user's voice and estimate the emotion using voice analysis technology. The input unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the input unit estimates the emotion based on heart rate fluctuations. Next, the input unit determines the priority of prompts to be input based on the estimated user's emotion. For example, if the user is feeling stressed, prompts related to relaxation can be input with priority. Also, if the user is relaxed, detailed health data can be input with priority. Also, if the user is in a hurry, the minimum necessary data can be input with priority. This allows more appropriate input by determining the priority of prompts to be input based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using 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. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit may input the user's emotion data into the generation AI, and the generation AI may automatically determine the priority of prompts.

[0088] The input unit can select the optimal input method by taking into account the user's geographical location information when inputting a prompt. The input unit, for example, considers the user's geographical location information when inputting a prompt. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the input unit can suggest an input method related to that area. Furthermore, if the user is traveling, the input unit can also suggest an input method related to the user's travel destination. Furthermore, if the user is at home, the input unit can also suggest an input method near the user's home. In this way, the optimal input method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the input unit may be performed using, for example, AI, or may be performed without using AI. For example, the input unit can input the user's geographical location information to AI, and the AI ​​can automatically select the optimal input method.

[0089] The input unit can analyze the user's social media activity and suggest an input method when the user inputs a prompt. The input unit, for example, analyzes the user's social media activity when the user inputs a prompt. Social media activity includes the content of posts, like history, follow relationships, etc. For example, if the user posts about a specific topic, the input unit can suggest an input method related to the topic. Furthermore, if the user is participating in a specific event, the input unit can suggest an input method related to the event. Furthermore, if the user uses a specific hashtag, the input unit can suggest an input method related to the hashtag. In this way, the optimal input method can be suggested by analyzing the user's social media activity. Some or all of the above-mentioned processing in the input unit may be performed, for example, using AI, or may be performed without using AI. For example, the input unit can input the user's social media activity into AI, which can then automatically suggest the optimal input method.

[0090] The providing unit can estimate the user's emotions and adjust the display method of the answer based on the estimated user's emotions. The providing unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the providing unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The providing unit can also record the user's voice and estimate the emotion using voice analysis technology. The providing unit can also estimate the emotion by collecting the user's biometric data (heart rate and electrodermal activity) with a sensor. For example, the providing unit estimates the emotion based on heart rate fluctuations. Next, the providing unit adjusts the display method of the answer based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that focuses on the main points can be provided. This allows the display method of the answer to be adjusted according to the user's emotions, enabling more appropriate display. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit may input user emotion data into the generation AI, and the generation AI may automatically adjust the way in which the answer is displayed.

[0091] The providing unit can select the optimal display method by referring to the user's past answer history when providing an answer. The providing unit, for example, refers to the user's past answer history when providing an answer. The answer history includes past answer content, answer frequency, answer method, etc. For example, the providing unit preferentially provides display methods that the user has previously preferred. The providing unit can also select a display method suitable for a specific time period from the user's past answer history. The providing unit can also select the most efficient display method based on the user's past answer history. In this way, the optimal display method can be selected by referring to the user's past answer history. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past answer history into AI, and the AI ​​can automatically select the optimal display method.

[0092] The providing unit can customize the answering method based on the user's current situation when providing an answer. For example, the providing unit takes the user's current situation into consideration when providing an answer. The current situation includes the user's current activity, current location, current mood, etc. For example, if the user is exercising, the providing unit can prioritize providing an audio answer. Also, if the user is at work, the providing unit can prioritize providing a text answer. Also, if the user is immersed in a hobby, the providing unit can provide an answering method related to that hobby. This allows for more appropriate answers by customizing the answering method based on the user's current situation. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input the user's current situation into AI, and the AI ​​can automatically customize the answering method.

[0093] The providing unit can estimate the user's emotions and prioritize answers based on the estimated user emotions. The providing unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the providing unit captures the user's facial expressions with a camera and estimates the emotions using facial expression recognition technology. The providing unit can also record the user's voice and estimate the emotions using voice analysis technology. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions. For example, the providing unit estimates the emotions based on heart rate fluctuations. Next, the providing unit prioritizes answers based on the estimated user emotions. For example, if the user is feeling stressed, answers related to relaxation can be prioritized. Also, if the user is relaxed, detailed health data can be prioritized. Also, if the user is in a hurry, the minimum necessary data can be prioritized. This allows for more appropriate answers to be provided by prioritizing answers according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit may input user emotion data into the generation AI, and the generation AI may automatically determine the priority of answers.

[0094] The providing unit can select the optimal answering method by taking into account the user's geographical location information when providing an answer. For example, the providing unit can consider the user's geographical location information when providing an answer. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the providing unit can prioritize providing answers related to that area. Furthermore, if the user is traveling, the providing unit can prioritize providing answers related to the user's travel destination. Furthermore, if the user is at home, the providing unit can prioritize providing answers around the user's home. In this way, the optimal answering method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's geographical location information into AI, and the AI ​​can automatically select the optimal answering method.

[0095] When providing an answer, the providing unit can analyze the user's social media activity and suggest a means of answering. For example, the providing unit analyzes the user's social media activity when providing an answer. Social media activity includes the content of posts, like history, follow relationships, etc. For example, if the user posts about a specific topic, the providing unit can provide an answer related to that topic. Furthermore, if the user is participating in a specific event, the providing unit can also provide an answer related to that event. Furthermore, if the user uses a specific hashtag, the providing unit can also provide an answer related to that hashtag. In this way, by analyzing the user's social media activity, the optimal means of answering can be suggested. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's social media activity into AI, and the AI ​​can automatically suggest the optimal way of answering.

[0096] The collaboration unit can estimate the user's emotions and adjust the timing of collaboration based on the estimated user emotions. The collaboration unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the collaboration unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The collaboration unit can also record the user's voice and estimate the emotion using voice analysis technology. The collaboration unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the collaboration unit estimates the emotion based on heart rate fluctuations. Next, the collaboration unit adjusts the timing of collaboration based on the estimated user emotions. For example, if the user is feeling stressed, the collaboration timing can be delayed to perform collaboration in a relaxed state. Also, if the user is relaxed, the collaboration can be proactive. Also, if the user is in a hurry, the collaboration can be performed quickly. This allows for more appropriate collaboration by adjusting the timing of collaboration according to 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collaboration unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collaboration unit may input user emotion data into the generation AI, and the generation AI may automatically adjust the timing of collaboration.

[0097] The collaboration unit can analyze the user's past collaboration history and select the optimal collaboration method at the time of collaboration. For example, the collaboration unit analyzes the user's past collaboration history at the time of collaboration. The collaboration history includes past collaboration content, collaboration frequency, collaboration method, etc. For example, the collaboration unit prioritizes suggesting collaboration methods that the user has frequently used in the past. The collaboration unit can also select a collaboration method suitable for a specific time period from the user's past collaboration history. The collaboration unit can also select the most efficient collaboration method based on the user's past collaboration history. In this way, the optimal collaboration method can be selected by analyzing the user's past collaboration history. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can input the user's past collaboration history into AI, and the AI ​​can automatically select the optimal collaboration method.

[0098] The linking unit can estimate the user's emotions and determine the priority of linking based on the estimated user's emotions. The linking unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the linking unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The linking unit can also record the user's voice and estimate the emotion using voice analysis technology. The linking unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the linking unit estimates the emotion based on heart rate fluctuations. Next, the linking unit determines the priority of linking based on the estimated user's emotions. For example, if the user is feeling stressed, linking related to relaxation can be prioritized. Also, if the user is relaxed, detailed health data can be prioritized for linking. Also, if the user is in a hurry, the minimum necessary data can be prioritized for linking. This enables more appropriate linking by determining the priority of linking based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collaboration unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the collaboration unit may input user emotion data into the generation AI, and the generation AI may automatically determine collaboration priorities.

[0099] The linking unit can select the optimal linking method by taking into account the user's geographical location information when linking. For example, the linking unit can consider the user's geographical location information when linking. Geographical location information includes GPS data, Wi-Fi location information, IP address, etc. For example, if the user is in a specific area, the linking unit can suggest a linking method related to that area. Furthermore, if the user is traveling, the linking unit can also suggest a linking method related to the user's travel destination. Furthermore, if the user is at home, the linking unit can suggest a linking method near the user's home. In this way, the optimal linking method can be selected by taking into account the user's geographical location information. Some or all of the above-described processing in the linking unit may be performed using, for example, AI, or may be performed without using AI. For example, the linking unit can input the user's geographical location information into AI, and the AI ​​can automatically select the optimal linking method.

[0100] The accuracy improvement unit can estimate a user's emotion and select training data based on the estimated user's emotion. The accuracy improvement unit estimates, for example, the user's emotion. Emotions include joy, sadness, anger, surprise, etc. For example, the accuracy improvement unit captures the user's facial expression with a camera and estimates the emotion using facial expression recognition technology. The accuracy improvement unit can also record the user's voice and estimate the emotion using voice analysis technology. The accuracy improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion. For example, the accuracy improvement unit estimates the emotion based on heart rate fluctuations. Next, the accuracy improvement unit selects training data based on the estimated user's emotion. For example, if the user is relaxed, detailed data can be used for training. If the user is in a hurry, brief data can be used for training. If the user is excited, visually stimulating data can be used for training. This enables more appropriate training by selecting training data according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using 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. Some or all of the above-described processing in the accuracy improvement unit may be performed using, or without, the generation AI. For example, the accuracy improvement unit may input user emotion data into the generation AI, and the generation AI may automatically select training data.

[0101] The accuracy improvement unit can optimize the learning algorithm by referring to past learning data during learning. The accuracy improvement unit, for example, refers to past learning data during learning. The learning data includes past training data, labeled data, feedback data, etc. For example, the accuracy improvement unit selects an optimal algorithm based on the past learning data. The accuracy improvement unit can also extract specific patterns from the past learning data and optimize the algorithm. The accuracy improvement unit can also analyze the past learning data and adjust the parameters of the algorithm. In this way, the learning algorithm can be optimized by referring to the past learning data. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit can input past learning data into AI, and the AI ​​can automatically optimize the learning algorithm.

[0102] The accuracy improvement unit can estimate the user's emotions and adjust the learning frequency based on the estimated user emotions. The accuracy improvement unit, for example, estimates the user's emotions. Emotions include joy, sadness, anger, surprise, etc. For example, the accuracy improvement unit can capture the user's facial expressions with a camera and estimate the emotions using facial expression recognition technology. The accuracy improvement unit can also record the user's voice and estimate the emotions using voice analysis technology. The accuracy improvement unit can also estimate the user's emotions by collecting the user's biometric data (heart rate and electrodermal activity) with a sensor. For example, the accuracy improvement unit can estimate the emotions based on heart rate fluctuations. Next, the accuracy improvement unit adjusts the learning frequency based on the estimated user emotions. For example, if the user is relaxed, learning can be performed more frequently. If the user is in a hurry, learning frequency can be reduced. If the user is excited, learning frequency can be adjusted. This allows more appropriate learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the accuracy improvement unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the accuracy improvement unit may input user emotion data into the generation AI, and the generation AI may automatically adjust the frequency of learning.

[0103] The accuracy improvement unit can weight the training data based on the time of data collection during training. For example, the accuracy improvement unit takes into account the time of data collection during training. The time of data collection includes the collection date and time, collection frequency, collection period, etc. For example, the accuracy improvement unit performs training by assigning a higher weight to recently collected data. The accuracy improvement unit can also perform training by assigning a lower weight to data collected in the past. The accuracy improvement unit can also perform weighting based on data collected during a specific time period. In this way, weighting the training data based on the time of data collection enables more appropriate training. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit can input the time of data collection into AI, and the AI ​​can automatically weight the training data. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, generation unit, input unit, provision unit, collaboration unit, and accuracy improvement unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects the user's personal data using the camera 42 and microphone 38B of the smart device 14 and transmits the collected data to the data processing device 12 via the control unit 46A. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a prompt based on the collected data. The input unit inputs the generated prompt to the specific processing unit 290 of the data processing device 12 to obtain an answer from the AI. The provision unit provides the AI's answer to the user via the display 40A and speaker 40B of the smart device 14. The collaboration unit collaborates with the friend function via the control unit 46A of the smart device 14 and adjusts schedules based on calendar information. The accuracy improvement unit improves accuracy using MoE via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, generation unit, input unit, provision unit, collaboration unit, and accuracy improvement unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects personal data of the user using the camera 42 and microphone 238 of the smart glasses 214 and transmits the data to the data processing device 12 via the control unit 46A. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a prompt based on the collected data. The input unit inputs the generated prompt to the specific processing unit 290 of the data processing device 12 and obtains an answer from the AI. The provision unit provides the AI's answer to the user via the speaker 240 of the smart glasses 214. The collaboration unit collaborates with the friend function via the control unit 46A of the smart glasses 214 and adjusts schedules based on calendar information. The accuracy improvement unit improves accuracy using MoE via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, generation unit, input unit, provision unit, collaboration unit, and accuracy improvement unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects personal data of the user using the camera 42 and microphone 238 of the headset-type terminal 314 and transmits the data to the data processing device 12 via the control unit 46A. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a prompt based on the collected data. The input unit inputs the generated prompt to the specific processing unit 290 of the data processing device 12 to obtain an answer from the AI. The provision unit provides the AI's answer to the user via the display 343 and speaker 240 of the headset-type terminal 314. The collaboration unit collaborates with the friend function via the control unit 46A of the headset-type terminal 314 and adjusts schedules based on calendar information. The accuracy improvement unit improves accuracy using MoE via the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, generation unit, input unit, provision unit, collaboration unit, and accuracy improvement unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects personal data of the user using the camera 42 and microphone 238 of the robot 414 and transmits the collected data to the data processing device 12 via the control unit 46A. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a prompt based on the collected data. The input unit inputs the generated prompt to the specific processing unit 290 of the data processing device 12 and obtains an answer from the AI. The provision unit provides the AI's answer to the user using the speaker 240 of the robot 414. The collaboration unit collaborates with the friend function via the control unit 46A of the robot 414 and adjusts schedules based on calendar information. The accuracy improvement unit improves accuracy using MoE via the specific processing unit 290 of the data processing device 12.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] When collecting a user's personal data, the collection unit can adjust the frequency of data collection taking into account the remaining battery level of the user's device. For example, if the remaining battery level is low, the collection frequency can be reduced, and if the remaining battery level is sufficient, the collection frequency can be increased. The collection unit can also determine the priority of data collection based on the remaining battery level of the device. For example, if the remaining battery level is low, only highly important data can be collected with priority, and if the remaining battery level is sufficient, detailed data can be collected. This enables efficient data collection by taking into account the remaining battery level of the device.

[0106] When collecting user data, the collection unit can adjust the data collection method taking into account the user's internet connection status. For example, if the internet connection is unstable, the data can be stored locally and sent all at once when the connection is stable. The collection unit can also determine the priority of data collection based on the internet connection status. For example, if the connection is unstable, it can prioritize collecting only highly important data, and when the connection is stable, it can collect detailed data. This allows for efficient data collection by taking the internet connection status into account.

[0107] The generator may generate prompts taking into account the user's current weather information. For example, if it is raining, the generator may generate prompts related to indoor activities, and if it is sunny, the generator may generate prompts related to outdoor activities. The generator may also adjust the content of the prompts based on the weather information. For example, the generator may generate prompts related to hot drinks on cold days and prompts related to cold drinks on hot days. This allows the generator to provide more appropriate prompts by taking into account the weather information.

[0108] The input unit can adjust the prompt input method taking into account the user's device usage status. For example, if the user is using a smartphone, touch input can be prioritized, and if the user is using a personal computer, keyboard input can be prioritized. The input unit can also customize the input method based on the device usage status. For example, if the user is driving, voice input can be prioritized, and if the user is in a meeting, text input can be prioritized. This makes it possible to provide a more appropriate input method by taking into account the device usage status.

[0109] The providing unit can adjust the display method of the answer taking into account the screen size of the user's device. For example, a simple and highly visible display method can be provided on the small screen of a smartphone, and a display method including detailed information can be provided on the large screen of a personal computer. The providing unit can also customize the display content based on the screen size of the device. For example, important information can be displayed preferentially on a smartphone, and a display including detailed information can be provided on a personal computer. This makes it possible to provide a more appropriate display method by taking into account the screen size of the device.

[0110] The collection unit can estimate the user's emotions and adjust the frequency of data collection based on the estimated user's emotions. For example, if the user is feeling stressed, the frequency of data collection can be reduced, and if the user is relaxed, the frequency of data collection can be increased. The collection unit can also adjust the type of data to be collected based on the emotions. For example, if the user is sad, positive data can be preferentially collected, and if the user is happy, detailed data can be collected. This allows for more appropriate data collection by taking the user's emotions into consideration.

[0111] The generation unit can estimate the user's emotion and adjust the tone of the prompt based on the estimated user's emotion. For example, if the user is relaxed, a soft-toned prompt can be generated, and if the user is in a hurry, a concise and quick prompt can be generated. The generation unit can also adjust the content of the prompt based on the emotion. For example, if the user is sad, a prompt including an encouraging message can be generated, and if the user is happy, a prompt including a congratulatory message can be generated. In this way, by taking the user's emotion into consideration, more appropriate prompts can be provided.

[0112] The input unit can estimate the user's emotions and adjust the prompt input method based on the estimated user's emotions. For example, if the user is feeling stressed, voice input can be prioritized, and if the user is relaxed, text input can be prioritized. The input unit can also adjust the timing of input based on the emotions. For example, if the user is in a hurry, the input unit can prompt the user to input quickly, and if the user is relaxed, the input unit can prompt the user to input slowly. This makes it possible to provide a more appropriate input method by taking the user's emotions into consideration.

[0113] The providing unit can estimate the user's emotions and adjust the display method of the answer based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided, and if the user is relaxed, a display method including detailed information can be provided. The providing unit can also customize the display content based on the emotions. For example, if the user is sad, a display including a positive message can be provided, and if the user is happy, a display including a congratulatory message can be provided. In this way, a more appropriate display method can be provided by taking the user's emotions into consideration.

[0114] The collaboration unit can estimate the user's emotions and adjust the timing of collaboration based on the estimated user's emotions. For example, if the user is feeling stressed, the collaboration timing can be delayed to allow collaboration to occur in a relaxed state, and if the user is relaxed, collaboration can be performed proactively. The collaboration unit can also adjust the content of collaboration based on the emotions. For example, if the user is in a hurry, collaboration can be performed quickly, and if the user is relaxed, collaboration can be performed in detail. This allows for more appropriate collaboration by taking the user's emotions into consideration.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The collection unit collects the user's personal data. The user's personal data includes name, age, gender, location information, browsing history, health data, purchase history, schedule information, social media posts, email content, and location information. For example, health data from a smartwatch, purchase history from a cashless app, schedule information from a calendar, text posts, image posts, video posts, email subjects, email bodies, attachments, GPS data, Wi-Fi location information, and IP addresses are collected. Step 2: The generator generates prompts based on the data collected by the collector. Prompts may be in the form of questions, instructions, or information, and are generated based on the user's current situation and past behavioral patterns. For example, they may be generated based on current activity, current location, current mood, past purchase history, past search history, past movement history, etc. The generator generates prompts using text generation AI (e.g., LLM) or multimodal generation AI. Step 3: The input unit inputs the generated prompt to the AI. The input unit inputs the generated prompt to the AI ​​and obtains the AI's answer. Step 4: The provider provides the AI's answer to the user. The provider provides the AI's answer to the user, and the user can receive an appropriate answer or service.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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 indicated, and when they approach the ideal, a state of pleasure is indicated. 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 collection unit that collects personal data of users; a generating unit that generates a prompt based on the data collected by the collecting unit; an input unit that inputs the prompt generated by the generation unit to the AI; A providing unit that provides the answer of the AI. A system characterized by:

2. The collecting unit Collecting SNS posts, email content, and location information 2. The system of claim 1.

3. The generation unit Generate prompts based on the user's current situation or past behavior 2. The system of claim 1.

4. The input unit Input the generated prompt to the AI 2. The system of claim 1.

5. The providing unit Providing AI answers to users 2. The system of claim 1.

6. Equipped with a linking section that links friend functions 2. The system of claim 1.

7. Equipped with an accuracy improvement unit that uses MoE to improve accuracy 2. The system of claim 1.

8. The collecting unit Inferring user emotions and adjusting the timing of data collection based on the estimated user emotions 2. The system of claim 1.

9. The collecting unit Analyze the user's past data collection history and select the optimal collection method 2. The system of claim 1.

Images