System

Abstract

To provide a system that provides interesting news on the basis of attribute information of a user and wakes up the user naturally.SOLUTION: A system according to the embodiment includes a collection unit, a selection unit, an audio unit, and an investigation unit. The collection unit collects attribute information of a user. The selection unit analyzes the attribute information collected by the collection unit and selects news in which the user is interested. The audio unit transmits the news selected by the selection unit by a synthesized voice. The investigation unit investigates whether or not the user has confirmed the details of the news transmitted by the audio unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not provide sufficient methods for effectively providing users with news that they are interested in and for waking them up naturally, and there is room for improvement.

[0005] The system according to the embodiment aims to wake up naturally by providing news that is of interest to the user based on the user's attribute information. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a selection unit, an audio unit, and an investigation unit. The collection unit collects attribute information of users. The selection unit analyzes the attribute information collected by the collection unit and selects news that interests the user. The audio unit delivers the news selected by the selection unit in a synthetic voice. The investigation unit investigates whether the user has confirmed details of the news delivered by the audio unit. Effect of the Invention

[0007] The system according to the embodiment provides news that is of interest to the user based on the user's attribute information, allowing the user to wake up naturally. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The alarm system according to the embodiment of the present invention is a system that stimulates intellectual curiosity by collecting attribute information of a user, selecting news that is likely to interest the user through a generation AI, and conveying a part of the news through a synthetic voice. This alarm system stimulates intellectual curiosity by collecting attribute information of a user, selecting news that is likely to interest the user through a generation AI, and conveying a part of the news through a synthetic voice. When a user is interested in the news, their mind becomes clear as they investigate the details, and they wake up. By using this alarm, the user is freed from the loud alarm sound every morning, and they can wake up actively of their own volition. For example, the attribute information of the user is collected. For example, information such as age, gender, occupation, and hobbies is collected. This information is input to the generation AI. Next, the generation AI analyzes the collected attribute information and selects news that may interest the user. For example, the latest sports news is selected for a user who likes sports, and the latest technology news is selected for a user who is interested in technology. The selected news is conveyed to the user through a synthetic voice. For example, a part of the news is delivered by synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." In addition, it is investigated whether the user has looked into the details of the news delivered. For example, it is checked whether the user clicked on a link in the app to look up the details of the news. This information is fed back to the generation AI and used for the next news selection. With this mechanism, users are freed from the shrill alarm sound every morning and can actively wake up of their own volition. For example, as they look up the details of a news item that interests them, they naturally wake up. In addition, the generation AI selects news that interests the user, making waking up every morning fun. This allows the alarm system to provide interesting news based on the user's attribute information, promoting natural waking.

[0029] The alarm system according to the embodiment includes a collection unit, a selection unit, a voice unit, and a survey unit. The collection unit collects attribute information of a user. The attribute information of a user includes, for example, age, sex, occupation, and hobbies, but is not limited to such examples. The collection unit collects the attribute information of a user, for example, by using a questionnaire. The collection unit can also collect the attribute information of a user by using a sensor. For example, the collection unit can also collect the attribute information of a user by using online data. The selection unit uses a generation AI to analyze the attribute information collected by the collection unit and selects news that may interest the user. The generation AI selects news, for example, by using a text generation AI (for example, LLM). The selection unit can also use the generation AI to select news based on the attribute information of a user. For example, the generation AI selects the latest sports news for a user who likes sports. For a user who is interested in technology, it selects the latest technology news. The voice unit conveys the news selected by the selection unit to the user by synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice unit can also deliver the news using synthetic voice. For example, the voice unit delivers a part of the news using synthetic voice, such as "Good morning. Today's news. I'll tell you the latest technology news." The survey unit investigates whether the user has confirmed the details of the news delivered by the voice unit. The survey is performed, for example, by counting the number of clicks. The survey unit can also check the details of the news using user feedback. For example, the survey unit checks whether the user clicked on a link in the app to check the details of the news. In this way, the alarm system according to the embodiment can provide interesting news based on the user's attribute information, and promote natural waking.

[0030] The collection unit collects attribute information of the user. The user's attribute information includes, but is not limited to, for example, age, sex, occupation, and hobbies. The collection unit collects the user's attribute information, for example, using a questionnaire. The questionnaire is provided in the form of an online form or a question in an app, and is designed so that the user can easily answer it. The collection unit can also collect the user's attribute information using a sensor. For example, data such as the user's activity level and sleep pattern can be collected through a wearable device such as a smart watch or a fitness tracker. This allows detailed information on the user's lifestyle and health condition to be obtained. Furthermore, the collection unit can also collect the user's attribute information using online data. For example, the user's interests and concerns can be understood by analyzing information shared by the user on social media and website browsing history. This allows the collection unit to build a comprehensive user profile from various data sources and collect more accurate attribute information. The collected data is stored in a secure database and encrypted for privacy protection. The collection unit can improve the accuracy and reliability of the entire system by periodically updating the data to reflect the latest attribute information of the user.

[0031] The selection unit uses the generation AI to analyze the attribute information collected by the collection unit and selects news that may interest the user. The generation AI selects news using, for example, a text generation AI (e.g., LLM). Specifically, the generation AI receives the user's attribute information as input and generates highly relevant news articles based on that information. For example, the generation AI selects the latest sports news for a user who likes sports, and the latest technology news for a user who is interested in technology. The generation AI uses natural language processing technology to analyze the content of the news article and extract parts that match the user's interests. The generation AI can also analyze news topics and keywords and select news that best suits the user's interests. Furthermore, the selection unit can use the generation AI to select news based on the user's attribute information. For example, the selection unit provides more personalized news by taking into account the user's past news browsing history and feedback. The selection unit can use the learning algorithm of the generation AI to respond to changes in the user's interests and always provide the latest information. This allows the selection unit to select the news that is most interesting to the user, maximizing the effectiveness of the alarm system.

[0032] The voice unit conveys the news selected by the selection unit to the user in a synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice synthesis engine can receive text data as an input and generate a natural voice. Specifically, the voice unit inputs the text of the selected news article into the voice synthesis engine and plays the generated voice to the user. For example, a part of the news is conveyed in a synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." The voice unit can also adjust the tone and speed of the voice based on the attribute information of the user. For example, the news is conveyed in a bright and lively tone to a young user, and in a slow and calm tone to an older user. In addition, the voice unit supports multiple languages ​​and can convey the news according to the language setting of the user. This allows the voice unit to provide the news in a form that is most easy for the user to hear. Furthermore, the voice unit can add music and sound effects according to the content of the news. For example, cheering music can be added to sports news and futuristic sound effects can be added to technology news to enhance the realism of the news. This allows the audio section to provide the user with engaging and informative news, promoting a natural wake-up experience.

[0033] The research unit investigates whether the user has confirmed the details of the news conveyed by the audio unit. The investigation is carried out, for example, by counting the number of clicks. Specifically, after the audio unit conveys the news, the number of times the user clicks on a link to confirm the details of the news in the app is counted. The research unit can also use user feedback to confirm the details of the news. For example, it checks whether the user clicks on a link in the app to check the details of the news. Furthermore, the research unit can collect user reactions and feedback to help improve the selection and provision method of news. For example, by analyzing how the user reacted to the news and which news attracted the most interest, it is possible to reflect this in future news selection. The research unit analyzes the user's behavioral data and builds a feedback loop to optimize the method and content of news provision. This allows the research unit to accurately grasp the user's interests and concerns and improve the accuracy and effectiveness of the entire system. Furthermore, in order to protect the user's privacy, the research unit anonymizes the collected data and manages it in a secure environment. This allows the research unit to collect data necessary for improving the system while maintaining the user's trust.

[0034] The collection unit can collect attribute information of the user's age, sex, occupation, and hobby. The collection unit, for example, collects the user's age. Specific ranges and classification criteria of age include, for example, teens, twenties, thirties, etc., but are not limited to such examples. The collection unit also collects the user's gender. Specific classification criteria of gender include, for example, male, female, other, etc., but are not limited to such examples. Furthermore, the collection unit collects the user's occupation. Specific classification criteria of occupation include, for example, student, company employee, self-employed, etc., but are not limited to such examples. The collection unit collects the user's hobbies. Specific classification criteria of hobbies include, for example, sports, reading, traveling, etc., but are not limited to such examples. As a result, the collection unit can select news with higher accuracy by collecting detailed attribute information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input questionnaire data into AI, and the AI ​​can analyze the data to collect attribute information.

[0035] The selection unit can analyze the collected attribute information by the generation AI and select news that interests the user. The selection unit can analyze the collected attribute information using, for example, the generation AI. The generation AI can analyze the attribute information using, for example, a text generation AI (for example, LLM). The selection unit can also use the generation AI to select news that interests the user. For example, the generation AI can select the latest sports news for a user who likes sports. For a user who is interested in technology, the generation AI can select the latest technology news. The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI can use keyword extraction technology to pick up particularly important information from the user's attribute information and select news based on that. As a result, the selection unit can use the generation AI to improve the accuracy of selecting news that matches the user's interests. Some or all of the above-mentioned processing in the selection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the selection unit can input the collected attribute information into an AI, and the AI ​​can analyze the data to select news.

[0036] The voice unit can convey the selected news to the user in synthetic voice. For example, the voice unit conveys the selected news to the user in synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice synthesis engine is a technology that converts text data into voice data and has advanced voice synthesis capabilities. The voice unit can also convey news using synthetic voice. For example, the voice unit conveys part of the news in synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." In this way, the voice unit can effectively convey news to the user by using synthetic voice. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice unit can input the selected news to AI, which generates voice data and conveys it to the user.

[0037] The research unit can confirm whether the user has checked the details of the news. For example, the research unit checks whether the user has checked the details of the news. A specific method of checking includes, for example, counting the number of clicks, but is not limited to such an example. The research unit can also check the details of the news using user feedback. For example, the research unit checks whether a link was clicked in the app to check the details of the news. This allows the research unit to grasp the user's interest in the news. A part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input data on the number of clicks into AI, and the AI ​​can analyze the data to check the details of the news.

[0038] The research unit can confirm whether or not a link was clicked in the app to check the details of the news. The research unit, for example, confirms whether or not a link was clicked in the app to check the details of the news. Specific actions of clicking a link include, for example, the number of clicks and the click position, but are not limited to such examples. This allows the research unit to grasp the specific actions of the user regarding the news. A part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input click data into AI, which analyzes the data to check the details of the news.

[0039] The collection unit can analyze the user's past attribute information and select the optimal collection method. The collection unit, for example, analyzes the user's past attribute information and selects the optimal collection method. The past attribute information includes, for example, past questionnaire results and past behavior history, but is not limited to such examples. The collection unit, for example, collects attribute information in the form of a simple question based on information provided by the user in the past. The collection unit can also analyze the user's past answer patterns and select the most efficient collection method. Furthermore, the collection unit can prioritize collection methods (questionnaires, voice input, etc.) that the user has used in the past. This enables the collection unit to select the optimal collection method based on the past attribute information, thereby enabling efficient information collection. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past attribute information into AI, and the AI ​​can analyze the data and select the optimal collection method.

[0040] The collection unit can perform filtering based on the user's current living situation and field of interest when collecting attribute information. For example, the collection unit performs filtering based on the user's current living situation and field of interest when collecting attribute information. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. The field of interest includes, for example, a hobby and a topic of interest, but is not limited to such examples. For example, when the user starts a new hobby, the collection unit preferentially collects attribute information related to the hobby. In addition, when the user changes jobs, the collection unit can also collect attribute information related to the new occupation. Furthermore, when the user moves, the collection unit can also collect attribute information related to the new area. As a result, the collection unit can select more appropriate news by collecting attribute information according to the user's current situation. Part or all of the above-mentioned 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 data on the current living situation and field of interest into AI, and the AI ​​can analyze the data and perform filtering.

[0041] The collection unit can preferentially collect highly relevant information in consideration of the geographical location information of the user when collecting attribute information. For example, the collection unit preferentially collects highly relevant information in consideration of the geographical location information of the user when collecting attribute information. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the collection unit preferentially collects news related to the area. In addition, if the user is traveling, the collection unit can also preferentially collect news related to the travel destination. Furthermore, if the user moves, the collection unit can also preferentially collect news related to the new area. In this way, the collection unit can collect information highly relevant to the user by considering the geographical location information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information to AI, and the AI ​​can analyze the data and preferentially collect highly relevant information.

[0042] The collection unit can analyze the social media activity of the user and collect related information when collecting the attribute information. For example, the collection unit can analyze the social media activity of the user and collect related information when collecting the attribute information. The social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the collection unit collects related attribute information based on the content that the user frequently shares on social media. The collection unit can also analyze the content of accounts that the user follows and collect related attribute information. Furthermore, the collection unit can also collect related attribute information based on the content of online communities in which the user participates. In this way, the collection unit can collect information that matches the user's interests by analyzing the social media activity. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data of social media activity to AI, and the AI ​​can analyze the data and collect related information.

[0043] The selection unit can select optimal news by referring to the user's past news browsing history when selecting news. For example, the selection unit selects optimal news by referring to the user's past news browsing history when selecting news. The past news browsing history includes, for example, the type of news browsed and the browsing time, but is not limited to such examples. For example, the selection unit selects related news based on a news category that the user frequently browsed in the past. The selection unit can also select related news based on news that the user has highly rated in the past. Furthermore, the selection unit can also select related news based on news that the user has shared in the past. Thereby, the selection unit can select news that is highly relevant to the user by referring to the past news browsing history. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the past news browsing history to the generation AI, and the generation AI can analyze the data to select optimal news.

[0044] The selection unit can customize the news based on the user's current living situation and field of interest when selecting news. For example, the selection unit customizes the news based on the user's current living situation and field of interest when selecting news. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. The field of interest includes, for example, a hobby and an interesting topic, but is not limited to such examples. For example, when the user starts a new hobby, the selection unit selects news related to the hobby. In addition, when the user changes jobs, the selection unit can also select news related to the new occupation. Furthermore, when the user moves, the selection unit can also select news related to the new area. In this way, the selection unit can select more interesting news by providing news according to the user's current situation. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input data on the current living situation and field of interest into the generation AI, and the generation AI can analyze the data to customize the news.

[0045] The selection unit can select highly relevant news in consideration of the geographical location information of the user when selecting news. For example, the selection unit selects highly relevant news in consideration of the geographical location information of the user when selecting news. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the selection unit selects news related to that area. In addition, if the user is traveling, the selection unit can also select news related to the travel destination. Furthermore, if the user has moved, the selection unit can also select news related to the new area. In this way, the selection unit can provide highly relevant news to the user by considering the geographical location information. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input geographical location information to the generation AI, and the generation AI can analyze the data to select highly relevant news.

[0046] The selection unit can analyze the social media activity of the user and select related news when selecting news. For example, the selection unit analyzes the social media activity of the user and selects related news when selecting news. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the selection unit selects related news based on the content that the user frequently shares on social media. The selection unit can also analyze the content of accounts that the user follows and select related news. Furthermore, the selection unit can select related news based on the content of online communities in which the user participates. In this way, the selection unit can provide news that matches the user's interests by analyzing social media activity. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input data of social media activity to the generation AI, and the generation AI can analyze the data and select related news.

[0047] The voice unit can adjust the level of detail of the voice based on the importance of the news when generating the synthetic voice. For example, the voice unit adjusts the level of detail of the voice based on the importance of the news when generating the synthetic voice. The importance of the news includes, for example, the influence and urgency of the news, but is not limited to such examples. For example, the voice unit provides a synthetic voice including a detailed explanation in the case of important news. In addition, the voice unit can also provide a synthetic voice including a brief explanation in the case of general news. Furthermore, in the case of light-topic news, the voice unit can also provide a synthetic voice that conveys only the main points. In this way, the voice unit can provide appropriate information to the user by adjusting the level of detail of the voice according to the importance of the news. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input the importance data of the news to the generation AI, and the generation AI can analyze the data and adjust the level of detail of the voice.

[0048] The voice unit can apply different voice algorithms depending on the news category when generating synthetic voice. For example, the voice unit applies different voice algorithms depending on the news category when generating synthetic voice. The news categories include, for example, entertainment, sports, politics, etc., but are not limited to such examples. For example, the voice unit applies a voice algorithm including technical terms in the case of technology news. In addition, the voice unit can also apply a voice algorithm that enhances excitement in the case of sports news. Furthermore, the voice unit can also apply a light voice algorithm in the case of entertainment news. In this way, the voice unit can provide appropriate information to the user by applying an optimal voice algorithm according to the news category. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news category data to the generation AI, and the generation AI can analyze the data and apply different voice algorithms.

[0049] The voice unit can determine the priority of the voice based on the time of news submission when generating the synthetic voice. For example, the voice unit determines the priority of the voice based on the time of news submission when generating the synthetic voice. The time of news submission includes, for example, the date and time of news announcement and the latest news, but is not limited to such examples. For example, the voice unit generates synthetic voice with the highest priority in the case of the latest news. In addition, the voice unit can also generate synthetic voice with normal priority in the case of general news. Furthermore, the voice unit can generate synthetic voice with low priority in the case of old news. In this way, the voice unit can provide appropriate information to the user by determining the priority of the voice according to the time of news submission. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news submission time data to the generation AI, and the generation AI can analyze the data to determine the priority of the voice.

[0050] The voice unit can adjust the order of the voices based on the relevance of the news when generating the synthetic voice. For example, the voice unit adjusts the order of the voices based on the relevance of the news when generating the synthetic voice. The relevance of the news includes, for example, the relevance of the topic and the degree of interest of the user, but is not limited to such examples. For example, the voice unit first conveys the news most relevant to the user's interest in the synthetic voice. The voice unit can also convey the news that is moderately relevant to the user's interest in the synthetic voice next. Furthermore, the voice unit can also convey the news that is least relevant to the user's interest in the synthetic voice last. In this way, the voice unit can provide appropriate information to the user by adjusting the order of the voices according to the relevance of the news. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of the voices.

[0051] The research unit can select the optimal confirmation method by referring to the user's past news browsing history when checking the details of the news. For example, the research unit selects the optimal confirmation method by referring to the user's past news browsing history when checking the details of the news. The past news browsing history includes, for example, the type of news browsed and the browsing time, but is not limited to such examples. For example, the research unit provides a related confirmation method based on a news category that the user has previously checked in detail. The research unit can also provide a related confirmation method based on news that the user has previously highly rated. Furthermore, the research unit can also provide a related confirmation method based on news that the user has previously shared. In this way, the research unit can provide a highly relevant confirmation method to the user by referring to the past news browsing history. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input the past news browsing history into AI, and the AI ​​can analyze the data to select the optimal confirmation method.

[0052] The investigation unit can customize the confirmation means based on the user's current living situation when confirming the details of the news. For example, the investigation unit customizes the confirmation means based on the user's current living situation when confirming the details of the news. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. For example, when the user starts a new hobby, the investigation unit provides a confirmation means related to the hobby. In addition, when the user changes jobs, the investigation unit can also provide a confirmation means related to the new occupation. Furthermore, when the user moves, the investigation unit can also provide a confirmation means related to the new area. This allows the investigation unit to provide a confirmation means according to the user's current situation, thereby enabling more effective information provision. Part or all of the above-mentioned processing in the investigation unit may be performed, for example, using AI, or may be performed without using AI. For example, the investigation unit can input data on the current living situation into AI, and the AI ​​can analyze the data to customize the confirmation means.

[0053] The research unit can select the optimal checking method in consideration of the geographical location information of the user when checking the details of the news. For example, the research unit selects the optimal checking method in consideration of the geographical location information of the user when checking the details of the news. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the research unit prioritizes checking the details of news related to that area. In addition, if the user is traveling, the research unit can also prioritize checking the details of news related to the travel destination. Furthermore, if the user has moved, the research unit can also prioritize checking the details of news related to the new area. In this way, the research unit can provide the user with a highly relevant checking method by considering the geographical location information. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input the geographical location information into AI, and the AI ​​can analyze the data to select the optimal checking method.

[0054] The research unit can analyze the social media activity of the user and suggest a means of confirmation when checking the details of the news. For example, when checking the details of the news, the research unit analyzes the social media activity of the user and suggests a means of confirmation. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the research unit suggests detailed confirmation of related news based on the content that the user frequently shares on social media. In addition, the research unit can analyze the content of accounts that the user follows and suggest detailed confirmation of related news. Furthermore, the research unit can suggest detailed confirmation of related news based on the content of online communities in which the user participates. In this way, the research unit can provide the user with a highly relevant means of confirmation by analyzing social media activity. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input data of social media activity into AI, which can analyze the data and suggest a means of confirmation.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The alarm system can further analyze the user's sleep pattern and provide an optimal timing for waking up. For example, the collection unit collects the user's sleep data, and the selection unit analyzes the collected data to identify the timing when the user is in the lightest sleep. The audio unit delivers news at that timing, encouraging the user to wake up naturally. The research unit can also track the user's behavior after waking up and evaluate the effectiveness of waking up. In this way, the alarm system can provide an optimal awakening based on the user's sleep pattern and support a healthier life.

[0057] The alarm system can further collect dietary information of the user and provide health-related news. For example, the collection unit collects the user's dietary records, and the selection unit analyzes the collected data to select news related to the user's diet. The audio unit delivers the selected news in a synthetic voice to increase the user's health awareness. The survey unit can also check whether the user has improved their dietary habits based on the provided health news. In this way, the alarm system can support the user's health and promote better lifestyle habits.

[0058] The alarm system can further collect exercise data of the user and provide fitness-related news. For example, the collection unit collects the user's exercise records, and the selection unit analyzes the collected data to select news related to the user's exercise habits. The audio unit delivers the selected news in a synthetic voice to increase the user's motivation to exercise. The survey unit can also check whether the user has improved their exercise habits based on the provided fitness news. In this way, the alarm system can support the user's fitness and promote a healthier life.

[0059] The alarm system can further analyze the user's stress level and provide news related to relaxation. For example, the collection unit collects the user's stress data, and the selection unit analyzes the collected data to select news related to the user's stress level. The audio unit promotes relaxation of the user by delivering the selected news in a synthetic voice. The survey unit can also confirm whether the user has performed stress management based on the provided relaxation news. In this way, the alarm system can support the user's stress management and promote a more relaxed life.

[0060] The alarm system can further collect the user's learning history and provide news related to education. For example, the collection unit collects the user's learning records, and the selection unit analyzes the collected data to select news related to the user's learning content. The audio unit delivers the selected news in a synthetic voice to increase the user's motivation to study. The survey unit can also check whether the user has improved their learning habits based on the provided educational news. In this way, the alarm system can support the user's learning and promote more effective learning habits.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The collection unit collects user attribute information. The user attribute information includes, for example, age, sex, occupation, hobbies, etc. The collection unit collects user attribute information using questionnaires, sensors, and online data. Step 2: The selection unit uses the generation AI to analyze the attribute information collected by the collection unit and selects news that the user is interested in. The generation AI selects news using, for example, a text generation AI (e.g., LLM). For a user who likes sports, the latest sports news is selected, and for a user who is interested in technology, the latest technology news is selected. Step 3: The voice unit conveys the news selected by the selection unit to the user in a synthetic voice. The synthetic voice is generated using a voice synthesis engine. For example, a part of the news is conveyed in a synthetic voice, such as "Good morning. Today's news. We will be reporting on the latest technology news." Step 4: The research department investigates whether the user checked the details of the news conveyed by the audio part. The investigation is carried out, for example, by counting the number of clicks or by using user feedback. For example, the research department checks whether the user clicked on a link in the app to check the details of the news.

[0063] (Example 2) The alarm system according to the embodiment of the present invention is a system that stimulates intellectual curiosity by collecting attribute information of a user, selecting news that is likely to interest the user through a generation AI, and conveying a part of the news through a synthetic voice. This alarm system stimulates intellectual curiosity by collecting attribute information of a user, selecting news that is likely to interest the user through a generation AI, and conveying a part of the news through a synthetic voice. When a user is interested in the news, their mind becomes clear as they investigate the details, and they wake up. By using this alarm, the user is freed from the loud alarm sound every morning, and they can wake up actively of their own volition. For example, the attribute information of the user is collected. For example, information such as age, gender, occupation, and hobbies is collected. This information is input to the generation AI. Next, the generation AI analyzes the collected attribute information and selects news that may interest the user. For example, the latest sports news is selected for a user who likes sports, and the latest technology news is selected for a user who is interested in technology. The selected news is conveyed to the user through a synthetic voice. For example, a part of the news is delivered by synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." In addition, it is investigated whether the user has looked into the details of the news delivered. For example, it is checked whether the user clicked on a link in the app to look up the details of the news. This information is fed back to the generation AI and used for the next news selection. With this mechanism, users are freed from the shrill alarm sound every morning and can actively wake up of their own volition. For example, as they look up the details of a news item that interests them, they naturally wake up. In addition, the generation AI selects news that interests the user, making waking up every morning fun. This allows the alarm system to provide interesting news based on the user's attribute information, promoting natural waking.

[0064] The alarm system according to the embodiment includes a collection unit, a selection unit, a voice unit, and a survey unit. The collection unit collects attribute information of a user. The attribute information of a user includes, for example, age, sex, occupation, and hobbies, but is not limited to such examples. The collection unit collects the attribute information of a user, for example, by using a questionnaire. The collection unit can also collect the attribute information of a user by using a sensor. For example, the collection unit can also collect the attribute information of a user by using online data. The selection unit uses a generation AI to analyze the attribute information collected by the collection unit and selects news that may interest the user. The generation AI selects news, for example, by using a text generation AI (for example, LLM). The selection unit can also use the generation AI to select news based on the attribute information of a user. For example, the generation AI selects the latest sports news for a user who likes sports. For a user who is interested in technology, it selects the latest technology news. The voice unit conveys the news selected by the selection unit to the user by synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice unit can also deliver the news using synthetic voice. For example, the voice unit delivers a part of the news using synthetic voice, such as "Good morning. Today's news. I'll tell you the latest technology news." The survey unit investigates whether the user has confirmed the details of the news delivered by the voice unit. The survey is performed, for example, by counting the number of clicks. The survey unit can also check the details of the news using user feedback. For example, the survey unit checks whether the user clicked on a link in the app to check the details of the news. In this way, the alarm system according to the embodiment can provide interesting news based on the user's attribute information, and promote natural waking.

[0065] The collection unit collects attribute information of the user. The user's attribute information includes, but is not limited to, for example, age, sex, occupation, and hobbies. The collection unit collects the user's attribute information, for example, using a questionnaire. The questionnaire is provided in the form of an online form or a question in an app, and is designed so that the user can easily answer it. The collection unit can also collect the user's attribute information using a sensor. For example, data such as the user's activity level and sleep pattern can be collected through a wearable device such as a smart watch or a fitness tracker. This allows detailed information on the user's lifestyle and health condition to be obtained. Furthermore, the collection unit can also collect the user's attribute information using online data. For example, the user's interests and concerns can be understood by analyzing information shared by the user on social media and website browsing history. This allows the collection unit to build a comprehensive user profile from various data sources and collect more accurate attribute information. The collected data is stored in a secure database and encrypted for privacy protection. The collection unit can improve the accuracy and reliability of the entire system by periodically updating the data to reflect the latest attribute information of the user.

[0066] The selection unit uses the generation AI to analyze the attribute information collected by the collection unit and selects news that may interest the user. The generation AI selects news using, for example, a text generation AI (e.g., LLM). Specifically, the generation AI receives the user's attribute information as input and generates highly relevant news articles based on that information. For example, the generation AI selects the latest sports news for a user who likes sports, and the latest technology news for a user who is interested in technology. The generation AI uses natural language processing technology to analyze the content of the news article and extract parts that match the user's interests. The generation AI can also analyze news topics and keywords and select news that best suits the user's interests. Furthermore, the selection unit can use the generation AI to select news based on the user's attribute information. For example, the selection unit provides more personalized news by taking into account the user's past news browsing history and feedback. The selection unit can use the learning algorithm of the generation AI to respond to changes in the user's interests and always provide the latest information. This allows the selection unit to select the news that is most interesting to the user, maximizing the effectiveness of the alarm system.

[0067] The voice unit conveys the news selected by the selection unit to the user in a synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice synthesis engine can receive text data as an input and generate a natural voice. Specifically, the voice unit inputs the text of the selected news article into the voice synthesis engine and plays the generated voice to the user. For example, a part of the news is conveyed in a synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." The voice unit can also adjust the tone and speed of the voice based on the attribute information of the user. For example, the news is conveyed in a bright and lively tone to a young user, and in a slow and calm tone to an older user. In addition, the voice unit supports multiple languages ​​and can convey the news according to the language setting of the user. This allows the voice unit to provide the news in a form that is most easy for the user to hear. Furthermore, the voice unit can add music and sound effects according to the content of the news. For example, cheering music can be added to sports news and futuristic sound effects can be added to technology news to enhance the realism of the news. This allows the audio section to provide the user with engaging and informative news, promoting a natural wake-up experience.

[0068] The research unit investigates whether the user has confirmed the details of the news conveyed by the audio unit. The investigation is carried out, for example, by counting the number of clicks. Specifically, after the audio unit conveys the news, the number of times the user clicks on a link to confirm the details of the news in the app is counted. The research unit can also use user feedback to confirm the details of the news. For example, it checks whether the user clicks on a link in the app to check the details of the news. Furthermore, the research unit can collect user reactions and feedback to help improve the selection and provision method of news. For example, by analyzing how the user reacted to the news and which news attracted the most interest, it is possible to reflect this in future news selection. The research unit analyzes the user's behavioral data and builds a feedback loop to optimize the method and content of news provision. This allows the research unit to accurately grasp the user's interests and concerns and improve the accuracy and effectiveness of the entire system. Furthermore, in order to protect the user's privacy, the research unit anonymizes the collected data and manages it in a secure environment. This allows the research unit to collect data necessary for improving the system while maintaining the user's trust.

[0069] The collection unit can collect attribute information of the user's age, sex, occupation, and hobby. The collection unit, for example, collects the user's age. Specific ranges and classification criteria of age include, for example, teens, twenties, thirties, etc., but are not limited to such examples. The collection unit also collects the user's gender. Specific classification criteria of gender include, for example, male, female, other, etc., but are not limited to such examples. Furthermore, the collection unit collects the user's occupation. Specific classification criteria of occupation include, for example, student, company employee, self-employed, etc., but are not limited to such examples. The collection unit collects the user's hobbies. Specific classification criteria of hobbies include, for example, sports, reading, traveling, etc., but are not limited to such examples. As a result, the collection unit can select news with higher accuracy by collecting detailed attribute information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input questionnaire data into AI, and the AI ​​can analyze the data to collect attribute information.

[0070] The selection unit can analyze the collected attribute information by the generation AI and select news that interests the user. The selection unit can analyze the collected attribute information using, for example, the generation AI. The generation AI can analyze the attribute information using, for example, a text generation AI (for example, LLM). The selection unit can also use the generation AI to select news that interests the user. For example, the generation AI can select the latest sports news for a user who likes sports. For a user who is interested in technology, the generation AI can select the latest technology news. The generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The generation AI can use keyword extraction technology to pick up particularly important information from the user's attribute information and select news based on that. As a result, the selection unit can use the generation AI to improve the accuracy of selecting news that matches the user's interests. Some or all of the above-mentioned processing in the selection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the selection unit can input the collected attribute information into an AI, and the AI ​​can analyze the data to select news.

[0071] The voice unit can convey the selected news to the user in synthetic voice. For example, the voice unit conveys the selected news to the user in synthetic voice. The synthetic voice is generated, for example, by using a voice synthesis engine. The voice synthesis engine is a technology that converts text data into voice data and has advanced voice synthesis capabilities. The voice unit can also convey news using synthetic voice. For example, the voice unit conveys part of the news in synthetic voice, such as "Good morning. Today's news. We will tell you the latest technology news." In this way, the voice unit can effectively convey news to the user by using synthetic voice. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice unit can input the selected news to AI, which generates voice data and conveys it to the user.

[0072] The research unit can confirm whether the user has checked the details of the news. For example, the research unit checks whether the user has checked the details of the news. A specific method of checking includes, for example, counting the number of clicks, but is not limited to such an example. The research unit can also check the details of the news using user feedback. For example, the research unit checks whether a link was clicked in the app to check the details of the news. This allows the research unit to grasp the user's interest in the news. A part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input data on the number of clicks into AI, and the AI ​​can analyze the data to check the details of the news.

[0073] The research unit can confirm whether or not a link was clicked in the app to check the details of the news. The research unit, for example, confirms whether or not a link was clicked in the app to check the details of the news. Specific actions of clicking a link include, for example, the number of clicks and the click position, but are not limited to such examples. This allows the research unit to grasp the specific actions of the user regarding the news. A part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input click data into AI, which analyzes the data to check the details of the news.

[0074] The collection unit can estimate the user's emotion and adjust the collection timing of the attribute information based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the collection timing of the attribute information based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the collection unit collects attribute information at night when the user is relaxed. In addition, the collection unit can also change the collection timing to morning when the user is stressed. Furthermore, the collection unit can set the collection timing to weekends when the user is busy. This allows the collection unit to collect attribute information at an optimal timing according to the user's emotion. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit inputs the user's emotion data to the generation AI, and the generation AI analyzes the data and adjusts the collection timing.

[0075] The collection unit can analyze the user's past attribute information and select the optimal collection method. The collection unit, for example, analyzes the user's past attribute information and selects the optimal collection method. The past attribute information includes, for example, past questionnaire results and past behavior history, but is not limited to such examples. The collection unit, for example, collects attribute information in the form of a simple question based on information provided by the user in the past. The collection unit can also analyze the user's past answer patterns and select the most efficient collection method. Furthermore, the collection unit can prioritize collection methods (questionnaires, voice input, etc.) that the user has used in the past. This enables the collection unit to select the optimal collection method based on the past attribute information, thereby enabling efficient information collection. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the past attribute information into AI, and the AI ​​can analyze the data and select the optimal collection method.

[0076] The collection unit can perform filtering based on the user's current living situation and field of interest when collecting attribute information. For example, the collection unit performs filtering based on the user's current living situation and field of interest when collecting attribute information. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. The field of interest includes, for example, a hobby and a topic of interest, but is not limited to such examples. For example, when the user starts a new hobby, the collection unit preferentially collects attribute information related to the hobby. In addition, when the user changes jobs, the collection unit can also collect attribute information related to the new occupation. Furthermore, when the user moves, the collection unit can also collect attribute information related to the new area. As a result, the collection unit can select more appropriate news by collecting attribute information according to the user's current situation. Part or all of the above-mentioned 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 data on the current living situation and field of interest into AI, and the AI ​​can analyze the data and perform filtering.

[0077] The collection unit can estimate the user's emotion and determine the priority of the attribute information to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and determines the priority of the attribute information to be collected based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, when the user is excited, the collection unit preferentially collects attribute information related to the latest news. In addition, when the user is relaxed, the collection unit can also preferentially collect attribute information related to hobbies. Furthermore, when the user is stressed, the collection unit can also preferentially collect attribute information related to relaxation. This enables the collection unit to determine the priority according to the user's emotion, thereby enabling more effective information collection. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data and determine the priority.

[0078] The collection unit can preferentially collect highly relevant information in consideration of the geographical location information of the user when collecting attribute information. For example, the collection unit preferentially collects highly relevant information in consideration of the geographical location information of the user when collecting attribute information. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the collection unit preferentially collects news related to the area. In addition, if the user is traveling, the collection unit can also preferentially collect news related to the travel destination. Furthermore, if the user moves, the collection unit can also preferentially collect news related to the new area. In this way, the collection unit can collect information highly relevant to the user by considering the geographical location information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input geographical location information to AI, and the AI ​​can analyze the data and preferentially collect highly relevant information.

[0079] The collection unit can analyze the social media activity of the user and collect related information when collecting the attribute information. For example, the collection unit can analyze the social media activity of the user and collect related information when collecting the attribute information. The social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the collection unit collects related attribute information based on the content that the user frequently shares on social media. The collection unit can also analyze the content of accounts that the user follows and collect related attribute information. Furthermore, the collection unit can also collect related attribute information based on the content of online communities in which the user participates. In this way, the collection unit can collect information that matches the user's interests by analyzing the social media activity. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data of social media activity to AI, and the AI ​​can analyze the data and collect related information.

[0080] The selection unit can estimate the user's emotion and adjust the news selection criteria based on the estimated user's emotion. The selection unit, for example, estimates the user's emotion and adjusts the news selection criteria based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the selection unit selects news on a light topic when the user is relaxed. In addition, the selection unit can also select stimulating news when the user is excited. Furthermore, the selection unit can also select news related to relaxation when the user is stressed. In this way, the selection unit can provide more appropriate news by adjusting the news selection criteria according to the user's emotion. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data and adjust the news selection criteria.

[0081] The selection unit can select optimal news by referring to the user's past news browsing history when selecting news. For example, the selection unit selects optimal news by referring to the user's past news browsing history when selecting news. The past news browsing history includes, for example, the type of news browsed and the browsing time, but is not limited to such examples. For example, the selection unit selects related news based on a news category that the user frequently browsed in the past. The selection unit can also select related news based on news that the user has highly rated in the past. Furthermore, the selection unit can also select related news based on news that the user has shared in the past. Thereby, the selection unit can select news that is highly relevant to the user by referring to the past news browsing history. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input the past news browsing history to the generation AI, and the generation AI can analyze the data to select optimal news.

[0082] The selection unit can customize the news based on the user's current living situation and field of interest when selecting news. For example, the selection unit customizes the news based on the user's current living situation and field of interest when selecting news. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. The field of interest includes, for example, a hobby and an interesting topic, but is not limited to such examples. For example, when the user starts a new hobby, the selection unit selects news related to the hobby. In addition, when the user changes jobs, the selection unit can also select news related to the new occupation. Furthermore, when the user moves, the selection unit can also select news related to the new area. In this way, the selection unit can select more interesting news by providing news according to the user's current situation. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input data on the current living situation and field of interest into the generation AI, and the generation AI can analyze the data to customize the news.

[0083] The selection unit can estimate the user's emotion and determine the priority order of news to be selected based on the estimated user's emotion. The selection unit, for example, estimates the user's emotion and determines the priority order of news to be selected based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the selection unit preferentially selects the latest news when the user is excited. In addition, the selection unit can also preferentially select news related to hobbies when the user is relaxed. Furthermore, the selection unit can also preferentially select news related to relaxation when the user is stressed. This allows the selection unit to determine the priority order of news according to the user's emotion, thereby enabling more effective news provision. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the selection unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data to determine the priority order of news.

[0084] The selection unit can select highly relevant news in consideration of the geographical location information of the user when selecting news. For example, the selection unit selects highly relevant news in consideration of the geographical location information of the user when selecting news. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the selection unit selects news related to that area. In addition, if the user is traveling, the selection unit can also select news related to the travel destination. Furthermore, if the user has moved, the selection unit can also select news related to the new area. In this way, the selection unit can provide highly relevant news to the user by considering the geographical location information. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input geographical location information to the generation AI, and the generation AI can analyze the data to select highly relevant news.

[0085] The selection unit can analyze the social media activity of the user and select related news when selecting news. For example, the selection unit analyzes the social media activity of the user and selects related news when selecting news. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the selection unit selects related news based on the content that the user frequently shares on social media. The selection unit can also analyze the content of accounts that the user follows and select related news. Furthermore, the selection unit can select related news based on the content of online communities in which the user participates. In this way, the selection unit can provide news that matches the user's interests by analyzing social media activity. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the selection unit can input data of social media activity to the generation AI, and the generation AI can analyze the data and select related news.

[0086] The voice unit can estimate the user's emotion and adjust the tone and speed of the synthetic voice based on the estimated user's emotion. The voice unit, for example, estimates the user's emotion and adjusts the tone and speed of the synthetic voice based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the voice unit provides a synthetic voice with a calm tone and a slow speed when the user is relaxed. In addition, the voice unit can also provide a synthetic voice with a bright tone and a fast speed when the user is excited. Furthermore, the voice unit can provide a synthetic voice with a calm tone and a medium speed when the user is stressed. This allows the voice unit to provide a more effective voice by adjusting the tone and speed of the synthetic voice according to the user's emotion. A part or all of the above-mentioned processing in the voice unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the voice unit can input the user's emotional data into the generation AI, which can then analyze the data and adjust the tone and speed of the synthesized voice.

[0087] The voice unit can adjust the level of detail of the voice based on the importance of the news when generating the synthetic voice. For example, the voice unit adjusts the level of detail of the voice based on the importance of the news when generating the synthetic voice. The importance of the news includes, for example, the influence and urgency of the news, but is not limited to such examples. For example, the voice unit provides a synthetic voice including a detailed explanation in the case of important news. In addition, the voice unit can also provide a synthetic voice including a brief explanation in the case of general news. Furthermore, in the case of light-topic news, the voice unit can also provide a synthetic voice that conveys only the main points. In this way, the voice unit can provide appropriate information to the user by adjusting the level of detail of the voice according to the importance of the news. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input the importance data of the news to the generation AI, and the generation AI can analyze the data and adjust the level of detail of the voice.

[0088] The voice unit can apply different voice algorithms depending on the news category when generating synthetic voice. For example, the voice unit applies different voice algorithms depending on the news category when generating synthetic voice. The news categories include, for example, entertainment, sports, politics, etc., but are not limited to such examples. For example, the voice unit applies a voice algorithm including technical terms in the case of technology news. In addition, the voice unit can also apply a voice algorithm that enhances excitement in the case of sports news. Furthermore, the voice unit can also apply a light voice algorithm in the case of entertainment news. In this way, the voice unit can provide appropriate information to the user by applying an optimal voice algorithm according to the news category. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news category data to the generation AI, and the generation AI can analyze the data and apply different voice algorithms.

[0089] The voice unit can estimate the user's emotion and adjust the length of the synthetic voice based on the estimated user's emotion. The voice unit, for example, estimates the user's emotion and adjusts the length of the synthetic voice based on the estimated user's emotion. The emotion estimation is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the voice unit provides a longer synthetic voice when the user is relaxed. In addition, the voice unit can also provide a shorter synthetic voice when the user is excited. Furthermore, the voice unit can also provide a medium-length synthetic voice when the user is stressed. This allows the voice unit to adjust the length of the synthetic voice according to the user's emotion, thereby enabling more effective voice provision. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the voice unit can input the user's emotion data to the generation AI, and the generation AI can analyze the data and adjust the length of the synthetic voice.

[0090] The voice unit can determine the priority of the voice based on the time of news submission when generating the synthetic voice. For example, the voice unit determines the priority of the voice based on the time of news submission when generating the synthetic voice. The time of news submission includes, for example, the date and time of news announcement and the latest news, but is not limited to such examples. For example, the voice unit generates synthetic voice with the highest priority in the case of the latest news. In addition, the voice unit can also generate synthetic voice with normal priority in the case of general news. Furthermore, the voice unit can generate synthetic voice with low priority in the case of old news. In this way, the voice unit can provide appropriate information to the user by determining the priority of the voice according to the time of news submission. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news submission time data to the generation AI, and the generation AI can analyze the data to determine the priority of the voice.

[0091] The voice unit can adjust the order of the voices based on the relevance of the news when generating the synthetic voice. For example, the voice unit adjusts the order of the voices based on the relevance of the news when generating the synthetic voice. The relevance of the news includes, for example, the relevance of the topic and the degree of interest of the user, but is not limited to such examples. For example, the voice unit first conveys the news most relevant to the user's interest in the synthetic voice. The voice unit can also convey the news that is moderately relevant to the user's interest in the synthetic voice next. Furthermore, the voice unit can also convey the news that is least relevant to the user's interest in the synthetic voice last. In this way, the voice unit can provide appropriate information to the user by adjusting the order of the voices according to the relevance of the news. Part or all of the above-mentioned processing in the voice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the voice unit can input news relevance data to the generation AI, and the generation AI can analyze the data and adjust the order of the voices.

[0092] The investigation unit can estimate the user's emotion and adjust the method of confirming the details of the news based on the estimated user's emotion. The investigation unit, for example, estimates the user's emotion and adjusts the method of confirming the details of the news based on the estimated user's emotion. The estimation of the emotion is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the investigation unit provides a detailed confirmation method when the user is relaxed. In addition, the investigation unit can also provide a concise confirmation method when the user is excited. Furthermore, the investigation unit can also provide a gentle confirmation method when the user is stressed. This allows the investigation unit to adjust the method of confirming the details of the news according to the user's emotion, thereby enabling more effective information provision. Part or all of the above-mentioned processing in the investigation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the investigation unit can input the user's emotion data into the generation AI, and the generation AI can analyze the data and adjust the method of confirming the details of the news.

[0093] The research unit can select the optimal confirmation method by referring to the user's past news browsing history when checking the details of the news. For example, the research unit selects the optimal confirmation method by referring to the user's past news browsing history when checking the details of the news. The past news browsing history includes, for example, the type of news browsed and the browsing time, but is not limited to such examples. For example, the research unit provides a related confirmation method based on a news category that the user has previously checked in detail. The research unit can also provide a related confirmation method based on news that the user has previously highly rated. Furthermore, the research unit can also provide a related confirmation method based on news that the user has previously shared. In this way, the research unit can provide a highly relevant confirmation method to the user by referring to the past news browsing history. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input the past news browsing history into AI, and the AI ​​can analyze the data to select the optimal confirmation method.

[0094] The investigation unit can customize the confirmation means based on the user's current living situation when confirming the details of the news. For example, the investigation unit customizes the confirmation means based on the user's current living situation when confirming the details of the news. The current living situation includes, for example, a professional situation and a family situation, but is not limited to such examples. For example, when the user starts a new hobby, the investigation unit provides a confirmation means related to the hobby. In addition, when the user changes jobs, the investigation unit can also provide a confirmation means related to the new occupation. Furthermore, when the user moves, the investigation unit can also provide a confirmation means related to the new area. This allows the investigation unit to provide a confirmation means according to the user's current situation, thereby enabling more effective information provision. Part or all of the above-mentioned processing in the investigation unit may be performed, for example, using AI, or may be performed without using AI. For example, the investigation unit can input data on the current living situation into AI, and the AI ​​can analyze the data to customize the confirmation means.

[0095] The investigation unit can estimate the user's emotion and determine the priority of checking the details of news based on the estimated user's emotion. The investigation unit, for example, estimates the user's emotion and determines the priority of checking the details of news based on the estimated user's emotion. The estimation of emotion is realized by using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. For example, the investigation unit prioritizes checking the details of the latest news when the user is excited. In addition, the investigation unit can also prioritize checking the details of news related to hobbies when the user is relaxed. Furthermore, the investigation unit can also prioritize checking the details of news related to relaxation when the user is stressed. This allows the investigation unit to determine the priority of checking the details of news according to the user's emotion, thereby enabling more effective information provision. Part or all of the above-mentioned processing in the investigation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the research department can input user emotional data into the generation AI, which can then analyze the data to determine priorities for checking news details.

[0096] The research unit can select the optimal checking method in consideration of the geographical location information of the user when checking the details of the news. For example, the research unit selects the optimal checking method in consideration of the geographical location information of the user when checking the details of the news. The geographical location information includes, for example, GPS data and location information services, but is not limited to such examples. For example, if the user lives in a specific area, the research unit prioritizes checking the details of news related to that area. In addition, if the user is traveling, the research unit can also prioritize checking the details of news related to the travel destination. Furthermore, if the user has moved, the research unit can also prioritize checking the details of news related to the new area. In this way, the research unit can provide the user with a highly relevant checking method by considering the geographical location information. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input the geographical location information into AI, and the AI ​​can analyze the data to select the optimal checking method.

[0097] The research unit can analyze the social media activity of the user and suggest a means of confirmation when checking the details of the news. For example, when checking the details of the news, the research unit analyzes the social media activity of the user and suggests a means of confirmation. Social media activity includes, for example, the content of posts and the number of likes, but is not limited to such examples. For example, the research unit suggests detailed confirmation of related news based on the content that the user frequently shares on social media. In addition, the research unit can analyze the content of accounts that the user follows and suggest detailed confirmation of related news. Furthermore, the research unit can suggest detailed confirmation of related news based on the content of online communities in which the user participates. In this way, the research unit can provide the user with a highly relevant means of confirmation by analyzing social media activity. Part or all of the above-mentioned processing in the research unit may be performed, for example, using AI, or may be performed without using AI. For example, the research unit can input data of social media activity into AI, which can analyze the data and suggest a means of confirmation.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The alarm system can further analyze the user's sleep pattern and provide an optimal timing for waking up. For example, the collection unit collects the user's sleep data, and the selection unit analyzes the collected data to identify the timing when the user is in the lightest sleep. The audio unit delivers news at that timing, encouraging the user to wake up naturally. The research unit can also track the user's behavior after waking up and evaluate the effectiveness of waking up. In this way, the alarm system can provide an optimal awakening based on the user's sleep pattern and support a healthier life.

[0100] The alarm system can further collect dietary information of the user and provide health-related news. For example, the collection unit collects the user's dietary records, and the selection unit analyzes the collected data to select news related to the user's diet. The audio unit delivers the selected news in a synthetic voice to increase the user's health awareness. The survey unit can also check whether the user has improved their dietary habits based on the provided health news. In this way, the alarm system can support the user's health and promote better lifestyle habits.

[0101] The alarm system can further collect exercise data of the user and provide fitness-related news. For example, the collection unit collects the user's exercise records, and the selection unit analyzes the collected data to select news related to the user's exercise habits. The audio unit delivers the selected news in a synthetic voice to increase the user's motivation to exercise. The survey unit can also check whether the user has improved their exercise habits based on the provided fitness news. In this way, the alarm system can support the user's fitness and promote a healthier life.

[0102] The alarm system can further analyze the user's stress level and provide news related to relaxation. For example, the collection unit collects the user's stress data, and the selection unit analyzes the collected data to select news related to the user's stress level. The audio unit promotes relaxation of the user by delivering the selected news in a synthetic voice. The survey unit can also confirm whether the user has performed stress management based on the provided relaxation news. In this way, the alarm system can support the user's stress management and promote a more relaxed life.

[0103] The alarm system can further collect the user's learning history and provide news related to education. For example, the collection unit collects the user's learning records, and the selection unit analyzes the collected data to select news related to the user's learning content. The audio unit delivers the selected news in a synthetic voice to increase the user's motivation to study. The survey unit can also check whether the user has improved their learning habits based on the provided educational news. In this way, the alarm system can support the user's learning and promote more effective learning habits.

[0104] The alarm system can further estimate the user's emotion and select a news topic based on the estimated emotion. For example, the selection unit selects light-hearted news when the user is relaxed. Also, the selection unit can select stimulating news when the user is excited. Furthermore, the selection unit can select news related to relaxation when the user is stressed. In this way, the selection unit can provide more appropriate news by adjusting the news topic according to the user's emotion.

[0105] The alarm system can further estimate the user's emotions and adjust the way the news is presented based on the estimated emotions. For example, the audio unit can present the news in a calm tone if the user is relaxed. Also, if the user is excited, the audio unit can present the news in a bright tone. Furthermore, if the user is stressed, the audio unit can present the news in a calm tone. This allows the audio unit to provide information more effectively by adjusting the way the news is presented depending on the user's emotions.

[0106] The alarm system can further estimate the user's emotion and adjust the level of detail of the news based on the estimated emotion. For example, the audio unit can provide detailed news when the user is relaxed, and can provide concise news when the user is excited. Furthermore, the audio unit can provide news with a medium level of detail when the user is stressed. This allows the audio unit to provide information more effectively by adjusting the level of detail of the news depending on the user's emotion.

[0107] The alarm system can further estimate the user's emotions and determine the priority order of news based on the estimated emotions. For example, if the user is excited, the selection unit can preferentially select the latest news. If the user is relaxed, the selection unit can preferentially select news related to hobbies. If the user is stressed, the selection unit can preferentially select news related to relaxation. This allows the selection unit to provide news more effectively by determining the priority order of news according to the user's emotions.

[0108] The alarm system can further estimate the user's emotions and adjust the news confirmation method based on the estimated emotions. For example, the research unit can provide a detailed confirmation method when the user is relaxed, and a brief confirmation method when the user is excited. Furthermore, a gentle confirmation method can be provided when the user is stressed. This allows the research unit to provide more effective information provision by adjusting the news confirmation method according to the user's emotions.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The collection unit collects user attribute information. The user attribute information includes, for example, age, sex, occupation, hobbies, etc. The collection unit collects user attribute information using questionnaires, sensors, and online data. Step 2: The selection unit uses the generation AI to analyze the attribute information collected by the collection unit and selects news that the user is interested in. The generation AI selects news using, for example, a text generation AI (e.g., LLM). For a user who likes sports, the latest sports news is selected, and for a user who is interested in technology, the latest technology news is selected. Step 3: The voice unit conveys the news selected by the selection unit to the user in a synthetic voice. The synthetic voice is generated using a voice synthesis engine. For example, a part of the news is conveyed in a synthetic voice, such as "Good morning. Today's news. We will be reporting on the latest technology news." Step 4: The research department investigates whether the user checked the details of the news conveyed by the audio part. The investigation is carried out, for example, by counting the number of clicks or by using user feedback. For example, the research department checks whether the user clicked on a link in the app to check the details of the news.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] For example, the collection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the collection unit can collect attribute information of the user using the camera 42 or the microphone 38B of the smart device 14. The selection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the collected attribute information using a generation AI and selects news that may interest the user. The voice unit is realized by, for example, the control unit 46A of the smart device 14, and conveys the news to the user using a synthetic voice engine. The investigation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and investigates whether the user has confirmed the details of the news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] 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.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] 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.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] For example, the collection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the collection unit can collect attribute information of the user using the camera 42 or the microphone 238 of the smart glasses 214. The selection unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the collected attribute information using a generation AI and selects news that may be of interest to the user. The voice unit is realized by, for example, the control unit 46A of the smart glasses 214, and conveys the news to the user using a synthetic voice engine. The investigation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and investigates whether the user has confirmed the details of the news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 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.

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

[0134] 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.

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

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

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

[0138] 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.

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

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

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

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

[0143] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] For example, the collection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the collection unit can collect attribute information of the user using the camera 42 or the microphone 238 of the headset type terminal 314. The selection unit is realized by the specific processing unit 290 of the data processing device 12, for example, and analyzes the collected attribute information using a generation AI to select news that may interest the user. The voice unit is realized by the control unit 46A of the headset type terminal 314, for example, and conveys the news to the user using a synthetic voice engine. The investigation unit is realized by the specific processing unit 290 of the data processing device 12, for example, and investigates whether the user has confirmed the details of the news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

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

[0150] 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.

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

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

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

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] 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.

[0156] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] For example, the collection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the collection unit can collect attribute information of the user using the camera 42 and microphone 238 of the robot 414. The selection unit is realized by the specific processing unit 290 of the data processing device 12, for example, and analyzes the collected attribute information using a generation AI to select news that may interest the user. The voice unit is realized by the control unit 46A of the robot 414, for example, and conveys the news to the user using a synthetic voice engine. The investigation unit is realized by the specific processing unit 290 of the data processing device 12, for example, and investigates whether the user has confirmed the details of the news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0171] 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.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0174] 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.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A collection unit that collects user attribute information; a selection unit that analyzes the attribute information collected by the collection unit and selects news that is of interest to the user; a voice unit that transmits the news selected by the selection unit in a synthetic voice; and a check unit for checking whether the user has confirmed the details of the news conveyed by the audio unit. A system characterized by: (Appendix 2) The collecting unit includes: Collect user attribute information such as age, gender, occupation, and hobbies 2. The system of claim 1, (Appendix 3) The selection unit is Generative AI analyzes collected attribute information and selects news that will interest the user. 2. The system of claim 1, (Appendix 4) The audio section includes: Selected news is conveyed to the user through synthetic voice 2. The system of claim 1, (Appendix 5) The investigation department: Check if the user has looked into the news in detail 2. The system of claim 1, (Appendix 6) The investigation department: Check if you clicked on a link in the app to find out more about a story 2. The system of claim 1, (Appendix 7) The collecting unit includes: To estimate a user's emotion and adjust a timing of collecting attribute information based on the estimated user's emotion. 2. The system of claim 1, (Appendix 8) The collecting unit includes: Analyze users' past attribute information and select the optimal collection method 2. The system of claim 1, (Appendix 9) The collecting unit includes: When collecting attribute information, filtering is performed based on the user's current living situation and areas of interest. 2. The system of claim 1, (Appendix 10) The collecting unit includes: A user's emotion is estimated, and a priority order of attribute information to be collected is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting attribute information, the system prioritizes collecting information that is highly relevant by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting attribute information, we analyze users' social media activity and collect related information. 2. The system of claim 1, (Appendix 13) The selection unit is Estimate user sentiment and adjust news selection criteria based on the estimated user sentiment 2. The system of claim 1, (Appendix 14) The selection unit is When selecting news, the most appropriate news is selected by referring to the user's past news browsing history. 2. The system of claim 1, (Appendix 15) The selection unit is When selecting news, customize the news based on the user's current life situation and areas of interest 2. The system of claim 1, (Appendix 16) The selection unit is Estimate user sentiment and determine the priority of news to be selected based on the estimated user sentiment 2. The system of claim 1, (Appendix 17) The selection unit is When selecting news, the system considers the user's geographic location information to select the most relevant news. 2. The system of claim 1, (Appendix 18) The selection unit is When selecting news, analyze users' social media activity and select relevant news. 2. The system of claim 1, (Appendix 19) The audio section includes: Estimate the user's emotions and adjust the tone and speed of the synthesized speech based on the estimated user's emotions. 2. The system of claim 1, (Appendix 20) The audio section includes: When generating synthetic speech, adjust the level of detail in the speech based on the importance of the news. 2. The system of claim 1, (Appendix 21) The audio section includes: When generating synthetic speech, different speech algorithms are applied depending on the news category. 2. The system of claim 1, (Appendix 22) The audio section includes: Estimating a user's emotion and adjusting the length of the synthesized speech based on the estimated user's emotion 2. The system of claim 1, (Appendix 23) The audio section includes: When generating synthetic speech, prioritize speech based on when the news was submitted 2. The system of claim 1, (Appendix 24) The audio section includes: Adjust the order of speech based on news relevance when generating synthetic speech 2. The system of claim 1, (Appendix 25) The investigation department: Estimate user sentiment and adjust news detail checking method based on estimated user sentiment 2. The system of claim 1, (Appendix 26) The investigation department: When checking news details, the system selects the optimal checking method by referring to the user's past news browsing history. 2. The system of claim 1, (Appendix 27) The investigation department: Customize the way you check news details based on your current life situation 2. The system of claim 1, (Appendix 28) The investigation department: Estimate user sentiment and determine priority for checking news details based on the estimated user sentiment 2. The system of claim 1, (Appendix 29) The investigation department: When checking news details, the optimal method of checking is selected based on the user's geographic location. 2. The system of claim 1, (Appendix 30) The investigation department: When checking news details, the app analyzes users' social media activity to suggest ways to check. 2. The system of claim 1, [Explanation of symbols]

[0183] 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 user attribute information; a selection unit that analyzes the attribute information collected by the collection unit and selects news that is of interest to the user; a voice unit that transmits the news selected by the selection unit in a synthetic voice; and a check unit for checking whether the user has confirmed the details of the news conveyed by the audio unit. A system characterized by:

2. The collecting unit includes: Collect user attribute information such as age, gender, occupation, and hobbies 2. The system of claim 1 .

3. The selection unit is Generative AI analyzes the collected attribute information and selects news that the user is interested in.

2. The system of claim 1 .

4. The investigation department: Check if you clicked on a link in the app to find out more about a story 2. The system of claim 1 .

5. The collecting unit includes: To estimate a user's emotion and adjust a timing of collecting attribute information based on the estimated user's emotion.

2. The system of claim 1 .

6. The collecting unit includes: Analyze users' past attribute information and select the optimal collection method 2. The system of claim 1 .

Images