system

Abstract

The system according to this embodiment aims to streamline long-term monitoring by providing notifications only when specific events occur. [Solution] The system according to the embodiment comprises a storage unit, a transmission unit, an analysis unit, and a notification unit. The storage unit stores camera images. The transmission unit transmits the images stored by the storage unit to a generation AI. The analysis unit analyzes the images transmitted by the transmission unit. The notification unit provides notifications based on the results of the analysis performed by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to perform manually when long-term monitoring is required, and there is a risk of missing a specific event.

[0005] The system according to the embodiment aims to improve the efficiency of long-term monitoring by performing notifications only when a specific event occurs.

Means for Solving the Problems

[0006] The system according to the embodiment includes a storage unit, a transmission unit, an analysis unit, and a notification unit. The storage unit stores camera images. The transmission unit transmits the images stored by the storage unit to a generation AI. The analysis unit analyzes the images transmitted by the transmission unit. The notification unit performs notifications based on the results analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline long-term monitoring by providing notifications only when specific events occur. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that analyzes camera images using a generating AI and provides notifications only when a specific event occurs. In this AI agent system, the camera saves images every few seconds, and the saved images are sent to the generating AI for analysis. The generating AI recognizes people and objects in the image and describes the situation. For example, if a person acting suspiciously is captured in the image, a notification is provided based on that information. This notification is delivered via a messaging platform or voice assistant. Furthermore, the prompts can be freely changed, and the system can be applied to various uses such as preventing theft of cars and crops, monitoring pets, and observing wild birds. For example, in the case of preventing car theft, the camera monitors the parking lot and provides a notification when suspicious activity is detected. In the case of preventing theft of crops, the system monitors the field and provides a notification when a suspicious person approaches. In the case of monitoring pets, the system monitors the pet's movements and provides a notification if there is an abnormality. In the case of observing wild birds, the system monitors wild birds that come to the garden and provides a notification when a specific type of wild bird appears. This mechanism allows for efficient monitoring without human intervention, even when long-term monitoring is required. Furthermore, by only sending notifications when specific events occur, it reduces unnecessary notifications and prevents important information from being missed. For example, it can be used in various situations, such as checking on pets while traveling or observing wild birds that visit your garden. This AI agent is compatible with inexpensive cameras and can provide the same functionality as expensive security cameras. For example, it sends an image to a generating AI to check if there is a person in the image and analyzes what that person is doing. It also compares the two most recent images, and if the similarity is high, it omits sending the image to the generating AI, thereby reducing token consumption. In this way, the AI ​​agent utilizing generating AI is a groundbreaking mechanism that can be applied to various uses such as security, surveillance, and observation. As a result, the AI ​​agent system can analyze camera images and send notifications only when specific events occur.

[0029] The AI ​​agent system according to this embodiment comprises a storage unit, a transmission unit, an analysis unit, and a notification unit. The storage unit stores camera images. For example, the camera stores images once every few seconds. When saving images, the storage unit can consider the type and resolution of the image. For example, the storage unit can store still images and videos. The storage unit can also adjust the resolution of the image before saving it. The transmission unit sends the images stored by the storage unit to the generating AI. For example, the transmission unit performs image analysis by sending the stored images to the generating AI. The transmission unit can adjust the method and timing of image transmission. For example, the transmission unit can transmit images in real time. The transmission unit can also transmit images at regular intervals. The analysis unit analyzes the images transmitted by the transmission unit. The analysis unit uses the generating AI to recognize people and objects in the image and describe the situation. For example, the analysis unit recognizes the face of a person in the image and analyzes what that person is doing. Furthermore, the analysis unit can recognize objects in the image and describe the situation of those objects. The notification unit provides notifications based on the results of the analysis performed by the analysis unit. For example, the notification unit provides notifications when a specific event occurs based on the results of the analysis performed by the analysis unit. The notification unit can adjust the notification method and timing. For example, the notification unit provides notifications through a messaging platform or a voice assistant. The notification unit can also adjust the timing of notifications to ensure that important information is not missed. As a result, the AI ​​agent system according to the embodiment can analyze camera images and provide notifications only when a specific event occurs.

[0030] The storage unit stores camera images. For example, the camera saves images every few seconds. When saving images, the storage unit can consider the image type and resolution. Specifically, the storage unit can save still images and videos. In the case of still images, a specific moment is captured and saved, so important moments are recorded without being missed. On the other hand, in the case of videos, continuous movement is recorded, so changes in the situation can be understood in detail. The storage unit can also adjust the resolution of the images before saving them. High-resolution images contain detailed information, which can improve the accuracy of analysis, but the storage capacity is large, so storage management becomes important. Low-resolution images save storage capacity, but the accuracy of analysis may decrease. The storage unit is required to consider these balances and save images at the optimal resolution. Furthermore, the storage unit can add metadata to the saved images. Metadata includes the date and time of shooting, the location of shooting, camera settings, etc., which is useful for later analysis and searching. This allows the storage unit to save images efficiently and effectively and provide the information necessary for subsequent processing.

[0031] The transmission unit sends images stored by the storage unit to the generation AI. For example, the transmission unit performs image analysis by sending stored images to the generation AI. The transmission unit can adjust the method and timing of image transmission. Specifically, the transmission unit can transmit images in real time. Real-time transmission is effective when immediate analysis is required and is suitable for situations where a rapid response is needed. The transmission unit can also transmit images at regular intervals. Transmission at regular intervals is suitable for periodic monitoring and long-term data collection, and can distribute the system load. The transmission unit is required to select the optimal transmission method considering the network status and system load. Furthermore, the transmission unit can compress and encrypt the images it transmits. Compression is effective in reducing the amount of data transmitted and saving network bandwidth. Encryption is important to ensure the security of transmitted data and prevent unauthorized access and data leakage. This allows the transmission unit to efficiently and securely transmit images and support analysis by the generation AI.

[0032] The analysis unit analyzes the images transmitted by the transmission unit. Using generation AI, the analysis unit recognizes people and objects in the image and describes their situation. Specifically, the analysis unit recognizes the faces of people in the image and analyzes what actions those people are taking. For example, using facial recognition technology, it can identify a specific person and analyze their emotions, such as smiling, being angry, or being sad. The analysis unit can also recognize objects in the image and describe their situation. For example, using object recognition technology, it can identify vehicles, furniture, animals, etc., and analyze their situation, such as whether they are moving, stationary, or damaged. Furthermore, the analysis unit can analyze the background and environmental information of the image to grasp the overall situation. For example, it can analyze information such as weather, time of day, and location to detect changes or anomalies in the situation. The analysis unit integrates this information to generate a comprehensive situation description and provides it to the notification unit. This allows the analysis unit to analyze the information obtained from the image in detail and accurately understand the situation.

[0033] The notification unit provides notifications based on the results analyzed by the analysis unit. For example, the notification unit provides notifications when a specific event occurs, based on the results analyzed by the analysis unit. Specifically, the notification unit provides notifications through messaging platforms and voice assistants. When using a messaging platform, it can send text messages, images, and videos to quickly convey important information to users. When using a voice assistant, it can issue voice notifications and alerts to attract the user's attention. The notification unit can adjust the method and timing of notifications. For example, the notification unit can send notifications at specific times to ensure that users do not miss important information. The notification unit can also set notification priorities, prioritizing the notification of high-priority information. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of notification content. For example, it can analyze user reactions and actions after receiving notifications to optimize the content and timing of notifications. This allows the notification unit to provide users with appropriate information quickly and reliably, improving the reliability and effectiveness of the entire system.

[0034] The analysis unit can recognize people and objects in an image and describe their situation. For example, the analysis unit can recognize the faces of people in an image and analyze what actions those people are taking. For example, the analysis unit can recognize the faces of people in an image using facial recognition technology. The analysis unit can also recognize objects in an image using object recognition technology. For example, the analysis unit can recognize the type and shape of objects in an image and describe the situation of those objects. For example, the analysis unit can analyze the actions of people in an image and determine whether those actions are suspicious. This improves the accuracy of notifications by recognizing people and objects in images and describing their situations. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit inputs an image into the generative AI, which recognizes people and objects in the image and describes their situation.

[0035] The notification unit can send notifications through messaging platforms or voice assistants. For example, the notification unit can send notifications through messaging platforms. For example, the notification unit can use messaging platforms to notify users of the results analyzed by the analysis unit. The notification unit can also send notifications through voice assistants. For example, the notification unit can use voice assistants to notify users of the results analyzed by the analysis unit. This allows information to be quickly conveyed to users by sending notifications through messaging platforms or voice assistants. Some or all of the above-described processes in the notification unit may be performed using AI or not. For example, the notification unit inputs the results analyzed by the analysis unit into AI, the AI ​​generates notification content, and sends the notification through messaging platforms or voice assistants.

[0036] The modification section allows the prompt to be freely modified. For example, the modification section allows the user to freely change the content of the prompt. For example, the modification section can provide an interface for the user to change the content of the prompt. For example, the modification section can provide a settings screen for the user to change the content of the prompt. By making the prompt freely modifiable, it can be applied to various uses. Some or all of the above processing in the modification section may be performed using AI or not. For example, the modification section inputs an interface for the user to change the content of the prompt to the AI, and the AI ​​generates a settings screen for changing the content of the prompt.

[0037] The similarity calculation unit calculates the similarity of the two most recent images, and if the similarity is high, it can omit sending the data to the generating AI. The similarity calculation unit calculates the similarity of the two most recent images, for example. The similarity calculation unit can calculate the similarity of the two most recent images using, for example, cosine similarity. The similarity calculation unit can also calculate the similarity of the two most recent images using Euclidean distance. The similarity calculation unit can omit sending the data to the generating AI if the similarity of the two most recent images is high. This reduces token consumption by omitting sending the data to the generating AI when the similarity is high. Some or all of the above processing in the similarity calculation unit may be performed using AI or not using AI. For example, the similarity calculation unit inputs the two most recent images to the AI, the AI ​​calculates the similarity, and if the similarity is high, it omits sending the data to the generating AI.

[0038] The modification unit can be applied to a variety of uses, such as preventing theft of cars and crops, monitoring pets, and observing wild birds. For example, the modification unit can be applied to preventing car theft. For example, the modification unit can monitor a parking lot with a camera and notify when it detects suspicious activity. For example, the modification unit can be applied to preventing theft of crops. For example, the modification unit can monitor a field and notify when a suspicious person approaches. For example, the modification unit can be applied to monitoring pets. For example, the modification unit can monitor the pet's movements and notify if there is an abnormality. For example, the modification unit can be applied to observing wild birds. For example, the modification unit can monitor wild birds that come to the garden and notify when a specific type of wild bird appears. This allows for application to a wide range of uses and can be utilized in various scenarios. Some or all of the above-mentioned processes in the modification unit may be performed using AI or not. For example, the modification unit inputs images captured by a camera into an AI, the AI ​​analyzes the images, and notifies when a specific event occurs.

[0039] The storage unit can automatically adjust image quality to optimize storage capacity during saving. For example, the storage unit can automatically adjust image resolution to optimize storage capacity during saving. For example, the storage unit can automatically adjust image compression ratio to optimize storage capacity during saving. For example, the storage unit can automatically adjust image color depth to optimize storage capacity during saving. In this way, storage capacity can be optimized by automatically adjusting image quality. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit inputs image resolution and compression ratio to the AI, which calculates the optimal quality and optimizes storage capacity.

[0040] The storage unit can change the resolution of images to be saved based on specific time periods or events. For example, at night, the storage unit can save data capacity by saving at a low resolution. During events, for example, the storage unit can save at a high resolution to preserve detailed records. During normal times, for example, the storage unit can balance this by saving at a medium resolution. This allows for efficient management of storage capacity by changing the image resolution based on specific time periods or events. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input information about specific time periods or events into the AI, which can then calculate the optimal resolution and manage storage capacity.

[0041] The storage unit can filter the content of images to be saved, taking into account the user's geographical location information. For example, if the user is in a specific location, the storage unit will prioritize saving images related to that location. For example, if the user is on the move, the storage unit will prioritize saving images related to the travel route. For example, if the user is at home, the storage unit will prioritize saving images related to home. In this way, by filtering the content of images while taking into account the user's geographical location information, highly relevant images can be saved. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can input the user's geographical location information into the AI, and the AI ​​will filter and save relevant images.

[0042] The storage unit can analyze the user's social media activity during saving and prioritize saving relevant images. For example, the storage unit may prioritize saving images that the user has shared on social media. For example, the storage unit may prioritize saving images that the user has tagged on social media. For example, the storage unit may prioritize saving images that the user has liked on social media. In this way, by analyzing the user's social media activity, relevant images can be prioritized for saving. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit may input the user's social media activity data into AI, which will analyze and save relevant images.

[0043] The transmitting unit can optimize the transmission speed during transmission, taking into account the network conditions. For example, if the network is congested, the transmitting unit will lower the transmission speed to ensure stability. For example, if the network is not congested, the transmitting unit will increase the transmission speed for faster transmission. For example, the transmitting unit will automatically adjust the transmission speed according to the network conditions. This allows for stable transmission by optimizing the transmission speed while considering the network conditions. Some or all of the above processing in the transmitting unit may be performed using AI, or it may be performed without AI. For example, the transmitting unit inputs network condition data to the AI, and the AI ​​optimizes the transmission speed.

[0044] The transmission unit can determine the transmission priority based on the importance of the images during transmission. For example, the transmission unit may prioritize the transmission of important images. For example, the transmission unit may transmit normal images at an appropriate time. For example, the transmission unit may postpone the transmission of less important images. In this way, by determining the transmission priority based on the importance of the images, important images can be transmitted preferentially. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit may input image importance data into the AI, and the AI ​​may determine the transmission priority.

[0045] The transmission unit can select the optimal transmission method at the time of transmission, taking into account the user's device information. For example, if the user is using a smartphone, the transmission unit provides a transmission method optimized for mobile data. For example, if the user is using a tablet, the transmission unit provides a transmission method optimized for a large screen. For example, if the user is using a personal computer, the transmission unit transmits high-resolution images. This enables transmission optimized for the user's device by selecting the optimal transmission method considering the user's device information. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit inputs the user's device information into the AI, and the AI ​​selects the optimal transmission method.

[0046] The transmission unit can customize the content of a transmission by referring to the user's past transmission history. For example, the transmission unit can analyze patterns in images previously sent by the user and suggest the most suitable content. For example, the transmission unit can prioritize sending images related to specific events from the user's past transmission history. For example, the transmission unit can customize and send the content based on the user's past transmission history. This allows for transmissions tailored to the user's needs by customizing the content based on the user's past transmission history. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit can input the user's past transmission history data into the AI, and the AI ​​can customize the content of the transmission.

[0047] The analysis unit can improve the accuracy of the analysis by considering the background information of the image during the analysis. For example, the analysis unit recognizes objects in the background of the image and reflects this in the analysis results. For example, the analysis unit improves the accuracy of the analysis by considering the brightness and hue of the background of the image. For example, the analysis unit reflects the movement of people in the background of the image in the analysis. In this way, the accuracy of the analysis is improved by considering the background information of the image. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit inputs the background information of the image into a generation AI, and the generation AI improves the accuracy of the analysis by considering the background information.

[0048] The analysis unit can optimize the analysis algorithm based on the image capture conditions during analysis. For example, the analysis unit optimizes the analysis algorithm by considering the image capture time and weather conditions. For example, the analysis unit optimizes the analysis algorithm by considering the image capture angle and distance. For example, the analysis unit optimizes the analysis algorithm by considering the characteristics of the image capture device. By optimizing the analysis algorithm based on the image capture conditions, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit inputs image capture condition data to a generation AI, and the generation AI optimizes the analysis algorithm by considering the capture conditions.

[0049] The analysis unit can determine the priority of analysis based on the location where the images were taken. For example, the analysis unit may prioritize the analysis of images taken at important locations. For example, the analysis unit may prioritize the analysis of images taken at locations specified by the user. For example, the analysis unit may automatically determine the priority of analysis based on the location where the images were taken. This allows important images to be analyzed preferentially by determining the priority of analysis based on the location where the images were taken. Some or all of the above processing in the analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the analysis unit inputs image location data into a generating AI, and the generating AI determines the priority of analysis considering the location.

[0050] The analysis unit can improve the accuracy of the analysis by referring to related image data during the analysis. For example, the analysis unit improves the accuracy of the analysis by referring to the image metadata. For example, the analysis unit optimizes the analysis algorithm based on related image data. For example, the analysis unit improves the reliability of the analysis results by referring to related image data. As a result, the accuracy of the analysis is improved by referring to related image data. Some or all of the above processes in the analysis unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the analysis unit inputs related image data into a generating AI, and the generating AI improves the accuracy of the analysis by referring to the related data.

[0051] The notification unit can determine the priority of notifications based on their importance when they are sent. For example, the notification unit may prioritize important notifications. For example, the notification unit may send regular notifications at appropriate times. For example, the notification unit may postpone sending less important notifications. In this way, by determining the priority of notifications based on their importance, important notifications can be given priority. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit may input notification importance data into the AI, and the AI ​​may determine the priority of the notifications.

[0052] The notification unit can customize notification content by referring to the user's past notification history when sending a notification. For example, the notification unit can analyze patterns of notifications the user has received in the past and suggest the most suitable notification content. For example, the notification unit can prioritize notifications related to specific events based on the user's past notification history. For example, the notification unit can customize notification content based on the user's past notification history. This makes it possible to provide notifications that meet the user's needs by customizing notification content by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input the user's past notification history data into the AI, and the AI ​​will customize the notification content.

[0053] The notification unit can select the optimal notification method when sending a notification, taking into account the user's device information. For example, if the user is using a smartphone, the notification unit provides a notification method optimized for mobile data. For example, if the user is using a tablet, the notification unit provides a notification method optimized for a large screen. For example, if the user is using a personal computer, the notification unit provides high-resolution notifications. This enables notifications optimized for the user's device by selecting the optimal notification method while considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit inputs the user's device information into the AI, and the AI ​​selects the optimal notification method.

[0054] The notification unit can adjust the content of notifications based on the user's current activity status. For example, if the user is working, the notification unit will only send important notifications. If the user is on a break, the notification unit will send regular notifications. If the user is traveling, the notification unit will send concise notifications. By adjusting the content of notifications based on the user's current activity status, it becomes possible to provide notifications that meet the user's needs. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit inputs user activity data into the AI, and the AI ​​adjusts the content of the notifications.

[0055] The change unit can select the optimal change by referring to past prompt change history when making a change. For example, the change unit can analyze patterns of prompts previously changed by the user and propose the optimal change. For example, the change unit can prioritize suggesting changes related to specific events from the user's past prompt change history. For example, the change unit can customize and propose changes based on the user's past prompt change history. This makes it possible to change prompts to meet the user's needs by selecting the optimal change by referring to past prompt change history. Some or all of the above processes in the change unit may be performed using AI or not. For example, the change unit can input past prompt change history data into AI, and the AI ​​can select the optimal change.

[0056] The modification unit can customize the prompt changes based on the user's current needs when making changes. For example, if the user has a specific need, the modification unit will suggest a prompt that meets that need. For example, the modification unit will suggest the optimal prompt based on the user's current situation. For example, the modification unit will analyze the user's current needs and suggest a customized prompt. This makes it possible to change prompts to meet the user's needs by customizing the prompt changes based on the user's current needs. Some or all of the above processing in the modification unit may be performed using AI or not. For example, the modification unit inputs the user's current needs data into the AI, and the AI ​​customizes the optimal prompt changes.

[0057] The similarity calculation unit can improve the accuracy of its calculations by considering the background information of the image during the similarity calculation. For example, the similarity calculation unit recognizes objects in the background of the image and reflects this in the similarity calculation. For example, the similarity calculation unit improves the accuracy of its similarity calculations by considering the brightness and hue of the background of the image. For example, the similarity calculation unit reflects the movement of people in the background of the image in the similarity calculation. By improving the accuracy of the similarity calculation by considering the background information of the image, a more accurate similarity calculation becomes possible. Some or all of the above processing in the similarity calculation unit may be performed using AI or not. For example, the similarity calculation unit inputs the background information of the image into the AI, and the AI ​​improves the accuracy of the similarity calculation by considering the background information.

[0058] The similarity calculation unit can determine the calculation priority based on the image's location during similarity calculation. For example, the similarity calculation unit may prioritize similarity calculations for images taken in important locations. For example, the similarity calculation unit may prioritize similarity calculations for images taken in locations specified by the user. For example, the similarity calculation unit may automatically determine the similarity calculation priority based on the image's location. This allows important images to be calculated preferentially by determining the calculation priority based on the image's location. Some or all of the above processing in the similarity calculation unit may be performed using AI or not. For example, the similarity calculation unit may input image location data into the AI, and the AI ​​may determine the similarity calculation priority considering the location.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The storage unit can optimize saved images by referencing the user's past saving history. For example, it can analyze patterns in images previously saved by the user and prioritize saving similar images. It can also automatically select optimal saving settings based on the resolution and quality of images previously saved by the user. Furthermore, it can prioritize saving related images by referencing tag information of images previously saved by the user. This enables efficient image saving by leveraging the user's past saving history.

[0061] The transmission unit can monitor the network status in real time when transmitting images and select the optimal transmission method. For example, if the network is congested, it can reduce the transmission speed to ensure stability. Conversely, if the network is uncongested, it can increase the transmission speed for faster transmission. Furthermore, it can automatically switch the transmission method according to the network status. This enables efficient image transmission that takes network conditions into consideration.

[0062] The storage unit can automatically categorize saved images based on specific events. For example, it can categorize images based on the types of people or objects they contain. It can also prioritize saving images related to specific events. Furthermore, the storage unit can automatically categorize images based on user-specified conditions. This enables efficient image management.

[0063] The transmission unit can select the optimal transmission method when transmitting images, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a transmission method optimized for mobile data. If the user is using a tablet, it can provide a transmission method optimized for the larger screen. Furthermore, if the user is using a PC, it can transmit high-resolution images. This enables transmission optimized for the user's device.

[0064] The analysis unit can improve the accuracy of image analysis by referring to the user's past analysis history. For example, the analysis unit can analyze patterns in images previously analyzed by the user and prioritize the analysis of similar images. It can also select the optimal analysis algorithm based on the results of images previously analyzed by the user. Furthermore, it can refer to the tag information of images previously analyzed by the user and prioritize the analysis of related images. This enables efficient image analysis by utilizing the user's past analysis history.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The storage unit saves the camera image. For example, the camera saves an image every few seconds. When saving an image, the storage unit can consider the image type and resolution. For example, the storage unit can save still images and videos. The storage unit can also adjust the resolution of the image before saving it. Step 2: The transmission unit sends the images saved by the storage unit to the generation AI. The transmission unit performs image analysis, for example, by sending the saved images to the generation AI. The transmission unit can adjust the method and timing of image transmission. For example, the transmission unit can transmit images in real time. Alternatively, the transmission unit can transmit images at regular intervals. Step 3: The analysis unit analyzes the image transmitted by the transmission unit. The analysis unit uses a generation AI to recognize people and objects in the image and describe their situation. For example, the analysis unit recognizes the faces of people in the image and analyzes what actions those people are taking. The analysis unit can also recognize objects in the image and describe the situation of those objects. Step 4: The notification unit sends notifications based on the results analyzed by the analysis unit. For example, the notification unit sends notifications when a specific event occurs based on the results analyzed by the analysis unit. The notification unit can adjust the notification method and timing. For example, the notification unit sends notifications through messaging platforms or voice assistants. The notification unit can also adjust the timing of notifications to ensure that important information is not missed.

[0067] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that analyzes camera images using a generating AI and provides notifications only when a specific event occurs. In this AI agent system, the camera saves images every few seconds, and the saved images are sent to the generating AI for analysis. The generating AI recognizes people and objects in the image and describes the situation. For example, if a person acting suspiciously is captured in the image, a notification is provided based on that information. This notification is delivered via a messaging platform or voice assistant. Furthermore, the prompts can be freely changed, and the system can be applied to various uses such as preventing theft of cars and crops, monitoring pets, and observing wild birds. For example, in the case of preventing car theft, the camera monitors the parking lot and provides a notification when suspicious activity is detected. In the case of preventing theft of crops, the system monitors the field and provides a notification when a suspicious person approaches. In the case of monitoring pets, the system monitors the pet's movements and provides a notification if there is an abnormality. In the case of observing wild birds, the system monitors wild birds that come to the garden and provides a notification when a specific type of wild bird appears. This mechanism allows for efficient monitoring without human intervention, even when long-term monitoring is required. Furthermore, by only sending notifications when specific events occur, it reduces unnecessary notifications and prevents important information from being missed. For example, it can be used in various situations, such as checking on pets while traveling or observing wild birds that visit your garden. This AI agent is compatible with inexpensive cameras and can provide the same functionality as expensive security cameras. For example, it sends an image to a generating AI to check if there is a person in the image and analyzes what that person is doing. It also compares the two most recent images, and if the similarity is high, it omits sending the image to the generating AI, thereby reducing token consumption. In this way, the AI ​​agent utilizing generating AI is a groundbreaking mechanism that can be applied to various uses such as security, surveillance, and observation. As a result, the AI ​​agent system can analyze camera images and send notifications only when specific events occur.

[0068] The AI ​​agent system according to this embodiment comprises a storage unit, a transmission unit, an analysis unit, and a notification unit. The storage unit stores camera images. For example, the camera stores images once every few seconds. When saving images, the storage unit can consider the type and resolution of the image. For example, the storage unit can store still images and videos. The storage unit can also adjust the resolution of the image before saving it. The transmission unit sends the images stored by the storage unit to the generating AI. For example, the transmission unit performs image analysis by sending the stored images to the generating AI. The transmission unit can adjust the method and timing of image transmission. For example, the transmission unit can transmit images in real time. The transmission unit can also transmit images at regular intervals. The analysis unit analyzes the images transmitted by the transmission unit. The analysis unit uses the generating AI to recognize people and objects in the image and describe the situation. For example, the analysis unit recognizes the face of a person in the image and analyzes what that person is doing. Furthermore, the analysis unit can recognize objects in the image and describe the situation of those objects. The notification unit provides notifications based on the results of the analysis performed by the analysis unit. For example, the notification unit provides notifications when a specific event occurs based on the results of the analysis performed by the analysis unit. The notification unit can adjust the notification method and timing. For example, the notification unit provides notifications through a messaging platform or a voice assistant. The notification unit can also adjust the timing of notifications to ensure that important information is not missed. As a result, the AI ​​agent system according to the embodiment can analyze camera images and provide notifications only when a specific event occurs.

[0069] The storage unit stores camera images. For example, the camera saves images every few seconds. When saving images, the storage unit can consider the image type and resolution. Specifically, the storage unit can save still images and videos. In the case of still images, a specific moment is captured and saved, so important moments are recorded without being missed. On the other hand, in the case of videos, continuous movement is recorded, so changes in the situation can be understood in detail. The storage unit can also adjust the resolution of the images before saving them. High-resolution images contain detailed information, which can improve the accuracy of analysis, but the storage capacity is large, so storage management becomes important. Low-resolution images save storage capacity, but the accuracy of analysis may decrease. The storage unit is required to consider these balances and save images at the optimal resolution. Furthermore, the storage unit can add metadata to the saved images. Metadata includes the date and time of shooting, the location of shooting, camera settings, etc., which is useful for later analysis and searching. This allows the storage unit to save images efficiently and effectively and provide the information necessary for subsequent processing.

[0070] The transmission unit sends images stored by the storage unit to the generation AI. For example, the transmission unit performs image analysis by sending stored images to the generation AI. The transmission unit can adjust the method and timing of image transmission. Specifically, the transmission unit can transmit images in real time. Real-time transmission is effective when immediate analysis is required and is suitable for situations where a rapid response is needed. The transmission unit can also transmit images at regular intervals. Transmission at regular intervals is suitable for periodic monitoring and long-term data collection, and can distribute the system load. The transmission unit is required to select the optimal transmission method considering the network status and system load. Furthermore, the transmission unit can compress and encrypt the images it transmits. Compression is effective in reducing the amount of data transmitted and saving network bandwidth. Encryption is important to ensure the security of transmitted data and prevent unauthorized access and data leakage. This allows the transmission unit to efficiently and securely transmit images and support analysis by the generation AI.

[0071] The analysis unit analyzes the images transmitted by the transmission unit. Using generation AI, the analysis unit recognizes people and objects in the image and describes their situation. Specifically, the analysis unit recognizes the faces of people in the image and analyzes what actions those people are taking. For example, using facial recognition technology, it can identify a specific person and analyze their emotions, such as smiling, being angry, or being sad. The analysis unit can also recognize objects in the image and describe their situation. For example, using object recognition technology, it can identify vehicles, furniture, animals, etc., and analyze their situation, such as whether they are moving, stationary, or damaged. Furthermore, the analysis unit can analyze the background and environmental information of the image to grasp the overall situation. For example, it can analyze information such as weather, time of day, and location to detect changes or anomalies in the situation. The analysis unit integrates this information to generate a comprehensive situation description and provides it to the notification unit. This allows the analysis unit to analyze the information obtained from the image in detail and accurately understand the situation.

[0072] The notification unit provides notifications based on the results analyzed by the analysis unit. For example, the notification unit provides notifications when a specific event occurs, based on the results analyzed by the analysis unit. Specifically, the notification unit provides notifications through messaging platforms and voice assistants. When using a messaging platform, it can send text messages, images, and videos to quickly convey important information to users. When using a voice assistant, it can issue voice notifications and alerts to attract the user's attention. The notification unit can adjust the method and timing of notifications. For example, the notification unit can send notifications at specific times to ensure that users do not miss important information. The notification unit can also set notification priorities, prioritizing the notification of high-priority information. Furthermore, the notification unit can collect user feedback and continuously improve the accuracy and effectiveness of notification content. For example, it can analyze user reactions and actions after receiving notifications to optimize the content and timing of notifications. This allows the notification unit to provide users with appropriate information quickly and reliably, improving the reliability and effectiveness of the entire system.

[0073] The analysis unit can recognize people and objects in an image and describe their situation. For example, the analysis unit can recognize the faces of people in an image and analyze what actions those people are taking. For example, the analysis unit can recognize the faces of people in an image using facial recognition technology. The analysis unit can also recognize objects in an image using object recognition technology. For example, the analysis unit can recognize the type and shape of objects in an image and describe the situation of those objects. For example, the analysis unit can analyze the actions of people in an image and determine whether those actions are suspicious. This improves the accuracy of notifications by recognizing people and objects in images and describing their situations. Some or all of the above processing in the analysis unit is performed using a generative AI. For example, the analysis unit inputs an image into the generative AI, which recognizes people and objects in the image and describes their situation.

[0074] The notification unit can send notifications through messaging platforms or voice assistants. For example, the notification unit can send notifications through messaging platforms. For example, the notification unit can use messaging platforms to notify users of the results analyzed by the analysis unit. The notification unit can also send notifications through voice assistants. For example, the notification unit can use voice assistants to notify users of the results analyzed by the analysis unit. This allows information to be quickly conveyed to users by sending notifications through messaging platforms or voice assistants. Some or all of the above-described processes in the notification unit may be performed using AI or not. For example, the notification unit inputs the results analyzed by the analysis unit into AI, the AI ​​generates notification content, and sends the notification through messaging platforms or voice assistants.

[0075] The modification section allows the prompt to be freely modified. For example, the modification section allows the user to freely change the content of the prompt. For example, the modification section can provide an interface for the user to change the content of the prompt. For example, the modification section can provide a settings screen for the user to change the content of the prompt. By making the prompt freely modifiable, it can be applied to various uses. Some or all of the above processing in the modification section may be performed using AI or not. For example, the modification section inputs an interface for the user to change the content of the prompt to the AI, and the AI ​​generates a settings screen for changing the content of the prompt.

[0076] The similarity calculation unit calculates the similarity of the two most recent images, and if the similarity is high, it can omit sending the data to the generating AI. The similarity calculation unit calculates the similarity of the two most recent images, for example. The similarity calculation unit can calculate the similarity of the two most recent images using, for example, cosine similarity. The similarity calculation unit can also calculate the similarity of the two most recent images using Euclidean distance. The similarity calculation unit can omit sending the data to the generating AI if the similarity of the two most recent images is high. This reduces token consumption by omitting sending the data to the generating AI when the similarity is high. Some or all of the above processing in the similarity calculation unit may be performed using AI or not using AI. For example, the similarity calculation unit inputs the two most recent images to the AI, the AI ​​calculates the similarity, and if the similarity is high, it omits sending the data to the generating AI.

[0077] The modification unit can be applied to a variety of uses, such as preventing theft of cars and crops, monitoring pets, and observing wild birds. For example, the modification unit can be applied to preventing car theft. For example, the modification unit can monitor a parking lot with a camera and notify when it detects suspicious activity. For example, the modification unit can be applied to preventing theft of crops. For example, the modification unit can monitor a field and notify when a suspicious person approaches. For example, the modification unit can be applied to monitoring pets. For example, the modification unit can monitor the pet's movements and notify if there is an abnormality. For example, the modification unit can be applied to observing wild birds. For example, the modification unit can monitor wild birds that come to the garden and notify when a specific type of wild bird appears. This allows for application to a wide range of uses and can be utilized in various scenarios. Some or all of the above-mentioned processes in the modification unit may be performed using AI or not. For example, the modification unit inputs images captured by a camera into an AI, the AI ​​analyzes the images, and notifies when a specific event occurs.

[0078] The storage unit can estimate the user's emotions and adjust the image saving frequency based on the estimated emotions. For example, if the user is stressed, the storage unit increases the saving frequency to provide a sense of security. For example, if the user is relaxed, the storage unit decreases the saving frequency to save data capacity. For example, if the user is excited, the storage unit sets the saving frequency to a moderate level to maintain balance. This allows for saving images according to the user's needs by adjusting the image saving frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit inputs user emotion data into the generative AI, the generative AI estimates the emotions, and adjusts the saving frequency.

[0079] The storage unit can automatically adjust image quality to optimize storage capacity during saving. For example, the storage unit can automatically adjust image resolution to optimize storage capacity during saving. For example, the storage unit can automatically adjust image compression ratio to optimize storage capacity during saving. For example, the storage unit can automatically adjust image color depth to optimize storage capacity during saving. In this way, storage capacity can be optimized by automatically adjusting image quality. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit inputs image resolution and compression ratio to the AI, which calculates the optimal quality and optimizes storage capacity.

[0080] The storage unit can change the resolution of images to be saved based on specific time periods or events. For example, at night, the storage unit can save data capacity by saving at a low resolution. During events, for example, the storage unit can save at a high resolution to preserve detailed records. During normal times, for example, the storage unit can balance this by saving at a medium resolution. This allows for efficient management of storage capacity by changing the image resolution based on specific time periods or events. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input information about specific time periods or events into the AI, which can then calculate the optimal resolution and manage storage capacity.

[0081] The storage unit can estimate the user's emotions and determine the priority of images to save based on the estimated emotions. For example, if the user is stressed, the storage unit will prioritize saving important images. For example, if the user is relaxed, the storage unit will prioritize saving normal images. For example, if the user is excited, the storage unit will prioritize saving images of specific events. This allows for the priority of saving important images by determining the priority of images to save according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit inputs user emotion data into a generative AI, which estimates the emotions and determines the priority of images to save.

[0082] The storage unit can filter the content of images to be saved, taking into account the user's geographical location information. For example, if the user is in a specific location, the storage unit will prioritize saving images related to that location. For example, if the user is on the move, the storage unit will prioritize saving images related to the travel route. For example, if the user is at home, the storage unit will prioritize saving images related to home. In this way, by filtering the content of images while taking into account the user's geographical location information, highly relevant images can be saved. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can input the user's geographical location information into the AI, and the AI ​​will filter and save relevant images.

[0083] The storage unit can analyze the user's social media activity during saving and prioritize saving relevant images. For example, the storage unit may prioritize saving images that the user has shared on social media. For example, the storage unit may prioritize saving images that the user has tagged on social media. For example, the storage unit may prioritize saving images that the user has liked on social media. In this way, by analyzing the user's social media activity, relevant images can be prioritized for saving. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit may input the user's social media activity data into AI, which will analyze and save relevant images.

[0084] The transmitting unit can estimate the user's emotions and adjust the timing of image transmission based on the estimated emotions. For example, if the user is stressed, the transmitting unit will immediately send an image. If the user is relaxed, the transmitting unit will send an image at an appropriate time. If the user is excited, the transmitting unit will send images frequently. By adjusting the timing of image transmission according to the user's emotions, transmission can be tailored to the user's needs. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transmitting unit may be performed using AI or not. For example, the transmitting unit inputs user emotion data into a generative AI, which estimates the emotion and adjusts the transmission timing.

[0085] The transmitting unit can optimize the transmission speed during transmission, taking into account the network conditions. For example, if the network is congested, the transmitting unit will lower the transmission speed to ensure stability. For example, if the network is not congested, the transmitting unit will increase the transmission speed for faster transmission. For example, the transmitting unit will automatically adjust the transmission speed according to the network conditions. This allows for stable transmission by optimizing the transmission speed while considering the network conditions. Some or all of the above processing in the transmitting unit may be performed using AI, or it may be performed without AI. For example, the transmitting unit inputs network condition data to the AI, and the AI ​​optimizes the transmission speed.

[0086] The transmission unit can determine the transmission priority based on the importance of the images during transmission. For example, the transmission unit may prioritize the transmission of important images. For example, the transmission unit may transmit normal images at an appropriate time. For example, the transmission unit may postpone the transmission of less important images. In this way, by determining the transmission priority based on the importance of the images, important images can be transmitted preferentially. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit may input image importance data into the AI, and the AI ​​may determine the transmission priority.

[0087] The transmitting unit can estimate the user's emotions and adjust the content of the images it transmits based on the estimated emotions. For example, if the user is stressed, the transmitting unit will prioritize sending important images. For example, if the user is relaxed, the transmitting unit will prioritize sending normal images. For example, if the user is excited, the transmitting unit will prioritize sending images related to specific events. This allows for transmission tailored to the user's needs by adjusting the content of the images transmitted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transmitting unit may be performed using AI or not. For example, the transmitting unit inputs user emotion data into a generative AI, the generative AI estimates the emotions, and adjusts the content of the images to be transmitted.

[0088] The transmission unit can select the optimal transmission method at the time of transmission, taking into account the user's device information. For example, if the user is using a smartphone, the transmission unit provides a transmission method optimized for mobile data. For example, if the user is using a tablet, the transmission unit provides a transmission method optimized for a large screen. For example, if the user is using a personal computer, the transmission unit transmits high-resolution images. This enables transmission optimized for the user's device by selecting the optimal transmission method considering the user's device information. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit inputs the user's device information into the AI, and the AI ​​selects the optimal transmission method.

[0089] The transmission unit can customize the content of a transmission by referring to the user's past transmission history. For example, the transmission unit can analyze patterns in images previously sent by the user and suggest the most suitable content. For example, the transmission unit can prioritize sending images related to specific events from the user's past transmission history. For example, the transmission unit can customize and send the content based on the user's past transmission history. This allows for transmissions tailored to the user's needs by customizing the content based on the user's past transmission history. Some or all of the above processing in the transmission unit may be performed using AI or not. For example, the transmission unit can input the user's past transmission history data into the AI, and the AI ​​can customize the content of the transmission.

[0090] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis results based on the estimated emotions. For example, if the user is stressed, the analysis unit provides concise and easy-to-understand analysis results. For example, if the user is relaxed, the analysis unit provides detailed analysis results. For example, if the user is excited, the analysis unit provides visually appealing analysis results. In this way, by adjusting the presentation of the analysis results according to the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using generative AI. For example, the analysis unit inputs the user's emotion data into the generative AI, the generative AI estimates the emotions, and adjusts the presentation of the analysis results.

[0091] The analysis unit can improve the accuracy of the analysis by considering the background information of the image during the analysis. For example, the analysis unit recognizes objects in the background of the image and reflects this in the analysis results. For example, the analysis unit improves the accuracy of the analysis by considering the brightness and hue of the background of the image. For example, the analysis unit reflects the movement of people in the background of the image in the analysis. In this way, the accuracy of the analysis is improved by considering the background information of the image. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit inputs the background information of the image into a generation AI, and the generation AI improves the accuracy of the analysis by considering the background information.

[0092] The analysis unit can optimize the analysis algorithm based on the image capture conditions during analysis. For example, the analysis unit optimizes the analysis algorithm by considering the image capture time and weather conditions. For example, the analysis unit optimizes the analysis algorithm by considering the image capture angle and distance. For example, the analysis unit optimizes the analysis algorithm by considering the characteristics of the image capture device. By optimizing the analysis algorithm based on the image capture conditions, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the analysis unit inputs image capture condition data to a generation AI, and the generation AI optimizes the analysis algorithm by considering the capture conditions.

[0093] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is stressed, the analysis unit provides a concise and easy-to-understand display method. For example, if the user is relaxed, the analysis unit provides a display method that includes detailed information. For example, if the user is excited, the analysis unit provides a visually appealing display method. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit is performed using the generative AI. For example, the analysis unit inputs the user's emotion data into the generative AI, the generative AI estimates the emotions, and adjusts the display method of the analysis results.

[0094] The analysis unit can determine the priority of analysis based on the location where the images were taken. For example, the analysis unit may prioritize the analysis of images taken at important locations. For example, the analysis unit may prioritize the analysis of images taken at locations specified by the user. For example, the analysis unit may automatically determine the priority of analysis based on the location where the images were taken. This allows important images to be analyzed preferentially by determining the priority of analysis based on the location where the images were taken. Some or all of the above processing in the analysis unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the analysis unit inputs image location data into a generating AI, and the generating AI determines the priority of analysis considering the location.

[0095] The analysis unit can improve the accuracy of the analysis by referring to related image data during the analysis. For example, the analysis unit improves the accuracy of the analysis by referring to the image metadata. For example, the analysis unit optimizes the analysis algorithm based on related image data. For example, the analysis unit improves the reliability of the analysis results by referring to related image data. As a result, the accuracy of the analysis is improved by referring to related image data. Some or all of the above processes in the analysis unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the analysis unit inputs related image data into a generating AI, and the generating AI improves the accuracy of the analysis by referring to the related data.

[0096] The notification unit can estimate the user's emotions and adjust the way notifications are presented based on the estimated emotions. For example, if the user is stressed, the notification unit will provide a concise and easy-to-understand notification. If the user is relaxed, the notification unit will provide a notification containing detailed information. If the user is excited, the notification unit will provide a visually appealing notification. By adjusting the way notifications are presented according to the user's emotions, it becomes possible to provide notifications that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit inputs user emotion data into the generative AI, the generative AI estimates the emotion, and adjusts the way notifications are presented.

[0097] The notification unit can determine the priority of notifications based on their importance when they are sent. For example, the notification unit may prioritize important notifications. For example, the notification unit may send regular notifications at appropriate times. For example, the notification unit may postpone sending less important notifications. In this way, by determining the priority of notifications based on their importance, important notifications can be given priority. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit may input notification importance data into the AI, and the AI ​​may determine the priority of the notifications.

[0098] The notification unit can customize notification content by referring to the user's past notification history when sending a notification. For example, the notification unit can analyze patterns of notifications the user has received in the past and suggest the most suitable notification content. For example, the notification unit can prioritize notifications related to specific events based on the user's past notification history. For example, the notification unit can customize notification content based on the user's past notification history. This makes it possible to provide notifications that meet the user's needs by customizing notification content by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input the user's past notification history data into the AI, and the AI ​​will customize the notification content.

[0099] The notification unit can estimate the user's emotions and adjust the timing of notifications based on the estimated emotions. For example, if the user is stressed, the notification unit will send an immediate notification. For example, if the user is relaxed, the notification unit will send a notification at an appropriate time. For example, if the user is excited, the notification unit will send frequent notifications. By adjusting the timing of notifications according to the user's emotions, it becomes possible to provide notifications that meet the user's needs. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not using AI. For example, the notification unit inputs user emotion data into a generative AI, the generative AI estimates the emotion, and adjusts the timing of notifications.

[0100] The notification unit can select the optimal notification method when sending a notification, taking into account the user's device information. For example, if the user is using a smartphone, the notification unit provides a notification method optimized for mobile data. For example, if the user is using a tablet, the notification unit provides a notification method optimized for a large screen. For example, if the user is using a personal computer, the notification unit provides high-resolution notifications. This enables notifications optimized for the user's device by selecting the optimal notification method while considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit inputs the user's device information into the AI, and the AI ​​selects the optimal notification method.

[0101] The notification unit can adjust the content of notifications based on the user's current activity status. For example, if the user is working, the notification unit will only send important notifications. If the user is on a break, the notification unit will send regular notifications. If the user is traveling, the notification unit will send concise notifications. By adjusting the content of notifications based on the user's current activity status, it becomes possible to provide notifications that meet the user's needs. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit inputs user activity data into the AI, and the AI ​​adjusts the content of the notifications.

[0102] The modification unit can estimate the user's emotions and suggest changes to prompts based on the estimated emotions. For example, if the user is stressed, the modification unit suggests a concise and easy-to-understand prompt. If the user is relaxed, the modification unit suggests a detailed prompt. If the user is excited, the modification unit suggests a visually appealing prompt. This allows for prompt changes tailored to the user's needs by suggesting changes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the modification unit may be performed using AI or not. For example, the modification unit inputs user emotion data into a generative AI, which estimates the emotion and suggests changes to the prompt.

[0103] The change unit can select the optimal change by referring to past prompt change history when making a change. For example, the change unit can analyze patterns of prompts previously changed by the user and propose the optimal change. For example, the change unit can prioritize suggesting changes related to specific events from the user's past prompt change history. For example, the change unit can customize and propose changes based on the user's past prompt change history. This makes it possible to change prompts to meet the user's needs by selecting the optimal change by referring to past prompt change history. Some or all of the above processes in the change unit may be performed using AI or not. For example, the change unit can input past prompt change history data into AI, and the AI ​​can select the optimal change.

[0104] The modification unit can estimate the user's emotions and adjust the frequency of prompt changes based on the estimated emotions. For example, if the user is stressed, the modification unit will change prompts frequently. For example, if the user is relaxed, the modification unit will change prompts at a moderate frequency. For example, if the user is excited, the modification unit will increase the frequency of prompt changes. This allows for prompt changes that meet the user's needs by adjusting the frequency of prompt changes according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the modification unit may be performed using AI or not. For example, the modification unit inputs user emotion data into a generative AI, the generative AI estimates the emotion, and adjusts the frequency of prompt changes.

[0105] The modification unit can customize the prompt changes based on the user's current needs when making changes. For example, if the user has a specific need, the modification unit will suggest a prompt that meets that need. For example, the modification unit will suggest the optimal prompt based on the user's current situation. For example, the modification unit will analyze the user's current needs and suggest a customized prompt. This makes it possible to change prompts to meet the user's needs by customizing the prompt changes based on the user's current needs. Some or all of the above processing in the modification unit may be performed using AI or not. For example, the modification unit inputs the user's current needs data into the AI, and the AI ​​customizes the optimal prompt changes.

[0106] The similarity calculation unit can estimate the user's emotions and adjust the similarity calculation criteria based on the estimated user emotions. For example, if the user is stressed, the similarity calculation unit performs a strict similarity calculation. For example, if the user is relaxed, the similarity calculation unit performs a moderate similarity calculation. For example, if the user is excited, the similarity calculation unit performs a loose similarity calculation. By adjusting the similarity calculation criteria according to the user's emotions, it becomes possible to perform similarity calculations that meet the user's needs. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the similarity calculation unit may be performed using AI or not using AI. For example, the similarity calculation unit inputs user emotion data into the generative AI, the generative AI estimates the emotions, and adjusts the similarity calculation criteria.

[0107] The similarity calculation unit can improve the accuracy of its calculations by considering the background information of the image during the similarity calculation. For example, the similarity calculation unit recognizes objects in the background of the image and reflects this in the similarity calculation. For example, the similarity calculation unit improves the accuracy of its similarity calculations by considering the brightness and hue of the background of the image. For example, the similarity calculation unit reflects the movement of people in the background of the image in the similarity calculation. By improving the accuracy of the similarity calculation by considering the background information of the image, a more accurate similarity calculation becomes possible. Some or all of the above processing in the similarity calculation unit may be performed using AI or not. For example, the similarity calculation unit inputs the background information of the image into the AI, and the AI ​​improves the accuracy of the similarity calculation by considering the background information.

[0108] The similarity calculation unit can estimate the user's emotions and adjust the order in which the similarity calculation results are displayed based on the estimated user emotions. For example, if the user is stressed, the similarity calculation unit will prioritize displaying important similarity calculation results. For example, if the user is relaxed, the similarity calculation unit will display normal similarity calculation results. For example, if the user is excited, the similarity calculation unit will prioritize displaying similarity calculation results related to a specific event. This allows for display tailored to the user's needs by adjusting the order in which the similarity calculation results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the similarity calculation unit may be performed using AI or not. For example, the similarity calculation unit inputs user emotion data into the generative AI, the generative AI estimates the emotions, and adjusts the order in which the similarity calculation results are displayed.

[0109] The similarity calculation unit can determine the calculation priority based on the image's location during similarity calculation. For example, the similarity calculation unit may prioritize similarity calculations for images taken in important locations. For example, the similarity calculation unit may prioritize similarity calculations for images taken in locations specified by the user. For example, the similarity calculation unit may automatically determine the similarity calculation priority based on the image's location. This allows important images to be calculated preferentially by determining the calculation priority based on the image's location. Some or all of the above processing in the similarity calculation unit may be performed using AI or not. For example, the similarity calculation unit may input image location data into the AI, and the AI ​​may determine the similarity calculation priority considering the location.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The analysis unit can estimate the emotions of the people in the image and adjust the notification content based on the estimated emotions. For example, if the person in the image is angry, the analysis unit can issue a warning notification. If the person in the image is sad, it can issue a notification that includes a message of comfort. Furthermore, if the person in the image is happy, it can issue a notification that shares that situation. This allows for the delivery of appropriate notifications that correspond to the emotions of the people in the image.

[0112] The storage unit can optimize saved images by referencing the user's past saving history. For example, it can analyze patterns in images previously saved by the user and prioritize saving similar images. It can also automatically select optimal saving settings based on the resolution and quality of images previously saved by the user. Furthermore, it can prioritize saving related images by referencing tag information of images previously saved by the user. This enables efficient image saving by leveraging the user's past saving history.

[0113] The notification unit can estimate the user's emotions and adjust the way notifications are presented based on those estimates. For example, if the user is stressed, it can provide a concise and easy-to-understand notification. If the user is relaxed, it can provide a notification with more detailed information. Furthermore, if the user is excited, it can provide a visually appealing notification. This allows for the delivery of appropriate notifications tailored to the user's emotions.

[0114] The transmission unit can monitor the network status in real time when transmitting images and select the optimal transmission method. For example, if the network is congested, it can reduce the transmission speed to ensure stability. Conversely, if the network is uncongested, it can increase the transmission speed for faster transmission. Furthermore, it can automatically switch the transmission method according to the network status. This enables efficient image transmission that takes network conditions into consideration.

[0115] The analysis unit can estimate the emotions of the people in the image and adjust the way the analysis results are presented based on the estimated emotions. For example, if the user is feeling stressed, it can provide concise and easy-to-understand analysis results. If the user is relaxed, it can provide detailed analysis results. Furthermore, if the user is excited, it can provide visually appealing analysis results. This allows for the provision of appropriate analysis results tailored to the user's emotions.

[0116] The storage unit can automatically categorize saved images based on specific events. For example, it can categorize images based on the types of people or objects they contain. It can also prioritize saving images related to specific events. Furthermore, the storage unit can automatically categorize images based on user-specified conditions. This enables efficient image management.

[0117] The notification unit can estimate the user's emotions and adjust the timing of notifications based on those emotions. For example, if the user is stressed, a notification can be sent immediately. If the user is relaxed, a notification can be sent at an appropriate time. Furthermore, if the user is excited, notifications can be sent frequently. This allows for appropriate notification timing tailored to the user's emotions.

[0118] The transmission unit can select the optimal transmission method when transmitting images, taking into account the user's device information. For example, if the user is using a smartphone, it can provide a transmission method optimized for mobile data. If the user is using a tablet, it can provide a transmission method optimized for the larger screen. Furthermore, if the user is using a PC, it can transmit high-resolution images. This enables transmission optimized for the user's device.

[0119] The analysis unit can improve the accuracy of image analysis by referring to the user's past analysis history. For example, the analysis unit can analyze patterns in images previously analyzed by the user and prioritize the analysis of similar images. It can also select the optimal analysis algorithm based on the results of images previously analyzed by the user. Furthermore, it can refer to the tag information of images previously analyzed by the user and prioritize the analysis of related images. This enables efficient image analysis by utilizing the user's past analysis history.

[0120] The change function can estimate the user's emotions and suggest changes to prompts based on those emotions. For example, if the user is stressed, it can suggest a concise and easy-to-understand prompt. If the user is relaxed, it can suggest a more detailed prompt. Furthermore, if the user is excited, it can suggest a visually appealing prompt. This allows for the provision of appropriate prompt changes that correspond to the user's emotions.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The storage unit saves the camera image. For example, the camera saves an image every few seconds. When saving an image, the storage unit can consider the image type and resolution. For example, the storage unit can save still images and videos. The storage unit can also adjust the resolution of the image before saving it. Step 2: The transmission unit sends the images saved by the storage unit to the generation AI. The transmission unit performs image analysis, for example, by sending the saved images to the generation AI. The transmission unit can adjust the method and timing of image transmission. For example, the transmission unit can transmit images in real time. Alternatively, the transmission unit can transmit images at regular intervals. Step 3: The analysis unit analyzes the image transmitted by the transmission unit. The analysis unit uses a generation AI to recognize people and objects in the image and describe their situation. For example, the analysis unit recognizes the faces of people in the image and analyzes what actions those people are taking. The analysis unit can also recognize objects in the image and describe the situation of those objects. Step 4: The notification unit sends notifications based on the results analyzed by the analysis unit. For example, the notification unit sends notifications when a specific event occurs based on the results analyzed by the analysis unit. The notification unit can adjust the notification method and timing. For example, the notification unit sends notifications through messaging platforms or voice assistants. The notification unit can also adjust the timing of notifications to ensure that important information is not missed.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the storage unit, transmission unit, analysis unit, notification unit, modification unit, and similarity calculation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the storage unit is implemented by the storage 50 of the smart device 14 and stores images from the camera 42. The transmission unit is implemented by the communication I / F 44 of the smart device 14 and transmits the stored images to the generation AI. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the transmitted images. The notification unit is implemented by the control unit 46A of the smart device 14 and provides notifications based on the analysis results. The modification unit is implemented by the control unit 46A of the smart device 14 and provides an interface that allows the user to freely change the content of the prompt. The similarity calculation unit is implemented by the identification processing unit 290 of the data processing device 12 and calculates the similarity of the two most recent images, and if the similarity is high, it omits transmission to the generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the storage unit, transmission unit, analysis unit, notification unit, modification unit, and similarity calculation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the storage unit is implemented by the storage 50 of the smart glasses 214 and stores images from the camera 42. The transmission unit is implemented by the communication I / F 44 of the smart glasses 214 and transmits the stored images to the generation AI. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the transmitted images. The notification unit is implemented by the control unit 46A of the smart glasses 214 and provides notifications based on the analysis results. The modification unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface that allows the user to freely change the content of the prompt. The similarity calculation unit is implemented by the identification processing unit 290 of the data processing device 12 and calculates the similarity of the two most recent images, and if the similarity is high, it omits transmission to the generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the storage unit, transmission unit, analysis unit, notification unit, modification unit, and similarity calculation unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the storage unit is implemented by the storage 50 of the headset terminal 314 and stores images from the camera 42. The transmission unit is implemented by the communication I / F 44 of the headset terminal 314 and transmits the stored images to the generation AI. The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes the transmitted images. The notification unit is implemented by the control unit 46A of the headset terminal 314 and provides notifications based on the analysis results. The modification unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface that allows the user to freely change the content of the prompt. The similarity calculation unit is implemented by the identification processing unit 290 of the data processing device 12 and calculates the similarity of the two most recent images, and if the similarity is high, it omits transmission to the generation AI. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the storage unit, transmission unit, analysis unit, notification unit, modification unit, and similarity calculation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the storage unit is implemented by the storage 50 of the robot 414 and stores images from the camera 42. The transmission unit is implemented by the communication I / F 44 of the robot 414 and transmits the stored images to the generation AI. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the transmitted images. The notification unit is implemented by the control unit 46A of the robot 414 and provides notifications based on the analysis results. The modification unit is implemented by the control unit 46A of the robot 414 and provides an interface that allows the user to freely change the content of the prompt. The similarity calculation unit is implemented by the identification processing unit 290 of the data processing unit 12 and calculates the similarity of the two most recent images, and if the similarity is high, it omits transmission to the generation AI. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A storage unit for saving camera images, A transmission unit that transmits the image stored by the storage unit to the generation AI, An analysis unit that analyzes the image transmitted by the transmission unit, A notification unit that provides notification based on the results of the analysis performed by the aforementioned analysis unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned analysis unit, It recognizes people and objects in an image and describes the situation. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned notification unit, Notifications are sent via messaging platforms and voice assistants. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a section that allows you to freely change the prompt. The system described in Appendix 1, characterized by the features described herein. (Note 5) The system includes a similarity calculation unit that calculates the similarity between the two most recent images and, if the similarity is high, omits sending the image to the generation AI. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned modified part is, It can be applied to a variety of uses, such as preventing theft of cars and crops, monitoring pets, and observing wild birds. The system described in Appendix 3, characterized by the features described herein. (Note 7) The aforementioned storage unit is It estimates the user's emotions and adjusts the frequency of image saving based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned storage unit is When saving, the image quality is automatically adjusted to optimize storage space. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned storage unit is When saving, change the resolution of the images to be saved based on a specific time period or event. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned storage unit is It estimates the user's emotions and determines the priority of images to save based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned storage unit is When saving, the content of the images to be saved is filtered based on the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned storage unit is When saving, the system analyzes the user's social media activity and prioritizes saving relevant images. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned transmitting unit It estimates the user's emotions and adjusts the timing of image transmission based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned transmitting unit When transmitting, the transmission speed is optimized considering the network conditions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned transmitting unit When sending images, the system prioritizes sending them based on their importance. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned transmitting unit It estimates the user's emotions and adjusts the content of the images sent based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned transmitting unit When sending data, the system selects the optimal transmission method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned transmitting unit When sending, the system customizes the message content by referring to the user's past sending history. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, It estimates the user's emotions and adjusts the way the analysis results are presented based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, During analysis, background information of the image is taken into consideration to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, the analysis algorithm is optimized based on the image capture conditions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on the location where the image was taken. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by referring to related data of the image. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, It estimates the user's emotions and adjusts the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned notification unit, When a notification is sent, the system prioritizes the notification based on its importance. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, When sending a notification, the notification content is customized by referencing the user's past notification history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, It estimates the user's emotions and adjusts the timing of notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, When sending notifications, the system selects the most suitable notification method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, When sending notifications, the content of the notifications will be adjusted to take into account the user's current activity status. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned modified part is, It estimates the user's emotions and suggests changes to the prompt based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned modified part is, When making changes, refer to the past prompt change history to select the most appropriate changes. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned modified part is, It estimates the user's emotions and adjusts the frequency of prompt changes based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned modified part is, When changes are made, the prompt changes are customized based on the user's current needs. The system described in Appendix 3, characterized by the features described herein. (Note 35) The similarity calculation unit, We estimate the user's sentiment and adjust the similarity calculation criteria based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 36) The similarity calculation unit, When calculating similarity, the background information of the image is taken into consideration to improve the accuracy of the calculation. The system described in Appendix 4, characterized by the features described herein. (Note 37) The similarity calculation unit, It estimates the user's sentiment and adjusts the order in which similarity calculation results are displayed based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 38) The similarity calculation unit, When calculating similarity, the calculation priority is determined based on the location where the image was taken. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A storage unit for saving camera images, A transmission unit transmits the image stored by the storage unit to the generation AI, An analysis unit that analyzes the image transmitted by the transmission unit, A notification unit that provides notification based on the results of the analysis performed by the aforementioned analysis unit, Equipped with A system characterized by the following features.

2. The aforementioned analysis unit, It recognizes people and objects in an image and describes the situation. The system according to feature 1.

3. The aforementioned notification unit, Notifications are sent via messaging platforms and voice assistants. The system according to feature 1.

4. It includes a section that allows you to freely change the prompt. The system according to feature 1.

5. The system includes a similarity calculation unit that calculates the similarity between the two most recent images and, if the similarity is high, omits sending the image to the generating AI. The system according to feature 1.

6. The aforementioned modified part is, It can be applied to a variety of uses, such as preventing theft of cars and crops, monitoring pets, and observing wild birds. The system according to feature 4.

7. The aforementioned storage unit is It estimates the user's emotions and adjusts the frequency of image saving based on the estimated user emotions. The system according to feature 1.

8. The aforementioned storage unit is When saving, the image quality is automatically adjusted to optimize storage space. The system according to feature 1.

Images