system

Abstract

The system according to this embodiment aims to prevent violent and aggressive posts in internal communications and to improve respect for others. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, an alert unit, a suggestion unit, and a learning unit. The reception unit receives the content of the post. The analysis unit analyzes the content of the post received by the reception unit. The alert unit issues an alert based on the content of the post analyzed by the analysis unit. The suggestion unit proposes an alternative expression based on the alert issued by the alert unit. The learning unit learns the user's response to the alternative expression proposed by the suggestion 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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, means for preventing violent and aggressive posts in in-house communication are not fully developed, and there is room for improvement.

[0005] The system according to the embodiment aims to prevent violent and aggressive posts in in-house communication and improve the awareness of respecting others.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, an alert unit, a suggestion unit, and a learning unit. The reception unit receives the content of a post. The analysis unit analyzes the content of the post received by the reception unit. The alert unit issues an alert based on the content of the post analyzed by the analysis unit. The suggestion unit proposes an alternative expression based on the alert issued by the alert unit. The learning unit learns the user's response to the alternative expression proposed by the suggestion unit. [Effects of the Invention]

[0007] The system according to this embodiment can prevent violent and offensive posts in internal communications and improve respect for others. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also 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) The internal communication tool according to an embodiment of the present invention is a system that incorporates a gentle mode and encourages self-reflection and improves respect for others by issuing alerts before sending posts containing violent or aggressive language or hate speech against others in internal communication. This system can improve the quality of communication and enhance the psychological safety of employees. For example, a user inputs content to post using the internal communication tool. At this time, the content is input to a generating AI. The generating AI analyzes the input content and determines whether it contains violent or aggressive language or language that includes hate speech against others. For example, if it contains discriminatory language against a specific nationality or gender, or offensive language, the generating AI will detect it. Next, the generating AI issues an alert to the user for the detected violent or aggressive language or language that includes hate speech against others. The alert indicates that the content of the post is inappropriate and encourages the user to reflect on it. For example, a message such as "This language is offensive. Please use a different expression." may be displayed. Furthermore, the generating AI suggests alternative expressions along with the alert. Alternative expressions are designed to help users communicate respectfully with others. They are suggested by the generative AI based on commonly used inappropriate expressions learned by the AI ​​itself, as well as individual and organizational tendencies. For example, a suggestion might be, "This expression is offensive. Try using the expression '〇〇' instead." The generative AI also learns from users' posts and responses to alerts, learning preferred and undesirable expressions on an individual basis. This allows the generative AI to provide feedback tailored to the user's tendencies, encouraging self-reflection and improvement. This mechanism enables everyone in a company or organization to communicate respectfully with others, improving the quality of communication and increasing employee psychological safety. For example, it can prevent users from unconsciously using offensive language in non-face-to-face communication such as internal social media or email, thereby improving respect for others. As a result, internal communication tools can enhance employee psychological safety and improve the quality of communication.

[0029] The internal communication tool according to this embodiment comprises a reception unit, an analysis unit, an alert unit, a suggestion unit, and a learning unit. The reception unit receives posted content. Posted content includes, but is not limited to, text, images, and videos. The reception unit can, for example, receive posted content in text format. The reception unit can also receive posted content in image format. Furthermore, the reception unit can also receive posted content in video format. For example, the reception unit receives posted content in text format and sends it to the analysis unit. Posted content in image format is sent to the analysis unit using image analysis technology. Posted content in video format is sent to the analysis unit using video analysis technology. The analysis unit analyzes the posted content received by the reception unit using a generation AI. The analysis is performed, for example, using natural language processing technology, but is not limited to this example. For example, the analysis unit analyzes posted content in text format using natural language processing technology. Furthermore, the analysis unit can also analyze posted content in image format using image analysis technology. Furthermore, the analysis unit can also analyze posted content in video format using video analysis technology. For example, the analysis unit uses natural language processing technology to analyze the text content of posts and detect violent, offensive, or hateful expressions. Image analysis technology analyzes specific keywords and context within images to detect violent or offensive expressions. Video analysis technology analyzes audio and text within videos to detect violent or offensive expressions. The alert unit issues alerts based on the post content analyzed by the analysis unit. Alerts are issued based on, for example, the notification method and type of alert, but are not limited to these examples. For example, the alert unit issues an alert to the user regarding inappropriate expressions detected by the analysis unit. The alert unit can also display a pop-up message as a notification method. The alert unit can also send email notifications. For example, the alert unit displays a pop-up message saying, "This expression is offensive. Please use a different expression." Email notifications send an alert message to the user's email address. The suggestion unit proposes alternative expressions based on the alerts issued by the alert unit.Alternative expressions are provided based on, for example, paraphrasing methods or suggestion criteria. For example, the suggestion unit suggests alternative expressions along with alerts. The suggestion unit can also use generative AI to suggest appropriate alternative expressions to the user. Furthermore, the suggestion unit can suggest individual alternative expressions based on the user's tendencies. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '○○'." The learning unit learns the user's responses to the alternative expressions suggested by the suggestion unit. Learning is performed using, for example, machine learning algorithms. For example, the learning unit learns the user's posts and responses to alerts to learn preferred and unpredictable expressions on an individual basis. The learning unit can also collect user responses as data as a method of incorporating feedback. Furthermore, the learning unit can provide feedback based on the user's tendencies. For example, the learning unit learns the user's posts and responses to alerts to provide individualized feedback. As a result, the internal communication tool according to the embodiment can enhance the psychological safety of employees and improve the quality of communication.

[0030] The reception unit receives submissions. Submissions include, but are not limited to, text, images, and videos. The reception unit can, for example, accept text submissions. It can also accept image submissions. Furthermore, it can also accept video submissions. For example, the reception unit accepts text submissions and sends them to the analysis unit. Image submissions are sent to the analysis unit using image analysis technology. Video submissions are sent to the analysis unit using video analysis technology. When receiving these submissions, the reception unit has a function to automatically determine the format of the submission and select the appropriate analysis technology. For example, text submissions are sent to the analysis unit using natural language processing technology. Image submissions are sent to the analysis unit using image recognition technology, and video submissions are sent to the analysis unit using speech recognition technology or video analysis technology. When receiving submissions, the reception unit also collects information about the submitter and sends it to the analysis unit. This allows the analysis unit to perform analysis by associating the submission content with the submitter's information. Furthermore, the reception unit temporarily saves the content of submitted data upon receipt and allows for re-analysis as needed. This enables the analysis unit to perform re-analysis as necessary when generating analysis results, thereby improving analysis accuracy. The reception unit also has a function to select the appropriate analysis technique based on the format and content of the submitted data upon receipt and transmit it to the analysis unit. This allows the reception unit to select the appropriate analysis technique based on the format and content of the submitted data and transmit it to the analysis unit.

[0031] The analysis unit uses generative AI to analyze the content of posts received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit can analyze text-based posts using natural language processing technology. The analysis unit can also analyze image-based posts using image analysis technology. Furthermore, the analysis unit can analyze video-based posts using video analysis technology. For example, the analysis unit uses natural language processing technology to analyze text-based posts and detect violent, offensive, or hateful expressions. Image analysis technology analyzes specific keywords and context within images to detect violent or offensive expressions. Video analysis technology analyzes audio and text within videos to detect violent or offensive expressions. When analyzing post content using generative AI, the analysis unit can understand the context and intent of the post content and produce appropriate analysis results. For example, when analyzing text-based posts using natural language processing technology, it can understand the context and intent of the post content and produce appropriate analysis results. When analyzing image-based posts using image analysis technology, it is possible to understand specific keywords and context within the image and produce appropriate analysis results. When analyzing video-based posts using video analysis technology, it is possible to understand the audio and text within the video and produce appropriate analysis results. Based on the analysis results of the post content, the analysis unit can provide appropriate information to the alert and suggestion units. In this way, the analysis unit can provide appropriate information to the alert and suggestion units based on the analysis results of the post content.

[0032] The alert unit issues alerts based on the content of posts analyzed by the analysis unit. Alerts are issued based on, for example, the notification method and the type of alert, but are not limited to these examples. For example, the alert unit will issue an alert to the user for inappropriate language detected by the analysis unit. The alert unit can also display a pop-up message as a notification method. The alert unit can also send email notifications. For example, the alert unit will display a pop-up message saying, "This language is offensive. Please use different language." Email notifications send an alert message to the user's email address. When issuing an alert, the alert unit has a function to select the appropriate notification method according to the content and importance of the alert. For example, for high-priority alerts, it can send a pop-up message or email notification, while for low-priority alerts, it can select the notification method. The alert unit has a function to select the appropriate notification method according to the content and importance of the alert. This allows the alert unit to select the appropriate notification method according to the content and importance of the alert. Furthermore, the alert unit can customize the type of alert and the notification method according to the content and importance of the alert. For example, specific alert types and notification methods can be customized for specific users. This allows the alerting unit to customize the type of alert and notification method according to the content and importance of the alert.

[0033] The suggestion unit proposes alternative expressions based on alerts issued by the alert unit. These alternative expressions may be based on, for example, paraphrasing methods or suggestion criteria, but are not limited to these examples. For example, the suggestion unit may propose alternative expressions along with alerts. The suggestion unit can also use generative AI to suggest appropriate alternative expressions to users. Furthermore, the suggestion unit can suggest individual alternative expressions based on user tendencies. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '〇〇'." When the suggestion unit uses generative AI to suggest appropriate alternative expressions to users, it can understand the user's posting content and tendencies and propose appropriate alternative expressions. This allows the suggestion unit to understand the user's posting content and tendencies and propose appropriate alternative expressions. Furthermore, the suggestion unit can understand the user's posting content and tendencies and propose appropriate alternative expressions. This allows the suggestion unit to understand the user's posting content and tendencies and propose appropriate alternative expressions.

[0034] The learning unit learns user responses to alternative expressions proposed by the suggestion unit. Learning is performed using, for example, machine learning algorithms, but is not limited to such examples. For example, the learning unit learns user responses to posts and alerts and learns preferred and unpredictable expressions on an individual basis. The learning unit can also collect user responses as data as a method of incorporating feedback. The learning unit can also provide feedback based on user trends. For example, the learning unit learns user responses to posts and alerts and provides individualized feedback. The learning unit learns user responses to posts and alerts using machine learning algorithms and learns preferred and unpredictable expressions on an individual basis. This allows the learning unit to learn user responses to posts and alerts and learn preferred and unpredictable expressions on an individual basis. Furthermore, the learning unit can learn user responses to posts and alerts and learn preferred and unpredictable expressions on an individual basis. This allows the learning unit to learn from users' posts and responses to alerts, enabling it to learn preferred and undesirable expressions on an individual basis.

[0035] The analysis unit can detect violent or offensive language and expressions containing hate speech against others in the posted content. For example, the analysis unit uses natural language processing technology to detect violent or offensive language in the posted content. For example, the analysis unit analyzes specific keywords or contexts to detect violent or offensive language. The analysis unit can also detect expressions containing hate speech against others. For example, the analysis unit detects discriminatory language and insulting language. This allows for the issuance of appropriate alerts by detecting violent or offensive language and expressions containing hate speech against others. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit inputs the posted content into a generative AI, and the generative AI detects violent or offensive language and expressions containing hate speech against others.

[0036] The alert unit can issue alerts to the user regarding detected inappropriate language. For example, the alert unit may display a message such as, "This language is offensive. Please use a different language." The alert unit can also display alerts as pop-up messages. For example, the alert unit may display "This language is offensive. Please use a different language." as a pop-up message. The alert unit can also send email notifications. For example, the alert unit may send an alert message to the user's email address. By issuing alerts for inappropriate language, it is possible to encourage self-reflection in the user and improve their respect for others. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit may input detected inappropriate language into the AI, and the AI ​​may generate an alert message.

[0037] The suggestion unit can suggest alternative expressions along with alerts. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '〇〇'." The suggestion unit can also use generative AI to suggest appropriate alternative expressions to the user. For example, the suggestion unit might suggest alternative expressions based on common inappropriate expressions learned by the generative AI, or based on individual or organizational tendencies. The suggestion unit can also suggest individual alternative expressions based on the user's tendencies. For example, the suggestion unit might suggest individual alternative expressions based on the user's past posts and responses to alerts. This allows users to communicate in a respectful manner by suggesting alternative expressions. Some or all of the above processing in the suggestion unit may be performed using generative AI, or not. For example, the suggestion unit inputs an alert and an alternative expression into the generative AI, and the generative AI suggests an alternative expression.

[0038] The learning unit can learn preferred and unpredictable expressions on an individual basis by learning from users' posts and responses to alerts. For example, the learning unit can learn from users' posts and responses to alerts. For example, the learning unit can collect user posts and responses to alerts as data and learn using machine learning algorithms. The learning unit can also learn preferred and unpredictable expressions on an individual basis. For example, the learning unit can provide individualized feedback based on user tendencies. This allows for feedback tailored to user tendencies, encouraging self-reflection and improvement. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user posts and responses to alerts into an AI, which then learns preferred and unpredictable expressions.

[0039] The reception department can analyze a user's past posting history and select the optimal reception method. For example, the reception department can analyze a user's past posting history. For example, the reception department can collect and analyze the user's past posting content as data. The reception department can also select the optimal reception method based on the past posting history. For example, if the reception department has made offensive posts in the past, it can display a confirmation message before accepting the post. The reception department can also quickly accept posts if the user has made appropriate posts in the past. Furthermore, if the reception department has seen a high number of offensive posts during a particular time period based on the user's past posting history, it can carefully accept posts from that time period. This makes the reception of posts more efficient by selecting the optimal reception method based on the user's past posting history. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can input the user's past posting history into AI, and the AI ​​can select the optimal reception method.

[0040] The reception unit can filter submitted content based on the user's current projects and areas of interest. For example, the reception unit can identify the user's current projects and areas of interest. For example, the reception unit can collect and analyze the user's project information and areas of interest as data. The reception unit can also filter submitted content based on the user's current projects and areas of interest. For example, the reception unit can prioritize submissions related to projects the user is currently working on. The reception unit can also prioritize submissions that are highly relevant based on the user's areas of interest. Furthermore, the reception unit can filter out inappropriate submissions based on the user's current projects and areas of interest. This allows for the priority of submissions that are highly relevant by filtering them based on the user's current projects and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit inputs the user's project information and areas of interest into the AI, and the AI ​​performs the filtering.

[0041] The reception unit can prioritize receiving posts that are highly relevant, taking into account the user's geographical location information. For example, the reception unit can obtain the user's geographical location information using GPS data. The reception unit can also filter posts that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the reception unit will prioritize receiving posts related to that region. The reception unit can also filter posts that are highly relevant based on the user's geographical location information. Furthermore, if the user is on the move, the reception unit can prioritize receiving posts related to their current location. This allows for efficient reception of region-related posts by prioritizing posts that are highly relevant based on the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit inputs the user's geographical location information into the AI, and the AI ​​filters posts that are highly relevant.

[0042] The reception unit can analyze the user's social media activity when receiving submissions and accept relevant submissions. For example, the reception unit can analyze the user's social media activity. For example, the reception unit can collect and analyze the user's social media activity as data. The reception unit can also accept relevant submissions based on the user's social media activity. For example, the reception unit can prioritize accepting submissions related to topics that the user frequently mentions on social media. The reception unit can also analyze topics of high interest from the user's social media activity and accept relevant submissions. Furthermore, the reception unit can filter appropriate submissions based on the user's social media activity. This allows for the priority of accepting submissions of high interest by accepting relevant submissions based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity into AI, and the AI ​​can filter relevant submissions.

[0043] The analysis unit can adjust the level of detail of the analysis based on the importance of the posted content during the analysis. For example, the analysis unit evaluates the importance of the posted content. For example, the analysis unit evaluates the impact and urgency of the posted content. The analysis unit can also adjust the level of detail of the analysis based on the importance of the posted content. For example, the analysis unit performs a detailed analysis for important posted content. The analysis unit can also perform a concise analysis for general posted content. The analysis unit can also perform a rapid analysis for urgent posted content. By adjusting the level of detail of the analysis based on the importance of the posted content, the analysis can be performed at an appropriate level of detail. Some or all of the above processes in the analysis unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis unit inputs the importance of the posted content into the generation AI, and the generation AI adjusts the level of detail of the analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the category of the posted content during analysis. For example, the analysis unit identifies the category of the posted content. For example, the analysis unit collects and analyzes the topic or theme of the posted content as data. The analysis unit can also apply different analysis algorithms depending on the category of the posted content. For example, the analysis unit can apply a specific analysis algorithm to offensive posted content. The analysis unit can also apply a different analysis algorithm to hate speech. The analysis unit can also apply a standard analysis algorithm to general posted content. This allows for appropriate analysis by applying different analysis algorithms depending on the category of the posted content. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit inputs the category of the posted content into the generative AI, and the generative AI applies an appropriate analysis algorithm.

[0045] The analysis unit can determine the priority of analysis based on the submission date of the posted content during the analysis process. For example, the analysis unit identifies the submission date of the posted content. For example, the analysis unit collects the submission date and time of the posted content as data and analyzes it. The analysis unit can also determine the priority of analysis based on the submission date of the posted content. For example, the analysis unit prioritizes the analysis of urgent posted content. The analysis unit can also analyze general posted content with normal priority. The analysis unit can also analyze past posted content as needed. By determining the priority of analysis based on the submission date of the posted content, urgent posted content can be analyzed preferentially. 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 submission date of the posted content into the generation AI, and the generation AI determines the priority of analysis.

[0046] The analysis unit can adjust the order of analysis based on the relevance of the posted content during analysis. For example, the analysis unit evaluates the relevance of the posted content. For example, the analysis unit collects and analyzes the topics and keywords of the posted content as data. The analysis unit can also adjust the order of analysis based on the relevance of the posted content. For example, the analysis unit prioritizes the analysis of highly relevant posted content. The analysis unit can also postpone the analysis of less relevant posted content. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the posted content. This allows for prioritizing the analysis of highly relevant posted content by adjusting the order of analysis based on the relevance of the posted content. 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 relevance of the posted content into a generation AI, and the generation AI adjusts the order of analysis.

[0047] The alert unit can adjust the level of detail of an alert based on the importance of the post content when displaying an alert. For example, the alert unit can evaluate the importance of the post content. For example, the alert unit can evaluate the impact and urgency of the post content. The alert unit can also adjust the level of detail of an alert based on the importance of the post content. For example, the alert unit can display a detailed alert for important posts. The alert unit can also display a concise alert for general posts. Furthermore, the alert unit can display an alert quickly for urgent posts. By adjusting the level of detail of an alert based on the importance of the post content, the alert can be displayed with an appropriate level of detail. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the importance of the post content into the AI, and the AI ​​adjusts the level of detail of the alert.

[0048] The alert unit can apply different alert messages depending on the category of the post content when displaying an alert. For example, the alert unit can identify the category of the post content. For example, the alert unit can collect and analyze the topic or theme of the post content as data. The alert unit can also apply different alert messages depending on the category of the post content. For example, the alert unit can display a specific alert message for offensive posts. The alert unit can also display a different alert message for hate speech. The alert unit can also display a standard alert message for general posts. This allows for the display of appropriate alerts by applying different alert messages depending on the category of the post content. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the category of the post content into the AI, and the AI ​​applies an appropriate alert message.

[0049] The alert unit can determine the priority of alerts based on the submission date of the posted content when displaying an alert. For example, the alert unit identifies the submission date of the posted content. For example, the alert unit collects and analyzes the submission date and time of the posted content as data. The alert unit can also determine the priority of alerts based on the submission date of the posted content. For example, the alert unit will display alerts preferentially for posts that are urgent. The alert unit can also display alerts with normal priority for general posts. Furthermore, the alert unit can display alerts for past posts as needed. In this way, by determining the priority of alerts based on the submission date of the posted content, alerts can be displayed preferentially for posts that are urgent. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the submission date of the posted content into the AI, and the AI ​​determines the priority of the alerts.

[0050] The alert unit can adjust the order of alerts based on the relevance of the posts when displaying alerts. For example, the alert unit evaluates the relevance of the posts. For example, the alert unit collects and analyzes the topics and keywords of the posts as data. The alert unit can also adjust the order of alerts based on the relevance of the posts. For example, the alert unit can prioritize displaying alerts for highly relevant posts. The alert unit can also postpone displaying alerts for less relevant posts. Furthermore, the alert unit can dynamically adjust the order of alerts based on the relevance of the posts. This allows for prioritizing the display of alerts for highly relevant posts by adjusting the order of alerts based on the relevance of the posts. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the relevance of the posts into the AI, and the AI ​​adjusts the order of alerts.

[0051] The proposal unit can adjust the level of detail of a proposal based on the importance of alternative expressions. For example, the proposal unit can evaluate the importance of alternative expressions. For example, the proposal unit can evaluate the impact and urgency of alternative expressions. The proposal unit can also adjust the level of detail of a proposal based on the importance of alternative expressions. For example, the proposal unit can provide detailed proposals for important alternative expressions. The proposal unit can also provide concise proposals for common alternative expressions. Furthermore, the proposal unit can provide rapid proposals for highly urgent alternative expressions. By adjusting the level of detail of a proposal based on the importance of alternative expressions, proposals can be made with an appropriate level of detail. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit inputs the importance of alternative expressions into the AI, and the AI ​​adjusts the level of detail of the proposal.

[0052] The proposal unit can apply different proposal algorithms depending on the category of the alternative expression during the proposal process. For example, the proposal unit can identify the category of the alternative expression. For example, the proposal unit can collect and analyze data on the topic or theme of the alternative expression. The proposal unit can also apply different proposal algorithms depending on the category of the alternative expression. For example, the proposal unit can apply a specific proposal algorithm to offensive expressions. The proposal unit can also apply a different proposal algorithm to hate speech. The proposal unit can also apply a standard proposal algorithm to general expressions. This allows for appropriate proposals to be made by applying different proposal algorithms depending on the category of the alternative expression. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit inputs the category of the alternative expression into a generative AI, and the generative AI applies an appropriate proposal algorithm.

[0053] The proposal department can determine the priority of proposals based on the submission timing of alternative expressions. For example, the proposal department can identify the submission timing of alternative expressions. For example, the proposal department can collect and analyze the submission dates and times of alternative expressions as data. The proposal department can also determine the priority of proposals based on the submission timing of alternative expressions. For example, the proposal department can prioritize proposals for alternative expressions that are urgent. The proposal department can also propose general alternative expressions with normal priority. Furthermore, the proposal department can propose past alternative expressions as needed. By determining the priority of proposals based on the submission timing of alternative expressions, proposals can be prioritized for alternative expressions that are urgent. Some or all of the above processing in the proposal department may be performed using a generative AI, or not. For example, the proposal department inputs the submission timing of alternative expressions into a generative AI, and the generative AI determines the priority of proposals.

[0054] The proposal unit can adjust the order of suggestions based on the relevance of alternative expressions during the proposal process. For example, the proposal unit evaluates the relevance of alternative expressions. For example, the proposal unit collects and analyzes the topics and keywords of alternative expressions as data. The proposal unit can also adjust the order of suggestions based on the relevance of alternative expressions. For example, the proposal unit prioritizes suggesting highly relevant alternative expressions. The proposal unit can also postpone suggesting less relevant alternative expressions. Furthermore, the proposal unit can dynamically adjust the order of suggestions based on the relevance of alternative expressions. This allows for prioritizing suggestions for highly relevant alternative expressions by adjusting the order based on their relevance. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit inputs the relevance of alternative expressions into a generative AI, and the generative AI adjusts the order of suggestions.

[0055] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can refer to past learning data. For example, the learning unit can collect and analyze past learning data. The learning unit can also optimize the learning algorithm based on past learning data. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also adjust the parameters of the learning algorithm from past learning data. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. In this way, the accuracy of learning can be improved by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit inputs past learning data into the AI, and the AI ​​optimizes the learning algorithm.

[0056] The learning unit can weight the training data based on the submission date of the posted content during training. For example, the learning unit can identify the submission date of the posted content. For example, the learning unit can collect and analyze the submission date and time of the posted content as data. The learning unit can also weight the training data based on the submission date of the posted content. For example, the learning unit can give higher weight to urgent posted content. The learning unit can also train with normal weighting for general posted content. Furthermore, the learning unit can adjust the weighting of the training data for past posted content as needed. This allows for appropriate weighting of urgent posted content by weighting the training data based on the submission date of the posted content. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit inputs the submission date of the posted content into the AI, and the AI ​​weights the training data.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The reception department can analyze a user's past posting history and understand trends in posting content during specific time periods. For example, if the reception department finds that a user tends to post aggressive content during certain time periods, it will send the content from those times to the analysis department with particular care. Conversely, if the reception department finds that a user tends to post positive content during certain time periods, it can process that content quickly. This allows for the optimization of how posts are received based on the user's posting history.

[0059] The alerting unit can analyze a user's past alert history and evaluate the effectiveness of alerts. For example, it can analyze how users have reacted to alerts in the past and adjust how alerts are displayed. It can also increase the frequency of alerts if a user has a tendency to ignore them in the past. This allows for the optimization of alert effectiveness based on the user's alert history.

[0060] The suggestion department can analyze a user's past suggestion history and evaluate the acceptance rate of suggestions. For example, it can analyze how often a user has accepted alternative expressions suggested in the past and adjust the content of suggestions accordingly. It can also make suggestions more specific if a user has a tendency to reject suggestions in the past. This allows for the optimization of suggestion acceptance rates based on the user's suggestion history.

[0061] The learning unit can analyze a user's past learning history and evaluate the effectiveness of their learning. For example, it can analyze how well a user understood previously learned material and adjust the learning content accordingly. It can also increase the frequency of learning if a user tends to forget previously learned material. This allows for the optimization of learning effectiveness based on the user's learning history.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The reception department receives the submission content. Submission content includes text, images, videos, etc. The reception department receives submission content in these formats and sends it to the analysis department. Step 2: The analysis unit uses a generation AI to analyze the content of posts received by the reception unit. The analysis is performed using natural language processing technology, image analysis technology, and video analysis technology. For example, it analyzes text-based posts to detect violent or offensive language and expressions containing hate speech against others. Step 3: The alert unit issues an alert based on the content of the post analyzed by the analysis unit. The alert is delivered via methods such as a pop-up message or email notification. For example, it might display, "This expression is offensive. Please use a different expression." Step 4: The suggestion unit proposes alternative expressions based on the alerts issued by the alert unit. The suggestions are made using generative AI to present appropriate alternative expressions to the user. For example, it might suggest, "This expression is offensive. Try using the expression '〇〇'." Step 5: The learning unit learns from user responses to the alternative expressions proposed by the proposal unit. Learning is performed using machine learning algorithms, collecting user posts and responses to alerts as data and providing individualized feedback.

[0064] (Example of form 2) The internal communication tool according to an embodiment of the present invention is a system that incorporates a gentle mode and encourages self-reflection and improves respect for others by issuing alerts before sending posts containing violent or aggressive language or hate speech against others in internal communication. This system can improve the quality of communication and enhance the psychological safety of employees. For example, a user inputs content to post using the internal communication tool. At this time, the content is input to a generating AI. The generating AI analyzes the input content and determines whether it contains violent or aggressive language or language that includes hate speech against others. For example, if it contains discriminatory language against a specific nationality or gender, or offensive language, the generating AI will detect it. Next, the generating AI issues an alert to the user for the detected violent or aggressive language or language that includes hate speech against others. The alert indicates that the content of the post is inappropriate and encourages the user to reflect on it. For example, a message such as "This language is offensive. Please use a different expression." may be displayed. Furthermore, the generating AI suggests alternative expressions along with the alert. Alternative expressions are designed to help users communicate respectfully with others. They are suggested by the generative AI based on commonly used inappropriate expressions learned by the AI ​​itself, as well as individual and organizational tendencies. For example, a suggestion might be, "This expression is offensive. Try using the expression '〇〇' instead." The generative AI also learns from users' posts and responses to alerts, learning preferred and undesirable expressions on an individual basis. This allows the generative AI to provide feedback tailored to the user's tendencies, encouraging self-reflection and improvement. This mechanism enables everyone in a company or organization to communicate respectfully with others, improving the quality of communication and increasing employee psychological safety. For example, it can prevent users from unconsciously using offensive language in non-face-to-face communication such as internal social media or email, thereby improving respect for others. As a result, internal communication tools can enhance employee psychological safety and improve the quality of communication.

[0065] The internal communication tool according to this embodiment comprises a reception unit, an analysis unit, an alert unit, a suggestion unit, and a learning unit. The reception unit receives posted content. Posted content includes, but is not limited to, text, images, and videos. The reception unit can, for example, receive posted content in text format. The reception unit can also receive posted content in image format. Furthermore, the reception unit can also receive posted content in video format. For example, the reception unit receives posted content in text format and sends it to the analysis unit. Posted content in image format is sent to the analysis unit using image analysis technology. Posted content in video format is sent to the analysis unit using video analysis technology. The analysis unit analyzes the posted content received by the reception unit using a generation AI. The analysis is performed, for example, using natural language processing technology, but is not limited to this example. For example, the analysis unit analyzes posted content in text format using natural language processing technology. Furthermore, the analysis unit can also analyze posted content in image format using image analysis technology. Furthermore, the analysis unit can also analyze posted content in video format using video analysis technology. For example, the analysis unit uses natural language processing technology to analyze the text content of posts and detect violent, offensive, or hateful expressions. Image analysis technology analyzes specific keywords and context within images to detect violent or offensive expressions. Video analysis technology analyzes audio and text within videos to detect violent or offensive expressions. The alert unit issues alerts based on the post content analyzed by the analysis unit. Alerts are issued based on, for example, the notification method and type of alert, but are not limited to these examples. For example, the alert unit issues an alert to the user regarding inappropriate expressions detected by the analysis unit. The alert unit can also display a pop-up message as a notification method. The alert unit can also send email notifications. For example, the alert unit displays a pop-up message saying, "This expression is offensive. Please use a different expression." Email notifications send an alert message to the user's email address. The suggestion unit proposes alternative expressions based on the alerts issued by the alert unit.Alternative expressions are provided based on, for example, paraphrasing methods or suggestion criteria. For example, the suggestion unit suggests alternative expressions along with alerts. The suggestion unit can also use generative AI to suggest appropriate alternative expressions to the user. Furthermore, the suggestion unit can suggest individual alternative expressions based on the user's tendencies. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '○○'." The learning unit learns the user's responses to the alternative expressions suggested by the suggestion unit. Learning is performed using, for example, machine learning algorithms. For example, the learning unit learns the user's posts and responses to alerts to learn preferred and unpredictable expressions on an individual basis. The learning unit can also collect user responses as data as a method of incorporating feedback. Furthermore, the learning unit can provide feedback based on the user's tendencies. For example, the learning unit learns the user's posts and responses to alerts to provide individualized feedback. As a result, the internal communication tool according to the embodiment can enhance the psychological safety of employees and improve the quality of communication.

[0066] The reception unit receives submissions. Submissions include, but are not limited to, text, images, and videos. The reception unit can, for example, accept text submissions. It can also accept image submissions. Furthermore, it can also accept video submissions. For example, the reception unit accepts text submissions and sends them to the analysis unit. Image submissions are sent to the analysis unit using image analysis technology. Video submissions are sent to the analysis unit using video analysis technology. When receiving these submissions, the reception unit has a function to automatically determine the format of the submission and select the appropriate analysis technology. For example, text submissions are sent to the analysis unit using natural language processing technology. Image submissions are sent to the analysis unit using image recognition technology, and video submissions are sent to the analysis unit using speech recognition technology or video analysis technology. When receiving submissions, the reception unit also collects information about the submitter and sends it to the analysis unit. This allows the analysis unit to perform analysis by associating the submission content with the submitter's information. Furthermore, the reception unit temporarily saves the content of submitted data upon receipt and allows for re-analysis as needed. This enables the analysis unit to perform re-analysis as necessary when generating analysis results, thereby improving analysis accuracy. The reception unit also has a function to select the appropriate analysis technique based on the format and content of the submitted data upon receipt and transmit it to the analysis unit. This allows the reception unit to select the appropriate analysis technique based on the format and content of the submitted data and transmit it to the analysis unit.

[0067] The analysis unit uses generative AI to analyze the content of posts received by the reception unit. The analysis is performed using, for example, natural language processing technology, but is not limited to this example. For example, the analysis unit can analyze text-based posts using natural language processing technology. The analysis unit can also analyze image-based posts using image analysis technology. Furthermore, the analysis unit can analyze video-based posts using video analysis technology. For example, the analysis unit uses natural language processing technology to analyze text-based posts and detect violent, offensive, or hateful expressions. Image analysis technology analyzes specific keywords and context within images to detect violent or offensive expressions. Video analysis technology analyzes audio and text within videos to detect violent or offensive expressions. When analyzing post content using generative AI, the analysis unit can understand the context and intent of the post content and produce appropriate analysis results. For example, when analyzing text-based posts using natural language processing technology, it can understand the context and intent of the post content and produce appropriate analysis results. When analyzing image-based posts using image analysis technology, it is possible to understand specific keywords and context within the image and produce appropriate analysis results. When analyzing video-based posts using video analysis technology, it is possible to understand the audio and text within the video and produce appropriate analysis results. Based on the analysis results of the post content, the analysis unit can provide appropriate information to the alert and suggestion units. In this way, the analysis unit can provide appropriate information to the alert and suggestion units based on the analysis results of the post content.

[0068] The alert unit issues alerts based on the content of posts analyzed by the analysis unit. Alerts are issued based on, for example, the notification method and the type of alert, but are not limited to these examples. For example, the alert unit will issue an alert to the user for inappropriate language detected by the analysis unit. The alert unit can also display a pop-up message as a notification method. The alert unit can also send email notifications. For example, the alert unit will display a pop-up message saying, "This language is offensive. Please use different language." Email notifications send an alert message to the user's email address. When issuing an alert, the alert unit has a function to select the appropriate notification method according to the content and importance of the alert. For example, for high-priority alerts, it can send a pop-up message or email notification, while for low-priority alerts, it can select the notification method. The alert unit has a function to select the appropriate notification method according to the content and importance of the alert. This allows the alert unit to select the appropriate notification method according to the content and importance of the alert. Furthermore, the alert unit can customize the type of alert and the notification method according to the content and importance of the alert. For example, specific alert types and notification methods can be customized for specific users. This allows the alerting unit to customize the type of alert and notification method according to the content and importance of the alert.

[0069] The suggestion unit proposes alternative expressions based on alerts issued by the alert unit. These alternative expressions may be based on, for example, paraphrasing methods or suggestion criteria, but are not limited to these examples. For example, the suggestion unit may propose alternative expressions along with alerts. The suggestion unit can also use generative AI to suggest appropriate alternative expressions to users. Furthermore, the suggestion unit can suggest individual alternative expressions based on user tendencies. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '〇〇'." When the suggestion unit uses generative AI to suggest appropriate alternative expressions to users, it can understand the user's posting content and tendencies and propose appropriate alternative expressions. This allows the suggestion unit to understand the user's posting content and tendencies and propose appropriate alternative expressions. Furthermore, the suggestion unit can understand the user's posting content and tendencies and propose appropriate alternative expressions. This allows the suggestion unit to understand the user's posting content and tendencies and propose appropriate alternative expressions.

[0070] The learning unit learns user responses to alternative expressions proposed by the suggestion unit. Learning is performed using, for example, machine learning algorithms, but is not limited to such examples. For example, the learning unit learns user responses to posts and alerts and learns preferred and unpredictable expressions on an individual basis. The learning unit can also collect user responses as data as a method of incorporating feedback. The learning unit can also provide feedback based on user trends. For example, the learning unit learns user responses to posts and alerts and provides individualized feedback. The learning unit learns user responses to posts and alerts using machine learning algorithms and learns preferred and unpredictable expressions on an individual basis. This allows the learning unit to learn user responses to posts and alerts and learn preferred and unpredictable expressions on an individual basis. Furthermore, the learning unit can learn user responses to posts and alerts and learn preferred and unpredictable expressions on an individual basis. This allows the learning unit to learn from users' posts and responses to alerts, enabling it to learn preferred and undesirable expressions on an individual basis.

[0071] The analysis unit can detect violent or offensive language and expressions containing hate speech against others in the posted content. For example, the analysis unit uses natural language processing technology to detect violent or offensive language in the posted content. For example, the analysis unit analyzes specific keywords or contexts to detect violent or offensive language. The analysis unit can also detect expressions containing hate speech against others. For example, the analysis unit detects discriminatory language and insulting language. This allows for the issuance of appropriate alerts by detecting violent or offensive language and expressions containing hate speech against others. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit inputs the posted content into a generative AI, and the generative AI detects violent or offensive language and expressions containing hate speech against others.

[0072] The alert unit can issue alerts to the user regarding detected inappropriate language. For example, the alert unit may display a message such as, "This language is offensive. Please use a different language." The alert unit can also display alerts as pop-up messages. For example, the alert unit may display "This language is offensive. Please use a different language." as a pop-up message. The alert unit can also send email notifications. For example, the alert unit may send an alert message to the user's email address. By issuing alerts for inappropriate language, it is possible to encourage self-reflection in the user and improve their respect for others. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit may input detected inappropriate language into the AI, and the AI ​​may generate an alert message.

[0073] The suggestion unit can suggest alternative expressions along with alerts. For example, the suggestion unit might suggest, "This expression is offensive. Please try using the expression '〇〇'." The suggestion unit can also use generative AI to suggest appropriate alternative expressions to the user. For example, the suggestion unit might suggest alternative expressions based on common inappropriate expressions learned by the generative AI, or based on individual or organizational tendencies. The suggestion unit can also suggest individual alternative expressions based on the user's tendencies. For example, the suggestion unit might suggest individual alternative expressions based on the user's past posts and responses to alerts. This allows users to communicate in a respectful manner by suggesting alternative expressions. Some or all of the above processing in the suggestion unit may be performed using generative AI, or not. For example, the suggestion unit inputs an alert and an alternative expression into the generative AI, and the generative AI suggests an alternative expression.

[0074] The learning unit can learn preferred and unpredictable expressions on an individual basis by learning from users' posts and responses to alerts. For example, the learning unit can learn from users' posts and responses to alerts. For example, the learning unit can collect user posts and responses to alerts as data and learn using machine learning algorithms. The learning unit can also learn preferred and unpredictable expressions on an individual basis. For example, the learning unit can provide individualized feedback based on user tendencies. This allows for feedback tailored to user tendencies, encouraging self-reflection and improvement. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user posts and responses to alerts into an AI, which then learns preferred and unpredictable expressions.

[0075] The reception desk can estimate the user's emotions and adjust the timing of receiving the post based on the estimated emotions. For example, the reception desk can estimate the user's emotions using facial expression analysis technology. The reception desk can also estimate the user's emotions using voice analysis technology. The reception desk can also estimate the user's emotions using text analysis technology. For example, the reception desk can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The reception desk adjusts the timing of receiving the post based on the estimated emotions. For example, if the user is angry, the reception desk can temporarily delay receiving the post to give them time to calm down. The reception desk can also quickly receive the post and provide support if the user is sad. The reception desk can also process the post more carefully than usual if the user is agitated, prompting them to review the content. This allows for the acceptance of submitted content at the appropriate time by adjusting the timing of content acceptance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The 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 reception unit may be performed using AI or not. For example, the reception unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotion.

[0076] The reception department can analyze a user's past posting history and select the optimal reception method. For example, the reception department can analyze a user's past posting history. For example, the reception department can collect and analyze the user's past posting content as data. The reception department can also select the optimal reception method based on the past posting history. For example, if the reception department has made offensive posts in the past, it can display a confirmation message before accepting the post. The reception department can also quickly accept posts if the user has made appropriate posts in the past. Furthermore, if the reception department has seen a high number of offensive posts during a particular time period based on the user's past posting history, it can carefully accept posts from that time period. This makes the reception of posts more efficient by selecting the optimal reception method based on the user's past posting history. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can input the user's past posting history into AI, and the AI ​​can select the optimal reception method.

[0077] The reception unit can filter submitted content based on the user's current projects and areas of interest. For example, the reception unit can identify the user's current projects and areas of interest. For example, the reception unit can collect and analyze the user's project information and areas of interest as data. The reception unit can also filter submitted content based on the user's current projects and areas of interest. For example, the reception unit can prioritize submissions related to projects the user is currently working on. The reception unit can also prioritize submissions that are highly relevant based on the user's areas of interest. Furthermore, the reception unit can filter out inappropriate submissions based on the user's current projects and areas of interest. This allows for the priority of submissions that are highly relevant by filtering them based on the user's current projects and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit inputs the user's project information and areas of interest into the AI, and the AI ​​performs the filtering.

[0078] The reception desk can estimate the user's emotions and determine the priority of submitted content based on the estimated emotions. For example, the reception desk can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the reception desk can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's submitted content and estimates their emotions. The reception desk determines the priority of submitted content based on the estimated emotions. For example, if the user is angry, the reception desk may lower the priority of the submitted content to give the user time to calm down. If the user is sad, the reception desk may raise the priority of the submitted content to respond quickly. If the user is agitated, the reception desk may also determine the priority of the submitted content more carefully than usual. This allows for the prioritization of posts based on the user's emotions, enabling the system to receive posts with appropriate priority. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The 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 reception unit may be performed using AI or not. For example, the reception unit inputs the user's facial expression data into the generative AI, which then estimates the emotion.

[0079] The reception unit can prioritize receiving posts that are highly relevant, taking into account the user's geographical location information. For example, the reception unit can obtain the user's geographical location information using GPS data. The reception unit can also filter posts that are highly relevant based on the user's geographical location information. For example, if the user is in a specific region, the reception unit will prioritize receiving posts related to that region. The reception unit can also filter posts that are highly relevant based on the user's geographical location information. Furthermore, if the user is on the move, the reception unit can prioritize receiving posts related to their current location. This allows for efficient reception of region-related posts by prioritizing posts that are highly relevant based on the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit inputs the user's geographical location information into the AI, and the AI ​​filters posts that are highly relevant.

[0080] The reception unit can analyze the user's social media activity when receiving submissions and accept relevant submissions. For example, the reception unit can analyze the user's social media activity. For example, the reception unit can collect and analyze the user's social media activity as data. The reception unit can also accept relevant submissions based on the user's social media activity. For example, the reception unit can prioritize accepting submissions related to topics that the user frequently mentions on social media. The reception unit can also analyze topics of high interest from the user's social media activity and accept relevant submissions. Furthermore, the reception unit can filter appropriate submissions based on the user's social media activity. This allows for the priority of accepting submissions of high interest by accepting relevant submissions based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity into AI, and the AI ​​can filter relevant submissions.

[0081] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using facial expression analysis technology. The analysis unit can also estimate the user's emotions using voice analysis technology. The analysis unit can also estimate the user's emotions using text analysis technology. For example, the analysis unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The analysis unit adjusts the way the analysis is presented based on the estimated emotions. For example, if the user is angry, the analysis unit can use a simple expression so that the analysis results can be received calmly. The analysis unit can also use a gentle expression to convey the analysis results if the user is sad. The analysis unit can also use a careful expression so that the analysis results can be received calmly if the user is excited. This allows the analysis results to be presented in an appropriate manner by adjusting the presentation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using the generative AI or not. For example, the analysis unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotions.

[0082] The analysis unit can adjust the level of detail of the analysis based on the importance of the posted content during the analysis. For example, the analysis unit evaluates the importance of the posted content. For example, the analysis unit evaluates the impact and urgency of the posted content. The analysis unit can also adjust the level of detail of the analysis based on the importance of the posted content. For example, the analysis unit performs a detailed analysis for important posted content. The analysis unit can also perform a concise analysis for general posted content. The analysis unit can also perform a rapid analysis for urgent posted content. By adjusting the level of detail of the analysis based on the importance of the posted content, the analysis can be performed at an appropriate level of detail. Some or all of the above processes in the analysis unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the analysis unit inputs the importance of the posted content into the generation AI, and the generation AI adjusts the level of detail of the analysis.

[0083] The analysis unit can apply different analysis algorithms depending on the category of the posted content during analysis. For example, the analysis unit identifies the category of the posted content. For example, the analysis unit collects and analyzes the topic or theme of the posted content as data. The analysis unit can also apply different analysis algorithms depending on the category of the posted content. For example, the analysis unit can apply a specific analysis algorithm to offensive posted content. The analysis unit can also apply a different analysis algorithm to hate speech. The analysis unit can also apply a standard analysis algorithm to general posted content. This allows for appropriate analysis by applying different analysis algorithms depending on the category of the posted content. Some or all of the above processing in the analysis unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the analysis unit inputs the category of the posted content into the generative AI, and the generative AI applies an appropriate analysis algorithm.

[0084] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the analysis unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The analysis unit adjusts the length of the analysis based on the estimated emotions. For example, if the user is angry, the analysis unit will summarize the analysis results briefly and concisely. If the user is sad, the analysis unit can explain the analysis results carefully. If the user is excited, the analysis unit can carefully summarize the analysis results so that they can be received calmly. In this way, by adjusting the length of the analysis according to the user's emotions, the analysis results can be provided at an appropriate length. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using the generative AI or not. For example, the analysis unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotion.

[0085] The analysis unit can determine the priority of analysis based on the submission date of the posted content during the analysis process. For example, the analysis unit identifies the submission date of the posted content. For example, the analysis unit collects the submission date and time of the posted content as data and analyzes it. The analysis unit can also determine the priority of analysis based on the submission date of the posted content. For example, the analysis unit prioritizes the analysis of urgent posted content. The analysis unit can also analyze general posted content with normal priority. The analysis unit can also analyze past posted content as needed. By determining the priority of analysis based on the submission date of the posted content, urgent posted content can be analyzed preferentially. 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 submission date of the posted content into the generation AI, and the generation AI determines the priority of analysis.

[0086] The analysis unit can adjust the order of analysis based on the relevance of the posted content during analysis. For example, the analysis unit evaluates the relevance of the posted content. For example, the analysis unit collects and analyzes the topics and keywords of the posted content as data. The analysis unit can also adjust the order of analysis based on the relevance of the posted content. For example, the analysis unit prioritizes the analysis of highly relevant posted content. The analysis unit can also postpone the analysis of less relevant posted content. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the posted content. This allows for prioritizing the analysis of highly relevant posted content by adjusting the order of analysis based on the relevance of the posted content. 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 relevance of the posted content into a generation AI, and the generation AI adjusts the order of analysis.

[0087] The alert unit can estimate the user's emotions and adjust how alerts are displayed based on those estimated emotions. For example, the alert unit can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the alert unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The alert unit adjusts how alerts are displayed based on the estimated user emotions. For example, if the user is angry, the alert unit can display a simple alert so that it can be received calmly. If the user is sad, the alert unit can display a gentle alert. If the user is excited, the alert unit can display a cautious alert so that it can be received calmly. In this way, by adjusting how alerts are displayed according to the user's emotions, alerts can be displayed in an appropriate manner. Emotion estimation is achieved using an emotion estimation function, for example, with 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-described processing in the alert unit may be performed using or without a generative AI. For example, the alert unit inputs user facial expression data into a generative AI, and the generative AI estimates the emotion.

[0088] The alert unit can adjust the level of detail of an alert based on the importance of the post content when displaying an alert. For example, the alert unit can evaluate the importance of the post content. For example, the alert unit can evaluate the impact and urgency of the post content. The alert unit can also adjust the level of detail of an alert based on the importance of the post content. For example, the alert unit can display a detailed alert for important posts. The alert unit can also display a concise alert for general posts. Furthermore, the alert unit can display an alert quickly for urgent posts. By adjusting the level of detail of an alert based on the importance of the post content, the alert can be displayed with an appropriate level of detail. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the importance of the post content into the AI, and the AI ​​adjusts the level of detail of the alert.

[0089] The alert unit can apply different alert messages depending on the category of the post content when displaying an alert. For example, the alert unit can identify the category of the post content. For example, the alert unit can collect and analyze the topic or theme of the post content as data. The alert unit can also apply different alert messages depending on the category of the post content. For example, the alert unit can display a specific alert message for offensive posts. The alert unit can also display a different alert message for hate speech. The alert unit can also display a standard alert message for general posts. This allows for the display of appropriate alerts by applying different alert messages depending on the category of the post content. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the category of the post content into the AI, and the AI ​​applies an appropriate alert message.

[0090] The alert unit can estimate the user's emotions and adjust the length of the alert based on the estimated emotions. For example, the alert unit can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the alert unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The alert unit adjusts the length of the alert based on the estimated emotions. For example, if the user is angry, the alert unit will make the alert short and concise. If the user is sad, the alert unit can explain the alert in detail. If the user is excited, the alert unit can carefully summarize the alert so that it can be received calmly. In this way, by adjusting the length of the alert according to the user's emotions, the alert can be displayed at an appropriate length. Emotion estimation is achieved using an emotion estimation function, for example, with 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-described processing in the alert unit may be performed using or without a generative AI. For example, the alert unit inputs user facial expression data into a generative AI, and the generative AI estimates the emotion.

[0091] The alert unit can determine the priority of alerts based on the submission date of the posted content when displaying an alert. For example, the alert unit identifies the submission date of the posted content. For example, the alert unit collects and analyzes the submission date and time of the posted content as data. The alert unit can also determine the priority of alerts based on the submission date of the posted content. For example, the alert unit will display alerts preferentially for posts that are urgent. The alert unit can also display alerts with normal priority for general posts. Furthermore, the alert unit can display alerts for past posts as needed. In this way, by determining the priority of alerts based on the submission date of the posted content, alerts can be displayed preferentially for posts that are urgent. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the submission date of the posted content into the AI, and the AI ​​determines the priority of the alerts.

[0092] The alert unit can adjust the order of alerts based on the relevance of the posts when displaying alerts. For example, the alert unit evaluates the relevance of the posts. For example, the alert unit collects and analyzes the topics and keywords of the posts as data. The alert unit can also adjust the order of alerts based on the relevance of the posts. For example, the alert unit can prioritize displaying alerts for highly relevant posts. The alert unit can also postpone displaying alerts for less relevant posts. Furthermore, the alert unit can dynamically adjust the order of alerts based on the relevance of the posts. This allows for prioritizing the display of alerts for highly relevant posts by adjusting the order of alerts based on the relevance of the posts. Some or all of the above processing in the alert unit may be performed using AI or not. For example, the alert unit inputs the relevance of the posts into the AI, and the AI ​​adjusts the order of alerts.

[0093] The suggestion function can estimate the user's emotions and adjust the way it presents its suggestions based on those estimated emotions. For example, the suggestion function can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the suggestion function can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The suggestion function adjusts the way it presents its suggestions based on the estimated user's emotions. For example, if the user is angry, the suggestion function can make simple suggestions that can be received calmly. If the user is sad, the suggestion function can make gentle suggestions. If the user is excited, the suggestion function can make careful suggestions that can be received calmly. This allows for the presentation of suggestions in an appropriate manner by adjusting the presentation style according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using the generative AI or not. For example, the suggestion unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotion.

[0094] The proposal unit can adjust the level of detail of a proposal based on the importance of alternative expressions. For example, the proposal unit can evaluate the importance of alternative expressions. For example, the proposal unit can evaluate the impact and urgency of alternative expressions. The proposal unit can also adjust the level of detail of a proposal based on the importance of alternative expressions. For example, the proposal unit can provide detailed proposals for important alternative expressions. The proposal unit can also provide concise proposals for common alternative expressions. Furthermore, the proposal unit can provide rapid proposals for highly urgent alternative expressions. By adjusting the level of detail of a proposal based on the importance of alternative expressions, proposals can be made with an appropriate level of detail. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit inputs the importance of alternative expressions into the AI, and the AI ​​adjusts the level of detail of the proposal.

[0095] The proposal unit can apply different proposal algorithms depending on the category of the alternative expression during the proposal process. For example, the proposal unit can identify the category of the alternative expression. For example, the proposal unit can collect and analyze data on the topic or theme of the alternative expression. The proposal unit can also apply different proposal algorithms depending on the category of the alternative expression. For example, the proposal unit can apply a specific proposal algorithm to offensive expressions. The proposal unit can also apply a different proposal algorithm to hate speech. The proposal unit can also apply a standard proposal algorithm to general expressions. This allows for appropriate proposals to be made by applying different proposal algorithms depending on the category of the alternative expression. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit inputs the category of the alternative expression into a generative AI, and the generative AI applies an appropriate proposal algorithm.

[0096] The suggestion function can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, the suggestion function can estimate the user's emotions using facial expression analysis technology. It can also estimate the user's emotions using voice analysis technology. It can also estimate the user's emotions using text analysis technology. For example, the suggestion function can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's post and estimates their emotions. The suggestion function adjusts the length of the suggestion based on the estimated emotions. For example, if the user is angry, the suggestion function will make the suggestion short and concise. If the user is sad, the suggestion function can explain the suggestion carefully. If the user is excited, the suggestion function can carefully summarize the suggestion so that it can be received calmly. In this way, by adjusting the length of the suggestion according to the user's emotions, it is possible to make suggestions of an appropriate length. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the proposed unit may be performed using a generative AI or not. For example, the proposed unit inputs user facial expression data into a generative AI, and the generative AI estimates the emotion.

[0097] The proposal department can determine the priority of proposals based on the submission timing of alternative expressions. For example, the proposal department can identify the submission timing of alternative expressions. For example, the proposal department can collect and analyze the submission dates and times of alternative expressions as data. The proposal department can also determine the priority of proposals based on the submission timing of alternative expressions. For example, the proposal department can prioritize proposals for alternative expressions that are urgent. The proposal department can also propose general alternative expressions with normal priority. Furthermore, the proposal department can propose past alternative expressions as needed. By determining the priority of proposals based on the submission timing of alternative expressions, proposals can be prioritized for alternative expressions that are urgent. Some or all of the above processing in the proposal department may be performed using a generative AI, or not. For example, the proposal department inputs the submission timing of alternative expressions into a generative AI, and the generative AI determines the priority of proposals.

[0098] The proposal unit can adjust the order of suggestions based on the relevance of alternative expressions during the proposal process. For example, the proposal unit evaluates the relevance of alternative expressions. For example, the proposal unit collects and analyzes the topics and keywords of alternative expressions as data. The proposal unit can also adjust the order of suggestions based on the relevance of alternative expressions. For example, the proposal unit prioritizes suggesting highly relevant alternative expressions. The proposal unit can also postpone suggesting less relevant alternative expressions. Furthermore, the proposal unit can dynamically adjust the order of suggestions based on the relevance of alternative expressions. This allows for prioritizing suggestions for highly relevant alternative expressions by adjusting the order based on their relevance. Some or all of the above processing in the proposal unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the proposal unit inputs the relevance of alternative expressions into a generative AI, and the generative AI adjusts the order of suggestions.

[0099] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, the learning unit can estimate the user's emotions using facial expression analysis technology. The learning unit can also estimate the user's emotions using voice analysis technology. The learning unit can also estimate the user's emotions using text analysis technology. For example, the learning unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's posts and estimates their emotions. The learning unit selects training data based on the estimated user emotions. For example, if the user is angry, the learning unit can select training data that can be received calmly. If the user is sad, the learning unit can select training data that conveys the message gently. If the user is excited, the learning unit can select training data that can be received calmly. This allows for the selection of training data according to the user's emotions, enabling learning using appropriate training data. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using the generative AI or not. For example, the learning unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotion.

[0100] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can refer to past learning data. For example, the learning unit can collect and analyze past learning data. The learning unit can also optimize the learning algorithm based on past learning data. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also adjust the parameters of the learning algorithm from past learning data. Furthermore, the learning unit can analyze past learning data to improve the accuracy of the learning algorithm. In this way, the accuracy of learning can be improved by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit inputs past learning data into the AI, and the AI ​​optimizes the learning algorithm.

[0101] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can estimate the user's emotions using facial expression analysis technology. The learning unit can also estimate the user's emotions using voice analysis technology. The learning unit can also estimate the user's emotions using text analysis technology. For example, the learning unit can analyze the user's facial expressions using facial expression analysis technology and estimate their emotions. Voice analysis technology analyzes the tone and speed of the user's voice and estimates their emotions. Text analysis technology analyzes the context of the user's posts and estimates their emotions. The learning unit adjusts the learning frequency based on the estimated emotions. For example, if the user is angry, the learning unit can reduce the learning frequency to give them time to calm down. The learning unit can also increase the learning frequency to provide support if the user is sad. The learning unit can also adjust the learning frequency more cautiously than usual if the user is excited. This allows learning to be performed at an appropriate frequency by adjusting the learning 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. The 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 learning unit may be performed using the generative AI or not. For example, the learning unit inputs the user's facial expression data into the generative AI, and the generative AI estimates the emotion.

[0102] The learning unit can weight the training data based on the submission date of the posted content during training. For example, the learning unit can identify the submission date of the posted content. For example, the learning unit can collect and analyze the submission date and time of the posted content as data. The learning unit can also weight the training data based on the submission date of the posted content. For example, the learning unit can give higher weight to urgent posted content. The learning unit can also train with normal weighting for general posted content. Furthermore, the learning unit can adjust the weighting of the training data for past posted content as needed. This allows for appropriate weighting of urgent posted content by weighting the training data based on the submission date of the posted content. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit inputs the submission date of the posted content into the AI, and the AI ​​weights the training data.

[0103] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0104] The reception department can analyze a user's past posting history and understand trends in posting content during specific time periods. For example, if the reception department finds that a user tends to post aggressive content during certain time periods, it will send the content from those times to the analysis department with particular care. Conversely, if the reception department finds that a user tends to post positive content during certain time periods, it can process that content quickly. This allows for the optimization of how posts are received based on the user's posting history.

[0105] The analysis unit can analyze the context of posts and detect changes in sentiment related to specific topics. For example, if a user tends to express heightened emotions when posting about a particular project, the analysis unit will analyze posts related to that project with particular care. Similarly, if a user tends to express calmer emotions when posting about a particular colleague, the analysis unit can quickly process posts about that colleague. This allows the analysis method to be optimized based on the context of the posts.

[0106] The alerting unit can analyze a user's past alert history and evaluate the effectiveness of alerts. For example, it can analyze how users have reacted to alerts in the past and adjust how alerts are displayed. It can also increase the frequency of alerts if a user has a tendency to ignore them in the past. This allows for the optimization of alert effectiveness based on the user's alert history.

[0107] The suggestion department can analyze a user's past suggestion history and evaluate the acceptance rate of suggestions. For example, it can analyze how often a user has accepted alternative expressions suggested in the past and adjust the content of suggestions accordingly. It can also make suggestions more specific if a user has a tendency to reject suggestions in the past. This allows for the optimization of suggestion acceptance rates based on the user's suggestion history.

[0108] The learning unit can analyze a user's past learning history and evaluate the effectiveness of their learning. For example, it can analyze how well a user understood previously learned material and adjust the learning content accordingly. It can also increase the frequency of learning if a user tends to forget previously learned material. This allows for the optimization of learning effectiveness based on the user's learning history.

[0109] The reception desk can estimate the user's emotions and adjust how it processes submissions based on those emotions. For example, if the user is angry, the reception desk can temporarily hold off on submitting the submission to give them time to calm down. Conversely, if the user is sad, the reception desk can quickly process the submission and provide support. This allows the system to optimize how submissions are processed according to the user's emotions.

[0110] The analysis unit can estimate the user's emotions and adjust the level of detail in the analysis based on the estimated emotions. For example, if the user is angry, the analysis unit will summarize the results concisely. Conversely, if the user is sad, the analysis unit can explain the results in detail. This allows the level of detail in the analysis to be optimized according to the user's emotions.

[0111] The alert function can estimate the user's emotions and adjust how alerts are displayed based on those emotions. For example, if the user is angry, the alert function will display a simple alert. Conversely, if the user is sad, the alert function can display a gentler alert. This allows for the optimization of alert display methods according to the user's emotions.

[0112] The suggestion function can estimate the user's emotions and adjust the content of the suggestion based on those emotions. For example, if the user is angry, the suggestion function will make the suggestion concise. Conversely, if the user is sad, the suggestion function can explain the suggestion in detail. This allows the content of the suggestion to be optimized according to the user's emotions.

[0113] The learning unit can estimate the user's emotions and adjust the learning content based on those emotions. For example, if the user is angry, the learning unit will summarize the learning content concisely. Conversely, if the user is sad, the learning unit can explain the learning content in detail. This allows the learning content to be optimized according to the user's emotions.

[0114] The following briefly describes the processing flow for example form 2.

[0115] Step 1: The reception department receives the submission content. Submission content includes text, images, videos, etc. The reception department receives submission content in these formats and sends it to the analysis department. Step 2: The analysis unit uses a generation AI to analyze the content of posts received by the reception unit. The analysis is performed using natural language processing technology, image analysis technology, and video analysis technology. For example, it analyzes text-based posts to detect violent or offensive language and expressions containing hate speech against others. Step 3: The alert unit issues an alert based on the content of the post analyzed by the analysis unit. The alert is delivered via methods such as a pop-up message or email notification. For example, it might display, "This expression is offensive. Please use a different expression." Step 4: The suggestion unit proposes alternative expressions based on the alerts issued by the alert unit. The suggestions are made using generative AI to present appropriate alternative expressions to the user. For example, it might suggest, "This expression is offensive. Try using the expression '〇〇'." Step 5: The learning unit learns from user responses to the alternative expressions proposed by the proposal unit. Learning is performed using machine learning algorithms, collecting user posts and responses to alerts as data and providing individualized feedback.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] Each of the multiple elements described above, including the reception unit, analysis unit, alert unit, suggestion unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives the user's posted content. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the posted content. The alert unit is implemented by the control unit 46A of the smart device 14 and issues an alert to the user. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests an alternative expression. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0120] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] The microphone 238 receives voice signals from the user and accepts instructions from the user. 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] Each of the multiple elements described above, including the reception unit, analysis unit, alert unit, suggestion unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives the user's posted content. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the posted content. The alert unit is implemented by the control unit 46A of the smart glasses 214 and issues an alert to the user. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests an alternative expression. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0136] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] The microphone 238 receives voice signals from the user and accepts instructions from the user. 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] Each of the multiple elements described above, including the reception unit, analysis unit, alert unit, suggestion unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives the user's posted content. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the posted content. The alert unit is implemented by the control unit 46A of the headset terminal 314 and issues an alert to the user. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests an alternative expression. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's response. 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.

[0152] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] The microphone 238 receives voice signals from the user and accepts instructions from the user. 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the reception unit, analysis unit, alert unit, suggestion unit, and learning unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives the user's posted content. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the posted content. The alert unit is implemented by the control unit 46A of the robot 414 and issues an alert to the user. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and suggests an alternative expression. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] (Note 1) The reception desk accepts submissions, An analysis unit analyzes the content of posts received by the aforementioned reception unit, An alert unit issues an alert based on the content of the post analyzed by the aforementioned analysis unit, A proposal unit proposes alternative expressions based on the alerts issued by the alert unit, The system includes a learning unit that learns the user's response to the alternative expression proposed by the proposal unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Detects violent or offensive language, as well as hate speech directed at others, within the content of posts. The system described in Appendix 1, characterized by the features described herein. (Note 3) The alert unit is, The system will alert the user to any detected inappropriate content. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, We will suggest alternative expressions along with the alert. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, It learns from user posts and responses to alerts, and learns preferred and undesirable expressions on an individual basis. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of submission based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the user's past posting history and select the most suitable submission method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When receiving submissions, the system filters them based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The system estimates the user's emotions and prioritizes the content of posts to be accepted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving submissions, the system prioritizes accepting submissions that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving submissions, the system analyzes the user's social media activity and accepts relevant submissions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on the importance of the content of the posts. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the posted content. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the priority of analysis is determined based on the submission date of the submitted content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the posted content. The system described in Appendix 1, characterized by the features described herein. (Note 18) The alert unit is, It estimates the user's emotions and adjusts how alerts are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The alert unit is, When displaying an alert, adjust the level of detail of the alert based on the importance of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 20) The alert unit is, When an alert is displayed, apply different alert messages depending on the category of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 21) The alert unit is, It estimates the user's sentiment and adjusts the length of the alert based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The alert unit is, When an alert is displayed, the alert priority is determined based on when the submitted content was received. The system described in Appendix 1, characterized by the features described herein. (Note 23) The alert unit is, When displaying alerts, adjust the order of alerts based on the relevance of the post content. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the importance of the alternative expression. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, When making a proposal, different proposal algorithms are applied depending on the category of the alternative representation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, When submitting a proposal, prioritize the proposals based on when alternative expressions are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, When making proposals, adjust the order of proposals based on the relevance of the alternative expressions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned learning unit, During training, the training data is weighted based on the submission date of the submitted content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0188] 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. The reception desk accepts submissions, An analysis unit analyzes the content of posts received by the aforementioned reception unit, An alert unit issues an alert based on the content of the post analyzed by the aforementioned analysis unit, A proposal unit proposes alternative expressions based on the alerts issued by the alert unit, The system includes a learning unit that learns the user's response to the alternative expression proposed by the proposal unit. A system characterized by the following features.

2. The aforementioned analysis unit, Detects violent or offensive language, as well as hate speech directed at others, within the content of posts. The system according to feature 1.

3. The alert unit is, The system will alert the user to any detected inappropriate content. The system according to feature 1.

4. The aforementioned proposal section is, We will suggest alternative expressions along with the alert. The system according to feature 1.

5. The aforementioned learning unit, It learns from user posts and responses to alerts, and learns preferred and undesirable expressions on an individual basis. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of submission based on those emotions. The system according to feature 1.

7. The aforementioned reception unit is Analyze the user's past posting history and select the most suitable submission method. The system according to feature 1.

8. The aforementioned reception unit is When receiving submissions, the system filters them based on the user's current projects and areas of interest. The system according to feature 1.

9. The aforementioned reception unit is The system estimates the user's emotions and prioritizes the content of posts to be accepted based on those estimated emotions. The system according to feature 1.

10. The aforementioned reception unit is When receiving submissions, the system prioritizes accepting submissions that are highly relevant, taking into account the user's geographical location. The system according to feature 1.

Images