system

Abstract

The system according to this embodiment aims to help employees working away from their families deepen their bonds with their families and maintain their mental health. [Solution] The system according to the embodiment comprises a collection unit, an SNS collection unit, an emotion analysis unit, a message generation unit, and a provision unit. The collection unit collects employee schedule information. The SNS collection unit collects SNS posts from family members. The emotion analysis unit analyzes emotions based on the information collected by the collection unit and the SNS collection unit. The message generation unit generates messages based on the emotions analyzed by the emotion analysis unit. The provision unit provides the messages generated by the message generation unit to employees.

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, a commuting employee is likely to feel insufficient communication and alienation from family members, which may cause mental stress and family disharmony.

[0005] The system according to the embodiment aims to deepen the bond between a commuting employee and family members and maintain mental health.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an SNS collection unit, an emotion analysis unit, a message generation unit, and a provision unit. The collection unit collects employee schedule information. The SNS collection unit collects SNS posts from family members. The emotion analysis unit analyzes emotions based on the information collected by the collection unit and the SNS collection unit. The message generation unit generates messages based on the emotions analyzed by the emotion analysis unit. The provision unit provides the messages generated by the message generation unit to employees. [Effects of the Invention]

[0007] The system according to this embodiment allows employees working away from their families to deepen their bonds with their families and maintain their mental health. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. 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 FamilyBridge AI system according to an embodiment of the present invention is designed to help employees working away from their families deepen their bonds with them. This system generates personalized messages using emotion analysis technology. Specifically, the FamilyBridge AI system analyzes emotions from the employee's schedule and family's social media posts, and generates messages and video messages tailored to the optimal timing and content. Furthermore, the FamilyBridge AI system performs emotion analysis based on the employee's emotional state and family feedback, and proposes appropriate message content. Facial recognition technology is also used for videos, allowing for more emotionally rich communication. For example, the FamilyBridge AI system creates an environment where employees working away from their families can work without feeling distant from them, improving work-life balance. As a result, the FamilyBridge AI system helps maintain the mental health of employees and improves corporate productivity. The FamilyBridge AI system also supports the harmony between work and family life, aiming to create a happy family environment. The FamilyBridge AI system targets employees working away from their families and their families, as well as companies that are committed to supporting work-life balance. Employees working away from their families are prone to feeling isolated and lacking communication, which can lead to mental stress and family discord. As a result, employee stress and family problems can negatively impact productivity for companies. This system uses AI to analyze an employee's emotions based on their schedule and family's social media posts, generating personalized messages and video messages tailored to the optimal timing and content. Furthermore, the FamilyBridge AI system analyzes the employee's emotional state and family feedback to suggest appropriate message content. Videos also utilize facial recognition technology to convey emotions more vividly. In terms of market size, the number of employees working away from their families in Japan alone amounts to several hundred thousand, and with the increasing number of companies providing work-life balance support, the potential market size is enormous. Advances in generation AI and facial recognition technology have made it possible to generate more human-like messages.In today's world, where work-style reform and the emphasis on family well-being are widespread, there is demand for solutions that address both mental health and performance improvement. The FamilyBridge AI system creates an environment where employees working away from home can work without feeling distant from their families, thereby improving work-life balance. Through this, the FamilyBridge AI system aims to improve employees' mental health and corporate productivity, while also supporting the harmony between work and family life and creating a happy family environment. Therefore, the FamilyBridge AI system can create an environment where employees working away from home can work without feeling distant from their families, thereby improving work-life balance.

[0029] The FamilyBridge AI system according to this embodiment comprises a collection unit, an SNS collection unit, a sentiment analysis unit, a message generation unit, and a provision unit. The collection unit collects employee schedule information. The collection unit can collect, for example, employee meeting schedules, business trip schedules, and vacation schedules. The collection unit can also obtain information from employee schedule management tools. The collection unit can also collect schedule information from employee calendar applications. The collection unit can also extract schedule information from employee emails. The SNS collection unit collects family SNS posts. The SNS collection unit can also obtain information from family SNS accounts. The SNS collection unit can also monitor family SNS feeds and collect posts. The SNS collection unit can also extract information from family SNS messages. The sentiment analysis unit analyzes emotions based on the information collected by the collection unit and the SNS collection unit. The sentiment analysis unit analyzes text data using, for example, natural language processing technology to determine emotions. The sentiment analysis unit can classify text data as positive, negative, or neutral. The sentiment analysis unit can also calculate an emotion score for text data. The emotion analysis unit can also assign emotion labels to text data. The message generation unit generates messages based on the emotions analyzed by the emotion analysis unit. The message generation unit can, for example, perform template-based generation. The message generation unit can also generate messages using natural language generation technology. The message generation unit can also generate message content that corresponds to emotions. The message generation unit can also analyze facial expressions from video data using facial recognition technology and determine emotions. The delivery unit provides the messages generated by the message generation unit to employees. The delivery unit can, for example, send the generated messages to employees via email. The delivery unit can also notify employees of the generated messages via a chat application. The delivery unit can also display the generated messages to employees via a web application. The delivery unit can also provide employees with generated video messages.As a result, the FamilyBridge AI system according to this embodiment can deepen the bond between employees and their families by collecting employee schedule information and family SNS posts, analyzing emotions, and generating and providing personalized messages.

[0030] The data collection unit collects employee schedule information. Specifically, it can collect employee meeting schedules, business trip schedules, and vacation schedules. The data collection unit can also obtain information from employee schedule management tools. This allows for real-time collection of employee schedule information and the maintenance of up-to-date information. Furthermore, the data collection unit can also collect schedule information from employee calendar applications. For example, it can synchronize data from smartphone calendar apps to centrally manage employee schedules. The data collection unit can also extract schedule information from employee emails. For example, it can analyze the content of emails and automatically extract schedule-related information such as meeting invitations and business trip notifications. This allows the data collection unit to collect schedule information from diverse sources and accurately understand employee schedules. The data collection unit centrally manages this information and can collaborate with other systems and departments as needed. For example, collected schedule information can be stored on a cloud server and made accessible to the sentiment analysis unit and message generation unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The SNS Collection Unit collects social media posts from family members. It can also retrieve information from family members' social media accounts. For example, it can automatically collect family posting data using the APIs of various social media platforms. This allows for real-time access to the family's latest posts, comments, and photos. The SNS Collection Unit can also monitor family members' social media feeds to collect posts. For example, it can monitor specific keywords or hashtags and collect related posts. This allows for understanding changes in family members' interests and emotions. The SNS Collection Unit can also extract information from family members' social media messages. For example, it can analyze the content of private and direct messages to extract emotions and important information. This allows the SNS Collection Unit to collect family social media posts from diverse sources and accurately understand the family's situation and emotions. The SNS Collection Unit centrally manages this information and can collaborate with other systems and departments as needed. For example, collected social media information can be stored on a cloud server and accessed by the Sentiment Analysis Unit and the Message Generation Unit. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the SNS Collection Unit to collect data efficiently and effectively, improving the overall system performance.

[0032] The Sentiment Analysis Department analyzes emotions based on information collected by the Data Collection Department and the Social Media Data Collection Department. Specifically, it analyzes text data using natural language processing technology to determine emotions. For example, it can classify text data as positive, negative, or neutral. The Sentiment Analysis Department can also calculate emotion scores for text data. For example, it can quantify the degree of positivity or negativity for each text to evaluate the strength of the emotion. The Sentiment Analysis Department can also assign emotion labels to text data. For example, it can assign labels corresponding to specific emotions (joy, sadness, anger, etc.) to text to clarify the type of emotion. Based on these analysis results, the Sentiment Analysis Department can grasp changes and trends in the emotions of employees and their families. Furthermore, the Sentiment Analysis Department can predict long-term emotional fluctuations by utilizing past data and statistical information. For example, based on past emotional data, it can predict emotional fluctuations at specific times or events and formulate future countermeasures. In addition, the Sentiment Analysis Department can use anomaly detection algorithms to detect unusual patterns and abnormal emotions and issue warnings early. This allows the emotion analysis unit to not only grasp emotions in real time, but also to handle long-term emotion management and anomaly detection, thereby improving the reliability and security of the entire system.

[0033] The message generation unit generates messages based on emotions analyzed by the emotion analysis unit. Specifically, it can perform template-based generation. For example, it generates congratulatory messages for positive emotions and encouraging messages for negative emotions. The message generation unit can also generate messages using natural language generation technology. For example, it can use generation AI to generate natural-sounding sentences that correspond to emotions. The message generation unit can also generate message content that corresponds to emotions. For example, if the emotion score is high, it generates a more detailed and empathetic message, and if the emotion score is low, it generates a concise and direct message. The message generation unit can also analyze facial expressions from video data using facial recognition technology to determine emotions. For example, it can analyze the facial expressions of employees and their families and generate video messages that correspond to their emotions. This allows the message generation unit to generate personalized messages that correspond to emotions and provide them to employees and their families. Furthermore, the message generation unit can evaluate the effectiveness of the generated messages and continuously improve them. For example, it can collect feedback from message recipients and improve the message content and generation algorithm. In addition, the message generation unit can combine multiple message generation methods to generate the optimal message. This allows the message generation unit to always utilize the latest technology and provide the best possible message.

[0034] The delivery department provides employees with messages generated by the message generation department. Specifically, it can send generated messages to employees via email. For example, it can automatically send messages to employees' email addresses to quickly convey important information. The delivery department can also notify employees of generated messages via chat applications. For example, it can notify messages in real time through chat applications. The delivery department can also display generated messages to employees via web applications. For example, it can display messages through the company portal site or a dedicated web application, allowing employees to access them at any time. The delivery department can also provide employees with generated video messages. For example, it can record video messages and send them to employees to achieve more emotionally engaging communication. This allows the delivery department to quickly deliver appropriate messages to each employee, strengthening the bond between employees and their families. Furthermore, the delivery department can monitor the delivery status and effectiveness of messages and continuously improve them. For example, it can analyze message open rates and click-through rates to optimize delivery methods and message content. In addition, the delivery department can combine multiple delivery methods to ensure information is reliably transmitted. For example, it can use email, chat, web, and video in combination to ensure important information is delivered reliably. This allows the service department to deliver messages to employees quickly and reliably, strengthening the bond between employees and their families.

[0035] The sentiment analysis unit can analyze text data using natural language processing technology and determine emotions. For example, the sentiment analysis unit can perform morphological analysis of text data and determine emotions. The sentiment analysis unit can also perform grammatical analysis of text data and determine emotions. The sentiment analysis unit can also perform semantic analysis of text data and determine emotions. The sentiment analysis unit can also calculate an emotion score for text data. The sentiment analysis unit can also assign emotion labels to text data. This improves the accuracy of emotion determination from text data by using natural language processing technology. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can determine emotions using an AI model that takes text data as input and outputs emotions.

[0036] The message generation unit can analyze facial expressions from video data using facial recognition technology and determine emotions. For example, the message generation unit can detect faces from video data using a face detection algorithm. The message generation unit can also classify facial expressions from video data using a facial classification algorithm. The message generation unit can calculate facial expression scores for video data. The message generation unit can also assign facial expression labels to video data. This improves the accuracy of emotion determination from video data by using facial recognition technology. Some or all of the above-described processes in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can determine emotions using an AI model that takes video data as input and outputs emotions.

[0037] The message generation unit can perform sentiment analysis based on the employee's emotional state and family feedback, and propose appropriate message content. For example, the message generation unit can analyze the employee's emotional state and propose appropriate message content. The message generation unit can also analyze family feedback and propose appropriate message content. The message generation unit can combine the employee's emotional state and family feedback to propose appropriate message content. The message generation unit can also adjust the tone and content of the message based on the results of the sentiment analysis. This allows for the proposal of more personalized message content by considering the employee's emotional state and family feedback. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can propose message content using an AI model that takes the employee's emotional state and family feedback as input and outputs appropriate message content.

[0038] The service provider can provide the generated messages to employees. For example, the service provider can send the generated messages to employees via email. The service provider can also notify employees of the generated messages via a chat application. The service provider can also display the generated messages to employees via a web application. The service provider can also provide employees with the generated messages on paper. This can facilitate communication between employees and their families by providing them with the generated messages. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can provide messages using an AI model that takes the generated messages as input and outputs a method for providing them to employees.

[0039] The service provider can provide the generated video message to employees. For example, the service provider can send the generated video message to employees via email. The service provider can also notify employees of the generated video message via a chat application. The service provider can also display the generated video message to employees via a web application. The service provider can also provide the generated video message to employees in paper form. This allows for more emotionally rich communication by providing employees with the generated video message. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can provide the video message using an AI model that takes the generated video message as input and outputs a method for providing it to employees.

[0040] The data collection unit can analyze an employee's past schedule history and select the optimal data collection method. For example, the data collection unit may prioritize using schedule management tools that the employee has frequently used in the past. The data collection unit can also analyze an employee's past schedule patterns and determine the optimal timing for data collection. The data collection unit can also select a method for collecting data during a specific time period based on the employee's past schedule history. This allows for the selection of the optimal data collection method by analyzing past schedule history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can select a data collection method using an AI model that takes an employee's past schedule history as input and outputs the optimal data collection method.

[0041] The data collection unit can filter schedule information based on an employee's current projects and tasks. For example, the unit can collect only schedule information related to ongoing projects. The unit can also prioritize the collection of schedule information related to specific tasks. The unit can also collect only important schedule information, taking into account the employee's current workload. This allows for the collection of highly relevant schedule information by filtering based on current projects and tasks. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can perform filtering using an AI model that takes an employee's current projects and tasks as input and outputs filtered schedule information.

[0042] The data collection unit can prioritize the collection of highly relevant information by considering the geographical location of employees when collecting schedule information. For example, the data collection unit can prioritize the collection of schedule information related to the employee's current location. The data collection unit can also collect schedule information related to the next destination based on the employee's travel plans. The data collection unit can also collect schedule information for nearby events and meetings based on the employee's geographical location. This allows for the priority collection of highly relevant schedule information by considering geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes the employee's geographical location as input and outputs highly relevant schedule information.

[0043] The data collection unit can collect relevant information by analyzing employees' social media activity when collecting schedule information. For example, the data collection unit can collect schedule information for events and meetings that employees have shared on social media. The data collection unit can also collect schedule information related to employees' interests from their social media activity. The data collection unit can also collect relevant schedule information by analyzing the content of employees' social media posts. In this way, relevant schedule information can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes employees' social media activity as input and outputs relevant schedule information.

[0044] The SNS collection unit can analyze a family's past SNS posting history and select the optimal collection method. For example, the SNS collection unit can collect SNS posts during times when family members frequently posted in the past. The SNS collection unit can also prioritize collecting posts related to specific themes from a family's past SNS posting history. The SNS collection unit can also analyze a family's past SNS posting history and collect the most relevant posts. This allows the optimal collection method to be selected by analyzing past SNS posting history. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can select a collection method using an AI model that takes a family's past SNS posting history as input and outputs the optimal collection method.

[0045] The SNS collection unit can filter SNS posts based on the family's current living situation and areas of interest when collecting them. For example, the SNS collection unit can prioritize collecting SNS posts related to the family's current living situation. The SNS collection unit can also prioritize collecting SNS posts related to the family's areas of interest. The SNS collection unit can also filter and collect highly relevant SNS posts based on the family's current living situation and areas of interest. This allows for the collection of highly relevant SNS posts by filtering based on the current living situation and areas of interest. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can perform filtering using an AI model that takes the family's current living situation and areas of interest as input and outputs filtered SNS posts.

[0046] The SNS collection unit can prioritize collecting highly relevant posts by considering the geographical location information of the family when collecting SNS posts. For example, the SNS collection unit can prioritize collecting SNS posts related to the family's current location. The SNS collection unit can also collect SNS posts related to the next destination based on the family's travel plans. The SNS collection unit can also collect SNS posts related to nearby events and activities based on the family's geographical location information. In this way, by considering geographical location information, highly relevant SNS posts can be prioritized. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can collect information using an AI model that takes the family's geographical location information as input and outputs highly relevant SNS posts.

[0047] The SNS collection unit can analyze the social media activities of families and collect relevant posts when collecting SNS posts. For example, the SNS collection unit can collect posts about events and activities shared by families on social media. The SNS collection unit can also collect posts related to interests from the families' social media activities. The SNS collection unit can also analyze the content of families' social media posts and collect relevant posts. In this way, relevant SNS posts can be collected by analyzing social media activities. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can collect information using an AI model that takes the families' social media activities as input and outputs relevant SNS posts.

[0048] The sentiment analysis unit can improve the accuracy of sentiment analysis by considering the context of the text data. For example, the sentiment analysis unit can improve the accuracy of sentiment by analyzing the context before and after the text data. The sentiment analysis unit can also determine the intensity of the emotion based on the context of the text data. The sentiment analysis unit can also classify the type of emotion in detail by considering the context of the text data. This improves the accuracy of sentiment analysis by considering the context of the text data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can improve the accuracy of sentiment by using an AI model that takes text data and its context as input and outputs emotions.

[0049] The emotion analysis unit can analyze audio data to determine emotions during emotion analysis. For example, the emotion analysis unit can analyze the tone and pitch of the audio data to determine emotions. The emotion analysis unit can also analyze the speed and rhythm of the audio data to determine the intensity of emotions. The emotion analysis unit can also combine the content and characteristics of the audio data to determine emotions in detail. This improves the accuracy of emotion determination by analyzing the audio data. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can determine emotions using an AI model that takes audio data as input and outputs emotions.

[0050] The emotion analysis unit can analyze image data to determine emotions during emotion analysis. For example, the emotion analysis unit can analyze facial expressions in image data to determine emotions. The emotion analysis unit can also analyze the background and context of image data to determine the intensity of emotions. The emotion analysis unit can also combine the content of image data with facial features to determine emotions in detail. This improves the accuracy of emotion determination by analyzing image data. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can determine emotions using an AI model that takes image data as input and outputs emotions.

[0051] The emotion analysis unit can analyze changes in emotions by referring to past emotion data during emotion analysis. For example, the emotion analysis unit can analyze changes in emotions over time based on past emotion data. The emotion analysis unit can also compare past emotion data with current emotion data to determine changes in emotions. The emotion analysis unit can also analyze patterns of changes in emotions by referring to past emotion data. This allows for a detailed analysis of changes in emotions by referring to past emotion data. Some or all of the above processes in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can analyze changes in emotions using an AI model that takes past emotion data as input and outputs changes in emotions.

[0052] The message generation unit can adjust the level of detail of a message based on the intensity of emotion during message generation. For example, if the intensity of emotion is high, the message generation unit generates a detailed message. If the intensity of emotion is low, the message generation unit can also generate a concise message. The message generation unit can also adjust the content and length of the message according to the intensity of emotion. In this way, an appropriate message can be generated by adjusting the level of detail of the message based on the intensity of emotion. The intensity of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without using AI. For example, the message generation unit can adjust the level of detail using an AI model that takes emotion intensity data as input and outputs the level of detail of the message.

[0053] The message generation unit can apply different message generation algorithms depending on the type of emotion when generating a message. For example, in the case of a positive emotion, the message generation unit can apply an algorithm that generates messages of gratitude or congratulations. In the case of a negative emotion, the message generation unit can also apply an algorithm that generates messages of encouragement or comfort. The message generation unit can also select an appropriate message generation algorithm depending on the type of emotion. This allows for the generation of more appropriate messages by applying a message generation algorithm that matches the type of emotion. The type of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without using AI. For example, the message generation unit can apply an algorithm using an AI model that takes emotion type data as input and outputs a message generation algorithm.

[0054] The message generation unit can determine message priorities based on when emotions occurred during message generation. For example, if an emotion occurred recently, the message generation unit will prioritize generating the message. If an emotion occurred in the past, the message generation unit may also postpone generating the message. The message generation unit can also adjust the message generation order according to when the emotion occurred. This enables timely message delivery by determining message priorities based on when emotions occurred. The timing of emotion occurrence is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can determine priorities using an AI model that takes emotion occurrence timing data as input and outputs message priorities.

[0055] The message generation unit can adjust the order of messages based on emotional relevance during message generation. For example, the message generation unit will prioritize generating messages with high emotional relevance. It can also delay the generation of messages with low emotional relevance. The message generation unit can also adjust the order of message generation according to emotional relevance. This allows for more effective message delivery by adjusting the order of messages based on emotional relevance. Emotional relevance is realized using an emotion estimation function, for example, using an emotion engine or a 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 message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can adjust the order using an AI model that takes emotional relevance data as input and outputs the order of messages.

[0056] The delivery unit can select the optimal delivery method by referring to the employee's past message reception history when delivering a message. For example, the delivery unit may prioritize using a message delivery method that the employee has preferred in the past. The delivery unit can also determine the optimal delivery timing from the employee's past message reception history. The delivery unit can also analyze the employee's past message reception history and select the most effective delivery method. This allows the delivery unit to select the optimal delivery method by referring to past message reception history. Some or all of the above processes in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select a delivery method using an AI model that takes the employee's past message reception history as input and outputs the optimal delivery method.

[0057] The delivery unit can select the optimal delivery method when delivering messages, taking into account the employee's device information. For example, if an employee is using a smartphone, the delivery unit will deliver a message adapted to the screen size. If an employee is using a tablet, the delivery unit can also deliver a message optimized for a larger screen. If an employee is using a smartwatch, the delivery unit can also deliver a concise and highly visible message. This makes it possible to deliver the optimal message by considering device information. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select the delivery method using an AI model that takes employee device information as input and outputs the optimal delivery method.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The FamilyBridge AI system can also include a behavior prediction unit. The behavior prediction unit predicts future behavior based on past behavioral data of employees and their families. For example, it can predict future behavior based on actions an employee has taken in the past on specific days of the week or time slots. The behavior prediction unit can also analyze behavioral data and determine future behavioral patterns. This allows for the delivery of messages at a more appropriate time by using behavior prediction. Some or all of the above-described processes in the behavior prediction unit may be performed using AI, for example, or without AI. For example, the behavior prediction unit can predict behavior using an AI model that takes behavioral data as input and outputs future behavior.

[0060] The FamilyBridge AI system may also include a context analysis unit. The context analysis unit analyzes the context of messages and social media posts from employees and their families and provides this information to the sentiment analysis unit. For example, it can analyze the context of a message sent by an employee in a specific situation or background and estimate the emotion based on that information. The context analysis unit can also analyze contextual data and determine the intensity and type of emotion. This allows for more accurate sentiment analysis by using context. Some or all of the above processing in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can determine the emotion using an AI model that takes contextual data as input and outputs an emotion.

[0061] The FamilyBridge AI system may also include a device integration unit. This unit integrates with devices used by employees and their families and provides device data to the emotion analysis unit. For example, if an employee uses a smartphone, tablet, or smartwatch, the system can estimate their emotions based on data collected from these devices. The device integration unit can also analyze the device data and determine changes in emotions. This allows for more detailed emotion analysis using device data. Some or all of the above-described processes in the device integration unit may be performed using AI, for example, or without AI. For example, the device integration unit can determine emotions using an AI model that takes device data as input and outputs emotions.

[0062] The FamilyBridge AI system may also include an environmental data collection unit. The environmental data collection unit collects environmental data from the surrounding environment of employees and their families and provides it to the sentiment analysis unit. For example, it can collect environmental data such as weather, temperature, and noise levels at the location where an employee is, and estimate their emotions based on that data. The environmental data collection unit can also analyze the environmental data and determine changes in emotions. This allows for more accurate sentiment analysis by using environmental data. Some or all of the above-described processing in the environmental data collection unit may be performed using AI, for example, or without AI. For example, the environmental data collection unit can determine emotions using an AI model that takes environmental data as input and outputs emotions.

[0063] The FamilyBridge AI system may also include a personalization settings unit. This unit adjusts the system's operation based on the individual settings and preferences of employees and their families. For example, if an employee wants to receive messages at a specific time, the system can adjust the timing of message delivery based on that setting. The personalization settings unit can also analyze individual settings and preferences and optimize the system's operation. This enables personalization based on individual settings and preferences. Some or all of the above-described processes in the personalization settings unit may be performed using AI, for example, or not. For example, the personalization settings unit can adjust its operation using an AI model that takes individual setting data as input and outputs the system's operation.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The collection unit collects employee schedule information. The collection unit can collect, for example, employee meeting schedules, business trip schedules, and vacation schedules. The collection unit can also obtain information from employee schedule management tools. The collection unit can also collect schedule information from employee calendar applications. The collection unit can also extract schedule information from employee emails. Step 2: The SNS collection unit collects family members' SNS posts. The SNS collection unit can also obtain information from family members' SNS accounts. The SNS collection unit can also monitor family members' SNS feeds and collect posts. The SNS collection unit can also extract information from family members' SNS messages. Step 3: The sentiment analysis unit analyzes emotions based on the information collected by the data collection unit and the social media data collection unit. The sentiment analysis unit analyzes text data using, for example, natural language processing technology to determine emotions. The sentiment analysis unit can classify text data as positive, negative, or neutral. The sentiment analysis unit can also calculate an emotion score for text data. The sentiment analysis unit can also assign emotion labels to text data. Step 4: The message generation unit generates a message based on the emotions analyzed by the emotion analysis unit. The message generation unit can, for example, perform template-based generation. The message generation unit can also generate messages using natural language generation technology. The message generation unit can also generate message content that corresponds to emotions. The message generation unit can also analyze facial expressions from video data using facial recognition technology and determine emotions. Step 5: The delivery unit provides the message generated by the message generation unit to the employee. The delivery unit can, for example, send the generated message to the employee via email. The delivery unit can also notify the employee of the generated message via a chat application. The delivery unit can also display the generated message to the employee via a web application. The delivery unit can also provide the employee with a generated video message.

[0066] (Example of form 2) The FamilyBridge AI system according to an embodiment of the present invention is designed to help employees working away from their families deepen their bonds with them. This system generates personalized messages using emotion analysis technology. Specifically, the FamilyBridge AI system analyzes emotions from the employee's schedule and family's social media posts, and generates messages and video messages tailored to the optimal timing and content. Furthermore, the FamilyBridge AI system performs emotion analysis based on the employee's emotional state and family feedback, and proposes appropriate message content. Facial recognition technology is also used for videos, allowing for more emotionally rich communication. For example, the FamilyBridge AI system creates an environment where employees working away from their families can work without feeling distant from them, improving work-life balance. As a result, the FamilyBridge AI system helps maintain the mental health of employees and improves corporate productivity. The FamilyBridge AI system also supports the harmony between work and family life, aiming to create a happy family environment. The FamilyBridge AI system targets employees working away from their families and their families, as well as companies that are committed to supporting work-life balance. Employees working away from their families are prone to feeling isolated and lacking communication, which can lead to mental stress and family discord. As a result, employee stress and family problems can negatively impact productivity for companies. This system uses AI to analyze an employee's emotions based on their schedule and family's social media posts, generating personalized messages and video messages tailored to the optimal timing and content. Furthermore, the FamilyBridge AI system analyzes the employee's emotional state and family feedback to suggest appropriate message content. Videos also utilize facial recognition technology to convey emotions more vividly. In terms of market size, the number of employees working away from their families in Japan alone amounts to several hundred thousand, and with the increasing number of companies providing work-life balance support, the potential market size is enormous. Advances in generation AI and facial recognition technology have made it possible to generate more human-like messages.In today's world, where work-style reform and the emphasis on family well-being are widespread, there is demand for solutions that address both mental health and performance improvement. The FamilyBridge AI system creates an environment where employees working away from home can work without feeling distant from their families, thereby improving work-life balance. Through this, the FamilyBridge AI system aims to improve employees' mental health and corporate productivity, while also supporting the harmony between work and family life and creating a happy family environment. Therefore, the FamilyBridge AI system can create an environment where employees working away from home can work without feeling distant from their families, thereby improving work-life balance.

[0067] The FamilyBridge AI system according to this embodiment comprises a collection unit, an SNS collection unit, a sentiment analysis unit, a message generation unit, and a provision unit. The collection unit collects employee schedule information. The collection unit can collect, for example, employee meeting schedules, business trip schedules, and vacation schedules. The collection unit can also obtain information from employee schedule management tools. The collection unit can also collect schedule information from employee calendar applications. The collection unit can also extract schedule information from employee emails. The SNS collection unit collects family SNS posts. The SNS collection unit can also obtain information from family SNS accounts. The SNS collection unit can also monitor family SNS feeds and collect posts. The SNS collection unit can also extract information from family SNS messages. The sentiment analysis unit analyzes emotions based on the information collected by the collection unit and the SNS collection unit. The sentiment analysis unit analyzes text data using, for example, natural language processing technology to determine emotions. The sentiment analysis unit can classify text data as positive, negative, or neutral. The sentiment analysis unit can also calculate an emotion score for text data. The emotion analysis unit can also assign emotion labels to text data. The message generation unit generates messages based on the emotions analyzed by the emotion analysis unit. The message generation unit can, for example, perform template-based generation. The message generation unit can also generate messages using natural language generation technology. The message generation unit can also generate message content that corresponds to emotions. The message generation unit can also analyze facial expressions from video data using facial recognition technology and determine emotions. The delivery unit provides the messages generated by the message generation unit to employees. The delivery unit can, for example, send the generated messages to employees via email. The delivery unit can also notify employees of the generated messages via a chat application. The delivery unit can also display the generated messages to employees via a web application. The delivery unit can also provide employees with generated video messages.As a result, the FamilyBridge AI system according to this embodiment can deepen the bond between employees and their families by collecting employee schedule information and family SNS posts, analyzing emotions, and generating and providing personalized messages.

[0068] The data collection unit collects employee schedule information. Specifically, it can collect employee meeting schedules, business trip schedules, and vacation schedules. The data collection unit can also obtain information from employee schedule management tools. For example, it can obtain data from common schedule management tools via APIs. This allows for real-time collection of employee schedule information and the maintenance of up-to-date data. Furthermore, the data collection unit can also collect schedule information from employee calendar applications. For example, it can synchronize data from smartphone calendar apps to centrally manage employee schedules. The data collection unit can also extract schedule information from employee emails. For example, it can analyze the content of emails and automatically extract schedule-related information such as meeting invitations and business trip notifications. This allows the data collection unit to collect schedule information from diverse sources and accurately understand employee schedules. The data collection unit centrally manages this information and can collaborate with other systems and departments as needed. For example, collected schedule information can be stored on a cloud server and made accessible to the sentiment analysis unit and message generation unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses can be made according to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0069] The SNS Collection Unit collects social media posts from family members. It can also retrieve information from family members' social media accounts. For example, it can automatically collect family posting data using the APIs of various social media platforms. This allows for real-time access to the family's latest posts, comments, and photos. The SNS Collection Unit can also monitor family members' social media feeds to collect posts. For example, it can monitor specific keywords or hashtags and collect related posts. This allows for understanding changes in family members' interests and emotions. The SNS Collection Unit can also extract information from family members' social media messages. For example, it can analyze the content of private and direct messages to extract emotions and important information. This allows the SNS Collection Unit to collect family social media posts from diverse sources and accurately understand the family's situation and emotions. The SNS Collection Unit centrally manages this information and can collaborate with other systems and departments as needed. For example, collected social media information can be stored on a cloud server and accessed by the Sentiment Analysis Unit and the Message Generation Unit. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the SNS Collection Unit to collect data efficiently and effectively, improving the overall system performance.

[0070] The Sentiment Analysis Department analyzes emotions based on information collected by the Data Collection Department and the Social Media Data Collection Department. Specifically, it analyzes text data using natural language processing technology to determine emotions. For example, it can classify text data as positive, negative, or neutral. The Sentiment Analysis Department can also calculate emotion scores for text data. For example, it can quantify the degree of positivity or negativity for each text to evaluate the strength of the emotion. The Sentiment Analysis Department can also assign emotion labels to text data. For example, it can assign labels corresponding to specific emotions (joy, sadness, anger, etc.) to text to clarify the type of emotion. Based on these analysis results, the Sentiment Analysis Department can grasp changes and trends in the emotions of employees and their families. Furthermore, the Sentiment Analysis Department can predict long-term emotional fluctuations by utilizing past data and statistical information. For example, based on past emotional data, it can predict emotional fluctuations at specific times or events and formulate future countermeasures. In addition, the Sentiment Analysis Department can use anomaly detection algorithms to detect unusual patterns and abnormal emotions and issue warnings early. This allows the emotion analysis unit to handle not only real-time emotion recognition but also long-term emotion management and anomaly detection, thereby improving the reliability and security of the entire system.

[0071] The message generation unit generates messages based on emotions analyzed by the emotion analysis unit. Specifically, it can perform template-based generation. For example, it generates congratulatory messages for positive emotions and encouraging messages for negative emotions. The message generation unit can also generate messages using natural language generation technology. For example, it can use generation AI to generate natural-sounding sentences that correspond to emotions. The message generation unit can also generate message content that corresponds to emotions. For example, if the emotion score is high, it generates a more detailed and empathetic message, and if the emotion score is low, it generates a concise and direct message. The message generation unit can also analyze facial expressions from video data using facial recognition technology to determine emotions. For example, it can analyze the facial expressions of employees and their families and generate video messages that correspond to their emotions. This allows the message generation unit to generate personalized messages that correspond to emotions and provide them to employees and their families. Furthermore, the message generation unit can evaluate the effectiveness of the generated messages and continuously improve them. For example, it can collect feedback from message recipients and improve the message content and generation algorithm. In addition, the message generation unit can combine multiple message generation methods to generate the optimal message. This allows the message generation unit to always utilize the latest technology and provide the best possible message.

[0072] The delivery department provides employees with messages generated by the message generation department. Specifically, it can send generated messages to employees via email. For example, it can automatically send messages to employees' email addresses to quickly convey important information. The delivery department can also notify employees of generated messages via chat applications. For example, it can notify messages in real time through chat applications. The delivery department can also display generated messages to employees via web applications. For example, it can display messages through the company portal site or a dedicated web application, allowing employees to access them at any time. The delivery department can also provide employees with generated video messages. For example, it can record video messages and send them to employees to achieve more emotionally engaging communication. This allows the delivery department to quickly deliver appropriate messages to each employee, strengthening the bond between employees and their families. Furthermore, the delivery department can monitor the delivery status and effectiveness of messages and continuously improve them. For example, it can analyze message open rates and click-through rates to optimize delivery methods and message content. In addition, the delivery department can combine multiple delivery methods to ensure information is reliably transmitted. For example, it can use email, chat, web, and video in combination to ensure important information is delivered reliably. This allows the service department to deliver messages to employees quickly and reliably, strengthening the bond between employees and their families.

[0073] The sentiment analysis unit can analyze text data using natural language processing technology and determine emotions. For example, the sentiment analysis unit can perform morphological analysis of text data and determine emotions. The sentiment analysis unit can also perform grammatical analysis of text data and determine emotions. The sentiment analysis unit can also perform semantic analysis of text data and determine emotions. The sentiment analysis unit can also calculate an emotion score for text data. The sentiment analysis unit can also assign emotion labels to text data. This improves the accuracy of emotion determination from text data by using natural language processing technology. Some or all of the above-described processes in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can determine emotions using an AI model that takes text data as input and outputs emotions.

[0074] The message generation unit can analyze facial expressions from video data using facial recognition technology and determine emotions. For example, the message generation unit can detect faces from video data using a face detection algorithm. The message generation unit can also classify facial expressions from video data using a facial classification algorithm. The message generation unit can calculate facial expression scores for video data. The message generation unit can also assign facial expression labels to video data. This improves the accuracy of emotion determination from video data by using facial recognition technology. Some or all of the above-described processes in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can determine emotions using an AI model that takes video data as input and outputs emotions.

[0075] The message generation unit can perform sentiment analysis based on the employee's emotional state and family feedback, and propose appropriate message content. For example, the message generation unit can analyze the employee's emotional state and propose appropriate message content. The message generation unit can also analyze family feedback and propose appropriate message content. The message generation unit can combine the employee's emotional state and family feedback to propose appropriate message content. The message generation unit can also adjust the tone and content of the message based on the results of the sentiment analysis. This allows for the proposal of more personalized message content by considering the employee's emotional state and family feedback. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can propose message content using an AI model that takes the employee's emotional state and family feedback as input and outputs appropriate message content.

[0076] The service provider can provide the generated messages to employees. For example, the service provider can send the generated messages to employees via email. The service provider can also notify employees of the generated messages via a chat application. The service provider can also display the generated messages to employees via a web application. The service provider can also provide employees with the generated messages on paper. This can facilitate communication between employees and their families by providing them with the generated messages. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can provide messages using an AI model that takes the generated messages as input and outputs a method for providing them to employees.

[0077] The service provider can provide the generated video message to employees. For example, the service provider can send the generated video message to employees via email. The service provider can also notify employees of the generated video message via a chat application. The service provider can also display the generated video message to employees via a web application. The service provider can also provide the generated video message to employees in paper form. This allows for more emotionally rich communication by providing employees with the generated video message. Some or all of the above processes in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can provide the video message using an AI model that takes the generated video message as input and outputs a method for providing it to employees.

[0078] The data collection unit can estimate employees' emotions and adjust the timing of schedule information collection based on the estimated emotions. For example, if an employee is feeling stressed, the data collection unit can collect schedule information during a time when they can relax. If an employee is busy, the data collection unit can also collect schedule information after their work has finished. If an employee is relaxed, the data collection unit can collect schedule information in real time. This allows for more appropriate timing of information collection by adjusting the timing of schedule information collection according to the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, or not using AI. For example, the data collection unit can adjust the collection timing using an AI model that takes employee emotion data as input and outputs the timing of schedule information collection.

[0079] The data collection unit can analyze an employee's past schedule history and select the optimal data collection method. For example, the data collection unit may prioritize using schedule management tools that the employee has frequently used in the past. The data collection unit can also analyze an employee's past schedule patterns and determine the optimal timing for data collection. The data collection unit can also select a method for collecting data during a specific time period based on the employee's past schedule history. This allows for the selection of the optimal data collection method by analyzing past schedule history. Some or all of the above processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can select a data collection method using an AI model that takes an employee's past schedule history as input and outputs the optimal data collection method.

[0080] The data collection unit can filter schedule information based on an employee's current projects and tasks. For example, the unit can collect only schedule information related to ongoing projects. The unit can also prioritize the collection of schedule information related to specific tasks. The unit can also collect only important schedule information, taking into account the employee's current workload. This allows for the collection of highly relevant schedule information by filtering based on current projects and tasks. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can perform filtering using an AI model that takes an employee's current projects and tasks as input and outputs filtered schedule information.

[0081] The data collection unit can estimate employees' emotions and determine the priority of schedule information to collect based on the estimated emotions. For example, if an employee is stressed, the data collection unit will prioritize collecting schedule information related to relaxing activities. If an employee is busy, the data collection unit can also prioritize collecting schedule information related to important tasks. If an employee is relaxed, the data collection unit can collect all schedule information equally. This allows for the priority collection of important information by prioritizing schedule information based on employees' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI or not. For example, the data collection unit can determine priorities using an AI model that takes employee emotion data as input and outputs the priority of schedule information.

[0082] The data collection unit can prioritize the collection of highly relevant information by considering the geographical location of employees when collecting schedule information. For example, the data collection unit can prioritize the collection of schedule information related to the employee's current location. The data collection unit can also collect schedule information related to the next destination based on the employee's travel plans. The data collection unit can also collect schedule information for nearby events and meetings based on the employee's geographical location. This allows for the priority collection of highly relevant schedule information by considering geographical location. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes the employee's geographical location as input and outputs highly relevant schedule information.

[0083] The data collection unit can collect relevant information by analyzing employees' social media activity when collecting schedule information. For example, the data collection unit can collect schedule information for events and meetings that employees have shared on social media. The data collection unit can also collect schedule information related to employees' interests from their social media activity. The data collection unit can also collect relevant schedule information by analyzing the content of employees' social media posts. In this way, relevant schedule information can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can collect information using an AI model that takes employees' social media activity as input and outputs relevant schedule information.

[0084] The SNS collection unit can estimate the emotions of family members and adjust the timing of SNS post collection based on the estimated emotions. For example, if a family member is stressed, the SNS collection unit will collect SNS posts during times when they can relax. If a family member is busy, the SNS collection unit can also collect SNS posts after their work is finished. If a family member is relaxed, the SNS collection unit can also collect SNS posts in real time. This allows for information to be collected at a more appropriate time by adjusting the timing of SNS post collection according to the family member's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the SNS collection unit may be performed using AI, or not using AI. For example, the SNS collection unit can adjust the collection timing using an AI model that takes family emotion data as input and outputs the timing of SNS post collection.

[0085] The SNS collection unit can analyze a family's past SNS posting history and select the optimal collection method. For example, the SNS collection unit can collect SNS posts during times when family members frequently posted in the past. The SNS collection unit can also prioritize collecting posts related to specific themes from a family's past SNS posting history. The SNS collection unit can also analyze a family's past SNS posting history and collect the most relevant posts. This allows the optimal collection method to be selected by analyzing past SNS posting history. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can select a collection method using an AI model that takes a family's past SNS posting history as input and outputs the optimal collection method.

[0086] The SNS collection unit can filter SNS posts based on the family's current living situation and areas of interest when collecting them. For example, the SNS collection unit can prioritize collecting SNS posts related to the family's current living situation. The SNS collection unit can also prioritize collecting SNS posts related to the family's areas of interest. The SNS collection unit can also filter and collect highly relevant SNS posts based on the family's current living situation and areas of interest. This allows for the collection of highly relevant SNS posts by filtering based on the current living situation and areas of interest. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can perform filtering using an AI model that takes the family's current living situation and areas of interest as input and outputs filtered SNS posts.

[0087] The SNS collection unit can estimate the emotions of family members and determine the priority of SNS posts to collect based on the estimated emotions. For example, if family members are stressed, the SNS collection unit will prioritize collecting SNS posts with relaxing content. If family members are busy, the SNS collection unit can also prioritize collecting SNS posts containing important information. If family members are relaxed, the SNS collection unit can collect all SNS posts equally. This allows for the priority collection of important information by determining the priority of SNS posts based on family emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can determine the priority using an AI model that takes family emotion data as input and outputs the priority of SNS posts.

[0088] The SNS collection unit can prioritize collecting highly relevant posts by considering the geographical location information of the family when collecting SNS posts. For example, the SNS collection unit can prioritize collecting SNS posts related to the family's current location. The SNS collection unit can also collect SNS posts related to the next destination based on the family's travel plans. The SNS collection unit can also collect SNS posts related to nearby events and activities based on the family's geographical location information. In this way, by considering geographical location information, highly relevant SNS posts can be prioritized. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can collect information using an AI model that takes the family's geographical location information as input and outputs highly relevant SNS posts.

[0089] The SNS collection unit can analyze the social media activities of families and collect relevant posts when collecting SNS posts. For example, the SNS collection unit can collect posts about events and activities shared by families on social media. The SNS collection unit can also collect posts related to interests from the families' social media activities. The SNS collection unit can also analyze the content of families' social media posts and collect relevant posts. In this way, relevant SNS posts can be collected by analyzing social media activities. Some or all of the above processing in the SNS collection unit may be performed using AI, for example, or without AI. For example, the SNS collection unit can collect information using an AI model that takes the families' social media activities as input and outputs relevant SNS posts.

[0090] The sentiment analysis unit can estimate the emotions of employees and their families and adjust the criteria for sentiment analysis based on the estimated emotions. For example, if an employee is stressed, the sentiment analysis unit can relax the criteria for sentiment analysis and emphasize positive emotions. If a family member is relaxed, the sentiment analysis unit can also tighten the criteria for sentiment analysis and perform a more detailed sentiment analysis. The sentiment analysis unit can also dynamically adjust the criteria for sentiment analysis according to the emotional state of employees and their families. This dynamic adjustment of the criteria for sentiment analysis enables more accurate sentiment analysis. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can adjust the criteria using an AI model that takes employee and family emotion data as input and outputs sentiment analysis criteria.

[0091] The sentiment analysis unit can improve the accuracy of sentiment analysis by considering the context of the text data. For example, the sentiment analysis unit can improve the accuracy of sentiment by analyzing the context before and after the text data. The sentiment analysis unit can also determine the intensity of the emotion based on the context of the text data. The sentiment analysis unit can also classify the type of emotion in detail by considering the context of the text data. This improves the accuracy of sentiment analysis by considering the context of the text data. Some or all of the above processing in the sentiment analysis unit may be performed using AI, for example, or without AI. For example, the sentiment analysis unit can improve the accuracy of sentiment by using an AI model that takes text data and its context as input and outputs emotions.

[0092] The emotion analysis unit can analyze audio data to determine emotions during emotion analysis. For example, the emotion analysis unit can analyze the tone and pitch of the audio data to determine emotions. The emotion analysis unit can also analyze the speed and rhythm of the audio data to determine the intensity of emotions. The emotion analysis unit can also combine the content and characteristics of the audio data to determine emotions in detail. This improves the accuracy of emotion determination by analyzing the audio data. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can determine emotions using an AI model that takes audio data as input and outputs emotions.

[0093] The sentiment analysis unit can estimate the emotions of employees and their families and adjust the order in which the sentiment analysis results are displayed based on the estimated emotions. For example, if an employee is feeling stressed, the sentiment analysis unit will prioritize displaying positive emotion results. If a family member is relaxed, the sentiment analysis unit can also display detailed sentiment analysis results. The sentiment analysis unit can also dynamically display the sentiment analysis results according to the emotional state of employees and their families. This allows for the provision of more appropriate information by dynamically displaying the sentiment analysis results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sentiment analysis unit may be performed using AI, or not using AI. For example, the sentiment analysis unit can adjust the order using an AI model that takes employee and family emotion data as input and outputs the order in which the sentiment analysis results are displayed.

[0094] The emotion analysis unit can analyze image data to determine emotions during emotion analysis. For example, the emotion analysis unit can analyze facial expressions in image data to determine emotions. The emotion analysis unit can also analyze the background and context of image data to determine the intensity of emotions. The emotion analysis unit can also combine the content of image data with facial features to determine emotions in detail. This improves the accuracy of emotion determination by analyzing image data. Some or all of the above processing in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can determine emotions using an AI model that takes image data as input and outputs emotions.

[0095] The emotion analysis unit can analyze changes in emotions by referring to past emotion data during emotion analysis. For example, the emotion analysis unit can analyze changes in emotions over time based on past emotion data. The emotion analysis unit can also compare past emotion data with current emotion data to determine changes in emotions. The emotion analysis unit can also analyze patterns of changes in emotions by referring to past emotion data. This allows for a detailed analysis of changes in emotions by referring to past emotion data. Some or all of the above processes in the emotion analysis unit may be performed using AI, for example, or without AI. For example, the emotion analysis unit can analyze changes in emotions using an AI model that takes past emotion data as input and outputs changes in emotions.

[0096] The message generation unit can estimate the emotions of employees and their families and adjust the message's expression based on the estimated emotions. For example, if an employee is feeling stressed, the message generation unit can generate an encouraging message. If a family member is relaxed, the message generation unit can also generate a message of gratitude. The message generation unit can also adjust the tone and content of the message according to the emotional state of the employee and their family. This allows for more effective communication by adjusting the message's expression based on emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the message generation unit may be performed using AI, or not. For example, the message generation unit can adjust the expression using an AI model that takes employee and family emotion data as input and outputs a message expression.

[0097] The message generation unit can adjust the level of detail of a message based on the intensity of emotion during message generation. For example, if the intensity of emotion is high, the message generation unit generates a detailed message. If the intensity of emotion is low, the message generation unit can also generate a concise message. The message generation unit can also adjust the content and length of the message according to the intensity of emotion. In this way, an appropriate message can be generated by adjusting the level of detail of the message based on the intensity of emotion. The intensity of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without using AI. For example, the message generation unit can adjust the level of detail using an AI model that takes emotion intensity data as input and outputs the level of detail of the message.

[0098] The message generation unit can apply different message generation algorithms depending on the type of emotion when generating a message. For example, in the case of a positive emotion, the message generation unit can apply an algorithm that generates messages of gratitude or congratulations. In the case of a negative emotion, the message generation unit can also apply an algorithm that generates messages of encouragement or comfort. The message generation unit can also select an appropriate message generation algorithm depending on the type of emotion. This allows for the generation of more appropriate messages by applying a message generation algorithm that matches the type of emotion. The type of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without using AI. For example, the message generation unit can apply an algorithm using an AI model that takes emotion type data as input and outputs a message generation algorithm.

[0099] The message generation unit can estimate the emotions of employees and their families and adjust the length of messages based on the estimated emotions. For example, if an employee is feeling stressed, the message generation unit can generate a short, concise message. If a family member is relaxed, the message generation unit can also generate a longer message with more detailed explanations. The message generation unit can also dynamically adjust the length of messages according to the emotional state of employees and their families. This allows for more effective communication by adjusting the length of messages based on emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a 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 message generation unit may be performed using AI or not. For example, the message generation unit can adjust the length using an AI model that takes employee and family emotion data as input and outputs the message length.

[0100] The message generation unit can determine message priorities based on when emotions occurred during message generation. For example, if an emotion occurred recently, the message generation unit will prioritize generating the message. If an emotion occurred in the past, the message generation unit may also postpone generating the message. The message generation unit can also adjust the message generation order according to when the emotion occurred. This enables timely message delivery by determining message priorities based on when emotions occurred. The timing of emotion occurrence is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can determine priorities using an AI model that takes emotion occurrence timing data as input and outputs message priorities.

[0101] The message generation unit can adjust the order of messages based on emotional relevance during message generation. For example, the message generation unit will prioritize generating messages with high emotional relevance. It can also delay the generation of messages with low emotional relevance. The message generation unit can also adjust the order of message generation according to emotional relevance. This allows for more effective message delivery by adjusting the order of messages based on emotional relevance. Emotional relevance is realized using an emotion estimation function, for example, using an emotion engine or a 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 message generation unit may be performed using AI, for example, or without AI. For example, the message generation unit can adjust the order using an AI model that takes emotional relevance data as input and outputs the order of messages.

[0102] The delivery unit can estimate the emotions of employees and their families and adjust the way messages are delivered based on the estimated emotions. For example, if an employee is feeling stressed, the delivery unit will deliver a message in a relaxing way. If a family member is relaxed, the delivery unit may also deliver a message of gratitude. The delivery unit can also adjust the way messages are delivered according to the emotional state of employees and their families. This allows for more effective communication by adjusting the way messages are delivered based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can adjust the delivery method using an AI model that takes employee and family emotion data as input and outputs a message delivery method.

[0103] The delivery unit can select the optimal delivery method by referring to the employee's past message reception history when delivering a message. For example, the delivery unit may prioritize using a message delivery method that the employee has preferred in the past. The delivery unit can also determine the optimal delivery timing from the employee's past message reception history. The delivery unit can also analyze the employee's past message reception history and select the most effective delivery method. This allows the delivery unit to select the optimal delivery method by referring to past message reception history. Some or all of the above processes in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select a delivery method using an AI model that takes the employee's past message reception history as input and outputs the optimal delivery method.

[0104] The delivery unit can estimate the emotions of employees and their families and adjust the timing of message delivery based on the estimated emotions. For example, if an employee is feeling stressed, the delivery unit will deliver a message during a time when they can relax. The delivery unit can also deliver a message in real time if a family member is relaxed. The delivery unit can also dynamically adjust the timing of message delivery according to the emotional state of employees and their families. This allows for more effective communication by adjusting the timing of message delivery based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can adjust the timing of message delivery using an AI model that takes employee and family emotion data as input and outputs the timing of message delivery.

[0105] The delivery unit can select the optimal delivery method when delivering messages, taking into account the employee's device information. For example, if an employee is using a smartphone, the delivery unit will deliver a message adapted to the screen size. If an employee is using a tablet, the delivery unit can also deliver a message optimized for a larger screen. If an employee is using a smartwatch, the delivery unit can also deliver a concise and highly visible message. This makes it possible to deliver the optimal message by considering device information. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can select the delivery method using an AI model that takes employee device information as input and outputs the optimal delivery method.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The FamilyBridge AI system can also be equipped with a speech recognition unit. The speech recognition unit collects voice data from employees and their families and provides it to the emotion analysis unit. For example, it can collect voices spoken by employees during phone or video calls with their families and analyze that voice data to estimate their emotions. The speech recognition unit can also analyze the tone, pitch, and speed of the voice data to determine the intensity and type of emotion. This allows for more accurate emotion analysis using voice data. Some or all of the above processing in the speech recognition unit may be performed using AI, for example, or without AI. For example, the speech recognition unit can determine emotions using an AI model that takes voice data as input and outputs emotions.

[0108] The FamilyBridge AI system may also include a location information collection unit. The location information collection unit collects geographical location information of employees and their families and provides it to the sentiment analysis unit. For example, it can collect location information of employees while they are on business trips and perform sentiment analysis based on that information. The location information collection unit can also estimate the emotions associated with a specific location if the employee is in that location. This allows for more detailed sentiment analysis by using geographical location information. Some or all of the above processing in the location information collection unit may be performed using AI, for example, or without AI. For example, the location information collection unit can determine emotions using an AI model that takes geographical location information as input and outputs emotions.

[0109] The FamilyBridge AI system can also be equipped with a health data collection unit. The health data collection unit collects health data of employees and their families and provides it to the emotion analysis unit. For example, it can collect employee heart rate and sleep data and estimate emotions based on that data. The health data collection unit can also analyze fluctuations in health data and determine changes in emotions. This makes it possible to perform more accurate emotion analysis by using health data. Some or all of the above processing in the health data collection unit may be performed using AI, for example, or without AI. For example, the health data collection unit can determine emotions using an AI model that takes health data as input and outputs emotions.

[0110] The FamilyBridge AI system can also be equipped with a Hobbies & Interests Collection Unit. This unit collects data on the hobbies and interests of employees and their families and provides it to the Sentiment Analysis Unit. For example, it can collect information on sports and music that employees enjoy and estimate their emotions based on that information. The Hobbies & Interests Collection Unit can also analyze data related to hobbies and interests to determine changes in emotions. This allows for more detailed emotion analysis using data based on hobbies and interests. Some or all of the above-described processes in the Hobbies & Interests Collection Unit may be performed using AI, or not. For example, the Hobbies & Interests Collection Unit can determine emotions using an AI model that takes data on hobbies and interests as input and outputs emotions.

[0111] The FamilyBridge AI system may also include a feedback collection unit. The feedback collection unit collects feedback from employees and their families and provides it to the sentiment analysis unit. For example, it can collect employees' reactions and impressions to messages they receive and estimate their emotions based on that information. The feedback collection unit can also analyze the content of the feedback and determine changes in emotion. This allows for more accurate sentiment analysis by using feedback. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can determine emotions using an AI model that takes feedback data as input and outputs emotions.

[0112] The FamilyBridge AI system can also include a behavior prediction unit. The behavior prediction unit predicts future behavior based on past behavioral data of employees and their families. For example, it can predict future behavior based on actions an employee has taken in the past on specific days of the week or time slots. The behavior prediction unit can also analyze behavioral data and determine future behavioral patterns. This allows for the delivery of messages at a more appropriate time by using behavior prediction. Some or all of the above-described processes in the behavior prediction unit may be performed using AI, for example, or without AI. For example, the behavior prediction unit can predict behavior using an AI model that takes behavioral data as input and outputs future behavior.

[0113] The FamilyBridge AI system may also include a context analysis unit. The context analysis unit analyzes the context of messages and social media posts from employees and their families and provides this information to the sentiment analysis unit. For example, it can analyze the context of a message sent by an employee in a specific situation or background and estimate the emotion based on that information. The context analysis unit can also analyze contextual data and determine the intensity and type of emotion. This allows for more accurate sentiment analysis by using context. Some or all of the above processing in the context analysis unit may be performed using AI, for example, or without AI. For example, the context analysis unit can determine the emotion using an AI model that takes contextual data as input and outputs an emotion.

[0114] The FamilyBridge AI system may also include a device integration unit. This unit integrates with devices used by employees and their families and provides device data to the emotion analysis unit. For example, if an employee uses a smartphone, tablet, or smartwatch, the system can estimate their emotions based on data collected from these devices. The device integration unit can also analyze the device data and determine changes in emotions. This allows for more detailed emotion analysis using device data. Some or all of the above-described processes in the device integration unit may be performed using AI, for example, or without AI. For example, the device integration unit can determine emotions using an AI model that takes device data as input and outputs emotions.

[0115] The FamilyBridge AI system may also include an environmental data collection unit. The environmental data collection unit collects environmental data from the surrounding environment of employees and their families and provides it to the sentiment analysis unit. For example, it can collect environmental data such as weather, temperature, and noise levels at the location where an employee is, and estimate their emotions based on that data. The environmental data collection unit can also analyze the environmental data and determine changes in emotions. This allows for more accurate sentiment analysis by using environmental data. Some or all of the above-described processing in the environmental data collection unit may be performed using AI, for example, or without AI. For example, the environmental data collection unit can determine emotions using an AI model that takes environmental data as input and outputs emotions.

[0116] The FamilyBridge AI system may also include a personalization settings unit. This unit adjusts the system's operation based on the individual settings and preferences of employees and their families. For example, if an employee wants to receive messages at a specific time, the system can adjust the timing of message delivery based on that setting. The personalization settings unit can also analyze individual settings and preferences and optimize the system's operation. This enables personalization based on individual settings and preferences. Some or all of the above-described processes in the personalization settings unit may be performed using AI, for example, or not. For example, the personalization settings unit can adjust its operation using an AI model that takes individual setting data as input and outputs the system's operation.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The collection unit collects employee schedule information. The collection unit can collect, for example, employee meeting schedules, business trip schedules, and vacation schedules. The collection unit can also obtain information from employee schedule management tools. The collection unit can also collect schedule information from employee calendar applications. The collection unit can also extract schedule information from employee emails. Step 2: The SNS collection unit collects social media posts from family members. The SNS collection unit can also obtain information from family members' social media accounts. The SNS collection unit can also monitor family members' social media feeds and collect posts. The SNS collection unit can also extract information from family members' social media messages. Step 3: The sentiment analysis unit analyzes emotions based on the information collected by the data collection unit and the social media data collection unit. The sentiment analysis unit analyzes text data using, for example, natural language processing technology to determine emotions. The sentiment analysis unit can classify text data as positive, negative, or neutral. The sentiment analysis unit can also calculate an emotion score for text data. The sentiment analysis unit can also assign emotion labels to text data. Step 4: The message generation unit generates a message based on the emotions analyzed by the emotion analysis unit. The message generation unit can, for example, perform template-based generation. The message generation unit can also generate messages using natural language generation technology. The message generation unit can also generate message content that corresponds to emotions. The message generation unit can also analyze facial expressions from video data using facial recognition technology and determine emotions. Step 5: The delivery unit provides the message generated by the message generation unit to the employee. The delivery unit can, for example, send the generated message to the employee via email. The delivery unit can also notify the employee of the generated message via a chat application. The delivery unit can also display the generated message to the employee via a web application. The delivery unit can also provide the employee with a generated video message.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] Each of the multiple elements described above, including the collection unit, SNS collection unit, sentiment analysis unit, message generation unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects employee schedule information. The SNS collection unit is implemented by the control unit 46A of the smart device 14 and collects SNS posts from family members. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes sentiment based on the collected information. The message generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a message based on the analyzed sentiment. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the generated message to the employee. 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.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] Each of the multiple elements described above, including the collection unit, SNS collection unit, sentiment analysis unit, message generation unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects employee schedule information. The SNS collection unit is implemented by the control unit 46A of the smart glasses 214 and collects family SNS posts. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes sentiment based on the collected information. The message generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a message based on the analyzed sentiment. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the generated message to the employee. 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.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] Each of the multiple elements described above, including the collection unit, SNS collection unit, sentiment analysis unit, message generation unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects employee schedule information. The SNS collection unit is implemented by the control unit 46A of the headset terminal 314 and collects SNS posts from family members. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes emotions based on the collected information. The message generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a message based on the analyzed emotions. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the generated message to the employee. 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.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] Each of the multiple elements described above, including the collection unit, SNS collection unit, sentiment analysis unit, message generation unit, and provision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects employee schedule information. The SNS collection unit is implemented by, for example, the control unit 46A of the robot 414 and collects family SNS posts. The sentiment analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes emotions based on the collected information. The message generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates a message based on the analyzed emotions. The provision unit is implemented by, for example, the control unit 46A of the robot 414 and provides the generated message to the employee. 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] (Note 1) A collection department that collects employee schedule information, The SNS collection department collects family SNS posts, A sentiment analysis unit that analyzes emotions based on the information collected by the collection unit and the SNS collection unit, A message generation unit that generates a message based on the emotions analyzed by the emotion analysis unit, The system includes a message generation unit that provides messages generated by the message generation unit to employees. A system characterized by the following features. (Note 2) The aforementioned emotion analysis unit, Natural language processing techniques are used to analyze text data and determine emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The message generation unit, Using facial recognition technology, facial expressions are analyzed from video data to determine emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The message generation unit, We conduct sentiment analysis based on employees' emotional states and feedback from their families, and propose appropriate message content. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Provide the generated message to employees. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, Provide the generated video message to employees. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates employees' emotions and adjusts the timing of schedule information collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze employees' past schedule history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting schedule information, filter it based on the employee's current projects and work responsibilities. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates employees' emotions and prioritizes the schedule information to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting schedule information, prioritize the collection of highly relevant information by considering the geographical location of employees. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting schedule information, we analyze employees' social media activity and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned SNS collection unit, The system estimates family members' emotions and adjusts the timing of collecting social media posts based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned SNS collection unit, Analyze the family's past social media posting history to select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned SNS collection unit, When collecting social media posts, filters are applied based on the family's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned SNS collection unit, The system estimates family members' emotions and prioritizes which social media posts to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned SNS collection unit, When collecting social media posts, the system prioritizes collecting posts that are highly relevant, taking into account the family's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned SNS collection unit, When collecting social media posts, analyze the family's social media activity and collect relevant posts. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned emotion analysis unit, We estimate the emotions of employees and their families, and adjust the criteria for emotion analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned emotion analysis unit, When performing sentiment analysis, consider the context of the text data to improve the accuracy of the sentiment analysis. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned emotion analysis unit, During emotion analysis, the voice data is analyzed to determine the emotion. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned emotion analysis unit, The system estimates the emotions of employees and their families, and adjusts the order in which the sentiment analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned emotion analysis unit, During emotion analysis, image data is analyzed to determine emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion analysis unit, During emotion analysis, past emotion data is referenced to analyze changes in emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The message generation unit, We estimate the feelings of employees and their families and adjust the way messages are expressed based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 26) The message generation unit, When generating messages, adjust the level of detail based on the intensity of emotion. The system described in Appendix 1, characterized by the features described herein. (Note 27) The message generation unit, When generating messages, different message generation algorithms are applied depending on the type of emotion. The system described in Appendix 1, characterized by the features described herein. (Note 28) The message generation unit, The system estimates the feelings of employees and their families and adjusts the length of messages based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 29) The message generation unit, When generating messages, prioritize messages based on when emotions arise. The system described in Appendix 1, characterized by the features described herein. (Note 30) The message generation unit, When generating messages, the order of messages is adjusted based on emotional relevance. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, We estimate the feelings of employees and their families and adjust how messages are delivered based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, When delivering a message, the system will refer to the employee's past message reception history to select the most suitable delivery method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned supply unit is, We estimate the emotions of employees and their families and adjust the timing of message delivery based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, When delivering messages, the optimal delivery method is selected considering the employee's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection department that collects employee schedule information, The SNS collection department collects family SNS posts, A sentiment analysis unit that analyzes emotions based on the information collected by the collection unit and the SNS collection unit, A message generation unit that generates a message based on the emotions analyzed by the emotion analysis unit, The system includes a message generation unit that provides messages generated by the message generation unit to employees. A system characterized by the following features.

2. The aforementioned emotion analysis unit, Natural language processing techniques are used to analyze text data and determine emotions. The system according to feature 1.

3. The message generation unit, Using facial recognition technology, facial expressions are analyzed from video data to determine emotions. The system according to feature 1.

4. The message generation unit, We conduct sentiment analysis based on employees' emotional states and feedback from their families, and propose appropriate message content. The system according to feature 1.

5. The aforementioned supply unit is, Provide the generated message to employees. The system according to feature 1.

6. The aforementioned supply unit is, Provide the generated video message to employees. The system according to feature 1.

7. The aforementioned collection unit is The system estimates employees' emotions and adjusts the timing of schedule information collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze employees' past schedule history and select the optimal data collection method. The system according to feature 1.

9. The aforementioned collection unit is When collecting schedule information, filter it based on the employee's current projects and work responsibilities. The system according to feature 1.

10. The aforementioned collection unit is The system estimates employees' emotions and prioritizes the schedule information to collect based on those estimated emotions. The system according to feature 1.

Images