system

Abstract

The system according to this embodiment aims to detect expressions that may offend the recipient in message exchanges and to prompt the sender to become aware of them. [Solution] The system according to the embodiment comprises a monitoring unit, an analysis unit, an analysis unit, a proposal unit, and a provision unit. The monitoring unit monitors messages. The analysis unit analyzes the messages collected by the monitoring unit. The analysis unit analyzes the sentiment of the messages analyzed by the analysis unit. The proposal unit makes proposals based on the results obtained by the analysis unit. The provision unit provides the proposals made by the proposal unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, when an expression that may hurt the other party is included in the message exchange, the sender may not notice it, which may lead to the deterioration of the relationship.

[0005] The system according to the embodiment aims to detect an expression that may hurt the other party in the message exchange and prompt the sender to notice.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a monitoring unit, an analysis unit, an analysis unit, a proposal unit, and a provision unit. The monitoring unit monitors messages. The analysis unit analyzes the messages collected by the monitoring unit. The analysis unit analyzes the sentiment of the messages analyzed by the analysis unit. The proposal unit makes proposals based on the results obtained by the analysis unit. The provision unit provides the proposals made by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect expressions that may offend the recipient in a message exchange and prompt the sender to become aware of them. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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] [[ID=1J]]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 message monitoring system according to an embodiment of the present invention is a system that uses AI to monitor messaging app exchanges and intervenes to issue comments when aggressive words or hurtful expressions are included. The message monitoring system monitors message exchanges in real time and analyzes the content of messages using natural language processing (NLP). Next, it performs sentiment analysis to determine whether the message contains negative emotions. If negative emotions are found, the message monitoring system provides the sender with a real-time suggestion such as "Let's soften the words a little." This mechanism helps to alert the sender before the problem escalates and supports the maintenance and repair of relationships. For example, the message monitoring system monitors message exchanges in real time. In this process, the message monitoring system analyzes the content of messages using natural language processing (NLP) to determine whether aggressive words or hurtful expressions are included. For example, if an aggressive phrase such as "You're always like that" is included, the message monitoring system detects that message. Next, the message monitoring system performs sentiment analysis to determine whether the message contains negative emotions. For example, if the message "You're always like that" is determined to contain negative emotions, the message monitoring system senses the risk. If a message contains negative emotions, the message monitoring system provides the sender with real-time suggestions such as, "Let's soften our words a little." For example, if someone is about to send a message saying, "You're always like that," the system might suggest, "Those words might be a little too strong. How about trying a softer expression?" This mechanism helps senders become aware of potential problems before they escalate, supporting the maintenance and repair of relationships. For instance, by revising the message according to the system's suggestions, the sender can continue communicating without hurting the other person.Furthermore, the intervention of a message monitoring system can make dialogue more objective, reducing emotional burden and promoting constructive communication. This allows the system to monitor message exchanges, detect aggressive or hurtful language, and offer appropriate suggestions to the sender, thereby supporting the maintenance and repair of relationships.

[0029] The message monitoring system according to this embodiment comprises a monitoring unit, an analysis unit, an analysis unit, a proposal unit, and a provision unit. The monitoring unit monitors messages. For example, the monitoring unit monitors the exchange of messages in a messaging application in real time. The monitoring unit collects the content of messages and sends it to the analysis unit. The analysis unit analyzes the collected messages. For example, the analysis unit analyzes the content of messages using natural language processing (NLP). The analysis unit analyzes the content of messages and determines whether they contain offensive words or hurtful expressions. For example, the analysis unit analyzes messages using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the sentiment of the messages analyzed by the analysis unit. For example, the analysis unit performs sentiment analysis and determines whether the message contains negative emotions. The analysis unit uses a sentiment analysis algorithm to determine the emotional state of the message. The proposal unit makes suggestions based on the results obtained by the analysis unit. For example, if negative emotions are found, the proposal unit provides the sender with a suggestion in real time, such as "Let's soften the words a little." The proposal unit generates the content of the proposal and sends it to the delivery unit. The delivery unit provides the proposal generated by the proposal unit to the sender. The delivery unit, for example, notifies the sender of the proposal. The delivery unit selects a method for providing the proposal to the sender and provides the proposal at an appropriate time. As a result, the message monitoring system according to the embodiment can monitor message exchanges, analyze them, perform sentiment analysis, make proposals, and provide solutions, thereby prompting the sender to become aware of the problem before it escalates and supporting the maintenance and repair of relationships.

[0030] The monitoring unit monitors messages. For example, the monitoring unit monitors messaging app interactions in real time. Specifically, the monitoring unit uses the messaging app's API to acquire messages sent and received in real time. This allows it to instantly understand the content of messages sent and received by users. The monitoring unit collects the message content and sends it to the analysis unit. The collected messages are stored as text data and made accessible to the analysis unit. The monitoring unit also collects metadata such as information about the message sender and recipient, the time of transmission, and the message content. This allows it to grasp the overall picture of message exchanges and provides the analysis unit with basic data for more detailed analysis. Furthermore, the monitoring unit has a function to prioritize sending important messages to the analysis unit based on the message content, triggered by specific keywords or phrases. For example, messages containing keywords such as "help" or "urgent" are immediately sent to the analysis unit, requiring a quick response. This allows the monitoring unit to efficiently and effectively monitor message exchanges and improve the overall system performance.

[0031] The analysis unit analyzes the collected messages. For example, the analysis unit uses natural language processing (NLP) to analyze the message content. Specifically, the analysis unit uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze messages. Morphological analysis divides the message into individual words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the grammatical structure of the message, clarifying relationships such as subject, predicate, and object. Semantic analysis understands the context and meaning of the message and determines whether it contains offensive language or hurtful expressions. Based on these analysis results, the analysis unit gains a detailed understanding of the message content and identifies problematic messages. For example, the analysis unit can detect messages containing specific offensive words or phrases and evaluate the degree of aggression in those messages. Furthermore, the analysis unit can analyze message trends and patterns based on past message data and user behavior history to predict future risks. This allows the analysis unit to quickly and accurately analyze collected messages, improving the overall reliability and security of the system.

[0032] The analysis unit analyzes the sentiment of messages analyzed by the analysis unit. For example, the analysis unit performs sentiment analysis to determine whether a message contains negative emotions. Specifically, the analysis unit uses a sentiment analysis algorithm to determine the emotional state of a message. The sentiment analysis algorithm takes the text data of a message as input and classifies it into sentiment categories such as positive, negative, and neutral. For example, it calculates the sentiment score of words and phrases contained in the message and evaluates the overall emotional state of the message by combining these scores. Based on the results of the sentiment analysis, the analysis unit quantifies the degree to which the message contains negative emotions and sends the results to the proposal unit. Furthermore, the analysis unit can perform more accurate sentiment analysis by considering not only the emotional state of the message but also the emotional tendencies of the sender and receiver, as well as the history of past interactions. This allows the analysis unit to accurately grasp the emotional state of messages and improve the overall sentiment management function of the system.

[0033] The proposal department makes suggestions based on the results obtained by the analysis department. For example, if negative emotions are present, the proposal department will provide the sender with a real-time suggestion such as, "Let's soften the language a little." Specifically, the proposal department generates appropriate suggestions based on the sentiment analysis results received from the analysis department. The proposal department uses an algorithm to make optimal suggestions by learning from past suggestion history and user responses. For example, it selects the most effective suggestion based on how the sender has responded to suggestions in the past. The proposal department sends the generated suggestions to the delivery department and provides the suggestions to the sender at the appropriate time. This allows the proposal department to encourage appropriate actions from the sender and support smooth message exchange. Furthermore, the proposal department can continuously evaluate the effectiveness of the suggestions and improve the accuracy of the suggestion algorithm. This allows the proposal department to always provide optimal suggestions and maximize the overall effectiveness of the system.

[0034] The provisioning department provides the sender with the proposals generated by the suggestion department. The provisioning department notifies the sender of the proposals, for example. Specifically, the provisioning department selects a method for providing the proposal content to the sender and provides the proposal at an appropriate time. The provisioning department uses the notification function of the messaging app to notify the sender of the proposal in real time. For example, it can display the proposal immediately after the message is sent, giving the sender an opportunity to revise the message. The provisioning department can also use visual interfaces and voice guidance to make the proposal content easy for the sender to understand. This allows the provisioning department to provide appropriate proposals to the sender quickly and effectively, supporting smooth message exchange. Furthermore, the provisioning department can collect the sender's response after the proposal is provided and evaluate the effectiveness of the proposal content. This allows the provisioning department to continuously improve the method and timing of proposal delivery and maximize the overall effectiveness of the system.

[0035] The monitoring unit can monitor messaging app interactions in real time. For example, the monitoring unit can monitor messaging app interactions in real time and detect problems immediately. The monitoring unit collects the content of messages and sends it to the analysis unit. This allows for immediate problem detection by monitoring messaging app interactions in real time. Real-time monitoring is performed based on criteria such as monitoring delay time and update frequency. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can monitor messaging app interactions in real time, input the collected messages into the AI, and the AI ​​can detect problems.

[0036] The analysis unit can analyze the content of a message using natural language processing. For example, the analysis unit analyzes the content of a message using natural language processing (NLP). The analysis unit analyzes the content of a message and determines whether it contains offensive words or hurtful expressions. The analysis unit analyzes the message using techniques such as morphological analysis, grammatical analysis, and semantic analysis. This allows for accurate analysis of the message content using natural language processing. Natural language processing is performed using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, or they may not be performed using AI. For example, the analysis unit can input the collected messages into an AI, which can then analyze the content of the messages using natural language processing.

[0037] The analysis unit can perform sentiment analysis to determine whether a message contains negative emotions. For example, the analysis unit performs sentiment analysis to determine whether a message contains negative emotions. The analysis unit uses a sentiment analysis algorithm to determine the emotional state of the message. This allows for an accurate understanding of the emotional state of a message through sentiment analysis. Negative emotions are determined based on classification criteria for emotions such as anger, sadness, and anxiety. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the analyzed message into an AI, which can then perform sentiment analysis and determine the emotional state of the message.

[0038] The suggestion unit can provide suggestions to the sender in real time if negative emotions are present. For example, if negative emotions are present, the suggestion unit might provide the sender with a suggestion such as, "Let's soften the language a bit." The suggestion unit generates the content of the suggestion and sends it to the service unit. This facilitates the early resolution of problems by providing suggestions in real time when negative emotions are present. Real-time suggestions are made based on criteria such as the delay time and method of provision. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the analyzed message into AI, which can then generate the content of the suggestion and send it to the service unit.

[0039] The provisioning unit can provide proposals to the sender through the proposal unit. The provisioning unit, for example, notifies the sender of the proposal. The provisioning unit selects a method for providing the proposal to the sender and provides the proposal at an appropriate time. This allows the sender to take an appropriate action by providing the proposal. Provision is carried out based on criteria such as the timing and method of provision. Some or all of the above processing in the provisioning unit may be performed using AI or not. For example, the provisioning unit can input the content of the proposal into AI, and the AI ​​can select a method for providing the proposal to the sender and provide the proposal at an appropriate time.

[0040] The monitoring unit learns patterns in message exchanges and can focus its monitoring when specific patterns appear. For example, the monitoring unit can learn patterns of problems users have encountered in the past and focus its monitoring when similar patterns appear. The monitoring unit can also focus its monitoring on message exchanges if there is a sudden increase in those exchanges. The monitoring unit can also focus its monitoring on exchanges where specific keywords are frequently used. This allows for early detection of problems by focusing monitoring when specific patterns appear. Pattern learning is performed based on criteria such as the algorithm used and the target of learning. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input message exchange data into an AI, which can learn patterns and focus its monitoring when specific patterns appear.

[0041] The monitoring unit can determine monitoring priorities based on message length and frequency. For example, if long messages are sent frequently, the monitoring unit will prioritize monitoring those exchanges. The monitoring unit can also prioritize monitoring if short messages are sent in succession. The monitoring unit can also prioritize monitoring if the frequency of message transmissions increases rapidly. This enables efficient monitoring by determining monitoring priorities based on message length and frequency. Monitoring priorities are determined based on criteria such as priority criteria and determination methods. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input message length and frequency data into the AI, which can then determine the monitoring priorities.

[0042] The monitoring unit can adjust the intensity of monitoring based on the time of day when messages are exchanged. For example, the monitoring unit can increase the intensity of monitoring during late-night hours to aim for early detection of problems. The monitoring unit can also lower the intensity of monitoring during daytime hours to respect natural interactions. The monitoring unit can also adjust the intensity of monitoring on weekends and holidays to encourage user relaxation. By adjusting the intensity of monitoring based on the time of day when messages are exchanged, more appropriate monitoring becomes possible. The adjustment of monitoring intensity based on time of day is performed based on criteria such as time zone divisions and methods for adjusting intensity. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input data on the time of day when messages are exchanged into the AI, and the AI ​​can adjust the intensity of monitoring.

[0043] The monitoring unit can adjust the level of detail of monitoring based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the monitoring unit may lower the level of detail. If the sender and recipient are meeting for the first time, the monitoring unit may increase the level of detail. If the sender and recipient have a business relationship, the monitoring unit may adjust the level of detail to a moderate level. This allows for more appropriate monitoring by adjusting the level of detail based on the relationship between the message sender and recipient. The adjustment of the level of detail of monitoring based on the relationship is carried out based on criteria such as relationship evaluation criteria and methods for adjusting the level of detail. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input data on the relationship between the sender and recipient into the AI, and the AI ​​can adjust the level of detail of monitoring.

[0044] The analysis unit can improve the accuracy of its analysis by considering the context of the message. For example, the analysis unit can analyze the context of the message and detect offensive language based on the context. The analysis unit can also analyze the topic of the message and improve the accuracy of its analysis by considering the relevant context. The analysis unit can also analyze the flow of the message exchange and determine the sentiment based on the context. In this way, considering the context of the message improves the accuracy of the analysis. Contextual consideration is performed based on criteria such as criteria for evaluating context and methods for consideration. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input message contextual data into AI, and the AI ​​can improve the accuracy of its analysis by considering the context.

[0045] The analysis unit can customize its analysis method according to the language and dialect of the message. For example, if the message is in English, the analysis unit will take into account expressions specific to English. If the message is in Kansai dialect, the analysis unit can also take into account expressions specific to Kansai dialect. If the message contains slang, the analysis unit can also take into account expressions specific to slang. By customizing the analysis method according to the language and dialect of the message, more appropriate analysis becomes possible. The customization of analysis according to language and dialect is performed based on criteria such as the type of language and dialect and the method of customization. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the language and dialect data of the message into AI, and the AI ​​can customize the analysis method.

[0046] The analysis unit can improve the accuracy of its analysis by referring to past interactions between the message sender and receiver. For example, the analysis unit can analyze past interactions between the sender and receiver and determine sentiment based on context. The analysis unit can also improve the accuracy of its analysis by learning patterns in past interactions between the sender and receiver. The analysis unit can also refer to topics in past interactions between the sender and receiver and analyze considering the relevant context. This improves the accuracy of the analysis by referring to past interactions between the message sender and receiver. The referencing of past interactions is done based on criteria such as the type of data to be referenced and the method of referencing. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input data on past interactions between the sender and receiver into AI, which can then refer to past interactions to improve the accuracy of the analysis.

[0047] The analysis unit can select an analysis method based on the message topic. For example, if the message topic is business, the analysis unit will analyze while considering business-specific expressions. If the message topic is private, the analysis unit can also analyze while considering private-specific expressions. If the message topic is technical, the analysis unit can also analyze while considering technical-specific expressions. This allows for more appropriate analysis by selecting an analysis method based on the message topic. The selection of analysis based on the topic is made based on criteria such as topic classification criteria and selection methods. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input message topic data into AI, and the AI ​​can select an analysis method based on the topic.

[0048] The analysis unit can track changes in the sentiment of messages and detect early trends of increasing negative sentiment. For example, if the sentiment of a message is gradually changing to a negative state, the analysis unit can track and detect this change early. The analysis unit can also track and detect early trends of rapid negative changes in the sentiment of a message. The analysis unit can also track and detect early trends of messages that remain negative for a certain period of time. In this way, by tracking changes in the sentiment of messages, an increase in negative sentiment can be detected early. Tracking of sentiment changes is performed based on criteria such as the target of tracking and the method of tracking. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input message sentiment data into AI, which can track changes in sentiment and detect early trends of increasing negative sentiment.

[0049] The analysis unit can classify the emotions of messages into multiple categories and perform detailed sentiment analysis. For example, the analysis unit can classify and analyze the emotions of messages into categories such as "anger," "sadness," and "joy." The analysis unit can also classify and analyze the emotions of messages into categories such as "aggressive," "defensive," and "neutral." The analysis unit can also classify and analyze the emotions of messages into categories such as "positive," "negative," and "neutral." By classifying the emotions of messages into multiple categories, detailed sentiment analysis becomes possible. The classification of emotions into categories is performed based on criteria such as criteria for classifying emotions and classification methods. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI. For example, the analysis unit can input message emotion data into AI, and the AI ​​can classify the emotions into multiple categories and perform detailed sentiment analysis.

[0050] The analysis unit can analyze the emotional interactions between message senders and receivers and understand the dynamics of the dialogue. For example, the analysis unit can track changes in the emotions of senders and receivers and analyze the dynamics of the dialogue. The analysis unit can also analyze the emotional interactions between senders and receivers and understand the flow of the dialogue. The analysis unit can also learn patterns of emotions between senders and receivers and predict the dynamics of the dialogue. This allows for an understanding of the dynamics of the dialogue by analyzing the emotional interactions between message senders and receivers. The analysis of emotional interactions is performed based on criteria such as evaluation criteria and analysis methods for the interactions. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input sender and receiver emotion data into AI, which can analyze the emotional interactions and understand the dynamics of the dialogue.

[0051] The analysis unit can integrate the sentiment analysis results of messages with other data sources to perform a comprehensive sentiment assessment. For example, the analysis unit can integrate the sentiment analysis results of messages with social media data to perform a comprehensive sentiment assessment. The analysis unit can also integrate the sentiment analysis results of messages with users' past behavior data to perform a comprehensive sentiment assessment. The analysis unit can also integrate the sentiment analysis results of messages with users' profile data to perform a comprehensive sentiment assessment. This makes a comprehensive sentiment assessment possible by integrating the sentiment analysis results of messages with other data sources. Integration with other data sources is performed based on criteria such as the type of data to be integrated and the method of integration. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the sentiment analysis results of messages and data from other data sources into an AI, which can then perform a comprehensive sentiment assessment.

[0052] The proposal unit can adjust the specificity of its suggestions according to the content of the message. For example, if the message contains a specific problem, the proposal unit will propose a specific solution. If the message contains abstract content, the proposal unit may also propose general advice. If the message contains a question, the proposal unit may also propose a specific answer. By adjusting the specificity of the suggestions according to the content of the message, more appropriate suggestions can be made. The adjustment of the specificity of the suggestions is done based on criteria such as the criteria for specificity and the method of adjustment. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input message content data into AI, and the AI ​​can adjust the specificity of the suggestions.

[0053] The proposal unit can optimize the timing of its proposals according to the status of the message exchange. For example, if the message exchange is active, the proposal unit can make a proposal immediately. If the message exchange is infrequent, the proposal unit can also make a proposal at an appropriate time. If the message exchange has been interrupted, the proposal unit can also make a proposal to initiate a resumption. By optimizing the timing of proposals according to the status of the message exchange, more appropriate proposals can be made. The optimization of proposal timing is performed based on criteria such as timing standards and optimization methods. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input message exchange status data into the AI, and the AI ​​can optimize the timing of proposals.

[0054] The suggestion function can customize the content of suggestions based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the suggestion function will make a friendly suggestion. If the sender and recipient have a business relationship, the suggestion function can also make a formal suggestion. If the sender and recipient are meeting for the first time, the suggestion function can also make a general suggestion. By customizing the content of suggestions based on the relationship between the message sender and recipient, more appropriate suggestions can be made. The customization of suggestions based on the relationship is carried out based on criteria such as relationship evaluation criteria and customization methods. Some or all of the above processing in the suggestion function may be performed using AI or not. For example, the suggestion function can input data on the relationship between the sender and recipient into the AI, and the AI ​​can customize the content of the suggestions.

[0055] The proposal department can optimize the content of proposals based on past proposal history. For example, the proposal department can reuse proposals that were effective in the past. The proposal department can also avoid proposals that were ineffective in the past. The proposal department can also analyze past proposal history and make optimal proposals. This makes it possible to make more appropriate proposals by optimizing the content of proposals based on past proposal history. The optimization of proposals based on proposal history is performed based on criteria such as evaluation criteria for history and optimization methods. Some or all of the above processes in the proposal department may be performed using AI or not. For example, the proposal department can input past proposal history data into AI, and the AI ​​can optimize the content of proposals.

[0056] The delivery unit can select the optimal delivery method by referring to the user's past responses when delivering a proposal. For example, the delivery unit may reuse a delivery method that has received a favorable response in the past. The delivery unit may also avoid a delivery method that has received a negative response in the past. The delivery unit can also analyze past responses and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the user's past responses. The referencing of past responses is done based on criteria such as the type of data to be referenced and the method of reference. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's past response data into AI, and the AI ​​can select the optimal delivery method.

[0057] The service provider can select the optimal delivery method when providing a proposal, taking into account the user's device information. For example, if the user is using a smartphone, the service provider will select a delivery method that matches the screen size. If the user is using a tablet, the service provider can also select a delivery method optimized for a larger screen. If the user is using a smartwatch, the service provider can also select a concise and highly visible delivery method. In this way, the optimal delivery method can be selected by considering the user's device information. The consideration of device information is based on criteria such as the type of device and the method of consideration. Some or all of the above processing in the service provider may be performed using AI, or it may be performed without AI. For example, the service provider can input the user's device information data into AI, and the AI ​​can select the optimal delivery method.

[0058] The delivery unit can select the optimal delivery method when providing suggestions, taking into account the user's current situation. For example, if the user is on the move, the delivery unit can provide suggestions via voice. If the user is in a quiet place, the delivery unit can also provide suggestions via text. If the user is in a meeting, the delivery unit can provide suggestions with minimal notification. This allows the delivery unit to select the optimal delivery method by considering the user's current situation. The consideration of the current situation is based on criteria such as situation evaluation criteria and methods of consideration. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input user's current situation data into AI, and the AI ​​can select the optimal delivery method.

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

[0060] A message monitoring system can learn patterns in message exchanges and focus monitoring when specific patterns appear. For example, it can learn patterns of past user problems and focus monitoring when similar patterns appear. If there is a sudden increase in message exchanges, it can also focus monitoring on those exchanges. If specific keywords are used frequently, it can also focus monitoring on those exchanges. This allows for early detection of problems by focusing monitoring when specific patterns appear. Pattern learning is performed based on criteria such as the algorithm used and the target of learning. Some or all of the above processes in the system may be performed using AI or not. For example, the system can input message exchange data into an AI, which can learn patterns and focus monitoring when specific patterns appear.

[0061] The message monitoring system can adjust the level of detail of monitoring based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the level of detail of monitoring can be lowered. If the sender and recipient are meeting for the first time, the level of detail of monitoring can be increased. If the sender and recipient have a business relationship, the level of detail of monitoring can be adjusted to a medium level. This allows for more appropriate monitoring by adjusting the level of detail of monitoring based on the relationship between the message sender and recipient. The adjustment of the level of detail of monitoring based on the relationship is carried out based on criteria such as relationship evaluation criteria and methods for adjusting the level of detail. Some or all of the above processing in the system may be performed using AI or not. For example, the system can input data on the relationship between the sender and recipient into the AI, and the AI ​​can adjust the level of detail of monitoring.

[0062] A message monitoring system can determine monitoring priorities based on message length and frequency. For example, if long messages are sent frequently, those exchanges can be monitored preferentially. If short messages are sent in succession, those exchanges can also be monitored preferentially. If the frequency of message transmissions increases sharply, those exchanges can also be monitored preferentially. This allows for efficient monitoring by determining monitoring priorities based on message length and frequency. Monitoring priorities are determined based on criteria such as priority standards and methods. Some or all of the above processes in the system may be performed using AI, or not. For example, the system can input message length and frequency data into an AI, which can then determine the monitoring priorities.

[0063] A message monitoring system can improve the accuracy of its analysis by referring to past interactions between the message sender and receiver. For example, it can analyze past interactions between the sender and receiver to determine sentiment based on context. It can also learn patterns in past interactions between the sender and receiver to improve the accuracy of its analysis. It can also refer to topics in past interactions between the sender and receiver and analyze them while considering the relevant context. This improves the accuracy of the analysis by referring to past interactions between the message sender and receiver. The referencing of past interactions is done based on criteria such as the type of data to be referenced and the method of referencing. Some or all of the above processes in the system may be performed using AI or not. For example, the system can input data on past interactions between the sender and receiver into an AI, which can then refer to the past interactions to improve the accuracy of its analysis.

[0064] The message monitoring system can select an analysis method based on the message topic. For example, if the message topic is business, the analysis will take into account business-specific expressions. If the message topic is private, the analysis can also take into account private-specific expressions. If the message topic is technical, the analysis can also take into account technical-specific expressions. By selecting an analysis method based on the message topic, more appropriate analysis becomes possible. The selection of analysis based on the topic is carried out based on criteria such as topic classification criteria and selection methods. Some or all of the above processing in the system may be performed using AI, or it may be performed without AI. For example, the system can input message topic data into AI, and the AI ​​can select an analysis method based on the topic.

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

[0066] Step 1: The monitoring unit monitors messages. For example, it monitors messaging app interactions in real time, collects message content, and sends it to the analysis unit. Step 2: The analysis unit analyzes the collected messages. For example, it uses natural language processing (NLP) to analyze the content of the messages and determine whether they contain offensive words or hurtful expressions. Techniques such as morphological analysis, grammatical analysis, and semantic analysis are used. Step 3: The analysis unit analyzes the sentiment of the message analyzed by the analysis unit. For example, it performs sentiment analysis to determine whether the message contains negative emotions. It uses a sentiment analysis algorithm to determine the emotional state of the message. Step 4: The proposal department makes suggestions based on the results obtained by the analysis department. For example, if negative emotions are present, it provides the sender with a suggestion in real time such as, "Let's try softening the words a little." It generates the content of the suggestion and sends it to the provision department. Step 5: The providing department provides the proposal generated by the proposing department to the sender. For example, they select a method to notify the sender of the proposal and provide the proposal at an appropriate time.

[0067] (Example of form 2) The message monitoring system according to an embodiment of the present invention is a system that uses AI to monitor messaging app exchanges and intervenes to issue comments when aggressive words or hurtful expressions are included. The message monitoring system monitors message exchanges in real time and analyzes the content of messages using natural language processing (NLP). Next, it performs sentiment analysis to determine whether the message contains negative emotions. If negative emotions are found, the message monitoring system provides the sender with a real-time suggestion such as "Let's soften the words a little." This mechanism helps to alert the sender before the problem escalates and supports the maintenance and repair of relationships. For example, the message monitoring system monitors message exchanges in real time. In this process, the message monitoring system analyzes the content of messages using natural language processing (NLP) to determine whether aggressive words or hurtful expressions are included. For example, if an aggressive phrase such as "You're always like that" is included, the message monitoring system detects that message. Next, the message monitoring system performs sentiment analysis to determine whether the message contains negative emotions. For example, if the message "You're always like that" is determined to contain negative emotions, the message monitoring system senses the risk. If a message contains negative emotions, the message monitoring system provides the sender with real-time suggestions such as, "Let's soften our words a little." For example, if someone is about to send a message saying, "You're always like that," the system might suggest, "Those words might be a little too strong. How about trying a softer expression?" This mechanism helps senders become aware of potential problems before they escalate, supporting the maintenance and repair of relationships. For instance, by revising the message according to the system's suggestions, the sender can continue communicating without hurting the other person.Furthermore, the intervention of a message monitoring system can make dialogue more objective, reducing emotional burden and promoting constructive communication. This allows the system to monitor message exchanges, detect aggressive or hurtful language, and offer appropriate suggestions to the sender, thereby supporting the maintenance and repair of relationships.

[0068] The message monitoring system according to this embodiment comprises a monitoring unit, an analysis unit, an analysis unit, a proposal unit, and a provision unit. The monitoring unit monitors messages. For example, the monitoring unit monitors the exchange of messages in a messaging application in real time. The monitoring unit collects the content of messages and sends it to the analysis unit. The analysis unit analyzes the collected messages. For example, the analysis unit analyzes the content of messages using natural language processing (NLP). The analysis unit analyzes the content of messages and determines whether they contain offensive words or hurtful expressions. For example, the analysis unit analyzes messages using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The analysis unit analyzes the sentiment of the messages analyzed by the analysis unit. For example, the analysis unit performs sentiment analysis and determines whether the message contains negative emotions. The analysis unit uses a sentiment analysis algorithm to determine the emotional state of the message. The proposal unit makes suggestions based on the results obtained by the analysis unit. For example, if negative emotions are found, the proposal unit provides the sender with a suggestion in real time, such as "Let's soften the words a little." The proposal unit generates the content of the proposal and sends it to the delivery unit. The delivery unit provides the proposal generated by the proposal unit to the sender. The delivery unit, for example, notifies the sender of the proposal. The delivery unit selects a method for providing the proposal to the sender and provides the proposal at an appropriate time. As a result, the message monitoring system according to the embodiment can monitor message exchanges, analyze them, perform sentiment analysis, make proposals, and provide solutions, thereby prompting the sender to become aware of the problem before it escalates and supporting the maintenance and repair of relationships.

[0069] The monitoring unit monitors messages. For example, the monitoring unit monitors messaging app interactions in real time. Specifically, the monitoring unit uses the messaging app's API to acquire messages sent and received in real time. This allows it to instantly understand the content of messages sent and received by users. The monitoring unit collects the message content and sends it to the analysis unit. The collected messages are stored as text data and made accessible to the analysis unit. The monitoring unit also collects metadata such as information about the message sender and recipient, the time of transmission, and the message content. This allows it to grasp the overall picture of message exchanges and provides the analysis unit with basic data for more detailed analysis. Furthermore, the monitoring unit has a function to prioritize sending important messages to the analysis unit based on the message content, triggered by specific keywords or phrases. For example, messages containing keywords such as "help" or "urgent" are immediately sent to the analysis unit, requiring a quick response. This allows the monitoring unit to efficiently and effectively monitor message exchanges and improve the overall system performance.

[0070] The analysis unit analyzes the collected messages. For example, the analysis unit uses natural language processing (NLP) to analyze the message content. Specifically, the analysis unit uses techniques such as morphological analysis, grammatical analysis, and semantic analysis to analyze messages. Morphological analysis divides the message into individual words and identifies the part of speech and meaning of each word. Grammatical analysis analyzes the grammatical structure of the message, clarifying relationships such as subject, predicate, and object. Semantic analysis understands the context and meaning of the message and determines whether it contains offensive language or hurtful expressions. Based on these analysis results, the analysis unit gains a detailed understanding of the message content and identifies problematic messages. For example, the analysis unit can detect messages containing specific offensive words or phrases and evaluate the degree of aggression in those messages. Furthermore, the analysis unit can analyze message trends and patterns based on past message data and user behavior history to predict future risks. This allows the analysis unit to quickly and accurately analyze collected messages, improving the overall reliability and security of the system.

[0071] The analysis unit analyzes the sentiment of messages analyzed by the analysis unit. For example, the analysis unit performs sentiment analysis to determine whether a message contains negative emotions. Specifically, the analysis unit uses a sentiment analysis algorithm to determine the emotional state of a message. The sentiment analysis algorithm takes the text data of a message as input and classifies it into sentiment categories such as positive, negative, and neutral. For example, it calculates the sentiment score of words and phrases contained in the message and evaluates the overall emotional state of the message by combining these scores. Based on the results of the sentiment analysis, the analysis unit quantifies the degree to which the message contains negative emotions and sends the results to the proposal unit. Furthermore, the analysis unit can perform more accurate sentiment analysis by considering not only the emotional state of the message but also the emotional tendencies of the sender and receiver, as well as the history of past interactions. This allows the analysis unit to accurately grasp the emotional state of messages and improve the overall sentiment management function of the system.

[0072] The proposal department makes suggestions based on the results obtained by the analysis department. For example, if negative emotions are present, the proposal department will provide the sender with a real-time suggestion such as, "Let's soften the language a little." Specifically, the proposal department generates appropriate suggestions based on the sentiment analysis results received from the analysis department. The proposal department uses an algorithm to make optimal suggestions by learning from past suggestion history and user responses. For example, it selects the most effective suggestion based on how the sender has responded to suggestions in the past. The proposal department sends the generated suggestions to the delivery department and provides the suggestions to the sender at the appropriate time. This allows the proposal department to encourage appropriate actions from the sender and support smooth message exchange. Furthermore, the proposal department can continuously evaluate the effectiveness of the suggestions and improve the accuracy of the suggestion algorithm. This allows the proposal department to always provide optimal suggestions and maximize the overall effectiveness of the system.

[0073] The provisioning department provides the sender with the proposals generated by the suggestion department. The provisioning department notifies the sender of the proposals, for example. Specifically, the provisioning department selects a method for providing the proposal content to the sender and provides the proposal at an appropriate time. The provisioning department uses the notification function of the messaging app to notify the sender of the proposal in real time. For example, it can display the proposal immediately after the message is sent, giving the sender an opportunity to revise the message. The provisioning department can also use visual interfaces and voice guidance to make the proposal content easy for the sender to understand. This allows the provisioning department to provide appropriate proposals to the sender quickly and effectively, supporting smooth message exchange. Furthermore, the provisioning department can collect the sender's response after the proposal is provided and evaluate the effectiveness of the proposal content. This allows the provisioning department to continuously improve the method and timing of proposal delivery and maximize the overall effectiveness of the system.

[0074] The monitoring unit can monitor messaging app interactions in real time. For example, the monitoring unit can monitor messaging app interactions in real time and detect problems immediately. The monitoring unit collects the content of messages and sends it to the analysis unit. This allows for immediate problem detection by monitoring messaging app interactions in real time. Real-time monitoring is performed based on criteria such as monitoring delay time and update frequency. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can monitor messaging app interactions in real time, input the collected messages into the AI, and the AI ​​can detect problems.

[0075] The analysis unit can analyze the content of a message using natural language processing. For example, the analysis unit analyzes the content of a message using natural language processing (NLP). The analysis unit analyzes the content of a message and determines whether it contains offensive words or hurtful expressions. The analysis unit analyzes the message using techniques such as morphological analysis, grammatical analysis, and semantic analysis. This allows for accurate analysis of the message content using natural language processing. Natural language processing is performed using techniques such as morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, or they may not be performed using AI. For example, the analysis unit can input the collected messages into an AI, which can then analyze the content of the messages using natural language processing.

[0076] The analysis unit can perform sentiment analysis to determine whether a message contains negative emotions. For example, the analysis unit performs sentiment analysis to determine whether a message contains negative emotions. The analysis unit uses a sentiment analysis algorithm to determine the emotional state of the message. This allows for an accurate understanding of the emotional state of a message through sentiment analysis. Negative emotions are determined based on classification criteria for emotions such as anger, sadness, and anxiety. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the analyzed message into an AI, which can then perform sentiment analysis and determine the emotional state of the message.

[0077] The suggestion unit can provide suggestions to the sender in real time if negative emotions are present. For example, if negative emotions are present, the suggestion unit might provide the sender with a suggestion such as, "Let's soften the language a bit." The suggestion unit generates the content of the suggestion and sends it to the service unit. This facilitates the early resolution of problems by providing suggestions in real time when negative emotions are present. Real-time suggestions are made based on criteria such as the delay time and method of provision. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the analyzed message into AI, which can then generate the content of the suggestion and send it to the service unit.

[0078] The provisioning unit can provide proposals to the sender through the proposal unit. The provisioning unit, for example, notifies the sender of the proposal. The provisioning unit selects a method for providing the proposal to the sender and provides the proposal at an appropriate time. This allows the sender to take an appropriate action by providing the proposal. Provision is carried out based on criteria such as the timing and method of provision. Some or all of the above processing in the provisioning unit may be performed using AI or not. For example, the provisioning unit can input the content of the proposal into AI, and the AI ​​can select a method for providing the proposal to the sender and provide the proposal at an appropriate time.

[0079] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated emotions. For example, if the user is stressed, the monitoring unit can increase the monitoring frequency to aim for early detection of problems. If the user is relaxed, the monitoring unit can also reduce the monitoring frequency to respect natural interaction. If the user is in a hurry, the monitoring unit can also monitor only important messages. This allows for more appropriate monitoring by adjusting the monitoring frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 monitoring unit may be performed using AI or not. For example, the monitoring unit can input user emotion data into an AI, which can estimate the emotions and adjust the monitoring frequency.

[0080] The monitoring unit learns patterns in message exchanges and can focus its monitoring when specific patterns appear. For example, the monitoring unit can learn patterns of problems users have encountered in the past and focus its monitoring when similar patterns appear. The monitoring unit can also focus its monitoring on message exchanges if there is a sudden increase in those exchanges. The monitoring unit can also focus its monitoring on exchanges where specific keywords are frequently used. This allows for early detection of problems by focusing monitoring when specific patterns appear. Pattern learning is performed based on criteria such as the algorithm used and the target of learning. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input message exchange data into an AI, which can learn patterns and focus its monitoring when specific patterns appear.

[0081] The monitoring unit can determine monitoring priorities based on message length and frequency. For example, if long messages are sent frequently, the monitoring unit will prioritize monitoring those exchanges. The monitoring unit can also prioritize monitoring if short messages are sent in succession. The monitoring unit can also prioritize monitoring if the frequency of message transmissions increases rapidly. This enables efficient monitoring by determining monitoring priorities based on message length and frequency. Monitoring priorities are determined based on criteria such as priority criteria and determination methods. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input message length and frequency data into the AI, which can then determine the monitoring priorities.

[0082] The monitoring unit can estimate the user's emotions and select the types of messages to monitor based on the estimated emotions. For example, if the user is angry, the monitoring unit may focus on monitoring aggressive messages. If the user is sad, the monitoring unit may focus on monitoring comforting messages. If the user is happy, the monitoring unit may focus on monitoring congratulatory messages. This allows for more appropriate monitoring by selecting the types of messages to monitor based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input user emotion data into an AI, which can estimate the emotions and select the types of messages to monitor.

[0083] The monitoring unit can adjust the intensity of monitoring based on the time of day when messages are exchanged. For example, the monitoring unit can increase the intensity of monitoring during late-night hours to aim for early detection of problems. The monitoring unit can also lower the intensity of monitoring during daytime hours to respect natural interactions. The monitoring unit can also adjust the intensity of monitoring on weekends and holidays to encourage user relaxation. By adjusting the intensity of monitoring based on the time of day when messages are exchanged, more appropriate monitoring becomes possible. The adjustment of monitoring intensity based on time of day is performed based on criteria such as time zone divisions and methods for adjusting intensity. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input data on the time of day when messages are exchanged into the AI, and the AI ​​can adjust the intensity of monitoring.

[0084] The monitoring unit can adjust the level of detail of monitoring based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the monitoring unit may lower the level of detail. If the sender and recipient are meeting for the first time, the monitoring unit may increase the level of detail. If the sender and recipient have a business relationship, the monitoring unit may adjust the level of detail to a moderate level. This allows for more appropriate monitoring by adjusting the level of detail based on the relationship between the message sender and recipient. The adjustment of the level of detail of monitoring based on the relationship is carried out based on criteria such as relationship evaluation criteria and methods for adjusting the level of detail. Some or all of the above processing in the monitoring unit may be performed using AI or not. For example, the monitoring unit can input data on the relationship between the sender and recipient into the AI, and the AI ​​can adjust the level of detail of monitoring.

[0085] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the user is angry, the analysis unit may use an algorithm that focuses on analyzing aggressive language. If the user is sad, the analysis unit may also use an algorithm that focuses on analyzing comforting language. If the user is happy, the analysis unit may also use an algorithm that focuses on analyzing congratulatory language. By adjusting the analysis algorithm based on the user's emotions, more appropriate analysis becomes possible. 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 analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate the emotions and adjust the analysis algorithm.

[0086] The analysis unit can improve the accuracy of its analysis by considering the context of the message. For example, the analysis unit can analyze the context of the message and detect offensive language based on the context. The analysis unit can also analyze the topic of the message and improve the accuracy of its analysis by considering the relevant context. The analysis unit can also analyze the flow of the message exchange and determine the sentiment based on the context. In this way, considering the context of the message improves the accuracy of the analysis. Contextual consideration is performed based on criteria such as criteria for evaluating context and methods for consideration. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input message contextual data into AI, and the AI ​​can improve the accuracy of its analysis by considering the context.

[0087] The analysis unit can customize its analysis method according to the language and dialect of the message. For example, if the message is in English, the analysis unit will take into account expressions specific to English. If the message is in Kansai dialect, the analysis unit can also take into account expressions specific to Kansai dialect. If the message contains slang, the analysis unit can also take into account expressions specific to slang. By customizing the analysis method according to the language and dialect of the message, more appropriate analysis becomes possible. The customization of analysis according to language and dialect is performed based on criteria such as the type of language and dialect and the method of customization. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input the language and dialect data of the message into AI, and the AI ​​can customize the analysis method.

[0088] The analysis unit can estimate the user's emotions and determine the priority of analysis based on the estimated emotions. For example, if the user is angry, the analysis unit may prioritize analyzing aggressive messages. If the user is sad, the analysis unit may also prioritize analyzing comforting messages. If the user is happy, the analysis unit may also prioritize analyzing congratulatory messages. This allows for more appropriate analysis by determining the priority of analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of analysis.

[0089] The analysis unit can improve the accuracy of its analysis by referring to past interactions between the message sender and receiver. For example, the analysis unit can analyze past interactions between the sender and receiver and determine sentiment based on context. The analysis unit can also improve the accuracy of its analysis by learning patterns in past interactions between the sender and receiver. The analysis unit can also refer to topics in past interactions between the sender and receiver and analyze considering the relevant context. This improves the accuracy of the analysis by referring to past interactions between the message sender and receiver. The referencing of past interactions is done based on criteria such as the type of data to be referenced and the method of referencing. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input data on past interactions between the sender and receiver into AI, which can then refer to past interactions to improve the accuracy of the analysis.

[0090] The analysis unit can select an analysis method based on the message topic. For example, if the message topic is business, the analysis unit will analyze while considering business-specific expressions. If the message topic is private, the analysis unit can also analyze while considering private-specific expressions. If the message topic is technical, the analysis unit can also analyze while considering technical-specific expressions. This allows for more appropriate analysis by selecting an analysis method based on the message topic. The selection of analysis based on the topic is made based on criteria such as topic classification criteria and selection methods. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input message topic data into AI, and the AI ​​can select an analysis method based on the topic.

[0091] The analysis unit can estimate the user's emotions and adjust the criteria for emotion analysis based on the estimated emotions. For example, if the user is angry, the analysis unit may use criteria that focus on analyzing aggressive emotions. If the user is sad, the analysis unit may also use criteria that focus on analyzing comforting emotions. If the user is happy, the analysis unit may also use criteria that focus on analyzing celebratory emotions. By adjusting the criteria for emotion analysis based on the user's emotions, more appropriate emotion analysis becomes possible. 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 analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can estimate emotions and adjust the criteria for emotion analysis.

[0092] The analysis unit can track changes in the sentiment of messages and detect early trends of increasing negative sentiment. For example, if the sentiment of a message is gradually changing to a negative state, the analysis unit can track and detect this change early. The analysis unit can also track and detect early trends of rapid negative changes in the sentiment of a message. The analysis unit can also track and detect early trends of messages that remain negative for a certain period of time. In this way, by tracking changes in the sentiment of messages, an increase in negative sentiment can be detected early. Tracking of sentiment changes is performed based on criteria such as the target of tracking and the method of tracking. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input message sentiment data into AI, which can track changes in sentiment and detect early trends of increasing negative sentiment.

[0093] The analysis unit can classify the emotions of messages into multiple categories and perform detailed sentiment analysis. For example, the analysis unit can classify and analyze the emotions of messages into categories such as "anger," "sadness," and "joy." The analysis unit can also classify and analyze the emotions of messages into categories such as "aggressive," "defensive," and "neutral." The analysis unit can also classify and analyze the emotions of messages into categories such as "positive," "negative," and "neutral." By classifying the emotions of messages into multiple categories, detailed sentiment analysis becomes possible. The classification of emotions into categories is performed based on criteria such as criteria for classifying emotions and classification methods. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without using AI. For example, the analysis unit can input message emotion data into AI, and the AI ​​can classify the emotions into multiple categories and perform detailed sentiment analysis.

[0094] The analysis unit can estimate the user's emotions and adjust the order in which the results of the emotion analysis are displayed based on the estimated emotions. For example, if the user is angry, the analysis unit may prioritize displaying results for aggressive emotions. If the user is sad, the analysis unit may also prioritize displaying results for comforting emotions. If the user is happy, the analysis unit may also prioritize displaying results for celebratory emotions. By adjusting the order in which the results of the emotion analysis are displayed based on the user's emotions, more appropriate information can be provided. 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 processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, the AI ​​can estimate the emotions, and the order in which the results of the emotion analysis are displayed can be adjusted.

[0095] The analysis unit can analyze the emotional interactions between message senders and receivers and understand the dynamics of the dialogue. For example, the analysis unit can track changes in the emotions of senders and receivers and analyze the dynamics of the dialogue. The analysis unit can also analyze the emotional interactions between senders and receivers and understand the flow of the dialogue. The analysis unit can also learn patterns of emotions between senders and receivers and predict the dynamics of the dialogue. This allows for an understanding of the dynamics of the dialogue by analyzing the emotional interactions between message senders and receivers. The analysis of emotional interactions is performed based on criteria such as evaluation criteria and analysis methods for the interactions. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input sender and receiver emotion data into AI, which can analyze the emotional interactions and understand the dynamics of the dialogue.

[0096] The analysis unit can integrate the sentiment analysis results of messages with other data sources to perform a comprehensive sentiment assessment. For example, the analysis unit can integrate the sentiment analysis results of messages with social media data to perform a comprehensive sentiment assessment. The analysis unit can also integrate the sentiment analysis results of messages with users' past behavior data to perform a comprehensive sentiment assessment. The analysis unit can also integrate the sentiment analysis results of messages with users' profile data to perform a comprehensive sentiment assessment. This makes a comprehensive sentiment assessment possible by integrating the sentiment analysis results of messages with other data sources. Integration with other data sources is performed based on criteria such as the type of data to be integrated and the method of integration. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the sentiment analysis results of messages and data from other data sources into an AI, which can then perform a comprehensive sentiment assessment.

[0097] The suggestion unit can estimate the user's emotions and adjust the content of its suggestions based on those emotions. For example, if the user is angry, the suggestion unit can offer suggestions to help them calm down. If the user is sad, the suggestion unit can offer suggestions that include words of comfort. If the user is happy, the suggestion unit can offer suggestions that include words of congratulations. By adjusting the content of suggestions based on the user's emotions, more appropriate suggestions can be made. 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 suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into an AI, which can estimate the emotion and adjust the content of its suggestions.

[0098] The proposal unit can adjust the specificity of its suggestions according to the content of the message. For example, if the message contains a specific problem, the proposal unit will propose a specific solution. If the message contains abstract content, the proposal unit may also propose general advice. If the message contains a question, the proposal unit may also propose a specific answer. By adjusting the specificity of the suggestions according to the content of the message, more appropriate suggestions can be made. The adjustment of the specificity of the suggestions is done based on criteria such as the criteria for specificity and the method of adjustment. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input message content data into AI, and the AI ​​can adjust the specificity of the suggestions.

[0099] The proposal unit can optimize the timing of its proposals according to the status of the message exchange. For example, if the message exchange is active, the proposal unit can make a proposal immediately. If the message exchange is infrequent, the proposal unit can also make a proposal at an appropriate time. If the message exchange has been interrupted, the proposal unit can also make a proposal to initiate a resumption. By optimizing the timing of proposals according to the status of the message exchange, more appropriate proposals can be made. The optimization of proposal timing is performed based on criteria such as timing standards and optimization methods. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input message exchange status data into the AI, and the AI ​​can optimize the timing of proposals.

[0100] The suggestion unit can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is angry, the suggestion unit will prioritize suggestions to calm down. If the user is sad, the suggestion unit may also prioritize comforting suggestions. If the user is happy, the suggestion unit may also prioritize congratulatory suggestions. By prioritizing suggestions based on the user's emotions, more appropriate suggestions can be made. 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 suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into an AI, which can estimate the emotion and determine the priority of suggestions.

[0101] The suggestion function can customize the content of suggestions based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the suggestion function will make a friendly suggestion. If the sender and recipient have a business relationship, the suggestion function can also make a formal suggestion. If the sender and recipient are meeting for the first time, the suggestion function can also make a general suggestion. By customizing the content of suggestions based on the relationship between the message sender and recipient, more appropriate suggestions can be made. The customization of suggestions based on the relationship is carried out based on criteria such as relationship evaluation criteria and customization methods. Some or all of the above processing in the suggestion function may be performed using AI or not. For example, the suggestion function can input data on the relationship between the sender and recipient into the AI, and the AI ​​can customize the content of the suggestions.

[0102] The proposal department can optimize the content of proposals based on past proposal history. For example, the proposal department can reuse proposals that were effective in the past. The proposal department can also avoid proposals that were ineffective in the past. The proposal department can also analyze past proposal history and make optimal proposals. This makes it possible to make more appropriate proposals by optimizing the content of proposals based on past proposal history. The optimization of proposals based on proposal history is performed based on criteria such as evaluation criteria for history and optimization methods. Some or all of the above processes in the proposal department may be performed using AI or not. For example, the proposal department can input past proposal history data into AI, and the AI ​​can optimize the content of proposals.

[0103] The service provider can estimate the user's emotions and adjust how suggestions are presented based on those emotions. For example, if the user is angry, the service provider can offer calming suggestions in a gentle tone. If the user is sad, the service provider can offer comforting suggestions in a gentle tone. If the user is happy, the service provider can offer congratulatory suggestions in a cheerful tone. By adjusting how suggestions are presented based on the user's emotions, more appropriate suggestions can be made. 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 service provider may be performed using AI or not. For example, the service provider can input user emotion data into an AI, which can estimate the emotion and adjust how suggestions are presented.

[0104] The delivery unit can select the optimal delivery method by referring to the user's past responses when delivering a proposal. For example, the delivery unit may reuse a delivery method that has received a favorable response in the past. The delivery unit may also avoid a delivery method that has received a negative response in the past. The delivery unit can also analyze past responses and select the optimal delivery method. In this way, the optimal delivery method can be selected by referring to the user's past responses. The referencing of past responses is done based on criteria such as the type of data to be referenced and the method of reference. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input the user's past response data into AI, and the AI ​​can select the optimal delivery method.

[0105] The service provider can estimate the user's emotions and adjust the frequency of suggestions based on the estimated emotions. For example, if the user is angry, the service provider can lower the frequency of suggestions to give the user time to calm down. If the user is sad, the service provider can increase the frequency of suggestions to offer more comforting words. If the user is happy, the service provider can adjust the frequency of suggestions appropriately. By adjusting the frequency of suggestions based on the user's emotions, more appropriate suggestions can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into an AI, which can estimate the emotion and adjust the frequency of suggestions.

[0106] The service provider can select the optimal delivery method when providing a proposal, taking into account the user's device information. For example, if the user is using a smartphone, the service provider will select a delivery method that matches the screen size. If the user is using a tablet, the service provider can also select a delivery method optimized for a larger screen. If the user is using a smartwatch, the service provider can also select a concise and highly visible delivery method. In this way, the optimal delivery method can be selected by considering the user's device information. The consideration of device information is based on criteria such as the type of device and the method of consideration. Some or all of the above processing in the service provider may be performed using AI, or it may be performed without AI. For example, the service provider can input the user's device information data into AI, and the AI ​​can select the optimal delivery method.

[0107] The delivery unit can select the optimal delivery method when providing suggestions, taking into account the user's current situation. For example, if the user is on the move, the delivery unit can provide suggestions via voice. If the user is in a quiet place, the delivery unit can also provide suggestions via text. If the user is in a meeting, the delivery unit can provide suggestions with minimal notification. This allows the delivery unit to select the optimal delivery method by considering the user's current situation. The consideration of the current situation is based on criteria such as situation evaluation criteria and methods of consideration. Some or all of the above processing in the delivery unit may be performed using AI or not. For example, the delivery unit can input user's current situation data into AI, and the AI ​​can select the optimal delivery method.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] A message monitoring system can estimate a user's emotions and adjust the tone of messages based on those emotions. For example, if a user is angry, the system can suggest a calmer tone for the message. If a user is sad, the system can suggest a comforting tone. If a user is happy, the system can suggest a celebratory tone. This allows for more appropriate communication by adjusting the tone of messages according to the user's emotions. Emotion estimation is achieved 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 system may be performed using AI or not. For example, the system can input user emotion data into an AI, which can estimate the emotion and adjust the tone of the message.

[0110] A message monitoring system can learn patterns in message exchanges and focus monitoring when specific patterns appear. For example, it can learn patterns of past user problems and focus monitoring when similar patterns appear. If there is a sudden increase in message exchanges, it can also focus monitoring on those exchanges. If specific keywords are used frequently, it can also focus monitoring on those exchanges. This allows for early detection of problems by focusing monitoring when specific patterns appear. Pattern learning is performed based on criteria such as the algorithm used and the target of learning. Some or all of the above processes in the system may be performed using AI or not. For example, the system can input message exchange data into an AI, which can learn patterns and focus monitoring when specific patterns appear.

[0111] A message monitoring system can estimate a user's emotions and customize message content based on those emotions. For example, if a user is angry, the system can generate a message to calm them down. If a user is sad, the system can also generate a message of comfort. If a user is happy, the system can also generate a message of congratulations. This allows for more appropriate communication by customizing message content based on the user's emotions. Emotion estimation is achieved using 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 system may be performed using AI or not. For example, the system can input user emotion data into an AI, which can estimate the emotion and customize the message content.

[0112] The message monitoring system can adjust the level of detail of monitoring based on the relationship between the message sender and recipient. For example, if the sender and recipient have a close relationship, the level of detail of monitoring can be lowered. If the sender and recipient are meeting for the first time, the level of detail of monitoring can be increased. If the sender and recipient have a business relationship, the level of detail of monitoring can be adjusted to a medium level. This allows for more appropriate monitoring by adjusting the level of detail of monitoring based on the relationship between the message sender and recipient. The adjustment of the level of detail of monitoring based on the relationship is carried out based on criteria such as relationship evaluation criteria and methods for adjusting the level of detail. Some or all of the above processing in the system may be performed using AI or not. For example, the system can input data on the relationship between the sender and recipient into the AI, and the AI ​​can adjust the level of detail of monitoring.

[0113] The message monitoring system can estimate the user's emotions and adjust the content of suggestions based on those emotions. For example, if the user is angry, the system will make suggestions to calm down. If the user is sad, the system may also make suggestions that include words of comfort. If the user is happy, the system may also make suggestions that include words of congratulations. By adjusting the content of suggestions based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved 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 system may be performed using AI or not. For example, the system can input user emotion data into an AI, which can estimate the emotion and adjust the content of suggestions.

[0114] A message monitoring system can determine monitoring priorities based on message length and frequency. For example, if long messages are sent frequently, those exchanges can be monitored preferentially. If short messages are sent in succession, those exchanges can also be monitored preferentially. If the frequency of message transmissions increases sharply, those exchanges can also be monitored preferentially. This allows for efficient monitoring by determining monitoring priorities based on message length and frequency. Monitoring priorities are determined based on criteria such as priority standards and methods. Some or all of the above processes in the system may be performed using AI, or not. For example, the system can input message length and frequency data into an AI, which can then determine the monitoring priorities.

[0115] The message monitoring system can estimate the user's emotions and adjust how suggestions are delivered based on those emotions. For example, if the user is angry, the system can offer calming suggestions in a gentle tone. If the user is sad, the system can offer comforting suggestions in a gentle tone. If the user is happy, the system can offer congratulatory suggestions in a cheerful tone. By adjusting how suggestions are delivered based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved 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 system may be performed using AI or not. For example, the system can input user emotion data into an AI, which can estimate the emotion and adjust how suggestions are delivered.

[0116] A message monitoring system can improve the accuracy of its analysis by referring to past interactions between the message sender and receiver. For example, it can analyze past interactions between the sender and receiver to determine sentiment based on context. It can also learn patterns in past interactions between the sender and receiver to improve the accuracy of its analysis. It can also refer to topics in past interactions between the sender and receiver and analyze them while considering the relevant context. This improves the accuracy of the analysis by referring to past interactions between the message sender and receiver. The referencing of past interactions is done based on criteria such as the type of data to be referenced and the method of referencing. Some or all of the above processes in the system may be performed using AI or not. For example, the system can input data on past interactions between the sender and receiver into an AI, which can then refer to the past interactions to improve the accuracy of its analysis.

[0117] A message monitoring system can estimate a user's emotions and prioritize analysis based on those emotions. For example, if a user is angry, the system will prioritize analyzing aggressive messages. If a user is sad, the system may also prioritize analyzing comforting messages. If a user is happy, the system may also prioritize analyzing congratulatory messages. This allows for more appropriate analysis by prioritizing analysis based on the user's emotions. Emotion estimation is achieved using 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 system may be performed using AI or not. For example, the system can input user emotion data into an AI, which can estimate the emotions and determine the analysis priority.

[0118] The message monitoring system can select an analysis method based on the message topic. For example, if the message topic is business, the analysis will take into account business-specific expressions. If the message topic is private, the analysis can also take into account private-specific expressions. If the message topic is technical, the analysis can also take into account technical-specific expressions. By selecting an analysis method based on the message topic, more appropriate analysis becomes possible. The selection of analysis based on the topic is carried out based on criteria such as topic classification criteria and selection methods. Some or all of the above processing in the system may be performed using AI, or it may be performed without AI. For example, the system can input message topic data into AI, and the AI ​​can select an analysis method based on the topic.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The monitoring unit monitors messages. For example, it monitors messaging app interactions in real time, collects message content, and sends it to the analysis unit. Step 2: The analysis unit analyzes the collected messages. For example, it uses natural language processing (NLP) to analyze the content of the messages and determine whether they contain offensive words or hurtful expressions. Techniques such as morphological analysis, grammatical analysis, and semantic analysis are used. Step 3: The analysis unit analyzes the sentiment of the message analyzed by the analysis unit. For example, it performs sentiment analysis to determine whether the message contains negative emotions. It uses a sentiment analysis algorithm to determine the emotional state of the message. Step 4: The proposal department makes suggestions based on the results obtained by the analysis department. For example, if negative emotions are present, it provides the sender with a suggestion in real time such as, "Let's try softening the words a little." It generates the content of the suggestion and sends it to the provision department. Step 5: The providing department provides the proposal generated by the proposing department to the sender. For example, they select a method to notify the sender of the proposal and provide the proposal at an appropriate time.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the monitoring unit, analysis unit, interpretation unit, proposal unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the smart device 14 and monitors the messaging application exchange in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of messages using natural language processing (NLP). The interpretation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a proposal if negative emotions are present. The provision unit is implemented by the control unit 46A of the smart device 14 and notifies the sender of the proposal. 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.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the monitoring unit, analysis unit, interpretation unit, proposal unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the smart glasses 214 and monitors the messaging application exchange in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of messages using natural language processing (NLP). The interpretation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a proposal if negative emotions are present. The provision unit is implemented by the control unit 46A of the smart glasses 214 and notifies the sender of the proposal. 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.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the monitoring unit, analysis unit, interpretation unit, proposal unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the headset terminal 314 and monitors the messaging application exchange in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of messages using natural language processing (NLP). The interpretation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a proposal if negative emotions are present. The provision unit is implemented by the control unit 46A of the headset terminal 314 and notifies the sender of the proposal. 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.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Each of the multiple elements described above, including the monitoring unit, analysis unit, interpretation unit, proposal unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit is implemented by the control unit 46A of the robot 414 and monitors the messaging application exchange in real time. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the content of messages using natural language processing (NLP). The interpretation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs sentiment analysis. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a proposal if negative emotions are included. The provision unit is implemented by the control unit 46A of the robot 414 and notifies the sender of the proposal. 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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."

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] (Note 1) The monitoring unit that monitors messages, An analysis unit analyzes the messages collected by the aforementioned monitoring unit, An analysis unit analyzes the sentiment of the message analyzed by the aforementioned analysis unit, A proposal unit makes proposals based on the results obtained by the analysis unit, The system comprises a provisioning unit that provides a proposal through the aforementioned proposal unit. A system characterized by the following features. (Note 2) The aforementioned monitoring unit, Monitor messaging app conversations in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Analyze the message content using natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned analysis unit is We perform sentiment analysis to determine whether the message contains negative emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, If negative emotions are present, we will provide suggestions to the sender in real time. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned supply unit is, The proposal department will provide the proposal to the sender. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned monitoring unit, It estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned monitoring unit, It learns patterns in message exchanges and focuses its monitoring when specific patterns appear. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned monitoring unit, Prioritize monitoring based on message length and frequency. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned monitoring unit, It estimates the user's emotions and selects the type of message to monitor based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned monitoring unit, The monitoring intensity is adjusted based on the time of day when messages are exchanged. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned monitoring unit, Adjust the level of monitoring based on the relationship between the message sender and recipient. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, Improve the accuracy of the analysis by considering the context of the message. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Customize the analysis method according to the language and dialect of the message. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, Referencing past interactions between the message sender and recipient improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, Select an analysis method based on the message topic. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit is It estimates the user's emotions and adjusts the criteria for sentiment analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit is Track emotional shifts in messages and detect early trends of increasing negative emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit is The emotions of the message are categorized into multiple categories, and a detailed sentiment analysis is performed. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit is It estimates the user's emotions and adjusts the order in which the sentiment analysis results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit is Analyze the emotional interplay between message senders and receivers to understand the dynamics of dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is The sentiment analysis results of the message are integrated with other data sources to perform a comprehensive sentiment assessment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, It estimates the user's emotions and adjusts the content of the suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, Adjust the specificity of the proposal according to the content of the message. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, Optimize the timing of proposals based on the context of the message exchange. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, Customize the suggestions based on the relationship between the message sender and recipient. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned proposal section is, The content of the proposal will be optimized based on past proposal history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, It estimates the user's emotions and adjusts how suggestions are delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, When providing a proposal, the optimal delivery method is selected by referring to the user's past responses. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned supply unit is, It estimates the user's emotions and adjusts the frequency of suggestions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, When providing a proposal, the optimal delivery method will be selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned supply unit is, When providing a proposal, we select the most suitable delivery method considering the user's current situation. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The monitoring unit that monitors messages, An analysis unit analyzes the messages collected by the aforementioned monitoring unit, An analysis unit analyzes the sentiment of the message analyzed by the aforementioned analysis unit, A proposal unit makes proposals based on the results obtained by the analysis unit, The system comprises a provisioning unit that provides a proposal through the aforementioned proposal unit. A system characterized by the following features.

2. The aforementioned monitoring unit, Monitor messaging app conversations in real time. The system according to feature 1.

3. The aforementioned analysis unit, Analyze the message content using natural language processing. The system according to feature 1.

4. The aforementioned analysis unit is We perform sentiment analysis to determine whether the message contains negative emotions. The system according to feature 1.

5. The aforementioned proposal section is, If negative emotions are present, we will provide suggestions to the sender in real time. The system according to feature 1.

6. The aforementioned supply unit is, Provided to the proposer by the aforementioned proposal unit The system according to feature 1.

7. The aforementioned monitoring unit, It estimates the user's emotions and adjusts the monitoring frequency based on the estimated emotions. The system according to feature 1.

8. The aforementioned monitoring unit, It learns patterns in message exchanges and focuses its monitoring when specific patterns appear. The system according to feature 1.

Images