system

Abstract

The system according to this embodiment aims to provide the optimal language for accurately conveying the user's intentions and emotions. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a selection unit, and a provision unit. The reception unit receives a text message from the user. The analysis unit analyzes the context of the text message received by the reception unit. The selection unit selects the most appropriate words based on the context analyzed by the analysis unit. The provision unit provides the words selected by the selection unit to the user.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of 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 prior art, it is difficult to accurately convey the intention and emotion of a user in text communication, and there is a risk of misunderstanding.

[0005] The system according to the embodiment aims to provide an optimal word for accurately conveying the intention and emotion of a user.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a selection unit, and a provision unit. The reception unit receives a text message from the user. The analysis unit analyzes the context of the text message received by the reception unit. The selection unit selects the most appropriate words based on the context analyzed by the analysis unit. The provision unit provides the words selected by the selection unit to the user. [Effects of the Invention]

[0007] The system according to this embodiment can provide the optimal words to accurately convey the user's intentions and emotions. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

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

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

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

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that helps accurately convey the user's intentions and emotions in text communication. This AI agent system solves the problem of "misunderstanding" by applying natural language processing technology to understand the context and selecting the most appropriate words to clarify communication. The AI ​​agent system also learns past communication patterns and emotional history and provides customized emotional expressions for each user. Furthermore, the AI ​​agent system proposes advice and optimal expressions for specific communication challenges faced by the user. For example, when a user inputs a text message, the AI ​​agent system uses natural language processing technology to understand the context in order to accurately convey the user's intentions and emotions. For example, in a business email or online message, if a user feels "Am I being scolded?", the AI ​​agent system analyzes the context and proposes an appropriate expression. Next, the AI ​​agent system learns past communication patterns and emotional history. This allows it to provide customized emotional expressions for each user. For example, it learns the patterns of messages that made the user feel "concerned" in the past and proposes an appropriate expression in a similar context. Furthermore, the AI ​​agent system proposes advice and optimal expressions for specific communication challenges faced by the user. For example, the AI ​​agent system provides specific advice on aspects that users find difficult to convey, enabling effective communication. This allows users to receive appropriate emotional expressions based on various contexts, leading to more effective communication. The AI ​​agent system learns the characteristics of individual users and suggests optimal expressions, saving time and effort. Furthermore, in today's world where digital communication is increasingly important due to the spread of teleworking, the technology for understanding emotional context is still immature, and early entry into this field is expected to establish a competitive advantage. This allows the AI ​​agent system to accurately convey the user's intentions and emotions.

[0029] The AI ​​agent system according to this embodiment comprises a reception unit, an analysis unit, a selection unit, and a provision unit. The reception unit receives text messages from the user. For example, the reception unit receives text messages entered by the user and sends them to the system. The reception unit can receive user input in real time. The analysis unit analyzes the context of the text message received by the reception unit. For example, the analysis unit understands the context of the text message using natural language processing technology. The analysis unit analyzes the context based on the type of context and the analysis algorithm. The selection unit selects the most appropriate words based on the context analyzed by the analysis unit. For example, the selection unit selects the most appropriate words based on the user's intentions and emotions. The selection unit selects words based on the criteria and methods for selecting the most appropriate words. The provision unit provides the words selected by the selection unit to the user. For example, the provision unit displays the selected words to the user. The provision unit provides the words to the user at an appropriate time. As a result, the AI ​​agent system according to this embodiment can accurately convey the user's intentions and emotions.

[0030] The reception unit receives user text messages. For example, it receives text messages entered by users and sends them to the system. The reception unit can receive user input in real time. Specifically, the reception unit instantly captures text messages entered by users through chat windows or messaging applications and sends them to the system's central server. To process user input quickly, the reception unit uses high-speed data transfer protocols and minimizes latency. Furthermore, the reception unit is equipped with input completion and spell check functions to accurately receive user input and can make appropriate corrections if the user makes a mistake. For example, if a user enters "hello," the reception unit instantly recognizes this message and sends it to the parsing unit. The reception unit is also designed to handle simultaneous input from multiple users and efficiently processes messages using parallel processing technology. This allows the reception unit to receive user input in real time and improve the overall responsiveness of the system. In addition, the reception unit can save the user's input history and refer to past messages to provide a foundation for providing more contextual responses.

[0031] The analysis unit analyzes the context of text messages received by the reception unit. The analysis unit understands the context of text messages using, for example, natural language processing techniques. The analysis unit analyzes the context based on the type of context and the analysis algorithm. Specifically, the analysis unit tokenizes the received text message and performs morphological analysis and dependency structure analysis to analyze the meaning of each token. Furthermore, the analysis unit generates a context vector to understand the context and uses it to estimate the intent and sentiment of the message. For example, if a user enters "What's the weather like today?", the analysis unit extracts keywords such as "today," "weather," and "how," and analyzes the relationships between these keywords to understand that the user is seeking weather information. The analysis unit can also refer to past conversation history and user profile information to perform more accurate context analysis. For example, if a user has previously asked "Please tell me the weather for tomorrow," the analysis unit considers this information and determines that there is a high probability that the user is seeking weather information again. Furthermore, the analysis unit can continuously improve the accuracy of context analysis using machine learning algorithms. This allows the analysis unit to accurately understand the user's intentions and emotions, thereby improving the overall response quality of the system.

[0032] The selection unit chooses the most appropriate words based on the context analyzed by the analysis unit. For example, the selection unit selects the most appropriate words based on the user's intent and emotions. The selection unit chooses words based on criteria and methods for selecting the most appropriate words. Specifically, the selection unit generates appropriate response candidates based on the contextual information provided by the analysis unit and selects the most appropriate one from among them. In generating response candidates, the selection unit utilizes pre-trained response templates and generative AI models. For example, if a user asks, "What's the weather like today?", the selection unit generates response candidates such as "It's sunny today" and selects the most appropriate one from among them. The selection unit can also adjust the tone and style of the response, taking into account the user's emotions and intentions. For example, if a user sends an emotional message, the selection unit will select a more polite and empathetic response. Furthermore, the selection unit can continuously improve its response selection criteria based on past response history and user feedback. This allows the selection unit to provide responses that are optimal to the user's intent and emotions, improving the overall user experience of the system.

[0033] The delivery unit provides the user with the words selected by the selection unit. The delivery unit, for example, displays the selected words to the user. The delivery unit provides the words to the user at the appropriate time. Specifically, the delivery unit displays the response provided by the selection unit on the user's device so that the user can see it immediately. The delivery unit adjusts the way and timing of the response is displayed to provide information in the most effective way for the user. For example, if the user is using a chat window, the delivery unit displays the response in real time so that the user can continue the conversation smoothly. The delivery unit can also provide text messages as voice using speech synthesis technology. This can accommodate users with visual impairments or users whose hands are occupied. Furthermore, the delivery unit can collect user feedback and continuously improve the quality and method of response delivery. For example, if a user rates a response as "good" or "bad," the delivery unit records this information and uses it to improve future responses. This allows the delivery unit to provide users with quick and appropriate responses and improve overall user satisfaction with the system.

[0034] The AI ​​agent system includes a learning unit that learns past communication patterns and emotional history. For example, the learning unit analyzes the user's past message history to learn communication patterns. The learning unit can learn the types and frequency of past messages, emotional expressions, etc. The learning unit learns the user's emotional history and understands patterns of emotional change. This allows the learning unit to provide emotional expressions customized for each user. Some or all of the above processing in the learning unit may be performed using AI, or not. For example, the learning unit can input past message history into the AI, which can then learn communication patterns and emotional history.

[0035] The AI ​​agent system includes a suggestion unit that provides advice and proposes optimal expressions for specific communication challenges faced by the user. For example, the suggestion unit provides specific advice on parts that the user feels are difficult to understand. The suggestion unit can analyze the user's communication challenges and propose optimal expressions. The suggestion unit provides appropriate advice based on the user's intentions and emotions. In this way, the suggestion unit can resolve the user's communication challenges. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the user's communication challenges into the AI, which can then propose optimal expressions.

[0036] The learning unit can provide emotionally customized expressions for each user. For example, the learning unit can customize emotionally customized expressions based on the user's past emotional history. The learning unit can learn the user's emotional change patterns and provide appropriate emotionally customized expressions. This allows the learning unit to provide appropriate emotionally customized expressions for each user. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the user's emotional history into the AI, which can then provide customized emotionally customized expressions.

[0037] The suggestion department can provide specific advice on aspects that users find difficult to understand. For example, it can provide specific advice if a user is using ambiguous or misleading language. The suggestion department can provide appropriate advice based on the user's intent and feelings. In this way, the suggestion department can resolve aspects that users find difficult to understand. Some or all of the above processing in the suggestion department may be performed using AI or not. For example, the suggestion department can input the user's text message into an AI, which can then provide specific advice.

[0038] The analysis unit can analyze the user's intent and emotions in business emails and online messages. For example, the analysis unit can accurately analyze the user's intent and emotions in business emails. Similarly, the analysis unit can analyze the user's intent and emotions in online messages. As a result, the analysis unit can accurately analyze the user's intent and emotions in business emails and online messages. 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 business emails and online messages into AI, which can then analyze the user's intent and emotions.

[0039] The reception unit can analyze the user's past message sending history and select the optimal reception method. For example, the reception unit may prioritize message sending methods that the user has frequently used in the past. The reception unit can suggest the optimal reception method for a specific time period based on the user's past message sending history. The reception unit can analyze the user's past message sending history and select the most effective reception method. This allows the reception unit to select the optimal reception method based on the user's past message sending history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's past message sending history into AI, and the AI ​​can select the optimal reception method.

[0040] The reception system can filter text messages based on the user's current situation and areas of interest. For example, if the user is at work, the reception system can prioritize receiving only work-related messages. If the user is on vacation, the reception system can prioritize receiving messages that promote relaxation. The reception system can also prioritize receiving relevant messages based on the user's areas of interest. This allows the reception system to receive appropriate messages based on the user's current situation and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the user's current situation and areas of interest into the AI, which can then perform the filtering.

[0041] The reception unit can prioritize receiving highly relevant messages when receiving text messages, taking into account the user's geographical location. For example, if the user is in a specific region, the reception unit can prioritize receiving messages related to that region. If the user is traveling, the reception unit can prioritize receiving messages related to their travel destination. The reception unit can prioritize receiving highly relevant messages based on the user's current location. In this way, the reception unit can prioritize receiving highly relevant messages based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location information into the AI, which can then select highly relevant messages.

[0042] The reception unit can analyze the user's social media activity when receiving text messages and receive relevant messages. For example, the reception unit can prioritize receiving messages related to topics the user has shown interest in on social media. The reception unit can also receive messages related to the user's current interests based on their social media activity. The reception unit can also prioritize receiving messages from accounts the user follows on social media. This allows the reception unit to receive relevant messages based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into an AI, which can then select relevant messages.

[0043] The analysis unit can adjust the level of detail of its analysis based on the importance of the message during contextual analysis. For example, the analysis unit can perform detailed contextual analysis on high-importance messages and simplified contextual analysis on low-importance messages. The analysis unit can dynamically adjust the level of detail of its analysis according to the importance of the message. 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 message importance data into the AI, which can then adjust the level of detail of its analysis.

[0044] The analysis unit can apply different analysis algorithms depending on the message category during contextual analysis. For example, the analysis unit can apply an analysis algorithm specialized for business context to business emails. For personal messages, it can apply an algorithm specialized for sentiment analysis. For social media messages, it can apply an algorithm specialized for trend analysis. This allows the analysis unit to apply the appropriate analysis algorithm according to the message category. 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 category data into the AI, and the AI ​​can apply the appropriate analysis algorithm.

[0045] The analysis unit can determine the priority of analysis based on the message transmission timing during contextual analysis. For example, the analysis unit may prioritize the analysis of recently transmitted messages. The analysis unit may also prioritize the analysis of messages transmitted at important times. The analysis unit can dynamically adjust the analysis priority according to the message transmission timing. This allows the analysis unit to determine the analysis priority according to the message transmission timing. 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 transmission timing data into the AI, and the AI ​​can determine the analysis priority.

[0046] The analysis unit can adjust the order of analysis based on the relevance of messages during contextual analysis. For example, the analysis unit may prioritize the analysis of highly relevant messages. The analysis unit may postpone the analysis of less relevant messages. The analysis unit can dynamically adjust the order of analysis according to the relevance of messages. This allows the analysis unit to adjust the order of analysis according to the relevance of messages. 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 relevance data into the AI, and the AI ​​can adjust the order of analysis.

[0047] The selection unit can adjust the level of detail of its selections based on the importance of the message when selecting words. For example, the selection unit can select detailed and polite words for high-importance messages. For low-importance messages, the selection unit can select concise and clear words. The selection unit can dynamically adjust the level of detail of its selections according to the importance of the message. This allows the selection unit to adjust the level of detail of its selections according to the importance of the message. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message importance data into the AI, and the AI ​​can adjust the level of detail of its selections.

[0048] The selection unit can apply different selection algorithms depending on the message category when selecting words. For example, for business emails, the selection unit can apply a selection algorithm specialized for business context. For personal messages, the selection unit can apply a selection algorithm specialized for emotional expression. For social media messages, the selection unit can apply a selection algorithm specialized for trends. This allows the selection unit to apply an appropriate selection algorithm depending on the message category. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message category data into AI, and the AI ​​can apply an appropriate selection algorithm.

[0049] The selection unit can determine the priority of selections based on the message sending time when selecting words. For example, the selection unit may prioritize words from recently sent messages. The selection unit may also prioritize words from messages sent at important times. The selection unit can dynamically adjust the selection priority according to the message sending time. This allows the selection unit to determine the selection priority according to the message sending time. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message sending time data into AI, and the AI ​​can determine the selection priority.

[0050] The selection unit can adjust the order of selection based on the relevance of the message when selecting words. For example, the selection unit can prioritize selecting words with high relevance. The selection unit can postpone selecting words with low relevance. The selection unit can dynamically adjust the order of selection according to the relevance of the message. In this way, the selection unit can adjust the order of selection according to the relevance of the message. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message relevance data into the AI, and the AI ​​can adjust the order of selection.

[0051] The delivery unit can adjust the level of detail provided based on the importance of the message when providing words. For example, the delivery unit can provide detailed and polite expressions for high-importance messages. For low-importance messages, the delivery unit can provide concise and clear expressions. The delivery unit can dynamically adjust the level of detail provided according to the importance of the message. This allows the delivery unit to adjust the level of detail provided according to the importance of the message. 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 message importance data into AI, and the AI ​​can adjust the level of detail provided.

[0052] The delivery unit can apply different delivery algorithms depending on the message category when delivering words. For example, the delivery unit can apply a delivery algorithm specialized for business contexts to business emails. For personal messages, it can apply a delivery algorithm specialized for emotional expression. For social media messages, it can apply a delivery algorithm specialized for trends. This allows the delivery unit to apply the appropriate delivery algorithm according to the message category. 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 message category data into AI, and the AI ​​can apply the appropriate delivery algorithm.

[0053] The service provider can determine the priority of word provision based on the message sending time. For example, the service provider may prioritize providing words from recently sent messages. The service provider may also prioritize providing words from messages sent at important times. The service provider can dynamically adjust the priority of word provision according to the message sending time. This allows the service provider to determine the priority of word provision according to the message sending time. 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 message sending time data into AI, and the AI ​​can determine the priority of word provision.

[0054] The delivery unit can adjust the order of delivery based on the relevance of the message when delivering words. For example, the delivery unit can prioritize delivering highly relevant words. The delivery unit can postpone delivering less relevant words. The delivery unit can dynamically adjust the order of delivery according to the relevance of the message. This allows the delivery unit to adjust the order of delivery according to the relevance of the message. 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 message relevance data into the AI, and the AI ​​can adjust the order of delivery.

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

[0056] The learning unit can weight the training data based on the timing of message transmission during training. For example, the learning unit can assign a higher weight to training data for recently transmitted messages. The learning unit can assign a higher weight to training data for messages transmitted at important times. The learning unit can dynamically adjust the weighting of the training data according to the timing of message transmission. This allows the learning unit to weight the training data according to the timing of message transmission. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input message transmission timing data into the AI, and the AI ​​can perform the weighting of the training data.

[0057] The proposal unit can adjust the level of detail of its proposals based on the importance of the message. For example, the proposal unit can provide detailed and thorough proposals for high-importance messages, and concise and clear proposals for low-importance messages. The proposal unit can dynamically adjust the level of detail of its proposals according to the importance of the message. This allows the proposal unit to adjust the level of detail of its proposals according to the importance of the message. 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 importance data into the AI, which can then adjust the level of detail of its proposals.

[0058] The suggestion function can apply different suggestion algorithms depending on the message category when making suggestions. For example, for business emails, the suggestion function can apply a suggestion algorithm specialized for the business context. For personal messages, the suggestion function can apply a suggestion algorithm specialized for emotional expression. For social media messages, the suggestion function can apply a suggestion algorithm specialized for trends. This allows the suggestion function to apply the appropriate suggestion algorithm according to the message category. 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 message category data into an AI, which can then apply the appropriate suggestion algorithm.

[0059] The proposal unit can determine the priority of proposals based on the timing of message transmission when making a proposal. For example, the proposal unit may prioritize proposals for recently sent messages. The proposal unit may also prioritize proposals for messages sent at important times. The proposal unit can dynamically adjust the priority of proposals according to the timing of message transmission. This allows the proposal unit to determine the priority of proposals according to the timing of message transmission. 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 transmission timing data into AI, and the AI ​​can determine the priority of proposals.

[0060] The proposal unit can adjust the order of proposals based on the relevance of the messages when making proposals. For example, the proposal unit may prioritize highly relevant proposals. The proposal unit may postpone less relevant proposals. The proposal unit can dynamically adjust the order of proposals according to the relevance of the messages. This allows the proposal unit to adjust the order of proposals according to the relevance of the messages. 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 relevance data into the AI, and the AI ​​can adjust the order of proposals.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The analysis unit can consider the user's past behavioral history and personality profile when analyzing the user's intentions and emotions. For example, it can analyze how the user has responded to past messages and predict their response to the current message. It can also determine what kind of expression is most appropriate for the user based on their personality profile. As a result, the analysis unit can perform a more accurate analysis of intentions and emotions based on the user's past behavioral history and personality profile.

[0063] The learning unit can dynamically adjust its learning algorithm according to the user's communication style. For example, if the user prefers a formal communication style, it will prioritize learning formal expressions. Similarly, if the user prefers a casual communication style, it can prioritize learning casual expressions. Furthermore, if the user's communication style changes, the learning algorithm can be adapted accordingly. This allows the learning unit to perform optimal learning according to the user's communication style.

[0064] The proposal department can provide training modules to improve users' communication skills. For example, if a user has difficulty with a particular expression, a training module can be provided to practice that expression. Similarly, if a user is unsure about how to write business emails, a training module can be provided to teach them how. Furthermore, the proposal department can monitor the user's progress and adjust the training content as needed. In this way, the proposal department can provide support to improve users' communication skills.

[0065] The analysis unit can apply different analysis algorithms depending on the message category during contextual analysis. For example, it can apply an analysis algorithm specialized for business contexts to business emails. For personal messages, it can apply an algorithm specialized for sentiment analysis. For social media messages, it can apply an algorithm specialized for trend analysis. This allows the analysis unit to apply the appropriate analysis algorithm according to the message category.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception desk receives user text messages. For example, it receives text messages entered by users and sends them to the system. The reception desk can receive user input in real time. Step 2: The analysis unit analyzes the context of the text message received by the reception unit. For example, it uses natural language processing techniques to understand the context of the text message. The analysis unit analyzes the context based on the type of context and the analysis algorithm. Step 3: The selection unit chooses the most appropriate words based on the context analyzed by the analysis unit. For example, it selects the most appropriate words based on the user's intent and emotions. The selection unit chooses words based on the criteria and methods for selecting the most appropriate words. Step 4: The providing unit provides the user with the word selected by the selection unit. For example, it displays the selected word to the user. The providing unit provides the word to the user at an appropriate time.

[0068] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that helps accurately convey the user's intentions and emotions in text communication. This AI agent system solves the problem of "misunderstanding" by applying natural language processing technology to understand the context and selecting the most appropriate words to clarify communication. The AI ​​agent system also learns past communication patterns and emotional history and provides customized emotional expressions for each user. Furthermore, the AI ​​agent system proposes advice and optimal expressions for specific communication challenges faced by the user. For example, when a user inputs a text message, the AI ​​agent system uses natural language processing technology to understand the context in order to accurately convey the user's intentions and emotions. For example, in a business email or online message, if a user feels "Am I being scolded?", the AI ​​agent system analyzes the context and proposes an appropriate expression. Next, the AI ​​agent system learns past communication patterns and emotional history. This allows it to provide customized emotional expressions for each user. For example, it learns the patterns of messages that made the user feel "concerned" in the past and proposes an appropriate expression in a similar context. Furthermore, the AI ​​agent system proposes advice and optimal expressions for specific communication challenges faced by the user. For example, the AI ​​agent system provides specific advice on aspects that users find difficult to convey, enabling effective communication. This allows users to receive appropriate emotional expressions based on various contexts, leading to more effective communication. The AI ​​agent system learns the characteristics of individual users and suggests optimal expressions, saving time and effort. Furthermore, in today's world where digital communication is increasingly important due to the spread of teleworking, the technology for understanding emotional context is still immature, and early entry into this field is expected to establish a competitive advantage. This allows the AI ​​agent system to accurately convey the user's intentions and emotions.

[0069] The AI ​​agent system according to this embodiment comprises a reception unit, an analysis unit, a selection unit, and a provision unit. The reception unit receives text messages from the user. For example, the reception unit receives text messages entered by the user and sends them to the system. The reception unit can receive user input in real time. The analysis unit analyzes the context of the text message received by the reception unit. For example, the analysis unit understands the context of the text message using natural language processing technology. The analysis unit analyzes the context based on the type of context and the analysis algorithm. The selection unit selects the most appropriate words based on the context analyzed by the analysis unit. For example, the selection unit selects the most appropriate words based on the user's intentions and emotions. The selection unit selects words based on the criteria and methods for selecting the most appropriate words. The provision unit provides the words selected by the selection unit to the user. For example, the provision unit displays the selected words to the user. The provision unit provides the words to the user at an appropriate time. As a result, the AI ​​agent system according to this embodiment can accurately convey the user's intentions and emotions.

[0070] The reception unit receives user text messages. For example, it receives text messages entered by users and sends them to the system. The reception unit can receive user input in real time. Specifically, the reception unit instantly captures text messages entered by users through chat windows or messaging applications and sends them to the system's central server. To process user input quickly, the reception unit uses high-speed data transfer protocols and minimizes latency. Furthermore, the reception unit is equipped with input completion and spell check functions to accurately receive user input and can make appropriate corrections if the user makes a mistake. For example, if a user enters "hello," the reception unit instantly recognizes this message and sends it to the parsing unit. The reception unit is also designed to handle simultaneous input from multiple users and efficiently processes messages using parallel processing technology. This allows the reception unit to receive user input in real time and improve the overall responsiveness of the system. In addition, the reception unit can save the user's input history and refer to past messages to provide a foundation for providing more contextual responses.

[0071] The analysis unit analyzes the context of text messages received by the reception unit. The analysis unit understands the context of text messages using, for example, natural language processing techniques. The analysis unit analyzes the context based on the type of context and the analysis algorithm. Specifically, the analysis unit tokenizes the received text message and performs morphological analysis and dependency structure analysis to analyze the meaning of each token. Furthermore, the analysis unit generates a context vector to understand the context and uses it to estimate the intent and sentiment of the message. For example, if a user enters "What's the weather like today?", the analysis unit extracts keywords such as "today," "weather," and "how," and analyzes the relationships between these keywords to understand that the user is seeking weather information. The analysis unit can also refer to past conversation history and user profile information to perform more accurate context analysis. For example, if a user has previously asked "Please tell me the weather for tomorrow," the analysis unit considers this information and determines that there is a high probability that the user is seeking weather information again. Furthermore, the analysis unit can continuously improve the accuracy of context analysis using machine learning algorithms. This allows the analysis unit to accurately understand the user's intentions and emotions, thereby improving the overall response quality of the system.

[0072] The selection unit chooses the most appropriate words based on the context analyzed by the analysis unit. For example, the selection unit selects the most appropriate words based on the user's intent and emotions. The selection unit chooses words based on criteria and methods for selecting the most appropriate words. Specifically, the selection unit generates appropriate response candidates based on the contextual information provided by the analysis unit and selects the most appropriate one from among them. In generating response candidates, the selection unit utilizes pre-trained response templates and generative AI models. For example, if a user asks, "What's the weather like today?", the selection unit generates response candidates such as "It's sunny today" and selects the most appropriate one from among them. The selection unit can also adjust the tone and style of the response, taking into account the user's emotions and intentions. For example, if a user sends an emotional message, the selection unit will select a more polite and empathetic response. Furthermore, the selection unit can continuously improve its response selection criteria based on past response history and user feedback. This allows the selection unit to provide responses that are optimal to the user's intent and emotions, improving the overall user experience of the system.

[0073] The delivery unit provides the user with the words selected by the selection unit. The delivery unit, for example, displays the selected words to the user. The delivery unit provides the words to the user at the appropriate time. Specifically, the delivery unit displays the response provided by the selection unit on the user's device so that the user can see it immediately. The delivery unit adjusts the way and timing of the response is displayed to provide information in the most effective way for the user. For example, if the user is using a chat window, the delivery unit displays the response in real time so that the user can continue the conversation smoothly. The delivery unit can also provide text messages as voice using speech synthesis technology. This can accommodate users with visual impairments or users whose hands are occupied. Furthermore, the delivery unit can collect user feedback and continuously improve the quality and method of response delivery. For example, if a user rates a response as "good" or "bad," the delivery unit records this information and uses it to improve future responses. This allows the delivery unit to provide users with quick and appropriate responses and improve overall user satisfaction with the system.

[0074] The AI ​​agent system includes a learning unit that learns past communication patterns and emotional history. For example, the learning unit analyzes the user's past message history to learn communication patterns. The learning unit can learn the types and frequency of past messages, emotional expressions, etc. The learning unit learns the user's emotional history and understands patterns of emotional change. This allows the learning unit to provide emotional expressions customized for each user. Some or all of the above processing in the learning unit may be performed using AI, or not. For example, the learning unit can input past message history into the AI, which can then learn communication patterns and emotional history.

[0075] The AI ​​agent system includes a suggestion unit that provides advice and proposes optimal expressions for specific communication challenges faced by the user. For example, the suggestion unit provides specific advice on parts that the user feels are difficult to understand. The suggestion unit can analyze the user's communication challenges and propose optimal expressions. The suggestion unit provides appropriate advice based on the user's intentions and emotions. In this way, the suggestion unit can resolve the user's communication challenges. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the user's communication challenges into the AI, which can then propose optimal expressions.

[0076] The learning unit can provide emotionally customized expressions for each user. For example, the learning unit can customize emotionally customized expressions based on the user's past emotional history. The learning unit can learn the user's emotional change patterns and provide appropriate emotionally customized expressions. This allows the learning unit to provide appropriate emotionally customized expressions for each user. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the user's emotional history into the AI, which can then provide customized emotionally customized expressions.

[0077] The suggestion department can provide specific advice on aspects that users find difficult to understand. For example, it can provide specific advice if a user is using ambiguous or misleading language. The suggestion department can provide appropriate advice based on the user's intent and feelings. In this way, the suggestion department can resolve aspects that users find difficult to understand. Some or all of the above processing in the suggestion department may be performed using AI or not. For example, the suggestion department can input the user's text message into an AI, which can then provide specific advice.

[0078] The analysis unit can analyze the user's intent and emotions in business emails and online messages. For example, the analysis unit can accurately analyze the user's intent and emotions in business emails. Similarly, the analysis unit can analyze the user's intent and emotions in online messages. As a result, the analysis unit can accurately analyze the user's intent and emotions in business emails and online messages. 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 business emails and online messages into AI, which can then analyze the user's intent and emotions.

[0079] The reception unit can estimate the user's emotions and adjust the timing of text message reception based on the estimated emotions. For example, if the user is stressed, the reception unit can delay the reception timing so that the user receives the message in a relaxed state. If the user is in a hurry, the reception unit can receive the message immediately to encourage a quick response. If the user is relaxed, the reception unit can receive the message at the appropriate time to facilitate natural communication. In this way, the reception unit can receive messages at the appropriate time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the reception timing.

[0080] The reception unit can analyze the user's past message sending history and select the optimal reception method. For example, the reception unit may prioritize message sending methods that the user has frequently used in the past. The reception unit can suggest the optimal reception method for a specific time period based on the user's past message sending history. The reception unit can analyze the user's past message sending history and select the most effective reception method. This allows the reception unit to select the optimal reception method based on the user's past message sending history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's past message sending history into AI, and the AI ​​can select the optimal reception method.

[0081] The reception system can filter text messages based on the user's current situation and areas of interest. For example, if the user is at work, the reception system can prioritize receiving only work-related messages. If the user is on vacation, the reception system can prioritize receiving messages that promote relaxation. The reception system can also prioritize receiving relevant messages based on the user's areas of interest. This allows the reception system to receive appropriate messages based on the user's current situation and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the user's current situation and areas of interest into the AI, which can then perform the filtering.

[0082] The reception desk can estimate the user's emotions and determine the priority of messages to receive based on the estimated emotions. For example, if the user is stressed, the reception desk may postpone less important messages. If the user is relaxed, the reception desk may prioritize receiving more important messages. If the user is in a hurry, the reception desk may prioritize receiving more urgent messages. In this way, the reception desk can determine message priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into a generative AI, which can estimate the emotions and determine message priorities.

[0083] The reception unit can prioritize receiving highly relevant messages when receiving text messages, taking into account the user's geographical location. For example, if the user is in a specific region, the reception unit can prioritize receiving messages related to that region. If the user is traveling, the reception unit can prioritize receiving messages related to their travel destination. The reception unit can prioritize receiving highly relevant messages based on the user's current location. In this way, the reception unit can prioritize receiving highly relevant messages based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location information into the AI, which can then select highly relevant messages.

[0084] The reception unit can analyze the user's social media activity when receiving text messages and receive relevant messages. For example, the reception unit can prioritize receiving messages related to topics the user has shown interest in on social media. The reception unit can also receive messages related to the user's current interests based on their social media activity. The reception unit can also prioritize receiving messages from accounts the user follows on social media. This allows the reception unit to receive relevant messages based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into an AI, which can then select relevant messages.

[0085] The analysis unit can estimate the user's emotions and adjust the contextual analysis method based on the estimated user emotions. For example, if the user is stressed, the analysis unit can perform a simple contextual analysis and extract only the important information. If the user is relaxed, the analysis unit can perform a detailed contextual analysis and provide rich information. If the user is in a hurry, the analysis unit can perform a rapid contextual analysis and provide concise information. In this way, the analysis unit can adjust the contextual analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI, which can estimate emotions and adjust the contextual analysis method.

[0086] The analysis unit can adjust the level of detail of its analysis based on the importance of the message during contextual analysis. For example, the analysis unit can perform detailed contextual analysis on high-importance messages and simplified contextual analysis on low-importance messages. The analysis unit can dynamically adjust the level of detail of its analysis according to the importance of the message. 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 message importance data into the AI, which can then adjust the level of detail of its analysis.

[0087] The analysis unit can apply different analysis algorithms depending on the message category during contextual analysis. For example, the analysis unit can apply an analysis algorithm specialized for business context to business emails. For personal messages, it can apply an algorithm specialized for sentiment analysis. For social media messages, it can apply an algorithm specialized for trend analysis. This allows the analysis unit to apply the appropriate analysis algorithm according to the message category. 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 category data into the AI, and the AI ​​can apply the appropriate analysis algorithm.

[0088] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can provide a display method that includes detailed information. If the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. In this way, the analysis unit can adjust the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 using AI. For example, the analysis unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the display method.

[0089] The analysis unit can determine the priority of analysis based on the message transmission timing during contextual analysis. For example, the analysis unit may prioritize the analysis of recently transmitted messages. The analysis unit may also prioritize the analysis of messages transmitted at important times. The analysis unit can dynamically adjust the analysis priority according to the message transmission timing. This allows the analysis unit to determine the analysis priority according to the message transmission timing. 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 transmission timing data into the AI, and the AI ​​can determine the analysis priority.

[0090] The analysis unit can adjust the order of analysis based on the relevance of messages during contextual analysis. For example, the analysis unit may prioritize the analysis of highly relevant messages. The analysis unit may postpone the analysis of less relevant messages. The analysis unit can dynamically adjust the order of analysis according to the relevance of messages. This allows the analysis unit to adjust the order of analysis according to the relevance of messages. 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 relevance data into the AI, and the AI ​​can adjust the order of analysis.

[0091] The selection unit can estimate the user's emotions and adjust its word selection method based on the estimated emotions. For example, if the user is stressed, the selection unit can select simple and clear words. If the user is relaxed, the selection unit can select detailed and polite words. If the user is in a hurry, the selection unit can select quick and concise words. In this way, the selection unit can adjust its word selection method to suit the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input user emotion data into a generative AI, which can estimate the emotions and adjust its word selection method.

[0092] The selection unit can adjust the level of detail of its selections based on the importance of the message when selecting words. For example, the selection unit can select detailed and polite words for high-importance messages. For low-importance messages, the selection unit can select concise and clear words. The selection unit can dynamically adjust the level of detail of its selections according to the importance of the message. This allows the selection unit to adjust the level of detail of its selections according to the importance of the message. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message importance data into the AI, and the AI ​​can adjust the level of detail of its selections.

[0093] The selection unit can apply different selection algorithms depending on the message category when selecting words. For example, for business emails, the selection unit can apply a selection algorithm specialized for business context. For personal messages, the selection unit can apply a selection algorithm specialized for emotional expression. For social media messages, the selection unit can apply a selection algorithm specialized for trends. This allows the selection unit to apply an appropriate selection algorithm depending on the message category. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message category data into AI, and the AI ​​can apply an appropriate selection algorithm.

[0094] The selection unit can estimate the user's emotions and determine the priority of words to select based on the estimated emotions. For example, if the user is stressed, the selection unit may postpone selecting less important words. If the user is relaxed, the selection unit may prioritize selecting more important words. If the user is in a hurry, the selection unit may prioritize selecting more urgent words. In this way, the selection unit can determine the priority of words to select according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of words.

[0095] The selection unit can determine the priority of selections based on the message sending time when selecting words. For example, the selection unit may prioritize words from recently sent messages. The selection unit may also prioritize words from messages sent at important times. The selection unit can dynamically adjust the selection priority according to the message sending time. This allows the selection unit to determine the selection priority according to the message sending time. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message sending time data into AI, and the AI ​​can determine the selection priority.

[0096] The selection unit can adjust the order of selection based on the relevance of the message when selecting words. For example, the selection unit can prioritize selecting words with high relevance. The selection unit can postpone selecting words with low relevance. The selection unit can dynamically adjust the order of selection according to the relevance of the message. In this way, the selection unit can adjust the order of selection according to the relevance of the message. Some or all of the above processing in the selection unit may be performed using AI or not. For example, the selection unit can input message relevance data into the AI, and the AI ​​can adjust the order of selection.

[0097] The service provider can estimate the user's emotions and adjust the way it expresses itself based on those emotions. For example, if the user is stressed, the service provider can provide simple and clear expressions. If the user is relaxed, the service provider can provide detailed and polite expressions. If the user is in a hurry, the service provider can provide quick and concise expressions. In this way, the service provider can adjust the way it expresses itself according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into a generative AI, which can estimate the emotion and adjust the expression.

[0098] The delivery unit can adjust the level of detail provided based on the importance of the message when providing words. For example, the delivery unit can provide detailed and polite expressions for high-importance messages. For low-importance messages, the delivery unit can provide concise and clear expressions. The delivery unit can dynamically adjust the level of detail provided according to the importance of the message. This allows the delivery unit to adjust the level of detail provided according to the importance of the message. 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 message importance data into AI, and the AI ​​can adjust the level of detail provided.

[0099] The delivery unit can apply different delivery algorithms depending on the message category when delivering words. For example, the delivery unit can apply a delivery algorithm specialized for business contexts to business emails. For personal messages, it can apply a delivery algorithm specialized for emotional expression. For social media messages, it can apply a delivery algorithm specialized for trends. This allows the delivery unit to apply the appropriate delivery algorithm according to the message category. 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 message category data into AI, and the AI ​​can apply the appropriate delivery algorithm.

[0100] The service provider can estimate the user's emotions and determine the priority of the words to be delivered based on the estimated emotions. For example, if the user is stressed, the service provider may postpone delivering less important words. If the user is relaxed, the service provider may prioritize delivering more important words. If the user is in a hurry, the service provider may prioritize delivering more urgent words. In this way, the service provider can determine the priority of the words to be delivered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not using AI. For example, the service provider can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of the words.

[0101] The service provider can determine the priority of word provision based on the message sending time. For example, the service provider may prioritize providing words from recently sent messages. The service provider may also prioritize providing words from messages sent at important times. The service provider can dynamically adjust the priority of word provision according to the message sending time. This allows the service provider to determine the priority of word provision according to the message sending time. 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 message sending time data into AI, and the AI ​​can determine the priority of word provision.

[0102] The delivery unit can adjust the order of delivery based on the relevance of the message when delivering words. For example, the delivery unit can prioritize delivering highly relevant words. The delivery unit can postpone delivering less relevant words. The delivery unit can dynamically adjust the order of delivery according to the relevance of the message. This allows the delivery unit to adjust the order of delivery according to the relevance of the message. 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 message relevance data into the AI, and the AI ​​can adjust the order of delivery.

[0103] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit can select training data that helps reduce stress. If the user is relaxed, the learning unit can select training data that helps maintain that relaxed state. If the user is in a hurry, the learning unit can select training data that helps provide a quick response. In this way, the learning unit can select training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 learning unit may be performed using AI or not using AI. For example, the learning unit can input user emotion data into a generative AI, which can estimate the emotions and select training data.

[0104] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can analyze past learning data and adjust the parameters of the learning algorithm. The learning unit can improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning unit can optimize the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI or not. For example, the learning unit can input past learning data into AI, and the AI ​​can optimize the learning algorithm.

[0105] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency to alleviate the burden. If the user is relaxed, the learning unit can increase the learning frequency to enhance the effect. If the user is in a hurry, the learning unit can adjust the learning frequency to enable a quick response. In this way, the learning unit can adjust the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not using AI. For example, the learning unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the learning frequency.

[0106] The learning unit can weight the training data based on the timing of message transmission during training. For example, the learning unit can assign a higher weight to training data for recently transmitted messages. The learning unit can assign a higher weight to training data for messages transmitted at important times. The learning unit can dynamically adjust the weighting of the training data according to the timing of message transmission. This allows the learning unit to weight the training data according to the timing of message transmission. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input message transmission timing data into the AI, and the AI ​​can perform the weighting of the training data.

[0107] The suggestion unit can estimate the user's emotions and adjust the way it presents its suggestions based on those emotions. For example, if the user is stressed, the suggestion unit can offer simple and clear suggestions. If the user is relaxed, the suggestion unit can offer detailed and thoughtful suggestions. If the user is in a hurry, the suggestion unit can offer quick and concise suggestions. This allows the suggestion unit to adjust the way it presents its suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the way it presents its suggestions.

[0108] The proposal unit can adjust the level of detail of its proposals based on the importance of the message. For example, the proposal unit can provide detailed and thorough proposals for high-importance messages, and concise and clear proposals for low-importance messages. The proposal unit can dynamically adjust the level of detail of its proposals according to the importance of the message. This allows the proposal unit to adjust the level of detail of its proposals according to the importance of the message. 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 importance data into the AI, which can then adjust the level of detail of its proposals.

[0109] The suggestion function can apply different suggestion algorithms depending on the message category when making suggestions. For example, for business emails, the suggestion function can apply a suggestion algorithm specialized for the business context. For personal messages, the suggestion function can apply a suggestion algorithm specialized for emotional expression. For social media messages, the suggestion function can apply a suggestion algorithm specialized for trends. This allows the suggestion function to apply the appropriate suggestion algorithm according to the message category. 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 message category data into an AI, which can then apply the appropriate suggestion algorithm.

[0110] The suggestion unit can estimate the user's emotions and determine the priority of suggestions based on those emotions. For example, if the user is stressed, the suggestion unit will postpone less important suggestions. If the user is relaxed, the suggestion unit can prioritize more important suggestions. If the user is in a hurry, the suggestion unit can prioritize more urgent suggestions. In this way, the suggestion unit can determine the priority of suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of suggestions.

[0111] The proposal unit can determine the priority of proposals based on the timing of message transmission when making a proposal. For example, the proposal unit may prioritize proposals for recently sent messages. The proposal unit may also prioritize proposals for messages sent at important times. The proposal unit can dynamically adjust the priority of proposals according to the timing of message transmission. This allows the proposal unit to determine the priority of proposals according to the timing of message transmission. 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 transmission timing data into AI, and the AI ​​can determine the priority of proposals.

[0112] The proposal unit can adjust the order of proposals based on the relevance of the messages when making proposals. For example, the proposal unit may prioritize highly relevant proposals. The proposal unit may postpone less relevant proposals. The proposal unit can dynamically adjust the order of proposals according to the relevance of the messages. This allows the proposal unit to adjust the order of proposals according to the relevance of the messages. 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 relevance data into the AI, and the AI ​​can adjust the order of proposals.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] The analysis unit can consider the user's past behavioral history and personality profile when analyzing the user's intentions and emotions. For example, it can analyze how the user has responded to past messages and predict their response to the current message. It can also determine what kind of expression is most appropriate for the user based on their personality profile. As a result, the analysis unit can perform a more accurate analysis of intentions and emotions based on the user's past behavioral history and personality profile.

[0115] The learning unit can dynamically adjust its learning algorithm according to the user's communication style. For example, if the user prefers a formal communication style, it will prioritize learning formal expressions. Similarly, if the user prefers a casual communication style, it can prioritize learning casual expressions. Furthermore, if the user's communication style changes, the learning algorithm can be adapted accordingly. This allows the learning unit to perform optimal learning according to the user's communication style.

[0116] The proposal department can provide training modules to improve users' communication skills. For example, if a user has difficulty with a particular expression, a training module can be provided to practice that expression. Similarly, if a user is unsure about how to write business emails, a training module can be provided to teach them how. Furthermore, the proposal department can monitor the user's progress and adjust the training content as needed. In this way, the proposal department can provide support to improve users' communication skills.

[0117] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, it can select training data that helps reduce stress. If the user is relaxed, the learning unit can select training data that helps maintain that relaxed state. If the user is in a hurry, the learning unit can select training data that helps provide a quick response. In this way, the learning unit can select training data according to the user's emotions.

[0118] The suggestion function can estimate the user's emotions and adjust the way it presents suggestions based on those emotions. For example, if the user is stressed, it can offer simple and clear suggestions. If the user is relaxed, it can offer detailed and thoughtful suggestions. If the user is in a hurry, it can offer quick and concise suggestions. In this way, the suggestion function can adjust the way it presents suggestions according to the user's emotions.

[0119] The analysis unit can estimate the user's emotions and adjust the contextual analysis method based on the estimated emotions. For example, if the user is stressed, it can perform a simple contextual analysis and extract only the essential information. If the user is relaxed, the analysis unit can perform a detailed contextual analysis and provide a wealth of information. If the user is in a hurry, the analysis unit can perform a rapid contextual analysis and provide concise information. In this way, the analysis unit can adjust the contextual analysis method according to the user's emotions.

[0120] The selection unit can estimate the user's emotions and adjust its word selection method based on those estimated emotions. For example, if the user is stressed, it will select simple and clear words. If the user is relaxed, the selection unit can select detailed and polite words. If the user is in a hurry, the selection unit can select quick and concise words. In this way, the selection unit can adjust its word selection method to suit the user's emotions.

[0121] The service provider can estimate the user's emotions and adjust the way it expresses itself based on those emotions. For example, if the user is stressed, it can provide simple and clear language. If the user is relaxed, it can provide detailed and polite language. If the user is in a hurry, it can provide quick and concise language. In this way, the service provider can adjust the way it expresses itself according to the user's emotions.

[0122] The suggestion function can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is stressed, it will postpone less important suggestions. If the user is relaxed, the suggestion function can prioritize more important suggestions. If the user is in a hurry, the suggestion function can prioritize urgent suggestions. In this way, the suggestion function can prioritize suggestions according to the user's emotions.

[0123] The analysis unit can apply different analysis algorithms depending on the message category during contextual analysis. For example, it can apply an analysis algorithm specialized for business contexts to business emails. For personal messages, it can apply an algorithm specialized for sentiment analysis. For social media messages, it can apply an algorithm specialized for trend analysis. This allows the analysis unit to apply the appropriate analysis algorithm according to the message category.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The reception desk receives user text messages. For example, it receives text messages entered by users and sends them to the system. The reception desk can receive user input in real time. Step 2: The analysis unit analyzes the context of the text message received by the reception unit. For example, it uses natural language processing techniques to understand the context of the text message. The analysis unit analyzes the context based on the type of context and the analysis algorithm. Step 3: The selection unit chooses the most appropriate words based on the context analyzed by the analysis unit. For example, it selects the most appropriate words based on the user's intent and emotions. The selection unit chooses words based on the criteria and methods for selecting the most appropriate words. Step 4: The providing unit provides the user with the word selected by the selection unit. For example, it displays the selected word to the user. The providing unit provides the word to the user at an appropriate time.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the reception unit, analysis unit, selection unit, provision unit, learning unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives the user's text message. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the context of the text message. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the most appropriate words based on the analyzed context. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the selected words to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past communication patterns and emotional history. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes advice and the most appropriate expressions for the user's communication challenges. 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.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the reception unit, analysis unit, selection unit, provision unit, learning unit, and suggestion unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives the user's text message. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the context of the text message. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the most appropriate words based on the analyzed context. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the selected words to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past communication patterns and emotional history. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes advice and the most appropriate expressions for the user's communication challenges. 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.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the reception unit, analysis unit, selection unit, provision unit, learning unit, and suggestion unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives the user's text message. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the context of the text message. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the most appropriate words based on the analyzed context. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the selected words to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past communication patterns and emotional history. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes advice and the most appropriate expressions for the user's communication challenges. 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.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the reception unit, analysis unit, selection unit, provision unit, learning unit, and proposal unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives the user's text message. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the context of the text message. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and selects the most appropriate words based on the analyzed context. The provision unit is implemented by the control unit 46A of the robot 414 and provides the selected words to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns past communication patterns and emotional history. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes advice and the most appropriate expressions for the user's communication challenges. 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) A reception desk that receives user text messages, An analysis unit analyzes the context of the text message received by the reception unit, A selection unit that selects the most appropriate word based on the context analyzed by the aforementioned analysis unit, The system includes a providing unit that provides the user with the word selected by the selection unit. A system characterized by the following features. (Note 2) It has a learning unit that learns past communication patterns and emotional history. The system described in Appendix 1, characterized by the features described herein. (Note 3) We have a proposal department that provides advice and suggests the most suitable expressions for the specific communication challenges that users face. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned learning unit, Provides customized emotional expressions for each user. The system described in Appendix 2, characterized by the features described herein. (Note 5) The aforementioned proposal section is, We provide specific advice on aspects that users find difficult to understand. The system described in Appendix 3, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Analyzing user intent and emotions in business emails and online messages. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of text message reception based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past message sending history and select the optimal receiving method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving text messages, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of messages to accept based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving text messages, the system prioritizes receiving messages that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When receiving text messages, the system analyzes the user's social media activity and accepts relevant messages. 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 contextual analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During contextual analysis, adjust the level of detail based on the importance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During contextual analysis, different analysis algorithms are applied depending on the message category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During contextual analysis, the priority of the analysis is determined based on when the message was sent. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During contextual analysis, the order of analysis is adjusted based on the relevance of the messages. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned selection unit is It estimates the user's emotions and adjusts the optimal word selection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned selection unit is When selecting words, adjust the level of detail based on the importance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned selection unit is When selecting words, different selection algorithms are applied depending on the message category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned selection unit is It estimates the user's emotions and determines the priority of words to select based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned selection unit is When selecting words, the priority of the selection is determined based on when the message was sent. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned selection unit is When selecting words, adjust the order of selections based on the relevance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way it expresses itself based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing information, adjust the level of detail based on the importance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing text, different provisioning algorithms are applied depending on the message category. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the words to be delivered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing messages, we prioritize their delivery based on when the message was sent. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing messages, adjust the order of delivery based on the relevance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned learning unit, During training, the training data is weighted based on when the messages were sent. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the importance of the message. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned proposal section is, When making a proposal, different proposal algorithms are applied depending on the message category. The system described in Appendix 3, characterized by the features described herein. (Note 38) 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 3, characterized by the features described herein. (Note 39) The aforementioned proposal section is, When making a proposal, prioritize the proposal based on when the message was sent. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned proposal section is, When making suggestions, adjust the order of suggestions based on the relevance of the messages. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that receives user text messages, An analysis unit analyzes the context of the text message received by the reception unit, A selection unit that selects the most appropriate word based on the context analyzed by the aforementioned analysis unit, The system includes a providing unit that provides the user with the word selected by the selection unit. A system characterized by the following features.

2. It has a learning unit that learns past communication patterns and emotional history. The system according to feature 1.

3. We have a proposal department that provides advice and suggests the most suitable expressions for the specific communication challenges that users face. The system according to feature 1.

4. The aforementioned learning unit, Provides customized emotional expressions for each user. The system according to feature 2.

5. The aforementioned proposal section is, We provide specific advice on aspects that users find difficult to understand. The system according to claim 3.

6. The aforementioned analysis unit, Analyzing user intent and emotions in business emails and online messages. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of text message reception based on the estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is Analyze the user's past message sending history and select the optimal receiving method. The system according to feature 1.

Images