System

Abstract

An object of a system according to an embodiment is to extract an appropriate emotional expression from a chat conversation and generate a stamp based on the extracted emotional expression.SOLUTION: A system includes a chat conversation acquisition part, a feeling conversion part, and a stamp generation part. The chat conversation acquisition unit acquires a chat conversation. The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into an emotional expression. The stamp generation part generates a stamp on the basis of the feeling expression converted by the feeling conversion part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of not being able to adequately extract appropriate emotional expressions from chat conversations and generate stamps based on them.

[0005] The system according to the embodiment aims to extract appropriate emotional expressions from chat conversations and generate stamps based on them. [Means for solving the problem]

[0006] The system according to the embodiment includes a chat conversation acquisition unit, an emotion conversion unit, and a stamp generation unit. The chat conversation acquisition unit acquires chat conversation. The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into an emotional expression. The stamp generation unit generates a stamp based on the emotional expression converted by the emotion conversion unit. [Effects of the Invention]

[0007] The system according to the embodiment can extract appropriate emotional expressions from chat conversations and generate stamps based on the extracted emotional expressions. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The stamp generation system according to an embodiment of the present invention automatically acquires chat conversations, converts them into emotional expressions using a generation AI, and generates stamps based on those emotional expressions. This allows the stamp generation system to extract appropriate emotional expressions based on the user's chat conversations and generate stamps based on those emotional expressions, thereby supporting user communication.

[0029] The stamp generation system according to the embodiment includes a chat conversation acquisition unit, an emotion conversion unit, and a stamp generation unit. The chat conversation acquisition unit acquires chat conversations. For example, it acquires text chat content. The chat conversation acquisition unit can also acquire voice chat content by converting it into text. The chat conversation acquisition unit can also acquire video chat content by analyzing it. For example, text chat content is acquired directly from a chat application. Voice chat content is converted into text using speech recognition technology. Video chat content is converted into text using video analysis technology. The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into an emotion expression. For example, the generation AI analyzes the conversation content using a text generation AI (e.g., LLM) and generates an emotion expression. The generation AI can also analyze the conversation content and generate an emotion expression using a multimodal generation AI. The generation AI can also understand the context of the conversation and generate appropriate emotion expressions. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI refers to relevant background information and topic models to understand the context of the conversation and generate appropriate emotional expressions. The stamp generation unit generates stamps based on the emotional expressions converted by the emotion conversion unit. For example, the stamp generation unit generates still image stamps based on the emotional expressions. The stamp generation unit can also generate animated stamps based on the emotional expressions. The stamp generation unit can also generate multiple stamp candidates based on the emotional expressions and allow the user to select one. For example, the stamp generation unit generates a smiling stamp based on the emotional expressions. Animated stamps provide dynamic emotional expressions based on the emotional expressions. The multiple stamp candidates generate stamps expressing different designs and emotions and allow the user to select one. As a result, the stamp generation system according to the embodiment can support user communication by extracting appropriate emotional expressions based on the user's chat conversation and generating stamps based on the emotional expressions.For example, the output unit provides the generated stamp to the user through a chat application or a social networking service (SNS) platform. The user can use the generated stamp in the chat application. Using the stamp on the SNS platform allows the user to share the stamp with other users. Sending the stamp via email allows the user to send the stamp directly to other users, providing quick communication.

[0030] The chat conversation acquisition unit can analyze conversations in real time and track changes in emotions sequentially. For example, the chat conversation acquisition unit analyzes conversations in real time and calculates an emotion score for each message. For example, if a user says, "I had a lot of fun today!" and then continues, "But I'm a little tired," the first message is assigned a high joy score and the next message is assigned a fatigue score. The chat conversation acquisition unit also tracks changes in emotions sequentially. For example, it records changes in emotions along the flow of the conversation and analyzes the transition of emotions. The chat conversation acquisition unit also analyzes changes in emotions in real time and generates appropriate emotional expressions. For example, it understands the context of the conversation and generates emotional expressions according to changes in emotions. In this way, by tracking changes in emotions in real time, more accurate emotional expressions can be generated.

[0031] The chat conversation acquisition unit can refer to past conversation history and take into account long-term emotional trends. The chat conversation acquisition unit, for example, refers to past conversation history and analyzes the user's long-term emotional trends. For example, based on the conversation history for the past week, it identifies emotions that the user frequently feels. The chat conversation acquisition unit also takes long-term emotional trends into account. For example, it analyzes the user's emotional patterns from the past conversation history and generates appropriate emotional expressions. The chat conversation acquisition unit also predicts emotional changes based on the past conversation history. For example, it analyzes past emotional data and predicts future emotional changes. In this way, by referring to the past conversation history, it is possible to generate emotional expressions that take into account long-term emotional trends.

[0032] The chat conversation acquisition unit can integrate conversation data from different chat platforms to generate a wider variety of emotional expressions. The chat conversation acquisition unit, for example, collects and integrates conversation data from different chat platforms. For example, it collects data from platforms such as WhatsApp, Facebook Messenger, and LINE. The chat conversation acquisition unit also converts data from different platforms into a unified format and analyzes it. For example, it unifies the data formats of each platform and generates emotional expressions. The chat conversation acquisition unit also generates a wider variety of emotional expressions based on data from different platforms. For example, it generates emotional expressions that correspond to different cultures and languages. In this way, by integrating conversation data from different chat platforms, a wider variety of emotional expressions can be generated.

[0033] In order to improve the accuracy of emotional expressions, the emotion conversion unit can learn the user's individual emotional history and generate personalized emotional expressions. The emotion conversion unit, for example, learns the user's individual emotional history and generates personalized emotional expressions. For example, it identifies emotions that the user frequently feels from past conversation history and generates emotional expressions based on the emotions. The emotion conversion unit also analyzes the user's emotional history and generates appropriate emotional expressions. For example, it analyzes the user's emotional patterns and generates personalized emotional expressions. The emotion conversion unit also customizes emotional expressions based on the user's emotional history. For example, it generates emotional expressions according to the user's preferences. In this way, personalized emotional expressions can be generated by learning the user's individual emotional history.

[0034] The emotion conversion unit can automatically translate emotional expressions into different languages ​​to accommodate international users. The emotion conversion unit, for example, automatically translates emotional expressions into different languages. For example, an emotional expression generated from a conversation such as "I had so much fun today!" is translated into English or French. The emotion conversion unit also generates emotional expressions corresponding to different languages. For example, it generates emotional expressions corresponding to languages ​​such as English, Japanese, and Chinese. The emotion conversion unit also generates emotional expressions that take cultural backgrounds into consideration to accommodate international users. For example, it generates appropriate emotional expressions taking into consideration differences in emotional expressions in different cultures. In this way, international users can be accommodated by automatically translating emotional expressions into different languages.

[0035] The emotion conversion unit converts the emotion expression into a visual note or a mind map to make it easier to understand visually. The emotion conversion unit, for example, converts the emotion expression into a visual note. For example, the emotion expression generated from the conversation, "I had so much fun today!" is displayed using diagrams or icons. The emotion conversion unit also converts the emotion expression into a mind map. For example, it generates a mind map that visually shows the relationships between emotions. The emotion conversion unit also uses color coding and icons to make the emotion expression easier to understand visually. For example, positive emotions are displayed using bright colors and negative emotions using dark colors. In this way, converting the emotion expression into a visual note or a mind map makes it easier to understand visually.

[0036] The stamp generation unit can generate multiple stamp candidates based on an emotional expression, allowing the user to select from them. The stamp generation unit generates multiple stamp candidates based on an emotional expression, for example. For example, multiple smiling stamps are generated from the emotional expression "joy" so that the user can select from them. The stamp generation unit also generates stamps with different designs. For example, stamps of different styles are generated for the same emotional expression. The stamp generation unit also displays the stamp candidates so that the user can select from them. For example, the generated stamp candidates are displayed in a list so that the user can select from them. In this way, multiple stamp candidates are generated, allowing the user to select from them.

[0037] The stamp generation unit can expand the learning dataset for the generation AI and generate stamps that correspond to a wider variety of emotional expressions. The stamp generation unit, for example, expands the learning dataset for the generation AI and generates stamps that correspond to a wider variety of emotional expressions. For example, it generates stamps that correspond to emotional expressions such as joy, sadness, and surprise. The stamp generation unit also generates new stamps based on the learning dataset. For example, it generates stamps that correspond to new emotional expressions. The stamp generation unit also periodically updates the learning dataset and generates stamps that correspond to the latest emotional expressions. For example, it adds new emotional data and increases the variety of stamps. In this way, by expanding the learning dataset, stamps that correspond to a wider variety of emotional expressions can be generated.

[0038] The stamp generation unit can animate the generated stamps to provide dynamic emotional expressions. For example, the stamp generation unit animates the generated stamps to provide dynamic emotional expressions. For example, the stamp generation unit animates a smiling stamp generated from the emotional expression "joy." The stamp generation unit also uses technology for generating animated stamps. For example, the stamps are animated using frame animation or motion graphics. The stamp generation unit also adjusts the movement of the stamps to provide dynamic emotional expressions. For example, the movement of the stamps is changed depending on the intensity of the emotion. This makes it possible to express dynamic emotions by animating the stamps.

[0039] The stamp generation unit can ensure compatibility of stamps between different devices, allowing users to use them on any device. The stamp generation unit, for example, ensures compatibility of stamps between different devices. For example, it enables stamps to be used on devices such as smartphones, tablets, and PCs. The stamp generation unit also standardizes data formats to ensure compatibility between devices. For example, it standardizes the data format of stamps to enable display on different devices. The stamp generation unit also performs compatibility tests to check operation on different devices. For example, it tests the display and operation of stamps on each device. This ensures compatibility between different devices, allowing users to use stamps on any device.

[0040] The stamp generation unit can provide a function that allows the generated stamp to be customized to suit the user's preferences. The stamp generation unit provides a function that allows the generated stamp to be customized to suit the user's preferences, for example, by allowing the color or shape of the stamp to be changed. The stamp generation unit also adjusts the stamp design according to the user's preferences. For example, the stamp is generated based on the color or shape selected by the user. The stamp generation unit also saves the customized stamp so that it can be reused. For example, the stamp customized by the user can be saved so that it can be reused later. This allows the stamp to be customized to suit the user's preferences, providing a more personalized experience.

[0041] The stamp generation unit can analyze the stamp usage history and prioritize displaying stamps that the user uses frequently. The stamp generation unit, for example, analyzes the stamp usage history and prioritizes displaying stamps that the user uses frequently. For example, based on the usage history for the past week, frequently used stamps are displayed preferentially. The stamp generation unit also adjusts the display order of stamps based on the usage history. For example, stamps that are used more frequently are displayed at the top. The stamp generation unit also suggests stamps based on the usage history. For example, new stamps related to stamps that the user uses frequently are suggested. In this way, by analyzing the stamp usage history, it is possible to prioritize displaying stamps that the user uses frequently.

[0042] The stamp generation unit can make stamps usable on other chat applications and social networking platforms. For example, the stamp generation unit makes stamps usable on other chat applications and social networking platforms. For example, the stamp generation unit makes stamps usable on platforms such as WhatsApp, Facebook Messenger, and LINE. The stamp generation unit also adjusts the data format of the stamps to ensure compatibility with other platforms. For example, the stamp generation unit generates stamps compatible with the data format of each platform. The stamp generation unit also provides a method for using the stamps on other platforms. For example, the stamp generation unit provides a stamp import and export function. This allows the stamps to be used on other chat applications and social networking platforms, thereby improving user convenience.

[0043] The stamp generation unit may provide the stamp generation process as an open API, allowing other developers to generate their own stamps. The stamp generation unit may, for example, provide the stamp generation process as an open API, allowing other developers to generate their own stamps. For example, the stamp generation unit may allow developers to generate stamps in their own applications. The stamp generation unit may also provide a method for generating stamps through the open API. For example, the stamp generation unit may provide an API endpoint and an authentication method. The stamp generation unit may also allow other developers to share the stamps they have generated. For example, the stamp generation unit may provide a stamp sharing platform. By providing the stamp generation process as an open API, other developers may be able to generate their own stamps.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The stamp generation system can further include a health condition acquisition unit that monitors the user's health condition. For example, the system can measure the user's heart rate and stress level and generate appropriate stamps based on the results. If the user's heart rate is high, a stamp encouraging relaxation can be generated, and if the stress level is high, a stamp encouraging encouragement can be generated. The health condition acquisition unit can also analyze the user's sleep patterns and generate a stamp encouraging rest if the user is sleep deprived. This allows for more personalized communication by providing stamps that correspond to the user's health condition.

[0046] The stamp generation system can further include an interest analysis unit that analyzes the user's hobbies and interests. For example, if the user is interested in sports, sports-related stamps can be generated. If the user is interested in music, music-related stamps can be generated. The interest analysis unit can also analyze the content posted by the user on social media and generate stamps based on topics of interest. This allows for more personalized communication by providing stamps that match the user's hobbies and interests.

[0047] The stamp generation system can further include a location information acquisition unit that acquires the user's location information. For example, if the user is traveling, a stamp related to the travel destination can be generated. If the user is participating in a specific event, a stamp related to the event can be generated. The location information acquisition unit can also generate region-specific stamps based on the user's current location. This allows for more context-appropriate communication by providing stamps according to the user's location information.

[0048] The stamp generation system can further include a calendar acquisition unit that acquires the user's calendar information. For example, based on the user's schedule, it can generate stamps of encouragement before a meeting and stamps encouraging relaxation during vacations. The calendar acquisition unit can also keep track of the user's birthdays and anniversaries and generate stamps related to special days. This allows for more timely communication by providing stamps that match the user's schedule.

[0049] The sticker generation system may further include a purchase history analysis unit that analyzes a user's purchase history. For example, stickers related to products recently purchased by the user may be generated. If the user has a preference for a particular brand, stickers related to that brand may be generated. The purchase history analysis unit may also analyze the user's purchasing patterns and generate stickers related to specific events (e.g., sale periods). This allows for more personalized communication by providing stickers based on the user's purchase history.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The chat conversation acquisition unit acquires chat conversations. For example, it acquires the contents of text chats. The chat conversation acquisition unit can also acquire voice chat contents by converting them into text. It can also acquire video chat contents by analyzing them. Specifically, the contents of text chats are acquired directly from the chat application, the contents of voice chats are converted into text using voice recognition technology, and the contents of video chats are converted into text using video analysis technology. Step 2: The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into emotional expressions. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze the conversation content and generate emotional expressions. It can also use a multimodal generation AI to analyze the conversation content and generate emotional expressions. The generation AI refers to relevant background information and topic models to understand the context of the conversation and generate appropriate emotional expressions. Step 3: The stamp generation unit generates stamps based on the emotional expression converted by the emotion conversion unit. For example, still image stamps or animated stamps can be generated based on the emotional expression. It is also possible to generate multiple stamp candidates and allow the user to select one. This allows the user to select stamps with different designs and that express different emotions.

[0052] (Example 2) The stamp generation system according to an embodiment of the present invention automatically acquires chat conversations, converts them into emotional expressions using a generation AI, and generates stamps based on those emotional expressions. This allows the stamp generation system to extract appropriate emotional expressions based on the user's chat conversations and generate stamps based on those emotional expressions, thereby supporting user communication.

[0053] The stamp generation system according to the embodiment includes a chat conversation acquisition unit, an emotion conversion unit, and a stamp generation unit. The chat conversation acquisition unit acquires chat conversations. For example, it acquires text chat content. The chat conversation acquisition unit can also acquire voice chat content by converting it into text. The chat conversation acquisition unit can also acquire video chat content by analyzing it. For example, text chat content is acquired directly from a chat application. Voice chat content is converted into text using speech recognition technology. Video chat content is converted into text using video analysis technology. The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into an emotion expression. For example, the generation AI analyzes the conversation content using a text generation AI (e.g., LLM) and generates an emotion expression. The generation AI can also analyze the conversation content and generate an emotion expression using a multimodal generation AI. The generation AI can also understand the context of the conversation and generate appropriate emotion expressions. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI refers to relevant background information and topic models to understand the context of the conversation and generate appropriate emotional expressions. The stamp generation unit generates stamps based on the emotional expressions converted by the emotion conversion unit. For example, the stamp generation unit generates still image stamps based on the emotional expressions. The stamp generation unit can also generate animated stamps based on the emotional expressions. The stamp generation unit can also generate multiple stamp candidates based on the emotional expressions and allow the user to select one. For example, the stamp generation unit generates a smiling stamp based on the emotional expressions. Animated stamps provide dynamic emotional expressions based on the emotional expressions. The multiple stamp candidates generate stamps expressing different designs and emotions and allow the user to select one. As a result, the stamp generation system according to the embodiment can support user communication by extracting appropriate emotional expressions based on the user's chat conversation and generating stamps based on the emotional expressions.For example, the output unit provides the generated stamp to the user through a chat application or a social networking service (SNS) platform. The user can use the generated stamp in the chat application. Using the stamp on the SNS platform allows the user to share the stamp with other users. Sending the stamp via email allows the user to send the stamp directly to other users, providing quick communication.

[0054] The emotion conversion unit can extract multiple emotions from a conversation and generate a composite emotional expression. The emotion conversion unit, for example, simultaneously extracts multiple emotions from a conversation. For example, a composite emotion of "joy" and "fatigue" is generated from a conversation such as "I had a lot of fun today, but I'm a little tired." The emotion conversion unit also generates a composite emotional expression that combines multiple emotions. For example, a composite emotion of "joy" and "surprise" is generated. The emotion conversion unit also analyzes multiple emotions and generates an appropriate composite emotional expression. For example, a composite emotion of "joy" and "gratitude" is generated. This allows multiple emotions to be expressed simultaneously, making it possible to express emotions with greater precision.

[0055] The chat conversation acquisition unit can analyze conversations in real time and track changes in emotions sequentially. For example, the chat conversation acquisition unit analyzes conversations in real time and calculates an emotion score for each message. For example, if a user says, "I had a lot of fun today!" and then continues, "But I'm a little tired," the first message is assigned a high joy score and the next message is assigned a fatigue score. The chat conversation acquisition unit also tracks changes in emotions sequentially. For example, it records changes in emotions along the flow of the conversation and analyzes the transition of emotions. The chat conversation acquisition unit also analyzes changes in emotions in real time and generates appropriate emotional expressions. For example, it understands the context of the conversation and generates emotional expressions according to changes in emotions. In this way, by tracking changes in emotions in real time, more accurate emotional expressions can be generated.

[0056] The chat conversation acquisition unit can refer to past conversation history and take into account long-term emotional trends. The chat conversation acquisition unit, for example, refers to past conversation history and analyzes the user's long-term emotional trends. For example, based on the conversation history for the past week, it identifies emotions that the user frequently feels. The chat conversation acquisition unit also takes long-term emotional trends into account. For example, it analyzes the user's emotional patterns from the past conversation history and generates appropriate emotional expressions. The chat conversation acquisition unit also predicts emotional changes based on the past conversation history. For example, it analyzes past emotional data and predicts future emotional changes. In this way, by referring to the past conversation history, it is possible to generate emotional expressions that take into account long-term emotional trends.

[0057] The chat conversation acquisition unit can estimate the user's emotion in real time using the emotion estimation function and filter conversation input based on the estimation result. The chat conversation acquisition unit, for example, uses the emotion estimation function to estimate the user's emotion in real time. For example, it estimates the emotion when the user inputs a positive message such as "I had a lot of fun today!". The chat conversation acquisition unit also filters the conversation input based on the emotion estimation result. For example, it filters messages containing negative emotions and processes positive messages preferentially. The chat conversation acquisition unit also generates an appropriate emotional expression based on the emotion estimation result. For example, it generates an emotional expression corresponding to the user's emotion based on the emotion estimation result. In this way, by using the emotion estimation function, filtering based on the user's emotion becomes possible.

[0058] The chat conversation acquisition unit can also analyze the content of voice input and video chat to generate multimodal emotional expressions. For example, the chat conversation acquisition unit analyzes voice input and infers emotions from the voice tone and pitch. For example, if a user says in a bright tone, "I had a lot of fun today!", the emotion of joy is highly evaluated. The chat conversation acquisition unit also analyzes the content of video chat and infers emotions from images. For example, emotions are inferred by analyzing the user's facial expressions and gestures. The chat conversation acquisition unit also integrates the content of voice input and video chat to generate multimodal emotional expressions. For example, it analyzes both voice and image to generate a comprehensive emotional expression. In this way, more accurate emotional expressions can be generated by analyzing the content of voice input and video chat.

[0059] The chat conversation acquisition unit can integrate conversation data from different chat platforms to generate a wider variety of emotional expressions. The chat conversation acquisition unit, for example, collects and integrates conversation data from different chat platforms. For example, it collects data from platforms such as WhatsApp, Facebook Messenger, and LINE. The chat conversation acquisition unit also converts data from different platforms into a unified format and analyzes it. For example, it unifies the data formats of each platform and generates emotional expressions. The chat conversation acquisition unit also generates a wider variety of emotional expressions based on data from different platforms. For example, it generates emotional expressions that correspond to different cultures and languages. In this way, by integrating conversation data from different chat platforms, a wider variety of emotional expressions can be generated.

[0060] The chat conversation acquisition unit can use the emotion estimation function to estimate the emotion of the user when inputting in real time and make suggestions to elicit positive emotions. The chat conversation acquisition unit, for example, uses the emotion estimation function to estimate the emotion of the user when inputting in real time. For example, it estimates the emotion when the user inputs, "I had a lot of fun today!". The chat conversation acquisition unit also makes suggestions to elicit positive emotions. For example, it suggests a positive message when the user expresses negative emotions. The chat conversation acquisition unit also provides appropriate feedback to the user based on the emotion estimation result. For example, it displays a message to elicit positive emotions. In this way, better communication is possible by estimating the user's emotion in real time and making suggestions to elicit positive emotions.

[0061] In order to improve the accuracy of emotional expressions, the emotion conversion unit can learn the user's individual emotional history and generate personalized emotional expressions. The emotion conversion unit, for example, learns the user's individual emotional history and generates personalized emotional expressions. For example, it identifies emotions that the user frequently feels from past conversation history and generates emotional expressions based on the emotions. The emotion conversion unit also analyzes the user's emotional history and generates appropriate emotional expressions. For example, it analyzes the user's emotional patterns and generates personalized emotional expressions. The emotion conversion unit also customizes emotional expressions based on the user's emotional history. For example, it generates emotional expressions according to the user's preferences. In this way, personalized emotional expressions can be generated by learning the user's individual emotional history.

[0062] The emotion conversion unit can use the emotion estimation function to collect user feedback on the emotion expression conversion results and continuously improve the conversion algorithm. For example, the emotion conversion unit uses the emotion estimation function to collect user feedback on the emotion expression conversion results. For example, it evaluates whether the user is satisfied with the emotion expression generated for the conversation, "I had a lot of fun today!". The emotion conversion unit also improves the conversion algorithm based on the collected feedback. For example, it analyzes the user feedback and improves the accuracy of the emotion expression. The emotion conversion unit also adjusts the emotion expression generation method based on the feedback. For example, it generates an emotion expression according to the user's preferences. In this way, the conversion algorithm is improved based on the user feedback, thereby improving the accuracy of the emotion expression.

[0063] The emotion conversion unit can automatically translate emotional expressions into different languages ​​to accommodate international users. The emotion conversion unit, for example, automatically translates emotional expressions into different languages. For example, an emotional expression generated from a conversation such as "I had so much fun today!" is translated into English or French. The emotion conversion unit also generates emotional expressions corresponding to different languages. For example, it generates emotional expressions corresponding to languages ​​such as English, Japanese, and Chinese. The emotion conversion unit also generates emotional expressions that take cultural backgrounds into consideration to accommodate international users. For example, it generates appropriate emotional expressions taking into consideration differences in emotional expressions in different cultures. In this way, international users can be accommodated by automatically translating emotional expressions into different languages.

[0064] The emotion conversion unit converts the emotion expression into a visual note or a mind map to make it easier to understand visually. The emotion conversion unit, for example, converts the emotion expression into a visual note. For example, the emotion expression generated from the conversation, "I had so much fun today!" is displayed using diagrams or icons. The emotion conversion unit also converts the emotion expression into a mind map. For example, it generates a mind map that visually shows the relationships between emotions. The emotion conversion unit also uses color coding and icons to make the emotion expression easier to understand visually. For example, positive emotions are displayed using bright colors and negative emotions using dark colors. In this way, converting the emotion expression into a visual note or a mind map makes it easier to understand visually.

[0065] The emotion conversion unit uses the emotion estimation function to collect the user's emotional reactions to the emotional expressions, and can improve the accuracy of the emotional expressions based on the collected emotional reactions. The emotion conversion unit, for example, uses the emotion estimation function to collect the user's emotional reactions to the emotional expressions in real time. For example, the emotion conversion unit collects reactions to the emotional expressions generated in response to a user's conversation such as, "I had a lot of fun today!" The emotion conversion unit also improves the accuracy of the emotional expressions based on the collected emotional reactions. For example, the emotion conversion unit analyzes the user's emotional reactions and improves the method for generating the emotional expressions. The emotion conversion unit also adjusts the emotional expressions based on the emotional reactions. For example, the emotion conversion unit generates an emotional expression according to the user's preferences. In this way, the accuracy of the emotional expressions is improved by collecting the user's emotional reactions.

[0066] The stamp generation unit can generate multiple stamp candidates based on an emotional expression, allowing the user to select from them. The stamp generation unit generates multiple stamp candidates based on an emotional expression, for example. For example, multiple smiling stamps are generated from the emotional expression "joy" so that the user can select from them. The stamp generation unit also generates stamps with different designs. For example, stamps of different styles are generated for the same emotional expression. The stamp generation unit also displays the stamp candidates so that the user can select from them. For example, the generated stamp candidates are displayed in a list so that the user can select from them. In this way, multiple stamp candidates are generated, allowing the user to select from them.

[0067] The stamp generation unit can expand the learning dataset for the generation AI and generate stamps that correspond to a wider variety of emotional expressions. The stamp generation unit, for example, expands the learning dataset for the generation AI and generates stamps that correspond to a wider variety of emotional expressions. For example, it generates stamps that correspond to emotional expressions such as joy, sadness, and surprise. The stamp generation unit also generates new stamps based on the learning dataset. For example, it generates stamps that correspond to new emotional expressions. The stamp generation unit also periodically updates the learning dataset and generates stamps that correspond to the latest emotional expressions. For example, it adds new emotional data and increases the variety of stamps. In this way, by expanding the learning dataset, stamps that correspond to a wider variety of emotional expressions can be generated.

[0068] The stamp generation unit uses the emotion estimation function to collect users' emotional reactions to the generated stamps, and can continuously improve the generation algorithm. The stamp generation unit, for example, uses the emotion estimation function to collect users' emotional reactions to the generated stamps. For example, it evaluates how a user reacts to a smiling stamp generated from the emotional expression of "joy." The stamp generation unit also improves the generation algorithm based on the collected emotional reactions. For example, it analyzes users' emotional reactions and improves the stamp generation method. The stamp generation unit also adjusts the stamp design based on the emotional reactions. For example, it generates stamps according to the user's preferences. In this way, the generation algorithm can be continuously improved by collecting users' emotional reactions.

[0069] The stamp generation unit can animate the generated stamps to provide dynamic emotional expressions. For example, the stamp generation unit animates the generated stamps to provide dynamic emotional expressions. For example, the stamp generation unit animates a smiling stamp generated from the emotional expression "joy." The stamp generation unit also uses technology for generating animated stamps. For example, the stamps are animated using frame animation or motion graphics. The stamp generation unit also adjusts the movement of the stamps to provide dynamic emotional expressions. For example, the movement of the stamps is changed depending on the intensity of the emotion. This makes it possible to express dynamic emotions by animating the stamps.

[0070] The stamp generation unit can ensure compatibility of stamps between different devices, allowing users to use them on any device. The stamp generation unit, for example, ensures compatibility of stamps between different devices. For example, it enables stamps to be used on devices such as smartphones, tablets, and PCs. The stamp generation unit also standardizes data formats to ensure compatibility between devices. For example, it standardizes the data format of stamps to enable display on different devices. The stamp generation unit also performs compatibility tests to check operation on different devices. For example, it tests the display and operation of stamps on each device. This ensures compatibility between different devices, allowing users to use stamps on any device.

[0071] The stamp generation unit uses the emotion estimation function to monitor the user's emotional reaction to the generated stamps in real time, and can continuously provide optimal stamps. The stamp generation unit, for example, uses the emotion estimation function to monitor the user's emotional reaction to the generated stamps in real time. For example, it evaluates how the user reacts to a smiling stamp generated from the emotional expression of "joy." The stamp generation unit also provides optimal stamps based on the emotional reactions collected in real time. For example, it adjusts the stamp design according to the user's emotional reaction. The stamp generation unit also improves the method of providing stamps based on the emotional reaction. For example, it preferentially displays stamps that match the user's preferences. In this way, by monitoring the user's emotional reactions in real time, it is possible to continuously provide optimal stamps.

[0072] The stamp generation unit can provide a function that allows the generated stamp to be customized to suit the user's preferences. The stamp generation unit provides a function that allows the generated stamp to be customized to suit the user's preferences, for example, by allowing the color or shape of the stamp to be changed. The stamp generation unit also adjusts the stamp design according to the user's preferences. For example, the stamp is generated based on the color or shape selected by the user. The stamp generation unit also saves the customized stamp so that it can be reused. For example, the stamp customized by the user can be saved so that it can be reused later. This allows the stamp to be customized to suit the user's preferences, providing a more personalized experience.

[0073] The stamp generation unit can analyze the stamp usage history and prioritize displaying stamps that the user uses frequently. The stamp generation unit, for example, analyzes the stamp usage history and prioritizes displaying stamps that the user uses frequently. For example, based on the usage history for the past week, frequently used stamps are displayed preferentially. The stamp generation unit also adjusts the display order of stamps based on the usage history. For example, stamps that are used more frequently are displayed at the top. The stamp generation unit also suggests stamps based on the usage history. For example, new stamps related to stamps that the user uses frequently are suggested. In this way, by analyzing the stamp usage history, it is possible to prioritize displaying stamps that the user uses frequently.

[0074] The stamp generation unit can make stamps usable on other chat applications and social networking platforms. For example, the stamp generation unit makes stamps usable on other chat applications and social networking platforms. For example, the stamp generation unit makes stamps usable on platforms such as WhatsApp, Facebook Messenger, and LINE. The stamp generation unit also adjusts the data format of the stamps to ensure compatibility with other platforms. For example, the stamp generation unit generates stamps compatible with the data format of each platform. The stamp generation unit also provides a method for using the stamps on other platforms. For example, the stamp generation unit provides a stamp import and export function. This allows the stamps to be used on other chat applications and social networking platforms, thereby improving user convenience.

[0075] The stamp generation unit may provide the stamp generation process as an open API, allowing other developers to generate their own stamps. The stamp generation unit may, for example, provide the stamp generation process as an open API, allowing other developers to generate their own stamps. For example, the stamp generation unit may allow developers to generate stamps in their own applications. The stamp generation unit may also provide a method for generating stamps through the open API. For example, the stamp generation unit may provide an API endpoint and an authentication method. The stamp generation unit may also allow other developers to share the stamps they have generated. For example, the stamp generation unit may provide a stamp sharing platform. By providing the stamp generation process as an open API, other developers may be able to generate their own stamps.

[0076] The stamp generation unit can use the emotion estimation function to analyze the user's emotional tendency based on the stamp usage status and provide personalized stamps. The stamp generation unit, for example, uses the emotion estimation function to analyze the user's emotional tendency based on the stamp usage status. For example, if the user frequently uses the "joy" stamp, it is analyzed that the user has a strong emotional tendency of joy. The stamp generation unit also provides personalized stamps based on the emotional tendency. For example, it generates stamps according to the user's emotional tendency. The stamp generation unit also adjusts the stamp design based on the user's emotional tendency. For example, it generates stamps according to the user's preferences. In this way, personalized stamps can be provided by analyzing the user's emotional tendency.

[0077] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0078] The stamp generation system can further include a health condition acquisition unit that monitors the user's health condition. For example, the system can measure the user's heart rate and stress level and generate appropriate stamps based on the results. If the user's heart rate is high, a stamp encouraging relaxation can be generated, and if the stress level is high, a stamp encouraging encouragement can be generated. The health condition acquisition unit can also analyze the user's sleep patterns and generate a stamp encouraging rest if the user is sleep deprived. This allows for more personalized communication by providing stamps that correspond to the user's health condition.

[0079] The stamp generation system can further include an interest analysis unit that analyzes the user's hobbies and interests. For example, if the user is interested in sports, sports-related stamps can be generated. If the user is interested in music, music-related stamps can be generated. The interest analysis unit can also analyze the content posted by the user on social media and generate stamps based on topics of interest. This allows for more personalized communication by providing stamps that match the user's hobbies and interests.

[0080] The stamp generation system can further include a location information acquisition unit that acquires the user's location information. For example, if the user is traveling, a stamp related to the travel destination can be generated. If the user is participating in a specific event, a stamp related to the event can be generated. The location information acquisition unit can also generate region-specific stamps based on the user's current location. This allows for more context-appropriate communication by providing stamps according to the user's location information.

[0081] The stamp generation system can further include a calendar acquisition unit that acquires the user's calendar information. For example, based on the user's schedule, it can generate stamps of encouragement before a meeting and stamps encouraging relaxation during vacations. The calendar acquisition unit can also keep track of the user's birthdays and anniversaries and generate stamps related to special days. This allows for more timely communication by providing stamps that match the user's schedule.

[0082] The sticker generation system may further include a purchase history analysis unit that analyzes a user's purchase history. For example, stickers related to products recently purchased by the user may be generated. If the user has a preference for a particular brand, stickers related to that brand may be generated. The purchase history analysis unit may also analyze the user's purchasing patterns and generate stickers related to specific events (e.g., sale periods). This allows for more personalized communication by providing stickers based on the user's purchase history.

[0083] The stamp generation system can further include a music recommendation unit that estimates the user's emotions and recommends music based on those emotions. For example, if the user expresses the emotion "I had a lot of fun today!", music that matches the user's happy mood can be recommended. Also, if the user expresses the emotion "I'm a little tired," relaxing music can be recommended. This allows for a richer communication experience by providing music that matches the user's emotions.

[0084] The stamp generation system can further include a feedback providing unit that estimates the user's emotions and provides feedback based on those emotions. For example, if the user expresses the emotion "I had a lot of fun today!", positive feedback can be provided. On the other hand, if the user expresses the emotion "I'm a little tired," encouraging feedback can be provided. This allows for better communication by providing feedback according to the user's emotions.

[0085] The stamp generation system can further include an action suggestion unit that estimates the user's emotions and suggests appropriate actions based on those emotions. For example, if the user expresses the emotion "I had so much fun today!", it can suggest sharing with friends. Also, if the user expresses the emotion "I'm a little tired," it can suggest taking a rest. This allows for more appropriate communication by suggesting actions according to the user's emotions.

[0086] The stamp generation system can further include a content recommendation unit that estimates the user's emotions and recommends appropriate content based on those emotions. For example, if the user expresses the emotion, "I had a lot of fun today!", it can recommend fun videos and articles. Or, if the user expresses the emotion, "I'm a little tired," it can recommend relaxing content. This allows for a richer communication experience by providing content that matches the user's emotions.

[0087] The stamp generation system can further include an activity suggestion unit that estimates the user's emotions and suggests appropriate activities based on those emotions. For example, if the user expresses the emotion, "I had so much fun today!", an outdoor activity can be suggested. Also, if the user expresses the emotion, "I'm a little tired," a relaxing activity can be suggested. This allows for more appropriate communication by suggesting activities that match the user's emotions.

[0088] The processing flow of the second embodiment will be briefly explained below.

[0089] Step 1: The chat conversation acquisition unit acquires chat conversations. For example, it acquires the contents of text chats. The chat conversation acquisition unit can also acquire voice chat contents by converting them into text. It can also acquire video chat contents by analyzing them. Specifically, the contents of text chats are acquired directly from the chat application, the contents of voice chats are converted into text using voice recognition technology, and the contents of video chats are converted into text using video analysis technology. Step 2: The emotion conversion unit converts the conversation acquired by the chat conversation acquisition unit into emotional expressions. For example, the generation AI uses a text generation AI (e.g., LLM) to analyze the conversation content and generate emotional expressions. It can also use a multimodal generation AI to analyze the conversation content and generate emotional expressions. The generation AI refers to relevant background information and topic models to understand the context of the conversation and generate appropriate emotional expressions. Step 3: The stamp generation unit generates stamps based on the emotional expression converted by the emotion conversion unit. For example, still image stamps or animated stamps can be generated based on the emotional expression. It is also possible to generate multiple stamp candidates and allow the user to select one. This allows the user to select stamps with different designs and that express different emotions.

[0090] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0091] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0092] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0093] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0094] 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.

[0095] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0096] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0097] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0098] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0099] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0100] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0101] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0102] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0103] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0104] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0105] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0108] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0109] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0110] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0118] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0119] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0124] 7, a 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.

[0125] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0131] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0133] The storage 32 stores a data generation model 58 and an 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 emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0134] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0135] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0137] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0140] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0141] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0142] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0143] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0144] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0145] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0146] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0147] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0148] 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.

[0149] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0150] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0151] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0152] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0153] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0154] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0155] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0156] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0157] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a chat conversation acquisition unit that acquires chat conversations; an emotion conversion unit that converts the conversation acquired by the chat conversation acquisition unit into an emotional expression; a stamp generation unit that generates stamps based on the emotional expressions converted by the emotion conversion unit. A system characterized by:

2. The chat conversation acquisition unit The conversation is analyzed in real time to track changes in emotions.

2. The system of claim 1.

3. The emotion conversion unit To improve the accuracy of emotional expressions, the system learns the user's individual emotional history and generates personalized emotional expressions.

2. The system of claim 1.

4. The stamp generation unit Based on the emotional expression, multiple stamp candidates are generated and the user can select one.

2. The system of claim 1.

5. The chat conversation acquisition unit Estimate the user's emotions in real time and filter conversational input based on the estimation results.

2. The system of claim 1.

Images