System

Abstract

To provide a system according to an embodiment for conveying a nuance including emotion to a deaf person by converting a sound into a sign language.SOLUTION: A system according to an embodiment, comprises a reception part, an analysis part, a sign language conversion part, and a character expression part. The reception part receives a sound. The analysis part analyzes the sound received by the reception part, and recognizes an emotion. The sign language conversion part converts the sound into a sign language on the basis of the emotion recognized by the analysis part. The character expression part expresses the sign language converted by the sign language conversion part so as to be put to a character on a screen.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, there was no established technology for converting speech into sign language, making it difficult to convey nuances, including emotions, to deaf people.

[0005] The system according to the embodiment aims to convert speech into sign language and convey nuances, including emotions, to deaf people. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a sign language conversion unit, and a character representation unit. The reception unit receives voice. The analysis unit analyzes the voice received by the reception unit and identifies emotions. The sign language conversion unit converts the voice into sign language based on the emotions identified by the analysis unit. The character representation unit represents the sign language converted by the sign language conversion unit by displaying it on a character on a screen. Effect of the Invention

[0007] The system according to the embodiment can convert speech into sign language and convey nuances, including emotions, to deaf people. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the 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 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention receives speech as input, uses a generation AI to identify emotional expressions such as joy, anger, sadness, and happiness conveyed from the speech, and outputs them in sign language. This system was born from the background that while the technology for transcribing speech is established, there is no technology for converting speech into sign language. Sign language can more effectively convey nuances and emotions that are difficult to express in print, so it can provide expressions that have been difficult to convey to deaf people until now. For example, if a speaker says "This project is very important" during a remote meeting, the generation AI identifies the emotion "important" from the speech and expresses it in sign language. The character on the screen expresses "important" in sign language, so that the emotion is conveyed to deaf people. This system makes it possible to provide information including emotional expressions to deaf people, improving the quality of communication. In addition, by utilizing sign language, expressions that have been difficult to convey until now can be conveyed more effectively. As a result, the system receives speech as input, uses a generation AI to identify emotional expressions conveyed from speech, and outputs them in sign language.

[0029] The system according to the embodiment includes a reception unit, an analysis unit, a sign language conversion unit, and a character representation unit. The reception unit receives voice. The voice includes, for example, spoken words, music, and environmental sounds, but is not limited to such examples. The reception unit can receive, for example, voice during a remote conference. The analysis unit uses a generation AI to analyze the voice received by the reception unit and identify emotions. The emotions include, for example, joy, sadness, anger, but are not limited to such examples. The generation AI identifies emotions from the voice using a text generation AI (for example, LLM) or a multimodal generation AI. The sign language conversion unit converts into sign language based on the emotions identified by the analysis unit using the generation AI. The sign language includes, for example, Japanese Sign Language, American Sign Language, etc., but is not limited to such examples. The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on a screen. The character includes, for example, an animation character, a 3D model, etc., but is not limited to such examples. As a result, the system according to the embodiment can convert speech into sign language and provide information including emotional expressions to deaf people.

[0030] The reception unit receives voice. The voice includes, but is not limited to, spoken words, music, and environmental sounds. The reception unit can receive, for example, voice during a remote conference. Specifically, the reception unit captures surrounding voice with high accuracy using a high-sensitivity microphone or a voice input device. This allows clear collection of voice, improving the processing accuracy in the subsequent analysis unit. Furthermore, the reception unit is equipped with noise canceling technology, which can effectively remove environmental sounds and background noise. This allows spoken words and important voice information to be clearly collected. The reception unit converts the voice data into a digital signal in real time and transmits it to the analysis unit. For example, when receiving voice during a remote conference, real-time emotion analysis is possible by sequentially capturing the remarks of the conference participants and transmitting them to the analysis unit. Furthermore, the reception unit also simultaneously collects metadata of the voice data (for example, the identification information of the speaker, the time of speech, etc.) and provides them to the analysis unit. This allows the analysis unit to perform analysis taking into account the context of the voice data and the characteristics of the speaker. The reception unit supports multiple voice input devices and can integrate and process voice data from different devices. For example, it centrally manages data from multiple microphones in a conference room and from the voice input devices of remote participants and provides it to the analysis unit. This allows the reception unit to efficiently collect data from various voice sources and improve the performance of the entire system.

[0031] The analysis unit uses the generation AI to analyze the voice received by the reception unit and identify the emotion. The emotion includes, for example, joy, sadness, anger, etc., but is not limited to such examples. The generation AI uses a text generation AI (for example, LLM) or a multimodal generation AI to identify the emotion from the voice. Specifically, the analysis unit converts the voice data into text using a voice recognition technology, and inputs the text data to the generation AI. The generation AI analyzes voice characteristics such as intonation, speed, and strength of the voice to identify the emotion. For example, if the voice has a high intonation and a fast speed, it is identified as "joy," and if the voice is low and the speed is identified as "sadness." The generation AI also identifies the emotion by taking into account the context and content of the voice data. For example, if the content of the statement is positive, it is identified as "joy," and if it is negative, it is identified as "sadness." Furthermore, the analysis unit improves the accuracy of emotion identification by using a generation AI model that has learned past voice data and emotion data. As a result, the analysis unit can identify emotions from the voice data with high accuracy and provide them to the sign language conversion unit. The analysis unit analyzes the voice data in real time and immediately transmits the emotion identification results to the sign language conversion unit. This improves the response speed of the entire system and enables quick feedback to be provided to the user. Furthermore, the analysis unit can accumulate the emotion identification results and analyze long-term emotion trends. This makes it possible to continuously monitor changes in the user's emotional state and take appropriate measures.

[0032] The sign language conversion unit converts the emotion identified by the analysis unit into sign language using the generation AI. The sign language includes, but is not limited to, Japanese Sign Language and American Sign Language. Specifically, the sign language conversion unit receives the emotion identification result and text data provided by the analysis unit as input, and converts the emotion into a sign language expression using the generation AI. The generation AI converts the text data into sign language using a model that has learned the grammar and expression method of sign language. For example, when the emotion "joy" is identified, the generation AI generates a sign language action that expresses "joy" and constructs a sign language sentence based on the content of the text data. The sign language conversion unit outputs the generated sign language action as animation data and provides it to the character expression unit. Furthermore, the sign language conversion unit supports multiple sign languages ​​and can select an appropriate sign language according to the user's settings. For example, the sign language conversion unit provides Japanese Sign Language to a user who uses Japanese Sign Language and American Sign Language to a user who uses American Sign Language. The sign language conversion unit periodically updates the learning data of the generation AI and incorporates new sign language expressions and grammar rules, so that it can always provide the latest sign language expressions. This allows the sign language conversion unit to provide the user with accurate and natural sign language expressions, facilitating smooth communication. Furthermore, the sign language conversion unit can collect user feedback and continuously improve the accuracy and naturalness of sign language expressions. This allows the sign language conversion unit to flexibly respond to user needs, improving the reliability of the entire system and user satisfaction.

[0033] The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on the screen. The character includes, but is not limited to, an animated character, a 3D model, and the like. Specifically, the character representation unit moves the character on the screen based on the animation data provided by the sign language conversion unit. The character representation unit generates the character's movements in real time and visually provides the sign language to the user. For example, the animated character finely controls the movement of the joints and the changes in facial expression in order to naturally express the sign language movements. This allows the user to accurately understand the sign language movements. The character representation unit can customize the appearance and style of the character according to the user's settings. For example, the user can select the character's clothing, hairstyle, facial expression, and the like to create a character of his or her own preference. Furthermore, the character representation unit can display multiple characters simultaneously and can express multiple speakers and different sign languages ​​simultaneously. This allows the character representation unit to handle complex communication scenarios and provide the user with a variety of sign language expressions. The character representation unit can collect user feedback and continuously improve the accuracy of the character's movements and expressions. This allows the character representation unit to provide high-quality sign language expressions to users and facilitate smooth communication. Furthermore, the character representation unit can link with other systems and devices to provide sign language expressions on a variety of platforms. For example, sign language expressions can be displayed on devices such as smartphones, tablets, and personal computers, allowing users to use sign language anywhere. This allows the character representation unit to improve user convenience and contribute to the spread of sign language communication.

[0034] The analysis unit can identify emotions from the voice. The analysis unit identifies emotions from the voice using a generation AI. Emotions include, but are not limited to, for example, joy, sadness, and anger. The generation AI identifies emotions from the voice using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI receives voice data as input, analyzes the characteristics of the voice, and identifies emotions. The generation AI can analyze characteristics such as tone, pitch, and rhythm of the voice to identify emotions. This improves the accuracy of sign language conversion by identifying emotions from voice.

[0035] The sign language conversion unit can convert into sign language based on the identified emotion. The sign language conversion unit converts into sign language based on the identified emotion using a generation AI. Sign languages ​​include, but are not limited to, Japanese Sign Language and American Sign Language. The generation AI converts into sign language based on emotion using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI receives the identified emotion as input and generates a sign language action. The generation AI can adjust the sign language action depending on the intensity and type of emotion. This enables sign language conversion based on emotion.

[0036] The character representation unit can express the sign language by placing it on a character on a screen. The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on a screen. The character includes, but is not limited to, for example, an animated character, a 3D model, and the like. The character representation unit applies the sign language action to the character and visually expresses it. For example, the character representation unit receives sign language action data as an input and generates a character action. The character representation unit can apply the sign language action to the character in real time and visually express it. Thereby, by expressing the sign language with a character on a screen, it is possible to visually convey emotions.

[0037] The reception unit can receive voice during a remote conference. The reception unit receives voice during a remote conference. Remote conferences include, but are not limited to, video conferences and audio conferences. The reception unit receives voice during a remote conference in real time and transmits the voice to the analysis unit. For example, the reception unit receives voice data during a remote conference as input and transmits the voice data to the analysis unit in real time. This makes it possible to convert the voice during a remote conference into sign language in real time by receiving the voice during the remote conference.

[0038] The character representation unit can represent sign language in real time. The character representation unit represents the sign language converted by the sign language conversion unit in real time. The characters include, but are not limited to, animated characters, 3D models, and the like. The character representation unit applies the sign language motion to the character in real time and visually represents it. For example, the character representation unit receives sign language motion data as input and generates character motion in real time. This allows emotions to be conveyed instantly by representing the sign language in real time.

[0039] The reception unit can automatically filter background noise when receiving voice to receive only clear voice. The reception unit uses AI to automatically filter background noise when receiving voice to receive only clear voice. Background noise includes, but is not limited to, environmental sounds, noise, and the like. For example, the reception unit analyzes surrounding noise in real time when receiving voice and extracts clear voice using noise canceling technology. In addition, the reception unit can filter noise in a specific frequency band when receiving voice to emphasize only the speaker's voice. Furthermore, the reception unit can learn background noise using AI and perform adaptive filtering. As a result, clear voice can be received by filtering background noise.

[0040] The reception unit can analyze the characteristics of the speaker's voice when receiving the voice, and create a different voice profile for each speaker. The reception unit uses AI to analyze the characteristics of the speaker's voice when receiving the voice, and create a different voice profile for each speaker. The voice profile includes, for example, tone, pitch, rhythm, etc., but is not limited to such examples. For example, the reception unit analyzes the tone and pitch of the speaker's voice when receiving the voice, and creates an individual voice profile. The reception unit can also analyze the strength and rhythm of the speaker's voice when receiving the voice, and create an individual voice profile. Furthermore, the reception unit can learn the characteristics of the speaker's voice when receiving the voice, and create a profile for improving the accuracy of future voice recognition. As a result, the accuracy of voice recognition is improved by creating a different voice profile for each speaker.

[0041] The reception unit can preferentially receive highly relevant voices in consideration of the geographical location information of the speaker when receiving the voice. The reception unit uses AI to preferentially receive highly relevant voices in consideration of the geographical location information of the speaker when receiving the voice. The geographical location information includes, but is not limited to, GPS data, IP address, and the like. For example, the reception unit acquires the speaker's current location when receiving the voice, and preferentially receives nearby voices. In addition, the reception unit can also preferentially receive voices in related areas based on the geographical location information of the speaker when receiving the voice. Furthermore, the reception unit can also preferentially analyze voices related to a specific area in consideration of the speaker's location information when receiving the voice. As a result, it is possible to preferentially receive highly relevant voices by considering the geographical location information of the speaker.

[0042] The reception unit can analyze the speaker's social media activity when receiving the voice, and preferentially receive related voice. The reception unit uses AI to analyze the speaker's social media activity when receiving the voice, and preferentially receive related voice. Social media activity includes, for example, the content of posts, the number of followers, and the like, but is not limited to such examples. For example, the reception unit analyzes the speaker's social media activity when receiving the voice, and preferentially receives voice on related topics. In addition, the reception unit can also preferentially receive related voice based on the content of the speaker's social media remarks when receiving the voice. Furthermore, the reception unit can also preferentially receive related voice in consideration of the activity of the speaker's social media followers and friends when receiving the voice. In this way, it is possible to preferentially receive related voice by analyzing social media activity.

[0043] The analysis unit can improve the accuracy of emotion identification by referring to the speaker's past speech history during voice analysis. The analysis unit uses the generation AI to improve the accuracy of emotion identification by referring to the speaker's past speech history during voice analysis. The speech history includes, for example, past conversation logs, speech records, etc., but is not limited to such examples. For example, the analysis unit improves the accuracy of identification by referring to the speaker's past speech history during voice analysis and learning emotion patterns. In addition, the analysis unit can also improve the accuracy of identification by predicting changes in emotion based on the speaker's past speech content during voice analysis. Furthermore, the analysis unit can also improve the accuracy of emotion identification by creating a database of the speaker's past speech history during voice analysis and referring to it in real time. As a result, the accuracy of emotion identification is improved by referring to the past speech history.

[0044] The analysis unit can identify emotions by analyzing the tone and pitch of the speaker's voice in detail during the voice analysis. The analysis unit uses the generation AI to analyze the tone and pitch of the speaker's voice in detail during the voice analysis to identify emotions. The tone and pitch of the voice include, but are not limited to, frequency analysis, acoustic features, and the like. For example, the analysis unit can analyze the tone of the speaker's voice in detail during the voice analysis to identify changes in emotions. The analysis unit can also analyze the pitch of the speaker's voice in detail during the voice analysis to identify the intensity of emotions. Furthermore, the analysis unit can analyze changes in the tone and pitch of the speaker's voice in real time during the voice analysis to identify emotions. As a result, the accuracy of emotion identification is improved by analyzing the tone and pitch of the voice in detail.

[0045] The analysis unit can perform emotion identification in consideration of the geographical location information of the speaker during voice analysis. The analysis unit performs emotion identification in consideration of the geographical location information of the speaker using the generation AI during voice analysis. The geographical location information includes, but is not limited to, for example, GPS data, IP address, etc. For example, the analysis unit identifies region-specific emotion expressions based on the geographical location information of the speaker during voice analysis. In addition, the analysis unit can also perform emotion identification based on a cultural background by taking into account the geographical location information of the speaker during voice analysis. Furthermore, the analysis unit can also perform emotion identification based on local events and situations by referring to the geographical location information of the speaker during voice analysis. As a result, region-specific emotion expressions can be identified by taking into account the geographical location information.

[0046] The analysis unit can improve the accuracy of emotion identification by referring to the speaker's related literature and past utterances during the voice analysis. The analysis unit uses the generation AI to improve the accuracy of emotion identification by referring to the speaker's related literature and past utterances during the voice analysis. The related literature includes, but is not limited to, academic papers, technical reports, and the like. For example, the analysis unit refers to the speaker's related literature during the voice analysis, understands the background of the emotion, and improves the identification accuracy. The analysis unit can also improve the identification accuracy by learning the emotion pattern during the voice analysis by referring to the speaker's past utterances. Furthermore, the analysis unit can improve the accuracy of emotion identification by creating a database of the speaker's related literature and past utterances during the voice analysis and referring to them in real time. As a result, the accuracy of emotion identification is improved by referring to the related literature and past utterances.

[0047] The sign language conversion unit can adjust the speed of the sign language movement according to the intensity of the identified emotion during sign language conversion. The sign language conversion unit adjusts the speed of the sign language movement according to the intensity of the identified emotion during sign language conversion using the generation AI. The intensity of the emotion includes, but is not limited to, an emotion scale, a psychological evaluation, and the like. For example, when the intensity of the emotion is high, the sign language conversion unit speeds up the sign language movement speed to emphasize the emotion. In addition, when the intensity of the emotion is low, the sign language conversion unit can also slow down the sign language movement speed to perform a gentle expression. Furthermore, the sign language conversion unit can also adjust the sign language movement speed in real time according to the intensity of the emotion. As a result, the emotion can be conveyed more accurately by adjusting the sign language movement speed according to the intensity of the emotion.

[0048] The sign language conversion unit can customize the sign language expression in consideration of the cultural background of the speaker at the time of sign language conversion. The sign language conversion unit uses the generation AI to customize the sign language expression in consideration of the cultural background of the speaker at the time of sign language conversion. The cultural background includes, but is not limited to, for example, nationality, religion, customs, etc. For example, the sign language conversion unit uses a sign language expression specific to a region in consideration of the cultural background of the speaker at the time of sign language conversion. In addition, the sign language conversion unit can also select an appropriate sign language expression based on the cultural background of the speaker at the time of sign language conversion. Furthermore, the sign language conversion unit can also customize the sign language expression by referring to the cultural background of the speaker at the time of sign language conversion. This enables more appropriate sign language expression by considering the cultural background.

[0049] The sign language conversion unit can adjust the sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion. The sign language conversion unit adjusts the sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion using the generation AI. The geographical location information includes, but is not limited to, for example, GPS data, IP address, etc. For example, the sign language conversion unit uses a sign language expression specific to a region based on the geographical location information of the speaker at the time of sign language conversion. In addition, the sign language conversion unit can also select an appropriate sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion. Furthermore, the sign language conversion unit can adjust the sign language expression by referring to the geographical location information of the speaker at the time of sign language conversion. As a result, by considering the geographical location information, a sign language expression specific to a region is possible.

[0050] The sign language conversion unit can customize the sign language expression by analyzing the social media activity of the speaker at the time of sign language conversion. The sign language conversion unit uses the generation AI to analyze the social media activity of the speaker at the time of sign language conversion and customize the sign language expression. Social media activity includes, for example, the content of posts, the number of followers, etc., but is not limited to such examples. For example, the sign language conversion unit analyzes the social media activity of the speaker at the time of sign language conversion and uses the sign language expression of a related topic. In addition, the sign language conversion unit can also select an appropriate sign language expression based on the content of the speaker's social media remarks at the time of sign language conversion. Furthermore, the sign language conversion unit can also customize the sign language expression by taking into account the activity of the speaker's social media followers and friends at the time of sign language conversion. This makes it possible to use related sign language expressions by analyzing social media activity.

[0051] The character expression unit can select an appropriate expression method by referring to the speaker's past speech history when expressing the character. The character expression unit uses AI to select an appropriate expression method by referring to the speaker's past speech history when expressing the character. The speech history includes, for example, past conversation logs, speech records, etc., but is not limited to such examples. For example, the character expression unit refers to the speaker's past speech history when expressing the character, learns emotional patterns, and selects the optimal expression method. In addition, the character expression unit can predict emotional changes based on the speaker's past speech content when expressing the character, and select the optimal expression method. Furthermore, the character expression unit can also create a database of the speaker's past speech history and refer to it in real time when expressing the character to select the optimal expression method. This makes it possible to express the character optimally by referring to the past speech history.

[0052] The character expression unit can adjust the character's movement based on the tone and pitch of the speaker's voice when expressing the character. The character expression unit adjusts the character's movement based on the tone and pitch of the speaker's voice when expressing the character using AI. The tone and pitch of the voice include, but are not limited to, frequency analysis, acoustic features, and the like. For example, the character expression unit adjusts the character's movement based on the tone of the speaker's voice when expressing the character. The character expression unit can also adjust the character's movement based on the pitch of the speaker's voice when expressing the character. Furthermore, the character expression unit can analyze changes in the tone and pitch of the speaker's voice in real time when expressing the character, and adjust the character's movement. This allows for more accurate emotional expression by adjusting the character's movement based on the tone and pitch of the voice.

[0053] The character representation unit can adjust the character's behavior in consideration of the speaker's geographical location information when expressing the character. The character representation unit adjusts the character's behavior in consideration of the speaker's geographical location information by using AI when expressing the character. The geographical location information includes, but is not limited to, GPS data, IP address, and the like. For example, the character representation unit uses a region-specific behavior based on the speaker's geographical location information when expressing the character. In addition, the character representation unit can also select an appropriate behavior in consideration of the speaker's geographical location information when expressing the character. Furthermore, the character representation unit can also adjust the character's behavior by referring to the speaker's geographical location information when expressing the character. This makes it possible to express a character in a region-specific manner by considering the geographical location information.

[0054] The character representation unit can customize the character's behavior by analyzing the speaker's social media activity when expressing the character. The character representation unit uses AI to analyze the speaker's social media activity when expressing the character and customize the character's behavior. Social media activity includes, but is not limited to, for example, the content of posts and the number of followers. For example, the character representation unit analyzes the speaker's social media activity when expressing the character and uses behavior of related topics. In addition, the character representation unit can also select an appropriate behavior based on the content of the speaker's social media remarks when expressing the character. Furthermore, the character representation unit can also customize the character's behavior by taking into account the activities of the speaker's social media followers and friends when expressing the character. This makes it possible to express related characters by analyzing social media activity.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] When identifying emotions from voice, the analysis unit can refer to the speaker's past speech history. For example, by creating a database of past conversation logs and speech records and referring to them in real time, it is possible to learn patterns of emotions and improve the accuracy of identification. In addition, it is also possible to predict changes in emotions based on the speaker's past speech content and improve the accuracy of identification. Furthermore, by referring to the past speech history, when a particular emotional expression is repeated, it is possible to identify that emotion more accurately. In this way, the accuracy of emotion identification is improved by utilizing the past speech history.

[0057] The sign language conversion unit can take into account the cultural background of the speaker when converting into sign language based on the identified emotion. For example, an appropriate sign language expression can be selected based on the cultural background of the speaker, such as the nationality, religion, and customs of the speaker. In addition, by using a sign language expression specific to a region, more appropriate sign language expression is possible. Furthermore, by referring to the cultural background of the speaker and customizing the sign language expression, emotions can be conveyed more accurately. In this way, the accuracy of the sign language expression is improved by taking the cultural background into consideration.

[0058] The character expression unit can analyze the tone and pitch of the speaker's voice in detail when expressing sign language through an on-screen character. For example, emotions can be conveyed more accurately by analyzing changes in voice tone and pitch in real time and adjusting the character's movements. In addition, the character's movements can be customized based on the voice tone and pitch. Furthermore, the characteristics of the voice tone and pitch can be learned to improve the accuracy of future character expressions. As a result, the accuracy of character expressions can be improved by analyzing the voice tone and pitch in detail.

[0059] When receiving voice, the reception unit can automatically filter background noise to receive only clear voice. For example, it can analyze ambient noise in real time and use noise canceling technology to extract clear voice. It can also filter noise in a specific frequency band to emphasize only the speaker's voice. Furthermore, AI can learn background noise and adaptively filter to receive clear voice. This improves the accuracy of voice reception by filtering background noise.

[0060] When receiving a voice, the reception unit can preferentially receive a highly relevant voice in consideration of the geographical location information of the speaker. For example, the current location of the speaker can be acquired and nearby voice can be preferentially received. Also, based on the geographical location information of the speaker, voice in a related area can be preferentially received. Furthermore, voice related to a specific area can be preferentially analyzed in consideration of the speaker's location information. In this way, by considering the geographical location information of the speaker, highly relevant voice can be preferentially received.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The reception unit receives a voice. The voice includes, but is not limited to, spoken words, music, and environmental sounds. The reception unit can receive, for example, a voice during a remote conference. Step 2: The analysis unit uses the generation AI to analyze the voice received by the reception unit and identify emotions. Emotions include, but are not limited to, joy, sadness, anger, etc. The generation AI identifies emotions from the voice using a text generation AI (e.g., LLM) or a multimodal generation AI. Step 3: The sign language conversion unit converts the emotion identified by the analysis unit into a sign language using the generation AI. Examples of sign languages ​​include, but are not limited to, Japanese Sign Language and American Sign Language. Step 4: The character representation unit represents the sign language converted by the sign language conversion unit on a character on the screen. The character may be, for example, an animated character, a 3D model, or the like, but is not limited to such examples.

[0063] (Example 2) The system according to the embodiment of the present invention receives speech as input, uses a generation AI to identify emotional expressions such as joy, anger, sadness, and happiness conveyed from the speech, and outputs them in sign language. This system was born from the background that while the technology for transcribing speech is established, there is no technology for converting speech into sign language. Sign language can more effectively convey nuances and emotions that are difficult to express in print, so it can provide expressions that have been difficult to convey to deaf people until now. For example, if a speaker says "This project is very important" during a remote meeting, the generation AI identifies the emotion "important" from the speech and expresses it in sign language. The character on the screen expresses "important" in sign language, so that the emotion is conveyed to deaf people. This system makes it possible to provide information including emotional expressions to deaf people, improving the quality of communication. In addition, by utilizing sign language, expressions that have been difficult to convey until now can be conveyed more effectively. As a result, the system receives speech as input, uses a generation AI to identify emotional expressions conveyed from speech, and outputs them in sign language.

[0064] The system according to the embodiment includes a reception unit, an analysis unit, a sign language conversion unit, and a character representation unit. The reception unit receives voice. The voice includes, for example, spoken words, music, and environmental sounds, but is not limited to such examples. The reception unit can receive, for example, voice during a remote conference. The analysis unit uses a generation AI to analyze the voice received by the reception unit and identify emotions. The emotions include, for example, joy, sadness, anger, but are not limited to such examples. The generation AI identifies emotions from the voice using a text generation AI (for example, LLM) or a multimodal generation AI. The sign language conversion unit converts into sign language based on the emotions identified by the analysis unit using the generation AI. The sign language includes, for example, Japanese Sign Language, American Sign Language, etc., but is not limited to such examples. The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on a screen. The character includes, for example, an animation character, a 3D model, etc., but is not limited to such examples. As a result, the system according to the embodiment can convert speech into sign language and provide information including emotional expressions to deaf people.

[0065] The reception unit receives voice. The voice includes, but is not limited to, spoken words, music, and environmental sounds. The reception unit can receive, for example, voice during a remote conference. Specifically, the reception unit captures surrounding voice with high accuracy using a high-sensitivity microphone or a voice input device. This allows clear collection of voice, improving the processing accuracy in the subsequent analysis unit. Furthermore, the reception unit is equipped with noise canceling technology, which can effectively remove environmental sounds and background noise. This allows spoken words and important voice information to be clearly collected. The reception unit converts the voice data into a digital signal in real time and transmits it to the analysis unit. For example, when receiving voice during a remote conference, real-time emotion analysis is possible by sequentially capturing the remarks of the conference participants and transmitting them to the analysis unit. Furthermore, the reception unit also simultaneously collects metadata of the voice data (for example, the identification information of the speaker, the time of speech, etc.) and provides them to the analysis unit. This allows the analysis unit to perform analysis taking into account the context of the voice data and the characteristics of the speaker. The reception unit supports multiple voice input devices and can integrate and process voice data from different devices. For example, it centrally manages data from multiple microphones in a conference room and from the voice input devices of remote participants and provides it to the analysis unit. This allows the reception unit to efficiently collect data from various voice sources and improve the performance of the entire system.

[0066] The analysis unit uses the generation AI to analyze the voice received by the reception unit and identify the emotion. The emotion includes, for example, joy, sadness, anger, etc., but is not limited to such examples. The generation AI uses a text generation AI (for example, LLM) or a multimodal generation AI to identify the emotion from the voice. Specifically, the analysis unit converts the voice data into text using a voice recognition technology, and inputs the text data to the generation AI. The generation AI analyzes voice characteristics such as intonation, speed, and strength of the voice to identify the emotion. For example, if the voice has a high intonation and a fast speed, it is identified as "joy," and if the voice is low and the speed is identified as "sadness." The generation AI also identifies the emotion by taking into account the context and content of the voice data. For example, if the content of the statement is positive, it is identified as "joy," and if it is negative, it is identified as "sadness." Furthermore, the analysis unit improves the accuracy of emotion identification by using a generation AI model that has learned past voice data and emotion data. As a result, the analysis unit can identify emotions from the voice data with high accuracy and provide them to the sign language conversion unit. The analysis unit analyzes the voice data in real time and immediately transmits the emotion identification results to the sign language conversion unit. This improves the response speed of the entire system and enables quick feedback to be provided to the user. Furthermore, the analysis unit can accumulate the emotion identification results and analyze long-term emotion trends. This makes it possible to continuously monitor changes in the user's emotional state and take appropriate measures.

[0067] The sign language conversion unit converts the emotion identified by the analysis unit into sign language using the generation AI. The sign language includes, but is not limited to, Japanese Sign Language and American Sign Language. Specifically, the sign language conversion unit receives the emotion identification result and text data provided by the analysis unit as input, and converts the emotion into a sign language expression using the generation AI. The generation AI converts the text data into sign language using a model that has learned the grammar and expression method of sign language. For example, when the emotion "joy" is identified, the generation AI generates a sign language action that expresses "joy" and constructs a sign language sentence based on the content of the text data. The sign language conversion unit outputs the generated sign language action as animation data and provides it to the character expression unit. Furthermore, the sign language conversion unit supports multiple sign languages ​​and can select an appropriate sign language according to the user's settings. For example, the sign language conversion unit provides Japanese Sign Language to a user who uses Japanese Sign Language and American Sign Language to a user who uses American Sign Language. The sign language conversion unit periodically updates the learning data of the generation AI and incorporates new sign language expressions and grammar rules, so that it can always provide the latest sign language expressions. This allows the sign language conversion unit to provide the user with accurate and natural sign language expressions, facilitating smooth communication. Furthermore, the sign language conversion unit can collect user feedback and continuously improve the accuracy and naturalness of sign language expressions. This allows the sign language conversion unit to flexibly respond to user needs, improving the reliability of the entire system and user satisfaction.

[0068] The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on the screen. The character includes, but is not limited to, an animated character, a 3D model, and the like. Specifically, the character representation unit moves the character on the screen based on the animation data provided by the sign language conversion unit. The character representation unit generates the character's movements in real time and visually provides the sign language to the user. For example, the animated character finely controls the movement of the joints and the changes in facial expression in order to naturally express the sign language movements. This allows the user to accurately understand the sign language movements. The character representation unit can customize the appearance and style of the character according to the user's settings. For example, the user can select the character's clothing, hairstyle, facial expression, and the like to create a character of his or her own preference. Furthermore, the character representation unit can display multiple characters simultaneously and can express multiple speakers and different sign languages ​​simultaneously. This allows the character representation unit to handle complex communication scenarios and provide the user with a variety of sign language expressions. The character representation unit can collect user feedback and continuously improve the accuracy of the character's movements and expressions. This allows the character representation unit to provide high-quality sign language expressions to users and facilitate smooth communication. Furthermore, the character representation unit can link with other systems and devices to provide sign language expressions on a variety of platforms. For example, sign language expressions can be displayed on devices such as smartphones, tablets, and personal computers, allowing users to use sign language anywhere. This allows the character representation unit to improve user convenience and contribute to the spread of sign language communication.

[0069] The analysis unit can identify emotions from the voice. The analysis unit identifies emotions from the voice using a generation AI. Emotions include, but are not limited to, for example, joy, sadness, and anger. The generation AI identifies emotions from the voice using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI receives voice data as input, analyzes the characteristics of the voice, and identifies emotions. The generation AI can analyze characteristics such as tone, pitch, and rhythm of the voice to identify emotions. This improves the accuracy of sign language conversion by identifying emotions from voice.

[0070] The sign language conversion unit can convert into sign language based on the identified emotion. The sign language conversion unit converts into sign language based on the identified emotion using a generation AI. Sign languages ​​include, but are not limited to, Japanese Sign Language and American Sign Language. The generation AI converts into sign language based on emotion using a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the generation AI receives the identified emotion as input and generates a sign language action. The generation AI can adjust the sign language action depending on the intensity and type of emotion. This enables sign language conversion based on emotion.

[0071] The character representation unit can express the sign language by placing it on a character on a screen. The character representation unit expresses the sign language converted by the sign language conversion unit by placing it on a character on a screen. The character includes, but is not limited to, for example, an animated character, a 3D model, and the like. The character representation unit applies the sign language action to the character and visually expresses it. For example, the character representation unit receives sign language action data as an input and generates a character action. The character representation unit can apply the sign language action to the character in real time and visually express it. Thereby, by expressing the sign language with a character on a screen, it is possible to visually convey emotions.

[0072] The reception unit can receive voice during a remote conference. The reception unit receives voice during a remote conference. Remote conferences include, but are not limited to, video conferences and audio conferences. The reception unit receives voice during a remote conference in real time and transmits the voice to the analysis unit. For example, the reception unit receives voice data during a remote conference as input and transmits the voice data to the analysis unit in real time. This makes it possible to convert the voice during a remote conference into sign language in real time by receiving the voice during the remote conference.

[0073] The character representation unit can represent sign language in real time. The character representation unit represents the sign language converted by the sign language conversion unit in real time. The characters include, but are not limited to, animated characters, 3D models, and the like. The character representation unit applies the sign language motion to the character in real time and visually represents it. For example, the character representation unit receives sign language motion data as input and generates character motion in real time. This allows emotions to be conveyed instantly by representing the sign language in real time.

[0074] The reception unit can estimate the user's emotion and adjust the timing of voice reception based on the user's emotion. The reception unit uses AI to estimate the user's emotion and adjusts the timing of voice reception based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is nervous, the reception unit delays the timing of voice reception to provide the user with time to relax. In addition, when the user is relaxed, the reception unit can also advance the timing of voice reception to promote smooth conversation. Furthermore, when the user is in a hurry, the reception unit can immediately accept the voice to enable a quick response. This allows more appropriate voice reception by adjusting the timing of voice reception according to the user's emotion.

[0075] The reception unit can automatically filter background noise when receiving voice to receive only clear voice. The reception unit uses AI to automatically filter background noise when receiving voice to receive only clear voice. Background noise includes, but is not limited to, environmental sounds, noise, and the like. For example, the reception unit analyzes surrounding noise in real time when receiving voice and extracts clear voice using noise canceling technology. In addition, the reception unit can filter noise in a specific frequency band when receiving voice to emphasize only the speaker's voice. Furthermore, the reception unit can learn background noise using AI and perform adaptive filtering. As a result, clear voice can be received by filtering background noise.

[0076] The reception unit can analyze the characteristics of the speaker's voice when receiving the voice, and create a different voice profile for each speaker. The reception unit uses AI to analyze the characteristics of the speaker's voice when receiving the voice, and create a different voice profile for each speaker. The voice profile includes, for example, tone, pitch, rhythm, etc., but is not limited to such examples. For example, the reception unit analyzes the tone and pitch of the speaker's voice when receiving the voice, and creates an individual voice profile. The reception unit can also analyze the strength and rhythm of the speaker's voice when receiving the voice, and create an individual voice profile. Furthermore, the reception unit can learn the characteristics of the speaker's voice when receiving the voice, and create a profile for improving the accuracy of future voice recognition. As a result, the accuracy of voice recognition is improved by creating a different voice profile for each speaker.

[0077] The reception unit can estimate the user's emotion and determine the priority of the voice to be received based on the user's emotion. The reception unit uses AI to estimate the user's emotion and determines the priority of the voice to be received based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is excited, the reception unit preferentially receives the voice and performs analysis quickly. In addition, when the user is calm, the reception unit can also receive the voice with normal priority. Furthermore, when the user is sad, the reception unit can also receive the voice with priority and perform analysis with emphasis on emotional expression. In this way, important voices can be processed preferentially by determining the priority of the voices according to the user's emotion.

[0078] The reception unit can preferentially receive highly relevant voices in consideration of the geographical location information of the speaker when receiving the voice. The reception unit uses AI to preferentially receive highly relevant voices in consideration of the geographical location information of the speaker when receiving the voice. The geographical location information includes, but is not limited to, GPS data, IP address, and the like. For example, the reception unit acquires the speaker's current location when receiving the voice, and preferentially receives nearby voices. In addition, the reception unit can also preferentially receive voices in related areas based on the geographical location information of the speaker when receiving the voice. Furthermore, the reception unit can also preferentially analyze voices related to a specific area in consideration of the speaker's location information when receiving the voice. As a result, it is possible to preferentially receive highly relevant voices by considering the geographical location information of the speaker.

[0079] The reception unit can analyze the speaker's social media activity when receiving the voice, and preferentially receive related voice. The reception unit uses AI to analyze the speaker's social media activity when receiving the voice, and preferentially receive related voice. Social media activity includes, for example, the content of posts, the number of followers, and the like, but is not limited to such examples. For example, the reception unit analyzes the speaker's social media activity when receiving the voice, and preferentially receives voice on related topics. In addition, the reception unit can also preferentially receive related voice based on the content of the speaker's social media remarks when receiving the voice. Furthermore, the reception unit can also preferentially receive related voice in consideration of the activity of the speaker's social media followers and friends when receiving the voice. In this way, it is possible to preferentially receive related voice by analyzing social media activity.

[0080] The analysis unit can estimate the user's emotion and adjust the accuracy of the analysis based on the user's emotion. The analysis unit uses the generation AI to estimate the user's emotion and adjust the accuracy of the analysis based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is relaxed, the analysis unit performs a detailed analysis to identify subtle changes in emotion. In addition, when the user is nervous, the analysis unit can also perform a quick analysis to identify the main emotion. Furthermore, when the user is excited, the analysis unit can perform an analysis that emphasizes the intensity of the emotion. This allows for more accurate emotion identification by adjusting the accuracy of the analysis according to the user's emotion.

[0081] The analysis unit can improve the accuracy of emotion identification by referring to the speaker's past speech history during voice analysis. The analysis unit uses the generation AI to improve the accuracy of emotion identification by referring to the speaker's past speech history during voice analysis. The speech history includes, for example, past conversation logs, speech records, etc., but is not limited to such examples. For example, the analysis unit improves the accuracy of identification by referring to the speaker's past speech history during voice analysis and learning emotion patterns. In addition, the analysis unit can also improve the accuracy of identification by predicting changes in emotion based on the speaker's past speech content during voice analysis. Furthermore, the analysis unit can also improve the accuracy of emotion identification by creating a database of the speaker's past speech history during voice analysis and referring to it in real time. As a result, the accuracy of emotion identification is improved by referring to the past speech history.

[0082] The analysis unit can identify emotions by analyzing the tone and pitch of the speaker's voice in detail during the voice analysis. The analysis unit uses the generation AI to analyze the tone and pitch of the speaker's voice in detail during the voice analysis to identify emotions. The tone and pitch of the voice include, but are not limited to, frequency analysis, acoustic features, and the like. For example, the analysis unit can analyze the tone of the speaker's voice in detail during the voice analysis to identify changes in emotions. The analysis unit can also analyze the pitch of the speaker's voice in detail during the voice analysis to identify the intensity of emotions. Furthermore, the analysis unit can analyze changes in the tone and pitch of the speaker's voice in real time during the voice analysis to identify emotions. As a result, the accuracy of emotion identification is improved by analyzing the tone and pitch of the voice in detail.

[0083] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the user's emotions. The analysis unit uses the generation AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, the analysis unit displays detailed analysis results when the user is relaxed. In addition, the analysis unit can also display concise analysis results when the user is nervous. Furthermore, the analysis unit can display visually emphasized analysis results when the user is excited. This makes it possible to provide more appropriate information by adjusting the display method of the analysis results according to the user's emotions.

[0084] The analysis unit can perform emotion identification in consideration of the geographical location information of the speaker during voice analysis. The analysis unit performs emotion identification in consideration of the geographical location information of the speaker using the generation AI during voice analysis. The geographical location information includes, but is not limited to, for example, GPS data, IP address, etc. For example, the analysis unit identifies region-specific emotion expressions based on the geographical location information of the speaker during voice analysis. In addition, the analysis unit can also perform emotion identification based on a cultural background by taking into account the geographical location information of the speaker during voice analysis. Furthermore, the analysis unit can also perform emotion identification based on local events and situations by referring to the geographical location information of the speaker during voice analysis. As a result, region-specific emotion expressions can be identified by taking into account the geographical location information.

[0085] The analysis unit can improve the accuracy of emotion identification by referring to the speaker's related literature and past utterances during the voice analysis. The analysis unit uses the generation AI to improve the accuracy of emotion identification by referring to the speaker's related literature and past utterances during the voice analysis. The related literature includes, but is not limited to, academic papers, technical reports, and the like. For example, the analysis unit refers to the speaker's related literature during the voice analysis, understands the background of the emotion, and improves the identification accuracy. The analysis unit can also improve the identification accuracy by learning the emotion pattern during the voice analysis by referring to the speaker's past utterances. Furthermore, the analysis unit can improve the accuracy of emotion identification by creating a database of the speaker's related literature and past utterances during the voice analysis and referring to them in real time. As a result, the accuracy of emotion identification is improved by referring to the related literature and past utterances.

[0086] The sign language conversion unit can estimate the user's emotion and adjust the sign language expression method based on the user's emotion. The sign language conversion unit uses a generation AI to estimate the user's emotion and adjusts the sign language expression method based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is excited, the sign language conversion unit increases the sign language movement to emphasize the emotion. In addition, when the user is relaxed, the sign language conversion unit can also slow down the sign language movement and perform a gentle expression. Furthermore, when the user is sad, the sign language conversion unit can reduce the sign language movement and perform a suppressed expression of emotion. This allows for more appropriate sign language expression by adjusting the sign language expression method according to the user's emotion.

[0087] The sign language conversion unit can adjust the speed of the sign language movement according to the intensity of the identified emotion during sign language conversion. The sign language conversion unit adjusts the speed of the sign language movement according to the intensity of the identified emotion during sign language conversion using the generation AI. The intensity of the emotion includes, but is not limited to, an emotion scale, a psychological evaluation, and the like. For example, when the intensity of the emotion is high, the sign language conversion unit speeds up the sign language movement speed to emphasize the emotion. In addition, when the intensity of the emotion is low, the sign language conversion unit can also slow down the sign language movement speed to perform a gentle expression. Furthermore, the sign language conversion unit can also adjust the sign language movement speed in real time according to the intensity of the emotion. As a result, the emotion can be conveyed more accurately by adjusting the sign language movement speed according to the intensity of the emotion.

[0088] The sign language conversion unit can customize the sign language expression in consideration of the cultural background of the speaker at the time of sign language conversion. The sign language conversion unit uses the generation AI to customize the sign language expression in consideration of the cultural background of the speaker at the time of sign language conversion. The cultural background includes, but is not limited to, for example, nationality, religion, customs, etc. For example, the sign language conversion unit uses a sign language expression specific to a region in consideration of the cultural background of the speaker at the time of sign language conversion. In addition, the sign language conversion unit can also select an appropriate sign language expression based on the cultural background of the speaker at the time of sign language conversion. Furthermore, the sign language conversion unit can also customize the sign language expression by referring to the cultural background of the speaker at the time of sign language conversion. This enables more appropriate sign language expression by considering the cultural background.

[0089] The sign language conversion unit can estimate the user's emotion and determine the priority of the sign language based on the user's emotion. The sign language conversion unit uses a generation AI to estimate the user's emotion and determines the priority of the sign language based on the estimated user's emotion. The emotion includes, but is not limited to, joy, sadness, anger, and the like. For example, when the user is excited, the sign language conversion unit preferentially expresses the emotion in sign language. In addition, when the user is relaxed, the sign language conversion unit can also express the emotion in sign language with normal priority. Furthermore, when the user is sad, the sign language conversion unit can also preferentially express the emotion in sign language. In this way, important emotions can be preferentially expressed by determining the priority of the sign language according to the user's emotion.

[0090] The sign language conversion unit can adjust the sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion. The sign language conversion unit adjusts the sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion using the generation AI. The geographical location information includes, but is not limited to, for example, GPS data, IP address, etc. For example, the sign language conversion unit uses a sign language expression specific to a region based on the geographical location information of the speaker at the time of sign language conversion. In addition, the sign language conversion unit can also select an appropriate sign language expression in consideration of the geographical location information of the speaker at the time of sign language conversion. Furthermore, the sign language conversion unit can adjust the sign language expression by referring to the geographical location information of the speaker at the time of sign language conversion. As a result, by considering the geographical location information, a sign language expression specific to a region is possible.

[0091] The sign language conversion unit can customize the sign language expression by analyzing the social media activity of the speaker at the time of sign language conversion. The sign language conversion unit uses the generation AI to analyze the social media activity of the speaker at the time of sign language conversion and customize the sign language expression. Social media activity includes, for example, the content of posts, the number of followers, etc., but is not limited to such examples. For example, the sign language conversion unit analyzes the social media activity of the speaker at the time of sign language conversion and uses the sign language expression of a related topic. In addition, the sign language conversion unit can also select an appropriate sign language expression based on the content of the speaker's social media remarks at the time of sign language conversion. Furthermore, the sign language conversion unit can also customize the sign language expression by taking into account the activity of the speaker's social media followers and friends at the time of sign language conversion. This makes it possible to use related sign language expressions by analyzing social media activity.

[0092] The character expression unit can estimate the user's emotion and adjust the character's expression method based on the user's emotion. The character expression unit uses AI to estimate the user's emotion and adjust the character's expression method based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is excited, the character expression unit increases the character's movement and emphasizes the emotion. In addition, when the user is relaxed, the character expression unit can also make the character's movement relaxed and perform a gentle expression. Furthermore, when the user is sad, the character expression unit can also reduce the character's movement and perform a suppressed expression of emotion. This allows for more appropriate emotional expression by adjusting the character's expression method according to the user's emotion.

[0093] The character expression unit can select an appropriate expression method by referring to the speaker's past speech history when expressing the character. The character expression unit uses AI to select an appropriate expression method by referring to the speaker's past speech history when expressing the character. The speech history includes, for example, past conversation logs, speech records, etc., but is not limited to such examples. For example, the character expression unit refers to the speaker's past speech history when expressing the character, learns emotional patterns, and selects the optimal expression method. In addition, the character expression unit can predict emotional changes based on the speaker's past speech content when expressing the character, and select the optimal expression method. Furthermore, the character expression unit can also create a database of the speaker's past speech history and refer to it in real time when expressing the character to select the optimal expression method. This makes it possible to express the character optimally by referring to the past speech history.

[0094] The character expression unit can adjust the character's movement based on the tone and pitch of the speaker's voice when expressing the character. The character expression unit adjusts the character's movement based on the tone and pitch of the speaker's voice when expressing the character using AI. The tone and pitch of the voice include, but are not limited to, frequency analysis, acoustic features, and the like. For example, the character expression unit adjusts the character's movement based on the tone of the speaker's voice when expressing the character. The character expression unit can also adjust the character's movement based on the pitch of the speaker's voice when expressing the character. Furthermore, the character expression unit can analyze changes in the tone and pitch of the speaker's voice in real time when expressing the character, and adjust the character's movement. This allows for more accurate emotional expression by adjusting the character's movement based on the tone and pitch of the voice.

[0095] The character expression unit can estimate the user's emotion and adjust the character's action sequence based on the user's emotion. The character expression unit uses AI to estimate the user's emotion and adjust the character's action sequence based on the estimated user's emotion. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, when the user is excited, the character expression unit preferentially reflects the emotion in the character's action. In addition, when the user is relaxed, the character expression unit can also express the character in a normal action sequence. Furthermore, when the user is sad, the character expression unit can also preferentially reflect the emotion in the character's action. This allows for more appropriate emotional expression by adjusting the character's action sequence according to the user's emotion.

[0096] The character representation unit can adjust the character's behavior in consideration of the speaker's geographical location information when expressing the character. The character representation unit adjusts the character's behavior in consideration of the speaker's geographical location information by using AI when expressing the character. The geographical location information includes, but is not limited to, GPS data, IP address, and the like. For example, the character representation unit uses a region-specific behavior based on the speaker's geographical location information when expressing the character. In addition, the character representation unit can also select an appropriate behavior in consideration of the speaker's geographical location information when expressing the character. Furthermore, the character representation unit can also adjust the character's behavior by referring to the speaker's geographical location information when expressing the character. This makes it possible to express a character in a region-specific manner by considering the geographical location information.

[0097] The character representation unit can customize the character's behavior by analyzing the speaker's social media activity when expressing the character. The character representation unit uses AI to analyze the speaker's social media activity when expressing the character and customize the character's behavior. Social media activity includes, but is not limited to, for example, the content of posts and the number of followers. For example, the character representation unit analyzes the speaker's social media activity when expressing the character and uses behavior of related topics. In addition, the character representation unit can also select an appropriate behavior based on the content of the speaker's social media remarks when expressing the character. Furthermore, the character representation unit can also customize the character's behavior by taking into account the activities of the speaker's social media followers and friends when expressing the character. This makes it possible to express related characters by analyzing social media activity.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] When identifying emotions from voice, the analysis unit can refer to the speaker's past speech history. For example, by creating a database of past conversation logs and speech records and referring to them in real time, it is possible to learn patterns of emotions and improve the accuracy of identification. In addition, it is also possible to predict changes in emotions based on the speaker's past speech content and improve the accuracy of identification. Furthermore, by referring to the past speech history, when a particular emotional expression is repeated, it is possible to identify that emotion more accurately. In this way, the accuracy of emotion identification is improved by utilizing the past speech history.

[0100] The sign language conversion unit can take into account the cultural background of the speaker when converting into sign language based on the identified emotion. For example, an appropriate sign language expression can be selected based on the cultural background of the speaker, such as the nationality, religion, and customs of the speaker. In addition, by using a sign language expression specific to a region, more appropriate sign language expression is possible. Furthermore, by referring to the cultural background of the speaker and customizing the sign language expression, emotions can be conveyed more accurately. In this way, the accuracy of the sign language expression is improved by taking the cultural background into consideration.

[0101] The character expression unit can analyze the tone and pitch of the speaker's voice in detail when expressing sign language through an on-screen character. For example, emotions can be conveyed more accurately by analyzing changes in voice tone and pitch in real time and adjusting the character's movements. In addition, the character's movements can be customized based on the voice tone and pitch. Furthermore, the characteristics of the voice tone and pitch can be learned to improve the accuracy of future character expressions. As a result, the accuracy of character expressions can be improved by analyzing the voice tone and pitch in detail.

[0102] When receiving voice, the reception unit can automatically filter background noise to receive only clear voice. For example, it can analyze ambient noise in real time and use noise canceling technology to extract clear voice. It can also filter noise in a specific frequency band to emphasize only the speaker's voice. Furthermore, AI can learn background noise and adaptively filter to receive clear voice. This improves the accuracy of voice reception by filtering background noise.

[0103] When receiving a voice, the reception unit can preferentially receive a highly relevant voice in consideration of the geographical location information of the speaker. For example, the current location of the speaker can be acquired and nearby voice can be preferentially received. Also, based on the geographical location information of the speaker, voice in a related area can be preferentially received. Furthermore, voice related to a specific area can be preferentially analyzed in consideration of the speaker's location information. In this way, by considering the geographical location information of the speaker, highly relevant voice can be preferentially received.

[0104] The reception unit can estimate the user's emotions and adjust the timing of voice reception based on the user's emotions. For example, if the user is nervous, the timing of voice reception can be delayed to provide the user with time to relax. Also, if the user is relaxed, the timing of voice reception can be advanced to promote smooth conversation. Furthermore, if the user is in a hurry, the timing of voice reception can be made immediate to enable a quick response. This allows more appropriate voice reception by adjusting the timing of voice reception according to the user's emotions.

[0105] The analysis unit can estimate the user's emotion and adjust the accuracy of the analysis based on the user's emotion. For example, if the user is relaxed, a detailed analysis can be performed to identify subtle changes in emotion. If the user is nervous, a quick analysis can be performed to identify the main emotion. Furthermore, if the user is excited, an analysis can be performed that emphasizes the intensity of the emotion. This allows for more accurate emotion identification by adjusting the accuracy of the analysis according to the user's emotion.

[0106] The sign language conversion unit can estimate the user's emotions and adjust the sign language expression method based on the user's emotions. For example, if the user is excited, the sign language movements can be made larger to emphasize the emotions. Also, if the user is relaxed, the sign language movements can be made slower to express a calmer emotion. Furthermore, if the user is sad, the sign language movements can be made smaller to express a more subdued emotion. In this way, by adjusting the sign language expression method according to the user's emotions, more appropriate sign language expression is possible.

[0107] The character expression unit can estimate the user's emotions and adjust the character's expression method based on the user's emotions. For example, if the user is excited, the character's movements can be made larger to emphasize the emotion. If the user is relaxed, the character's movements can be made slower to express a calmer emotion. Furthermore, if the user is sad, the character's movements can be made smaller to express a more subdued emotion. In this way, by adjusting the character's expression method according to the user's emotions, more appropriate emotional expression is possible.

[0108] The character expression unit can estimate the user's emotion and adjust the character's action sequence based on the user's emotion. For example, if the user is excited, the emotion can be preferentially reflected in the character's action. Also, if the user is relaxed, the character can be expressed in a normal action sequence. Furthermore, if the user is sad, the emotion can be preferentially reflected in the character's action. In this way, by adjusting the character's action sequence according to the user's emotion, more appropriate emotion expression is possible.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The reception unit receives a voice. The voice includes, but is not limited to, spoken words, music, and environmental sounds. The reception unit can receive, for example, a voice during a remote conference. Step 2: The analysis unit uses the generation AI to analyze the voice received by the reception unit and identify emotions. Emotions include, but are not limited to, joy, sadness, anger, etc. The generation AI identifies emotions from the voice using a text generation AI (e.g., LLM) or a multimodal generation AI. Step 3: The sign language conversion unit converts the emotion identified by the analysis unit into a sign language using the generation AI. Examples of sign languages ​​include, but are not limited to, Japanese Sign Language and American Sign Language. Step 4: The character representation unit represents the sign language converted by the sign language conversion unit on a character on the screen. The character may be, for example, an animated character, a 3D model, or the like, but is not limited to such examples.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned reception unit, analysis unit, sign language conversion unit, and character expression unit is realized, for example, in at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives voice through the microphone 38B of the smart device 14. The analysis unit analyzes the voice using a generation AI by the specific processing unit 290 of the data processing device 12 to identify emotions. The sign language conversion unit converts into sign language based on the emotions identified by the specific processing unit 290 of the data processing device 12. The character expression unit expresses the sign language by putting it on a character on the screen through the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0118] 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.

[0119] 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 the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] 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 performed in a secure state.

[0122] Fig. 4 shows an example of 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.

[0123] 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.

[0124] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 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 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0128] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned reception unit, analysis unit, sign language conversion unit, and character representation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives voice through the microphone 238 of the smart glasses 214. The analysis unit analyzes the voice using a generation AI by the specific processing unit 290 of the data processing device 12 to identify emotions. The sign language conversion unit converts into sign language based on the emotions identified by the specific processing unit 290 of the data processing device 12. The character representation unit expresses the sign language by placing it on a character on the screen through the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0134] 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.

[0135] 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 the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] 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 performed in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type 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.

[0139] 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.

[0140] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] 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 voice indicating a user input for 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.

[0144] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned reception unit, analysis unit, sign language conversion unit, and character representation unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit receives voice through the microphone 238 of the headset type terminal 314. The analysis unit analyzes the voice using a generation AI by the specific processing unit 290 of the data processing device 12 to identify emotions. The sign language conversion unit converts into sign language based on the emotions identified by the specific processing unit 290 of the data processing device 12. The character representation unit expresses the sign language by placing it on a character on a screen through the control unit 46A of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0150] 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.

[0151] 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 the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] 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 performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0155] 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.

[0156] 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.

[0157] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] 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 a voice indicating a user input for 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.

[0161] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0163] Each of the multiple elements including the above-mentioned reception unit, analysis unit, sign language conversion unit, and character expression unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives voice through the microphone 238 of the robot 414. The analysis unit analyzes the voice using a generation AI by the specific processing unit 290 of the data processing device 12 and identifies emotions. The sign language conversion unit converts into sign language based on the emotions identified by the specific processing unit 290 of the data processing device 12. The character expression unit expresses the sign language by putting it on a character on a screen through the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0171] 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.

[0172] 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 Universal Serial Bus (USB) 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.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] 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.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0177] As an example of a configuration using one 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 configuration in which a processor is used that realizes the functions of the 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.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A reception unit that receives voice; an analysis unit that analyzes the voice received by the reception unit and identifies emotions; a sign language conversion unit for converting into sign language based on the emotion identified by the analysis unit; a character representation unit that represents the sign language converted by the sign language conversion unit on a character on a screen; A system characterized by: (Appendix 2) The analysis unit is Identifying emotions from speech 2. The system of claim 1, (Appendix 3) The sign language conversion unit is Convert into sign language based on identified emotions 2. The system of claim 1, (Appendix 4) The character representation unit is Expressing sign language through on-screen characters 2. The system of claim 1, (Appendix 5) The reception unit is Accepting audio during a remote meeting 2. The system of claim 1, (Appendix 6) The character representation unit is Expressing sign language in real time 2. The system of claim 1, (Appendix 7) The reception unit is Estimate the user's emotions and adjust the timing of voice reception based on the user's emotions. 2. The system of claim 1, (Appendix 8) The reception unit is When receiving voice, automatically filters out background noise to only accept clear voice 2. The system of claim 1, (Appendix 9) The reception unit is When receiving audio, the speaker's vocal characteristics are analyzed and a unique voice profile is created for each speaker. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate user emotions and prioritize voices to be accepted based on the user emotions 2. The system of claim 1, (Appendix 11) The reception unit is When accepting audio, the system takes into account the speaker's geographic location to prioritize more relevant audio. 2. The system of claim 1, (Appendix 12) The reception unit is When accepting audio, analyze the speaker's social media activity and prioritize relevant audio. 2. The system of claim 1, (Appendix 13) The analysis unit is Estimate user emotions and adjust analysis accuracy based on user emotions 2. The system of claim 1, (Appendix 14) The analysis unit is When analyzing speech, improve the accuracy of emotion recognition by referring to the speaker's past speech history. 2. The system of claim 1, (Appendix 15) The analysis unit is During voice analysis, emotions are identified through detailed analysis of the speaker's tone and pitch 2. The system of claim 1, (Appendix 16) The analysis unit is Infer user emotions and adjust how analysis results are displayed based on the user's emotions 2. The system of claim 1, (Appendix 17) The analysis unit is When analyzing voice, emotion identification is performed taking into account the speaker's geographic location information. 2. The system of claim 1, (Appendix 18) The analysis unit is When analyzing speech, improve the accuracy of emotion identification by referring to the speaker's related literature and past utterances. 2. The system of claim 1, (Appendix 19) The sign language conversion unit is Estimate the user's emotions and adjust the sign language expression based on the user's emotions 2. The system of claim 1, (Appendix 20) The sign language conversion unit is During sign language conversion, the speed of sign language movements is adjusted according to the intensity of the identified emotion. 2. The system of claim 1, (Appendix 21) The sign language conversion unit is When converting sign language, customize the expression of sign language by considering the cultural background of the speaker. 2. The system of claim 1, (Appendix 22) The sign language conversion unit is Estimate the user's emotions and prioritize sign languages ​​based on the user's emotions 2. The system of claim 1, (Appendix 23) The sign language conversion unit is When converting sign language, adjust the sign language expression taking into account the speaker's geographic location information 2. The system of claim 1, (Appendix 24) The sign language conversion unit is When converting sign language, analyze the speaker's social media activity to customize sign language expressions 2. The system of claim 1, (Appendix 25) The character representation unit is Estimate the user's emotions and adjust the character's expressions based on the user's emotions 2. The system of claim 1, (Appendix 26) The character representation unit is When expressing a character, the appropriate expression method is selected by referring to the speaker's past speech history. 2. The system of claim 1, (Appendix 27) The character representation unit is When expressing a character, adjust the character's behavior based on the tone and pitch of the speaker's voice 2. The system of claim 1, (Appendix 28) The character representation unit is Estimate the user's emotions and adjust the character's action sequence based on the user's emotions 2. The system of claim 1, (Appendix 29) The character representation unit is When expressing a character, adjust the character's movements taking into account the speaker's geographic location information 2. The system of claim 1, (Appendix 30) The character representation unit is When expressing a character, analyze the speaker's social media activity to customize the character's behavior 2. The system of claim 1, [Explanation of symbols]

[0183] 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 reception unit that receives voice; an analysis unit that analyzes the voice received by the reception unit and identifies emotions; a sign language conversion unit for converting into sign language based on the emotion identified by the analysis unit; a character representation unit that represents the sign language converted by the sign language conversion unit on a character on a screen; A system characterized by:

2. The character representation unit is Expressing sign language through on-screen characters 2. The system of claim 1 .

3. The reception unit is Accepting audio during a remote meeting 2. The system of claim 1 .

4. The character representation unit is Expressing sign language in real time 2. The system of claim 1 .

5. The reception unit is Estimate the user's emotions and adjust the timing of voice reception based on the user's emotions.

2. The system of claim 1 .

6. The reception unit is When receiving voice, automatically filters out background noise to only accept clear voice 2. The system of claim 1 .

Images