system

Abstract

The objective is to provide a system that recognizes sign language movements in real time and converts them into natural language. [Solution] The data processing device 12 as a system includes a specific processing unit 290 that uses deep learning to analyze sign language movements captured in real time using multiple cameras, and a data generation model 58 that converts the sign language content identified by the specific processing unit 290 into natural language using a generation AI and outputs it as text.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to accurately recognize sign language movements in real time and convert them into natural language.

[0005] The system according to the embodiment aims to recognize sign language gestures in real time and convert them into natural language. [Means for solving the problem]

[0006] The system according to the embodiment includes a capturing unit, an analysis unit, and a generation unit. The capturing unit captures sign language movements in real time using multiple cameras. The analysis unit analyzes the sign language movements captured by the capturing unit using deep learning to identify the content of the sign language. The generation unit converts the content of the sign language identified by the analysis unit into natural language using a generation AI and outputs the result as text. [Effects of the Invention]

[0007] The system according to the embodiment can recognize sign language gestures in real time and convert them into natural language. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A sign language recognition system according to an embodiment of the present invention is a system that performs image recognition of sign language and verbalizes it using a generation AI. This sign language recognition system uses multiple cameras to capture sign language movements in real time, analyzes the sign language movements using image recognition technology based on deep learning, and converts the sign language content into natural language using a generation AI, which then outputs the text. For example, the sign language recognition system enables smooth communication between people who use sign language. This facilitates communication with people who do not understand sign language, thereby promoting social participation by people who use sign language. Furthermore, by saving the sign language content as text, the content can be reviewed later. Specifically, the sign language recognition system uses multiple cameras to capture sign language movements in real time. Next, it analyzes the sign language movements using image recognition technology based on deep learning to identify the sign language content. Finally, it uses a generation AI to convert the sign language content into natural language and output it as text. This enables smooth communication between people who use sign language. For example, it facilitates communication with people who do not understand sign language, thereby promoting social participation by people who use sign language. Furthermore, by saving the sign language content as text, the content can be reviewed later. This allows the sign language recognition system to facilitate smooth communication between people who use sign language.

[0029] A sign language recognition system according to an embodiment includes a camera unit, an analyzer, and a generator. The camera unit uses multiple cameras to capture sign language movements in real time. The camera unit includes, for example, multiple cameras that capture sign language movements from different angles. For example, the camera unit may arrange three cameras in a triangular configuration to capture sign language movements from multiple angles. The camera unit can also automatically remove the background from the sign language movements and emphasize only the sign language movements. For example, when the background is complex, a background removal algorithm is used to extract only the sign language movements. The analyzer uses deep learning to analyze the sign language movements and identify the content of the sign language. For example, the analyzer uses a convolutional neural network (CNN) to analyze the sign language movements. For example, the analyzer improves the accuracy of the analysis so that even subtle movements in the sign language movements can be detected. The generator converts the content of the sign language identified by the analyzer into natural language using a generation AI and outputs the text. For example, the generator uses the results of the analysis of the sign language movements as input, and the generation AI generates text in natural language. For example, the generation unit can also save the generated text. This allows the sign language recognition system to capture sign language movements in real time, analyze them, and convert them into natural language, enabling smoother communication between people who use sign language. For example, this makes it easier to communicate with people who cannot understand sign language, promoting the social participation of people who use sign language. In addition, by saving the content of the sign language as text, it is possible to check the content later.

[0030] The sign language recognition system includes multiple cameras that capture sign language actions from different angles. The camera unit, for example, has three cameras arranged in a triangle, allowing it to capture sign language actions from multiple angles. For example, one camera captures sign language actions from the front, another from the side, and still another from above. This allows for more detailed analysis of sign language actions. For example, it can accurately capture subtle movements of sign language actions and changes in hand position and angle. This allows for more detailed analysis by capturing sign language actions from different angles. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without using AI. For example, the camera unit may automatically adjust the camera position and angle using AI to optimize camera placement.

[0031] The analysis unit can analyze sign language movements using a convolutional neural network. The analysis unit analyzes sign language movements using, for example, a convolutional neural network (CNN). For example, the CNN extracts features of sign language movements and identifies the content of the sign language. For example, the CNN analyzes patterns of hand position and movement to understand the meaning of the sign language. The analysis unit can also improve the analysis accuracy so that even subtle movements of sign language movements can be detected. For example, subtle movements can be detected using high-resolution images. The analysis unit can also improve the analysis accuracy by increasing the number of layers of the convolutional neural network. For example, increasing the number of CNN layers can extract more features and improve the analysis accuracy. Thus, using a convolutional neural network improves the analysis accuracy of sign language movements. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze sign language movements using AI to extract features of sign language movements.

[0032] The generation unit can input the results of analyzing sign language movements, and the generation AI can generate natural language text. For example, the generation unit inputs the results of analyzing sign language movements, and the generation AI generates natural language text. For example, the generation AI converts the sign language content into natural language and outputs it as text. For example, the generation AI converts the sign language content into natural language using technologies such as GPT-4 (registered trademark) or Transformer. The generation unit can also save the generated text. For example, the generation unit saves the generated text as a text file. The generation unit can also save the generated text in a database. This improves the accuracy of converting the sign language content into natural language by using the generation AI. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the results of analyzing sign language movements to the generation AI and have the generation AI execute the natural language text.

[0033] The generation unit can save the generated text. For example, the generation unit saves the generated text as a text file. For example, the generation unit can also save the generated text in a database. For example, the generation unit can also save the generated text in cloud storage. By saving the generated text, it becomes possible to check the content later. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically classify and save the generated text using AI.

[0034] The camera unit can dynamically change the frame rate during shooting depending on the speed of the sign language movements. For example, if the sign language movements are fast, the camera unit sets the frame rate higher to capture the movements smoothly. For example, if the sign language movements are fast, the camera unit can set the frame rate to 60 fps to capture the movements smoothly. Also, if the sign language movements are slow, the camera unit can set the frame rate lower to save data. For example, if the sign language movements are slow, the camera unit can set the frame rate to 30 fps to save data. Also, if the sign language movements are not constant, the camera unit can adjust the frame rate in real time depending on the changes in the movements. For example, if the sign language movements speed up or slow down, the camera unit can dynamically change the frame rate to capture the movements smoothly. As a result, by adjusting the frame rate depending on the speed of the sign language movements, the movements can be captured smoothly. Some or all of the above-mentioned processing in the camera unit may be performed using, for example, AI, or may be performed without AI. For example, the camera unit can analyze the speed of the sign language movements using AI and automatically adjust the frame rate.

[0035] The camera unit can automatically remove the background of the sign language actions during shooting and emphasize only the sign language actions. For example, when the background is complex, the camera unit uses a background removal algorithm to extract only the sign language actions. For example, when the background is complex, the camera unit can use background separation technology using deep learning to extract only the sign language actions. Furthermore, when the background is monochromatic, the camera unit can also use chromakey technology to emphasize the sign language actions. For example, when the background is monochromatic, the camera unit can use chromakey technology to remove the background and emphasize the sign language actions. Furthermore, when the background is moving, the camera unit can also use motion detection technology to emphasize the sign language actions. For example, when the background is moving, the camera unit can use motion detection technology to emphasize the sign language actions. In this way, by removing the background, the sign language actions can be captured more clearly. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without AI. For example, the camera unit can optimize the background removal algorithm using AI to emphasize the sign language actions.

[0036] The camera unit can select an appropriate camera layout based on the user's position information when capturing images. For example, when the user is in the center, the camera unit can evenly arrange multiple cameras. For example, when the user is in the center, three cameras can be arranged in a triangular shape to capture sign language movements from multiple angles. Furthermore, when the user is at the edge, the cameras can be arranged to match the user's position. For example, when the user is at the edge, the cameras can be arranged to match the user's position to accurately capture sign language movements. Furthermore, when the user moves, the camera layout can be dynamically changed. For example, when the user moves, the camera layout can be dynamically changed to always capture sign language movements from the optimal angle. This enables optimal capturing by selecting the camera layout based on the user's position information. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without using AI. For example, the camera unit can analyze the user's position information using AI and automatically select the camera layout.

[0037] The image capturing unit can automatically apply optimal image capturing settings by referring to the user's past sign language action history when capturing an image. The image capturing unit, for example, automatically applies camera settings previously used by the user. For example, the image capturing unit can automatically apply the camera angle and zoom level previously used by the user to optimally capture sign language actions. The image capturing unit can also set an optimal frame rate based on the user's past sign language action history. For example, the image capturing unit can analyze the user's past sign language action history and set an optimal frame rate. The image capturing unit can also analyze the user's past sign language action history and set an optimal camera angle. For example, the image capturing unit can set an optimal camera angle based on the user's past sign language action history to accurately capture sign language actions. This allows the image capturing unit to automatically apply optimal image capturing settings by referring to the past sign language action history. Some or all of the above-described processing in the image capturing unit may be performed using, for example, AI, or may be performed without using AI. For example, the image capturing unit can analyze the user's past sign language action history using AI and automatically apply optimal image capturing settings.

[0038] The analysis unit can improve the analysis accuracy so that even subtle movements in sign language movements can be detected during analysis. The analysis unit, for example, detects subtle movements using high-resolution images. For example, the analysis unit can capture sign language movements using a high-resolution camera and detect subtle movements. The analysis unit can also improve the analysis accuracy by increasing the number of layers in a convolutional neural network (CNN). For example, increasing the number of CNN layers can extract more features and improve the analysis accuracy. The analysis unit can also improve the analysis accuracy using data augmentation technology. For example, data augmentation technology can be used to increase the variety of sign language movements and improve the analysis accuracy. This improves the analysis accuracy of sign language movements by detecting subtle movements. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze sign language movements using AI to detect subtle movements.

[0039] During analysis, the analysis unit can improve the accuracy of the analysis result based on the context of the sign language movements. The analysis unit, for example, performs analysis while taking into account the context of the sign language movements. For example, the meaning of the sign language can be understood by taking into account the context of the sign language movements. The analysis unit can also use a recurrent neural network (RNN) to understand the context of the sign language movements. For example, the RNN can be used to understand the context of the sign language movements and improve the analysis accuracy. The analysis unit can also improve the analysis accuracy by using a dataset that takes into account the context of the sign language movements. For example, the analysis accuracy can be improved by using a dataset that takes into account the context of the sign language movements. In this way, the accuracy of the analysis result is improved by taking the context of the sign language movements into account. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the context of the sign language movements using AI to improve the accuracy of the analysis result.

[0040] During analysis, the analysis unit can optimize the analysis algorithm based on regional and individual differences in sign language movements. The analysis unit, for example, performs analysis taking into account regional differences in sign language movements. For example, the analysis accuracy can be improved by taking into account regional differences in sign language movements. The analysis unit can also perform analysis taking into account individual differences in sign language movements. For example, the analysis accuracy can be improved by taking into account individual differences in sign language movements. The analysis unit can also optimize the analysis algorithm using a dataset that takes into account regional and individual differences. For example, the analysis algorithm can be optimized using a dataset that takes into account regional and individual differences. By taking into account regional and individual differences, the accuracy of the analysis algorithm is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze regional and individual differences using AI to optimize the analysis algorithm.

[0041] During analysis, the analysis unit can improve the analysis accuracy based on literature related to sign language movements. The analysis unit, for example, performs analysis by referring to the latest research papers on sign language movements. For example, the analysis accuracy can be improved by referring to the latest research papers on sign language movements. The analysis unit can also incorporate related literature on sign language movements into a dataset. For example, the analysis accuracy can be improved by incorporating related literature on sign language movements into a dataset. The analysis unit can also improve the analysis algorithm based on literature on sign language movements. For example, the analysis algorithm can be improved based on literature on sign language movements to improve the analysis accuracy. As a result, the analysis accuracy is improved by referring to related literature. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze related literature on sign language movements using AI to improve the analysis accuracy.

[0042] The generation unit can adjust the level of detail of the text based on the importance of the sign language content during generation. For example, the generation unit describes important sign language content in detail. For example, important sign language content can be described in detail to accurately convey the meaning of the sign language. In addition, less important sign language content can be described concisely. For example, less important sign language content can be described concisely to shorten the length of the text. In addition, the level of detail of the text can be dynamically adjusted according to the importance of the sign language content. For example, the level of detail of the text can be dynamically adjusted according to the importance of the sign language content to describe important content in detail. In this way, important content can be described in detail by adjusting the level of detail of the text according to the importance of the sign language content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the importance of the sign language content using AI and automatically adjust the level of detail of the text.

[0043] The generation unit can apply different generation algorithms depending on the category of the sign language content during generation. For example, if the sign language content is everyday conversation, the generation unit uses a general generation algorithm. For example, if the sign language content is everyday conversation, the generation unit can use a general generation algorithm to generate natural language text. Furthermore, if the sign language content includes technical terms, the generation unit can use a generation algorithm corresponding to the technical terms. For example, if the sign language content includes technical terms, the generation unit can use a generation algorithm corresponding to the technical terms to generate natural language text. Furthermore, if the sign language content includes emotions, the generation unit can use a generation algorithm corresponding to emotional expressions. For example, if the sign language content includes emotions, the generation unit can use a generation algorithm corresponding to emotional expressions to generate natural language text. In this way, by applying a generation algorithm depending on the category of the sign language content, more appropriate text is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the category of the sign language content using AI and automatically apply an appropriate generation algorithm.

[0044] The generation unit can determine the priority of texts based on the submission time of the sign language content during generation. For example, the generation unit prioritizes the conversion of sign language content with an upcoming submission deadline into text. For example, the generation unit prioritizes the conversion of sign language content with an upcoming submission deadline into text, thereby enabling important content to be provided quickly. Furthermore, the generation unit can postpone the conversion of sign language content with a distant submission deadline. For example, the generation unit can prioritize the conversion of important content by postponing the conversion of sign language content with a distant submission deadline. Furthermore, the generation unit can dynamically adjust the conversion priority according to the submission time. For example, the generation unit can dynamically adjust the conversion priority according to the submission time, thereby enabling important content to be preferentially converted into text. Thus, by determining the conversion priority according to the submission time, important content can be preferentially converted into text. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the submission time of the sign language content using AI and automatically determine the conversion priority.

[0045] The generation unit can adjust the order of text based on the relevance of the sign language content during generation. For example, the generation unit prioritizes the conversion of highly relevant sign language content into text. For example, by prioritizing the conversion of highly relevant sign language content into text, the meaning of the sign language can be accurately conveyed. The generation unit can also postpone the conversion of less relevant sign language content. For example, the generation unit can prioritize the conversion of more important sign language content into text, while postponing the conversion of less relevant sign language content into text. The generation unit can also dynamically adjust the order of text based on the relevance of the sign language content. For example, by dynamically adjusting the order of text based on the relevance of the sign language content, the meaning of the sign language can be accurately conveyed. In this way, by adjusting the order of text based on the relevance of the sign language content, more understandable text is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the relevance of the sign language content using AI and automatically adjust the order of text.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The sign language recognition system can analyze the speed of a user's sign language movements in real time and dynamically adjust the parameters of the analysis algorithm according to the speed of the movements. For example, if the sign language movements are fast, the sensitivity of the analysis algorithm can be set higher to accommodate the speed of the movements. On the other hand, if the sign language movements are slow, the sensitivity of the analysis algorithm can be set lower to more accurately capture the details of the movements. Furthermore, if the sign language movements are not constant, the parameters of the analysis algorithm can be adjusted in real time according to changes in the movements. In this way, by adjusting the parameters of the analysis algorithm according to the speed of the sign language movements, analysis accuracy can be improved.

[0048] The sign language recognition system can analyze the characteristics of a user's sign language movements and automatically adjust the camera's shooting settings based on the movement characteristics. For example, if the sign language movements are large, the camera's zoom can be reduced and the image can be shot with a wide angle. If the sign language movements are detailed, the camera's zoom can be set higher to capture the detailed movements. Furthermore, if the sign language movements are complex, the camera's frame rate can be set higher to capture the movements smoothly. This allows for more appropriate shooting by automatically adjusting the camera settings according to the characteristics of the sign language movements.

[0049] A sign language recognition system can analyze background information of a user's sign language actions and adjust the parameters of the analysis algorithm based on the background information. For example, if the background is complex, the sensitivity of the analysis algorithm can be set higher to accurately capture the sign language actions. On the other hand, if the background is simple, the sensitivity of the analysis algorithm can be set lower to more accurately analyze the details of the actions. Furthermore, if the background is moving, motion detection technology can be used to emphasize the sign language actions. In this way, by adjusting the parameters of the analysis algorithm according to the background information, analysis accuracy can be improved.

[0050] A sign language recognition system can analyze the context of a user's sign language actions and adjust the parameters of the analysis algorithm based on the context. For example, the sensitivity of the analysis algorithm can be adjusted taking into account the context of the sign language actions to accurately understand the meaning of the sign language. Recurrent neural networks (RNNs) can also be used to understand the context of sign language actions. Furthermore, analysis algorithms can be optimized using datasets that take into account the context of sign language actions. This improves the accuracy of the analysis results by taking into account the context of sign language actions.

[0051] The sign language recognition system can analyze regional and individual differences in the sign language movements of users and optimize the analysis algorithm based on these regional and individual differences. For example, the analysis algorithm parameters can be adjusted to take into account regional differences in sign language movements, improving analysis accuracy. The analysis algorithm parameters can also be adjusted to take into account individual differences in sign language movements. Furthermore, the analysis algorithm can be optimized using a dataset that takes into account regional and individual differences. This improves the accuracy of the analysis algorithm by taking into account regional and individual differences.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The camera unit uses multiple cameras to capture sign language movements in real time. For example, the camera unit can be equipped with multiple cameras that capture sign language movements from different angles, and three cameras can be arranged in a triangle to capture sign language movements from multiple angles. The camera unit can also automatically remove the background of the sign language movements and highlight only the sign language movements. If the background is complex, a background removal algorithm is used to extract only the sign language movements. Step 2: The analysis unit uses deep learning to analyze the sign language movements and identify the content of the sign language. For example, the analysis unit uses a convolutional neural network (CNN) to analyze the sign language movements and improve the analysis accuracy so that even the subtle movements of the sign language movements can be detected. Step 3: The generation unit converts the sign language content identified by the analysis unit into natural language using the generation AI and outputs it as text. For example, the generation unit can use the results of analyzing sign language movements as input, have the generation AI generate natural language text, and save the generated text.

[0054] (Example 2) A sign language recognition system according to an embodiment of the present invention is a system that performs image recognition of sign language and verbalizes it using a generation AI. This sign language recognition system uses multiple cameras to capture sign language movements in real time, analyzes the sign language movements using image recognition technology based on deep learning, and converts the sign language content into natural language using a generation AI, which then outputs the text. For example, the sign language recognition system enables smooth communication between people who use sign language. This facilitates communication with people who do not understand sign language, thereby promoting social participation by people who use sign language. Furthermore, by saving the sign language content as text, the content can be reviewed later. Specifically, the sign language recognition system uses multiple cameras to capture sign language movements in real time. Next, it analyzes the sign language movements using image recognition technology based on deep learning to identify the sign language content. Finally, it uses a generation AI to convert the sign language content into natural language and output it as text. This enables smooth communication between people who use sign language. For example, it facilitates communication with people who do not understand sign language, thereby promoting social participation by people who use sign language. Furthermore, by saving the sign language content as text, the content can be reviewed later. This allows the sign language recognition system to facilitate smooth communication between people who use sign language.

[0055] A sign language recognition system according to an embodiment includes a camera unit, an analyzer, and a generator. The camera unit uses multiple cameras to capture sign language movements in real time. The camera unit includes, for example, multiple cameras that capture sign language movements from different angles. For example, the camera unit may arrange three cameras in a triangular configuration to capture sign language movements from multiple angles. The camera unit can also automatically remove the background from the sign language movements and emphasize only the sign language movements. For example, when the background is complex, a background removal algorithm is used to extract only the sign language movements. The analyzer uses deep learning to analyze the sign language movements and identify the content of the sign language. For example, the analyzer uses a convolutional neural network (CNN) to analyze the sign language movements. For example, the analyzer improves the accuracy of the analysis so that even subtle movements in the sign language movements can be detected. The generator converts the content of the sign language identified by the analyzer into natural language using a generation AI and outputs the text. For example, the generator uses the results of the analysis of the sign language movements as input, and the generation AI generates text in natural language. For example, the generation unit can also save the generated text. This allows the sign language recognition system to capture sign language movements in real time, analyze them, and convert them into natural language, enabling smoother communication between people who use sign language. For example, this makes it easier to communicate with people who cannot understand sign language, promoting the social participation of people who use sign language. In addition, by saving the content of the sign language as text, it is possible to check the content later.

[0056] The sign language recognition system includes multiple cameras that capture sign language actions from different angles. The camera unit, for example, has three cameras arranged in a triangle, allowing it to capture sign language actions from multiple angles. For example, one camera captures sign language actions from the front, another from the side, and still another from above. This allows for more detailed analysis of sign language actions. For example, it can accurately capture subtle movements of sign language actions and changes in hand position and angle. This allows for more detailed analysis by capturing sign language actions from different angles. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without using AI. For example, the camera unit may automatically adjust the camera position and angle using AI to optimize camera placement.

[0057] The analysis unit can analyze sign language movements using a convolutional neural network. The analysis unit analyzes sign language movements using, for example, a convolutional neural network (CNN). For example, the CNN extracts features of sign language movements and identifies the content of the sign language. For example, the CNN analyzes patterns of hand position and movement to understand the meaning of the sign language. The analysis unit can also improve the analysis accuracy so that even subtle movements of sign language movements can be detected. For example, subtle movements can be detected using high-resolution images. The analysis unit can also improve the analysis accuracy by increasing the number of layers of the convolutional neural network. For example, increasing the number of CNN layers can extract more features and improve the analysis accuracy. Thus, using a convolutional neural network improves the analysis accuracy of sign language movements. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can analyze sign language movements using AI to extract features of sign language movements.

[0058] The generation unit can input the results of analyzing sign language movements, and the generation AI can generate natural language text. For example, the generation unit inputs the results of analyzing sign language movements, and the generation AI generates natural language text. For example, the generation AI converts the sign language content into natural language and outputs it as text. For example, the generation AI converts the sign language content into natural language using technologies such as GPT-4 or Transformer. The generation unit can also save the generated text. For example, the generation unit saves the generated text as a text file. The generation unit can also save the generated text in a database. This improves the accuracy of converting sign language content into natural language by using the generation AI. Some or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the results of analyzing sign language movements to the generation AI and have the generation AI execute the natural language text.

[0059] The generation unit can save the generated text. For example, the generation unit saves the generated text as a text file. For example, the generation unit can also save the generated text in a database. For example, the generation unit can also save the generated text in cloud storage. By saving the generated text, it becomes possible to check the content later. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically classify and save the generated text using AI.

[0060] The sign language recognition system includes specific means for estimating a user's emotion and automatically adjusting the camera's shooting angle and zoom based on the estimated user's emotion. The camera unit, for example, estimates the user's emotion and automatically adjusts the camera's shooting angle and zoom based on the estimated user's emotion. For example, if the user is nervous, the camera zoom can be reduced and the camera can be photographed with a wide angle to relax the user. Also, if the user is relaxed, the camera zoom can be set higher to capture the sign language movements in detail. Also, if the user is excited, the camera frame rate can be set higher depending on the speed of the movements to capture the movements clearly. This enables more appropriate shooting by automatically adjusting the camera settings according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the camera unit can be performed using, for example, AI, or without AI. For example, the camera unit can use AI to analyze the user's emotions and automatically adjust the camera settings to optimize them.

[0061] The camera unit can dynamically change the frame rate during shooting depending on the speed of the sign language movements. For example, if the sign language movements are fast, the camera unit sets the frame rate higher to capture the movements smoothly. For example, if the sign language movements are fast, the camera unit can set the frame rate to 60 fps to capture the movements smoothly. Also, if the sign language movements are slow, the camera unit can set the frame rate lower to save data. For example, if the sign language movements are slow, the camera unit can set the frame rate to 30 fps to save data. Also, if the sign language movements are not constant, the camera unit can adjust the frame rate in real time depending on the changes in the movements. For example, if the sign language movements speed up or slow down, the camera unit can dynamically change the frame rate to capture the movements smoothly. As a result, by adjusting the frame rate depending on the speed of the sign language movements, the movements can be captured smoothly. Some or all of the above-mentioned processing in the camera unit may be performed using, for example, AI, or may be performed without AI. For example, the camera unit can analyze the speed of the sign language movements using AI and automatically adjust the frame rate.

[0062] The camera unit can automatically remove the background of the sign language actions during shooting and emphasize only the sign language actions. For example, when the background is complex, the camera unit uses a background removal algorithm to extract only the sign language actions. For example, when the background is complex, the camera unit can use background separation technology using deep learning to extract only the sign language actions. Furthermore, when the background is monochromatic, the camera unit can also use chromakey technology to emphasize the sign language actions. For example, when the background is monochromatic, the camera unit can use chromakey technology to remove the background and emphasize the sign language actions. Furthermore, when the background is moving, the camera unit can also use motion detection technology to emphasize the sign language actions. For example, when the background is moving, the camera unit can use motion detection technology to emphasize the sign language actions. In this way, by removing the background, the sign language actions can be captured more clearly. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without AI. For example, the camera unit can optimize the background removal algorithm using AI to emphasize the sign language actions.

[0063] The sign language recognition system includes specific means for estimating a user's emotion and determining the priority of sign language actions to be captured based on the estimated user emotion. The capture unit, for example, estimates the user's emotion and determines the priority of sign language actions to be captured based on the estimated user emotion. For example, if the user is nervous, important sign language actions can be captured with priority. Also, if the user is relaxed, all sign language actions can be captured equally. Also, if the user is in a hurry, key sign language actions can be captured with priority. This allows important sign language actions to be captured with priority by determining the priority of capture according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can analyze the user's emotion using AI and automatically determine the priority of capture.

[0064] The camera unit can select an appropriate camera layout based on the user's position information when capturing images. For example, when the user is in the center, the camera unit can evenly arrange multiple cameras. For example, when the user is in the center, three cameras can be arranged in a triangular shape to capture sign language movements from multiple angles. Furthermore, when the user is at the edge, the cameras can be arranged to match the user's position. For example, when the user is at the edge, the cameras can be arranged to match the user's position to accurately capture sign language movements. Furthermore, when the user moves, the camera layout can be dynamically changed. For example, when the user moves, the camera layout can be dynamically changed to always capture sign language movements from the optimal angle. This enables optimal capturing by selecting the camera layout based on the user's position information. Some or all of the above-described processing in the camera unit may be performed using, for example, AI, or may be performed without using AI. For example, the camera unit can analyze the user's position information using AI and automatically select the camera layout.

[0065] The image capturing unit can automatically apply optimal image capturing settings by referring to the user's past sign language action history when capturing an image. The image capturing unit, for example, automatically applies camera settings previously used by the user. For example, the image capturing unit can automatically apply the camera angle and zoom level previously used by the user to optimally capture sign language actions. The image capturing unit can also set an optimal frame rate based on the user's past sign language action history. For example, the image capturing unit can analyze the user's past sign language action history and set an optimal frame rate. The image capturing unit can also analyze the user's past sign language action history and set an optimal camera angle. For example, the image capturing unit can set an optimal camera angle based on the user's past sign language action history to accurately capture sign language actions. This allows the image capturing unit to automatically apply optimal image capturing settings by referring to the past sign language action history. Some or all of the above-described processing in the image capturing unit may be performed using, for example, AI, or may be performed without using AI. For example, the image capturing unit can analyze the user's past sign language action history using AI and automatically apply optimal image capturing settings.

[0066] The sign language recognition system includes specific means for estimating a user's emotion and adjusting parameters of an analysis algorithm based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts parameters of the analysis algorithm based on the estimated user emotion. For example, if the user is nervous, the sensitivity of the analysis algorithm can be set high. Alternatively, if the user is relaxed, the sensitivity of the analysis algorithm can be set to normal. Alternatively, if the user is excited, the sensitivity of the analysis algorithm can be set to low. This improves analysis accuracy by adjusting the parameters of the analysis algorithm according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can analyze the user's emotion using AI and automatically adjust the parameters of the analysis algorithm.

[0067] The analysis unit can improve the analysis accuracy so that even subtle movements in sign language movements can be detected during analysis. The analysis unit, for example, detects subtle movements using high-resolution images. For example, the analysis unit can capture sign language movements using a high-resolution camera and detect subtle movements. The analysis unit can also improve the analysis accuracy by increasing the number of layers in a convolutional neural network (CNN). For example, increasing the number of CNN layers can extract more features and improve the analysis accuracy. The analysis unit can also improve the analysis accuracy using data augmentation technology. For example, data augmentation technology can be used to increase the variety of sign language movements and improve the analysis accuracy. This improves the analysis accuracy of sign language movements by detecting subtle movements. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze sign language movements using AI to detect subtle movements.

[0068] During analysis, the analysis unit can improve the accuracy of the analysis result based on the context of the sign language movements. The analysis unit, for example, performs analysis while taking into account the context of the sign language movements. For example, the meaning of the sign language can be understood by taking into account the context of the sign language movements. The analysis unit can also use a recurrent neural network (RNN) to understand the context of the sign language movements. For example, the RNN can be used to understand the context of the sign language movements and improve the analysis accuracy. The analysis unit can also improve the analysis accuracy by using a dataset that takes into account the context of the sign language movements. For example, the analysis accuracy can be improved by using a dataset that takes into account the context of the sign language movements. In this way, the accuracy of the analysis result is improved by taking the context of the sign language movements into account. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze the context of the sign language movements using AI to improve the accuracy of the analysis result.

[0069] The sign language recognition system includes specific means for estimating a user's emotion and adjusting the display method of the analysis results based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis results based on the estimated user emotion. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that focuses on the main points can be provided. This improves visibility by adjusting the display method of the analysis results according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can analyze the user's emotion using AI and automatically adjust the display method of the analysis results.

[0070] During analysis, the analysis unit can optimize the analysis algorithm based on regional and individual differences in sign language movements. The analysis unit, for example, performs analysis taking into account regional differences in sign language movements. For example, the analysis accuracy can be improved by taking into account regional differences in sign language movements. The analysis unit can also perform analysis taking into account individual differences in sign language movements. For example, the analysis accuracy can be improved by taking into account individual differences in sign language movements. The analysis unit can also optimize the analysis algorithm using a dataset that takes into account regional and individual differences. For example, the analysis algorithm can be optimized using a dataset that takes into account regional and individual differences. By taking into account regional and individual differences, the accuracy of the analysis algorithm is improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze regional and individual differences using AI to optimize the analysis algorithm.

[0071] During analysis, the analysis unit can improve the analysis accuracy based on literature related to sign language movements. The analysis unit, for example, performs analysis by referring to the latest research papers on sign language movements. For example, the analysis accuracy can be improved by referring to the latest research papers on sign language movements. The analysis unit can also incorporate related literature on sign language movements into a dataset. For example, the analysis accuracy can be improved by incorporating related literature on sign language movements into a dataset. The analysis unit can also improve the analysis algorithm based on literature on sign language movements. For example, the analysis algorithm can be improved based on literature on sign language movements to improve the analysis accuracy. As a result, the analysis accuracy is improved by referring to related literature. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can analyze related literature on sign language movements using AI to improve the analysis accuracy.

[0072] The sign language recognition system includes specific means for estimating a user's emotion and adjusting the expression style of the generated text based on the estimated user emotion. The generation unit, for example, estimates the user's emotion and adjusts the expression style of the generated text based on the estimated user emotion. For example, if the user is nervous, a simple and easy-to-understand expression style can be used. If the user is relaxed, a detailed expression style can be used. If the user is in a hurry, a simple and easy-to-understand expression style can be used. In this way, more appropriate text can be generated by adjusting the expression style of the text according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can analyze the user's emotion using AI and automatically adjust the expression style of the generated text.

[0073] The generation unit can adjust the level of detail of the text based on the importance of the sign language content during generation. For example, the generation unit describes important sign language content in detail. For example, important sign language content can be described in detail to accurately convey the meaning of the sign language. In addition, less important sign language content can be described concisely. For example, less important sign language content can be described concisely to shorten the length of the text. In addition, the level of detail of the text can be dynamically adjusted according to the importance of the sign language content. For example, the level of detail of the text can be dynamically adjusted according to the importance of the sign language content to describe important content in detail. In this way, important content can be described in detail by adjusting the level of detail of the text according to the importance of the sign language content. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the importance of the sign language content using AI and automatically adjust the level of detail of the text.

[0074] The generation unit can apply different generation algorithms depending on the category of the sign language content during generation. For example, if the sign language content is everyday conversation, the generation unit uses a general generation algorithm. For example, if the sign language content is everyday conversation, the generation unit can use a general generation algorithm to generate natural language text. Furthermore, if the sign language content includes technical terms, the generation unit can use a generation algorithm corresponding to the technical terms. For example, if the sign language content includes technical terms, the generation unit can use a generation algorithm corresponding to the technical terms to generate natural language text. Furthermore, if the sign language content includes emotions, the generation unit can use a generation algorithm corresponding to emotional expressions. For example, if the sign language content includes emotions, the generation unit can use a generation algorithm corresponding to emotional expressions to generate natural language text. In this way, by applying a generation algorithm depending on the category of the sign language content, more appropriate text is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the category of the sign language content using AI and automatically apply an appropriate generation algorithm.

[0075] The sign language recognition system includes specific means for estimating a user's emotion and adjusting the length of generated text based on the estimated user emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of generated text based on the estimated user emotion. For example, if the user is nervous, a short, to-the-point text can be generated. Also, if the user is relaxed, a longer text with detailed explanations can be generated. Also, if the user is in a hurry, a concise, short text can be generated. This allows for more appropriate text to be generated by adjusting the length of the text according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using AI, or may be performed without AI. For example, the generation unit can analyze the user's emotion using AI and automatically adjust the length of the generated text.

[0076] The generation unit can determine the priority of texts based on the submission time of the sign language content during generation. For example, the generation unit prioritizes the conversion of sign language content with an upcoming submission deadline into text. For example, the generation unit prioritizes the conversion of sign language content with an upcoming submission deadline into text, thereby enabling important content to be provided quickly. Furthermore, the generation unit can postpone the conversion of sign language content with a distant submission deadline. For example, the generation unit can prioritize the conversion of important content by postponing the conversion of sign language content with a distant submission deadline. Furthermore, the generation unit can dynamically adjust the conversion priority according to the submission time. For example, the generation unit can dynamically adjust the conversion priority according to the submission time, thereby enabling important content to be preferentially converted into text. Thus, by determining the conversion priority according to the submission time, important content can be preferentially converted into text. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the submission time of the sign language content using AI and automatically determine the conversion priority.

[0077] The generation unit can adjust the order of text based on the relevance of the sign language content during generation. For example, the generation unit prioritizes the conversion of highly relevant sign language content into text. For example, by prioritizing the conversion of highly relevant sign language content into text, the meaning of the sign language can be accurately conveyed. The generation unit can also postpone the conversion of less relevant sign language content. For example, the generation unit can prioritize the conversion of more important sign language content into text, while postponing the conversion of less relevant sign language content into text. The generation unit can also dynamically adjust the order of text based on the relevance of the sign language content. For example, by dynamically adjusting the order of text based on the relevance of the sign language content, the meaning of the sign language can be accurately conveyed. In this way, by adjusting the order of text based on the relevance of the sign language content, more understandable text is generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can analyze the relevance of the sign language content using AI and automatically adjust the order of text. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned photographing unit, analysis unit, and generation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the photographing unit photographs sign language movements in real time using the camera 42 of the smart device 14. The analysis unit analyzes the sign language movements using image recognition technology that employs deep learning by the specific processing unit 290 of the data processing device 12. The generation unit converts the sign language content into natural language using a generation AI by the specific processing unit 290 of the data processing device 12 and outputs it as text. Each of the elements of the photographing unit, analysis unit, and generation unit may also be realized by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-described image capturing unit, analysis unit, and generation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the image capturing unit captures sign language movements in real time using the camera 42 of the smart glasses 214. The analysis unit analyzes the sign language movements using image recognition technology that employs deep learning by the specific processing unit 290 of the data processing device 12. The generation unit converts the sign language content into natural language using a generation AI by the specific processing unit 290 of the data processing device 12 and outputs it as text. Each of the elements of the image capturing unit, analysis unit, and generation unit may also be realized by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned image capturing unit, analysis unit, and generation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the image capturing unit captures sign language movements in real time using the camera 42 of the headset type terminal 314. The analysis unit analyzes the sign language movements using image recognition technology that employs deep learning by the specific processing unit 290 of the data processing device 12. The generation unit converts the sign language content into natural language using a generation AI by the specific processing unit 290 of the data processing device 12, and outputs it as text. The elements of the image capturing unit, analysis unit, and generation unit may also be realized by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned photographing unit, analysis unit, and generation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the photographing unit photographs sign language movements in real time using the camera 42 of the robot 414. The analysis unit analyzes the sign language movements using image recognition technology that employs deep learning by the specific processing unit 290 of the data processing device 12. The generation unit converts the sign language content into natural language using a generation AI by the specific processing unit 290 of the data processing device 12, and outputs it as text. The elements of the photographing unit, analysis unit, and generation unit may also be realized by the control unit 46A of the robot 414.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The sign language recognition system can analyze the speed of a user's sign language movements in real time and dynamically adjust the parameters of the analysis algorithm according to the speed of the movements. For example, if the sign language movements are fast, the sensitivity of the analysis algorithm can be set higher to accommodate the speed of the movements. On the other hand, if the sign language movements are slow, the sensitivity of the analysis algorithm can be set lower to more accurately capture the details of the movements. Furthermore, if the sign language movements are not constant, the parameters of the analysis algorithm can be adjusted in real time according to changes in the movements. In this way, by adjusting the parameters of the analysis algorithm according to the speed of the sign language movements, analysis accuracy can be improved.

[0080] The sign language recognition system can analyze the characteristics of a user's sign language movements and automatically adjust the camera's shooting settings based on the movement characteristics. For example, if the sign language movements are large, the camera's zoom can be reduced and the image can be shot with a wide angle. If the sign language movements are detailed, the camera's zoom can be set higher to capture the detailed movements. Furthermore, if the sign language movements are complex, the camera's frame rate can be set higher to capture the movements smoothly. This allows for more appropriate shooting by automatically adjusting the camera settings according to the characteristics of the sign language movements.

[0081] A sign language recognition system can analyze background information of a user's sign language actions and adjust the parameters of the analysis algorithm based on the background information. For example, if the background is complex, the sensitivity of the analysis algorithm can be set higher to accurately capture the sign language actions. On the other hand, if the background is simple, the sensitivity of the analysis algorithm can be set lower to more accurately analyze the details of the actions. Furthermore, if the background is moving, motion detection technology can be used to emphasize the sign language actions. In this way, by adjusting the parameters of the analysis algorithm according to the background information, analysis accuracy can be improved.

[0082] A sign language recognition system can analyze the context of a user's sign language actions and adjust the parameters of the analysis algorithm based on the context. For example, the sensitivity of the analysis algorithm can be adjusted taking into account the context of the sign language actions to accurately understand the meaning of the sign language. Recurrent neural networks (RNNs) can also be used to understand the context of sign language actions. Furthermore, analysis algorithms can be optimized using datasets that take into account the context of sign language actions. This improves the accuracy of the analysis results by taking into account the context of sign language actions.

[0083] The sign language recognition system can analyze regional and individual differences in the sign language movements of users and optimize the analysis algorithm based on these regional and individual differences. For example, the analysis algorithm parameters can be adjusted to take into account regional differences in sign language movements, improving analysis accuracy. The analysis algorithm parameters can also be adjusted to take into account individual differences in sign language movements. Furthermore, the analysis algorithm can be optimized using a dataset that takes into account regional and individual differences. This improves the accuracy of the analysis algorithm by taking into account regional and individual differences.

[0084] The sign language recognition system can estimate the user's emotions and adjust the parameters of the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, the sensitivity of the analysis algorithm can be set higher to correspond to the speed of the user's movements. If the user is relaxed, the sensitivity of the analysis algorithm can be set to standard. Furthermore, if the user is excited, the sensitivity of the analysis algorithm can be set to lower. In this way, the analysis accuracy can be improved by adjusting the parameters of the analysis algorithm according to the user's emotions.

[0085] The sign language recognition system can estimate the user's emotions and automatically adjust the camera's shooting settings based on the estimated user's emotions. For example, if the user is nervous, the camera's zoom can be reduced and the camera can be set to a wide angle. If the user is relaxed, the camera's zoom can be set to a higher angle to capture the sign language movements in detail. Furthermore, if the user is excited, the camera's frame rate can be set higher depending on the speed of the movements to capture the movements clearly. This allows for more appropriate shooting by automatically adjusting the camera settings according to the user's emotions.

[0086] The sign language recognition system can estimate the user's emotions and adjust the way the generated text is expressed based on the estimated user's emotions. For example, if the user is nervous, a simple and easy-to-understand expression can be used. If the user is relaxed, an expression containing detailed information can be used. Furthermore, if the user is in a hurry, an expression that focuses on the main points can be used. In this way, by adjusting the way the text is expressed according to the user's emotions, more appropriate text can be generated.

[0087] The sign language recognition system can estimate the user's emotions and adjust the length of the generated text based on the estimated user emotions. For example, if the user is nervous, it can generate short, to-the-point text. If the user is relaxed, it can generate longer text with detailed explanations. Furthermore, if the user is in a hurry, it can generate concise, short text. In this way, more appropriate text can be generated by adjusting the length of the text according to the user's emotions.

[0088] The sign language recognition system can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. In this way, visibility can be improved by adjusting the display method of the analysis results according to the user's emotions.

[0089] The processing flow of the second embodiment will be briefly explained below.

[0090] Step 1: The camera unit uses multiple cameras to capture sign language movements in real time. For example, the camera unit can be equipped with multiple cameras that capture sign language movements from different angles, and three cameras can be arranged in a triangle to capture sign language movements from multiple angles. The camera unit can also automatically remove the background of the sign language movements and highlight only the sign language movements. If the background is complex, a background removal algorithm is used to extract only the sign language movements. Step 2: The analysis unit uses deep learning to analyze the sign language movements and identify the content of the sign language. For example, the analysis unit uses a convolutional neural network (CNN) to analyze the sign language movements and improve the analysis accuracy so that even the subtle movements of the sign language movements can be detected. Step 3: The generation unit converts the sign language content identified by the analysis unit into natural language using the generation AI and outputs it as text. For example, the generation unit can use the results of analyzing sign language movements as input, have the generation AI generate natural language text, and save the generated text.

[0091] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0092] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0093] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0094] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0095] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0096] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0097] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0098] 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.

[0099] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0100] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0101] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0102] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0103] 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.

[0104] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0105] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0106] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0108] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0109] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0110] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 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.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] 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.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] 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.

[0119] 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.

[0120] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0125] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 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.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] 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.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0135] 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.

[0136] 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.

[0137] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0142] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0145] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0146] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0147] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0148] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0149] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0150] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0151] 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.

[0152] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0153] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0154] 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.

[0155] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0156] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0157] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0158] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0159] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0160] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0161] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0162] [Explanation of symbols]

[0163] 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 camera unit that uses multiple cameras to capture sign language movements in real time; an analysis unit that analyzes the sign language actions captured by the imaging unit using deep learning and identifies the content of the sign language; a generation unit that converts the sign language content identified by the analysis unit into natural language using a generation AI and outputs the natural language content as text; Equipped with A system characterized by:

2. The imaging unit is Equipped with multiple cameras that capture sign language movements from different angles The system of claim 1 .

3. The analysis unit Analyzing sign language movements using convolutional neural networks The system of claim 1 .

4. The generation unit Using the results of analyzing sign language movements as input, generative AI generates text in natural language. The system of claim 1 .

5. The generation unit Save the generated text The system of claim 1 .

6. The imaging unit is It includes specific means for estimating the user's emotions and automatically adjusting the camera's shooting angle and zoom based on the estimated user's emotions. The system of claim 1 .

7. The imaging unit is When recording, the frame rate is dynamically changed according to the speed of sign language movements. The system of claim 1 .

8. The imaging unit is When taking a photo, the background of the sign language action is automatically removed, and only the sign language action is emphasized. The system of claim 1 .

Images