System

Abstract

An object of the system according to the embodiment is to realize a robot operation that flexibly responds to a user's request.SOLUTION: A system includes a reception unit, an analysis unit, a generation unit, and a control unit. The reception unit receives a voice input of a user. The analysis unit analyzes the voice input received by the reception unit and grasps a surrounding situation using the camera and the LIDAR sensor. The generation unit generates a Python code for realizing a robot operation for responding to the request on the basis of the surrounding situation grasped by the analysis unit. The control unit transmits the Python code generated by the generation unit to the control system of the robot and executes the Python code.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult for a robot to flexibly respond to movements that it has not learned, and there is room for improvement.

[0005] The system according to the embodiment aims to realize robot operations that flexibly respond to user requests. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a control unit. The reception unit receives a voice input from a user. The analysis unit analyzes the voice input received by the reception unit and grasps the surrounding situation using a camera and a LIDAR sensor. The generation unit generates Python code that realizes robot operations to respond to requests based on the surrounding situation grasped by the analysis unit. The control unit transmits the Python code generated by the generation unit to a control system of the robot and executes it. [Effects of the Invention]

[0007] The system according to the embodiment can realize robot operations that flexibly respond to user requests. [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 robot control system according to an embodiment of the present invention utilizes multimodal generative AI to realize actions that respond to a user's simple voice input. In this robot control system, the user inputs a simple request to a robot, and the generative AI analyzes the voice input and uses a camera and LIDAR sensor to grasp the surrounding situation. The generative AI generates Python code that implements the robot's actions to respond to the request and sends the code to the robot's control system for execution. For example, if a user inputs a request to a robot, such as "Pick up the book on the table," the generative AI analyzes the request and grasps the surrounding situation using the robot's camera and LIDAR sensor. Next, the generative AI generates action code for picking up the book and has the robot execute the code. This causes the robot to pick up the book from the table. This system enables the robot to flexibly respond to user requests, even if it has not previously learned the action. This system can be used in a variety of situations, such as household chores and factory work. Furthermore, because the generative AI grasps the surrounding situation, the robot can operate safely. This allows the robot control system to realize robot movements according to the user's requests. For example, it can be used in a variety of situations, such as household chores or factory work. In addition, the generation AI can grasp the surrounding situation, allowing the robot to operate safely.

[0029] A robot control system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a control unit. The reception unit receives a user's voice input. Examples of the user's voice input include, but are not limited to, voice input using a microphone or a smartphone. The reception unit receives the user's voice in real time using, for example, a microphone. The reception unit can also receive voice using the voice input function of a smartphone. The reception unit can also convert the voice input into text data using voice recognition technology. For example, the reception unit converts the voice into text using voice recognition software and transmits the text to the analysis unit. The analysis unit analyzes the voice input and grasps the surrounding situation using a camera and a LIDAR sensor. For example, the analysis unit analyzes the voice input using natural language processing technology. The analysis unit can also acquire image data of the surrounding area using a camera and acquire distance data of the surrounding area using a LIDAR sensor. For example, the analysis unit can analyze image data acquired by the camera using image recognition technology to identify the position and shape of an object. The LIDAR sensor uses laser light to acquire distance data about the surroundings and grasp the position and shape of objects in three dimensions. The generation unit uses a generation AI to generate Python code that enables the robot to operate in response to a request, based on the surrounding conditions grasped by the analysis unit. The generation unit generates the Python code using, for example, a generation AI (e.g., a Transformer model). The generation unit can also train the generation AI using deep learning technology. For example, the generation unit trains the generation AI with a large amount of code data to generate code according to the request. The generation unit inputs a prompt to the generation AI, such as "Please generate code to pick up the book on the table," and obtains the generated code. The control unit sends the Python code generated by the generation unit to the robot's control system and executes it. For example, the control unit sends the generated code to the robot in real time to control the robot's operation. The control unit can also monitor the execution results of the generated code and correct it as necessary. For example, the control unit monitors the robot's operation in real time and generates and sends correction code if an abnormality occurs.As a result, the robot control system according to the embodiment can realize robot operations according to user requests. For example, the robot control system can flexibly respond to user requests and can be used in a variety of situations, such as household chores and factory work. Furthermore, because the generation AI understands the surrounding situation, the robot can operate safely.

[0030] The generation unit can generate Python code using a generation AI. The generation unit generates Python code using, for example, a generation AI (e.g., a Transformer model). The generation AI has learned a large amount of code data and has advanced natural language processing capabilities. The generation unit inputs a prompt to the generation AI, such as "Please generate code to pick up the book on the table," and obtains the generated code. The generation unit can also train the generation AI using deep learning technology. For example, the generation unit trains the generation AI with a large amount of code data and generates code according to the request. This makes it possible to generate Python code using the generation AI. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI and obtains the generated code.

[0031] The analysis unit can grasp the surrounding situation using a camera and a LIDAR sensor. The analysis unit acquires image data of the surroundings using, for example, a camera. Examples of cameras include, but are not limited to, an RGB camera and a depth camera. The analysis unit analyzes the image data acquired by the camera using image recognition technology to identify the position and shape of an object. The analysis unit can also acquire distance data of the surroundings using a LIDAR sensor. Examples of LIDAR sensors include, but are not limited to, a rotary LIDAR and a fixed LIDAR. The analysis unit analyzes the distance data acquired by the LIDAR sensor to grasp the position and shape of an object in three dimensions. For example, the analysis unit identifies the position of an object using image data acquired by the camera, and grasps the shape of the object in three dimensions using the distance data acquired by the LIDAR sensor. In this way, the surrounding situation can be accurately grasped by using the camera and the LIDAR sensor. Some or all of the above-mentioned processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input image data acquired by a camera into AI and have the AI ​​identify the position and shape of an object.

[0032] The control unit can send the generated Python code to the robot's control system and execute it. For example, the control unit can send the generated code to the robot in real time and control the robot's operation. The control unit can also monitor the execution results of the generated code and correct it as necessary. For example, the control unit can monitor the robot's operation in real time and generate and send correction code if an abnormality occurs. The control unit can also record the execution results of the generated code as a log and analyze it later. For example, the control unit can collect the robot's operation log and evaluate the accuracy and efficiency of the operation. By doing so, the robot can execute the generated Python code to realize operation according to the user's request. Some or all of the above-mentioned processing in the control unit may be performed using AI or without AI. For example, the control unit can input the generated code to AI and have the AI ​​control the robot's operation.

[0033] The robot control system includes a monitoring unit that monitors the execution results of the generated code and corrects them as necessary. The monitoring unit monitors the execution results of the generated code and corrects them as necessary. For example, the monitoring unit monitors the execution results of the generated code in real time. The monitoring unit can also record the execution results of the generated code as a log and analyze it later. For example, the monitoring unit collects robot operation logs and evaluates the accuracy and efficiency of the operation. The monitoring unit can also generate correction codes based on the execution results of the generated code and send them to the robot. For example, the monitoring unit generates and sends correction codes when an abnormality occurs in the robot's operation. This allows the execution results of the generated code to be monitored and corrected as necessary, thereby improving the robot's operation accuracy. Some or all of the above-described processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input the execution results of the generated code into AI and have the AI ​​generate correction codes.

[0034] The generation unit can learn using deep learning. For example, the generation unit trains the generation AI using deep learning technology. Deep learning includes, but is not limited to, CNN (convolutional neural network) and RNN (recurrent neural network). The generation unit trains the generation AI with a large amount of code data to generate a code according to a request. For example, the generation unit inputs a prompt to the generation AI, such as "Please generate a code to pick up a book on the table," and obtains the generated code. The generation unit can also continuously provide learning data to the generation AI to improve generation accuracy. For example, the generation unit periodically trains the generation AI with new code data to generate code that corresponds to the latest technology. In this way, deep learning improves the learning accuracy of the generation unit. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI and obtains the generated code.

[0035] The reception unit can analyze the user's past voice input history and select an appropriate reception method. For example, the reception unit prioritizes reception of voice commands that the user has frequently used in the past. The reception unit can also predict and accept commands to be used in a specific time period based on the user's past voice input history. Furthermore, the reception unit can analyze the user's past voice input history and suggest the most efficient reception method. In this way, the optimal reception method can be selected by analyzing the past voice input history. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's voice input history data into AI and have the AI ​​select the optimal reception method.

[0036] The reception unit can perform filtering based on the user's current situation and environment when receiving voice input. For example, when the user is in a noisy environment, the reception unit applies noise cancellation to receive the voice input. The reception unit can also receive normal voice input when the user is in a quiet environment. Furthermore, when the user is moving, the reception unit can adjust the sensitivity of the voice input before receiving the voice input. This allows the voice input to be filtered according to the user's situation and environment, thereby receiving more appropriate voice input. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's environmental data into AI and have the AI ​​perform filtering of the voice input.

[0037] When receiving a voice input, the reception unit can select an appropriate reception means according to the user's input method. For example, if the user selects voice input, the reception unit receives the voice input using voice recognition. Furthermore, if the user selects text input, the reception unit can also receive the voice input using text analysis. Furthermore, if the user selects gesture input, the reception unit can also receive the voice input using gesture recognition. This allows for more appropriate voice input to be received by selecting the optimal reception means according to the user's input method. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's input method data into AI and have the AI ​​select the optimal reception means.

[0038] When receiving a voice input, the reception unit can prioritize receiving a highly relevant input by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit can prioritize receiving a voice input related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving a voice input related to the user's destination. Furthermore, when the user is at home, the reception unit can also prioritize receiving a voice input related to the user's home. In this way, by preferentially receiving a highly relevant voice input based on the user's geographical location information, more appropriate voice input is received. Some or all of the above-described processing in the reception unit may be performed using AI or without AI. For example, the reception unit can input the user's geographical location information data to AI and cause the AI ​​to select a highly relevant voice input.

[0039] When receiving a voice input, the reception unit can analyze the user's social media activity and receive related input. For example, the reception unit can preferentially receive voice input related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and receive related voice input. Furthermore, the reception unit can also receive related voice input by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, related voice input is preferentially received. Some or all of the above-described processing by the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data into AI and have the AI ​​select related voice input.

[0040] The reception unit can customize the reception method by reflecting the user's past feedback when receiving voice input. For example, the reception unit can suggest an optimal voice input reception method based on feedback provided by the user in the past. The reception unit can also preferentially accept a specific voice input method based on the user's past feedback. Furthermore, the reception unit can analyze the user's past feedback and suggest the most efficient voice input reception method. In this way, the optimal voice input reception method is provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using AI or without AI. For example, the reception unit can input the user's feedback data into AI and have the AI ​​customize the reception method.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the surrounding situation. For example, if the surrounding situation is an emergency, the analysis unit performs a detailed analysis. Furthermore, if the surrounding situation is normal, the analysis unit can also perform a standard analysis. Furthermore, if the surrounding situation is low-risk, the analysis unit can also perform a simplified analysis. In this way, by adjusting the level of detail of the analysis according to the importance of the surrounding situation, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​adjust the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the surrounding situation. For example, when the surrounding situation is indoors, the analysis unit applies an analysis algorithm specifically for indoor use. Furthermore, when the surrounding situation is outdoors, the analysis unit can also apply an analysis algorithm specifically for outdoors. Furthermore, when the surrounding situation is inside a factory, the analysis unit can also apply an analysis algorithm specifically for factories. In this way, by applying different analysis algorithms depending on the category of the surrounding situation, more appropriate analysis results are provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​select an analysis algorithm.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the current analysis accuracy based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results to improve the analysis accuracy. Furthermore, the analysis unit can analyze the user's past analysis results and suggest the most efficient analysis method. In this way, the analysis accuracy is improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into AI and have the AI ​​improve the analysis accuracy.

[0044] During analysis, the analysis unit can determine the priority of analysis based on changes in the surrounding situation. For example, if the surrounding situation suddenly changes, the analysis unit performs analysis with the highest priority. The analysis unit can also perform analysis with normal priority if the surrounding situation is stable. Furthermore, if the surrounding situation is low risk, the analysis unit can postpone analysis. In this way, by determining the priority of analysis based on changes in the surrounding situation, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​determine the priority of analysis.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the surrounding circumstances. For example, if the surrounding circumstances are highly relevant, the analysis unit performs analysis with the highest priority. Furthermore, if the surrounding circumstances are medium relevance, the analysis unit can also perform analysis in the normal order. Furthermore, if the surrounding circumstances are low relevance, the analysis unit can postpone analysis. In this way, by adjusting the order of analysis based on the relevance of the surrounding circumstances, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding circumstances data into AI and have the AI ​​adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terminology. Furthermore, if the user has general knowledge, the analysis unit can also provide analysis results that use less technical terminology. Furthermore, if the user is a beginner, the analysis unit can provide analysis results that do not use technical terminology at all. This allows for more appropriate analysis results to be provided by adjusting the use of technical terminology in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology.

[0047] When generating code, the generation unit can adjust the level of detail of the code to be generated based on the importance of the request. For example, if the request is of high importance, the generation unit generates detailed code. Furthermore, if the request is of medium importance, the generation unit can also generate standard code. Furthermore, if the request is of low importance, the generation unit can also generate simplified code. In this way, by adjusting the level of detail of the code to be generated based on the importance of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input data on the importance of the request into the generation AI and cause the generation AI to adjust the level of detail of the code.

[0048] When generating a code, the generation unit can apply different generation algorithms depending on the category of the request. For example, if the request is for home work, the generation unit can apply a generation algorithm specifically for home use. Furthermore, if the request is for factory work, the generation unit can also apply a generation algorithm specifically for factories. Furthermore, if the request is for outdoor work, the generation unit can also apply a generation algorithm specifically for outdoor use. In this way, by applying different generation algorithms depending on the category of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input request category data into the generation AI and have the generation AI select a generation algorithm.

[0049] When generating code, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit improves the current generation accuracy based on the user's past generation results. The generation unit can also extract specific patterns from the user's past generation results to improve the generation accuracy. Furthermore, the generation unit can analyze the user's past generation results and suggest the most efficient generation method. In this way, the generation accuracy is improved by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past generation result data into the generation AI and have the generation AI improve the generation accuracy.

[0050] When generating code, the generation unit can determine the generation priority based on the time of request submission. For example, if the request is urgent, the generation unit generates code with the highest priority. Also, if the request is normal, the generation unit can generate code with standard priority. Furthermore, if the request is low priority, the generation unit can generate code at a later date. In this way, by determining the generation priority based on the time of request submission, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on the time of request submission into the generation AI and causes the generation AI to determine the generation priority.

[0051] When generating code, the generation unit can adjust the generation order based on the relevance of the request. For example, if the request is highly relevant, the generation unit generates the code with the highest priority. Furthermore, if the request is medium relevance, the generation unit can also generate the code in the normal order. Furthermore, if the request is low relevance, the generation unit can also generate the code later. In this way, by adjusting the generation order based on the relevance of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the relevance data of the request into the generation AI and cause the generation AI to adjust the generation order.

[0052] When generating code, the generation unit can adjust the use of technical terminology in the generated code according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate code that uses a lot of technical terminology. Alternatively, if the user has general knowledge, the generation unit can generate code that uses less technical terminology. Furthermore, if the user is a beginner, the generation unit can generate code that does not use technical terminology at all. In this way, by adjusting the use of technical terminology in the generated code according to the user's level of expertise, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to use technical terminology.

[0053] During control, the control unit can adjust the level of detail of control based on the importance of the generated code. For example, if the generated code is of high importance, the control unit performs detailed control. Furthermore, if the generated code is of medium importance, the control unit can also perform standard control. Furthermore, if the generated code is of low importance, the control unit can also perform simplified control. In this way, by adjusting the level of detail of control based on the importance of the generated code, more appropriate control is performed. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input importance data of the generated code to AI and have the AI ​​adjust the level of detail of control.

[0054] During control, the control unit can apply different control algorithms depending on the category of the generated code. For example, if the generated code is for home work, the control unit applies a control algorithm specifically for home use. Furthermore, if the generated code is for factory work, the control unit can also apply a control algorithm specifically for factory use. Furthermore, if the generated code is for outdoor work, the control unit can also apply a control algorithm specifically for outdoor use. By applying different control algorithms depending on the category of the generated code, more appropriate control can be achieved. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input category data of the generated code into AI and have the AI ​​select a control algorithm.

[0055] During control, the control unit can improve the accuracy of control by referring to the user's past control results. The control unit, for example, improves the current control accuracy based on the user's past control results. The control unit can also extract specific patterns from the user's past control results and improve the control accuracy. Furthermore, the control unit can analyze the user's past control results and suggest the most efficient control method. In this way, the control accuracy is improved by referring to the user's past control results. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input the user's past control result data into AI and have the AI ​​improve the control accuracy.

[0056] During control, the control unit can determine the priority of control based on the submission time of the generated code. For example, if the generated code is urgent, the control unit performs control with the highest priority. Furthermore, if the generated code is normal, the control unit can also perform control with standard priority. Furthermore, if the generated code is low priority, the control unit can perform control at a later date. In this way, by determining the priority of control based on the submission time of the generated code, more appropriate control is performed. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input data on the submission time of the generated code into AI and have the AI ​​determine the priority of control.

[0057] During control, the control unit can adjust the order of control based on the relevance of the generated code. For example, if the generated code has high relevance, the control unit performs control with the highest priority. Furthermore, if the generated code has medium relevance, the control unit can also perform control in the normal order. Furthermore, if the generated code has low relevance, the control unit can perform control later. In this way, by adjusting the order of control based on the relevance of the generated code, more appropriate control is performed. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input relevance data of the generated code to AI and have the AI ​​adjust the order of control.

[0058] During control, the control unit can adjust the use of technical terminology in the control according to the user's level of expertise. For example, if the user has technical expertise, the control unit can provide a control method that uses a lot of technical terminology. Furthermore, if the user has general knowledge, the control unit can provide a control method that uses less technical terminology. Furthermore, if the user is a beginner, the control unit can provide a control method that does not use technical terminology at all. In this way, more appropriate control is performed by adjusting the use of technical terminology in the control unit according to the user's level of expertise. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology.

[0059] During monitoring, the monitoring unit can adjust the level of monitoring detail based on the importance of the execution result of the generated code. For example, if the execution result of the generated code is of high importance, the monitoring unit can perform detailed monitoring. Furthermore, if the execution result of the generated code is of medium importance, the monitoring unit can also perform standard monitoring. Furthermore, if the execution result of the generated code is of low importance, the monitoring unit can also perform simplified monitoring. In this way, by adjusting the level of monitoring detail based on the importance of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input importance data of the execution result of the generated code to AI and have the AI ​​adjust the level of monitoring detail.

[0060] During monitoring, the monitoring unit can apply different monitoring algorithms depending on the category of the execution result of the generated code. For example, if the execution result of the generated code is a domestic task, the monitoring unit applies a monitoring algorithm specifically for domestic use. Furthermore, if the execution result of the generated code is a factory task, the monitoring unit can also apply a monitoring algorithm specifically for factories. Furthermore, if the execution result of the generated code is an outdoor task, the monitoring unit can also apply a monitoring algorithm specifically for outdoor use. In this way, by applying different monitoring algorithms depending on the category of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input category data of the execution result of the generated code into AI and have the AI ​​select a monitoring algorithm.

[0061] During monitoring, the monitoring unit can improve the accuracy of monitoring by referring to the user's past monitoring results. The monitoring unit, for example, improves the current monitoring accuracy based on the user's past monitoring results. The monitoring unit can also extract specific patterns from the user's past monitoring results to improve the monitoring accuracy. Furthermore, the monitoring unit can analyze the user's past monitoring results and suggest the most efficient monitoring method. In this way, the monitoring accuracy is improved by referring to the user's past monitoring results. Some or all of the above-mentioned processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input the user's past monitoring result data into AI and have the AI ​​improve the monitoring accuracy.

[0062] During monitoring, the monitoring unit can determine the monitoring priority based on the submission time of the execution result of the generated code. For example, if the execution result of the generated code is urgent, the monitoring unit performs monitoring with the highest priority. In addition, if the execution result of the generated code is normal, the monitoring unit can also perform monitoring with a standard priority. Furthermore, if the execution result of the generated code is low priority, the monitoring unit can also perform monitoring at a later date. In this way, more appropriate monitoring is performed by determining the monitoring priority based on the submission time of the execution result of the generated code. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input data on the submission time of the execution result of the generated code to AI and have the AI ​​determine the monitoring priority.

[0063] During monitoring, the monitoring unit can adjust the monitoring order based on the relevance of the execution results of the generated code. For example, if the execution result of the generated code is highly relevant, the monitoring unit performs monitoring as a top priority. Furthermore, if the execution result of the generated code is medium relevance, the monitoring unit can also perform monitoring in a normal order. Furthermore, if the execution result of the generated code is low relevance, the monitoring unit can also perform monitoring at a later date. In this way, by adjusting the monitoring order based on the relevance of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input relevance data of the execution result of the generated code to AI and have the AI ​​adjust the monitoring order.

[0064] During monitoring, the monitoring unit can adjust the use of technical terminology in the monitoring according to the user's level of expertise. For example, if the user has technical expertise, the monitoring unit can provide a monitoring method that uses a lot of technical terminology. Furthermore, if the user has general knowledge, the monitoring unit can provide a monitoring method that uses less technical terminology. Furthermore, if the user is a beginner, the monitoring unit can provide a monitoring method that does not use technical terminology at all. In this way, more appropriate monitoring can be performed by adjusting the use of technical terminology in the monitoring according to the user's level of expertise. Some or all of the above-mentioned processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The reception unit can not only receive voice input from the user, but also accept gesture input from the user. For example, when the user raises their hand, the camera detects the gesture and transmits it to the reception unit as gesture input. The reception unit can also analyze the user's gesture input and combine it with the voice input to more accurately understand the user's request. Furthermore, the reception unit can analyze the user's gesture input in real time and respond immediately. In this way, by combining voice input and gesture input, the user's request can be more accurately understood and flexibly responded to.

[0067] The generation unit not only generates Python code using the generation AI, but can also generate code in other programming languages ​​according to user requests. For example, if a user requests "generate code in JavaScript (registered trademark)," the generation AI generates JavaScript code. The generation unit can also simultaneously generate code in multiple programming languages ​​according to user requests. Furthermore, the generation unit can optimize the generated code to provide efficient code. This allows the generation unit to flexibly respond to user requests and generate code in various programming languages.

[0068] The analysis unit not only uses the camera and LIDAR sensor to understand the surrounding situation, but also uses the audio sensor to understand the surrounding sound environment. For example, the analysis unit acquires surrounding audio data and analyzes it using voice recognition technology. The analysis unit also uses the audio data to complement the surrounding situation, allowing for a more accurate understanding of the situation. Furthermore, the analysis unit can analyze the audio data in real time and respond immediately. As a result, by using the audio sensor in addition to the camera and LIDAR sensor, the surrounding situation can be understood more accurately.

[0069] The control unit not only sends the generated Python code to the robot's control system and executes it, but also receives user feedback to improve the control method. For example, when a user provides feedback on the robot's operation, the control unit analyzes the feedback and improves the control method. The control unit can also receive user feedback in real time and immediately modify the control method. Furthermore, the control unit can accumulate user feedback and use it to improve the control method over the long term. This allows the control method to be continuously improved by utilizing user feedback, resulting in more appropriate control.

[0070] The monitoring unit not only monitors the execution results of the generated code and corrects them as necessary, but also monitors the user's health condition. For example, the monitoring unit acquires biometric data such as the user's heart rate and body temperature and analyzes the health condition. The monitoring unit can also adjust the robot's operation according to the user's health condition. Furthermore, the monitoring unit can monitor the user's health condition in real time and issue an alert if an abnormality occurs. This allows the monitoring unit to adjust the robot's operation taking the user's health condition into consideration, thereby achieving safe and appropriate operation.

[0071] The reception unit can analyze the user's past voice input history and select an appropriate reception method, as well as analyze and predict the user's past behavioral patterns. For example, if a user repeatedly makes a specific request during a specific time period, the reception unit can predict and prepare for that request during that time period. Also, if a user makes a specific request at a specific location, the reception unit can predict and prepare for that request when the user arrives at that location. Furthermore, the reception unit can analyze the user's past behavioral patterns to predict future requests and respond in advance. This allows for faster and more appropriate responses to be made by utilizing the user's past behavioral patterns.

[0072] When receiving voice input, the receiving unit not only filters the voice input based on the user's current situation and environment, but also prioritizes the voice input based on the user's current activity. For example, if the user is driving, voice input related to driving can be prioritized. Also, if the user is cooking, voice input related to cooking can be prioritized. Furthermore, if the user is exercising, voice input related to exercise can be prioritized. This allows the priority of voice input to be determined based on the user's current activity, allowing for more appropriate responses.

[0073] When receiving a voice input, the receiving unit not only selects an appropriate receiving means according to the user's input method, but also provides feedback according to the user's input method. For example, if the user selects voice input, the receiving unit provides feedback by voice. Also, if the user selects text input, the receiving unit can provide feedback by text. Furthermore, if the user selects gesture input, the receiving unit can provide visual feedback. This allows the receiving unit to provide appropriate feedback according to the user's input method and take a more appropriate action.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The reception unit receives a user's voice input. The user's voice input includes, for example, voice input using a microphone or voice input via a smartphone. The reception unit converts the voice input into text data using voice recognition technology and sends it to the analysis unit. Step 2: The analysis unit analyzes the voice input received by the reception unit and grasps the surrounding situation using the camera and LIDAR sensor. The analysis unit analyzes the voice input using natural language processing technology and analyzes the image data acquired by the camera using image recognition technology. It also acquires distance data about the surrounding area using the LIDAR sensor and grasps the position and shape of objects in three dimensions. Step 3: The generator generates Python code that enables the robot to operate in response to requests based on the surrounding situation grasped by the analyzer. The generator generates the Python code using a generation AI (e.g., GPT-3 or BERT), and can also train the generation AI using deep learning technology. Step 4: The control unit sends the Python code generated by the generation unit to the robot's control system and executes it. The control unit sends the generated code to the robot in real time and controls the robot's operation. The control unit can also monitor the execution results of the generated code and correct it if necessary.

[0076] (Example 2) A robot control system according to an embodiment of the present invention utilizes multimodal generative AI to realize actions that respond to a user's simple voice input. In this robot control system, the user inputs a simple request to a robot, and the generative AI analyzes the voice input and uses a camera and LIDAR sensor to grasp the surrounding situation. The generative AI generates Python code that implements the robot's actions to respond to the request and sends the code to the robot's control system for execution. For example, if a user inputs a request to a robot, such as "Pick up the book on the table," the generative AI analyzes the request and grasps the surrounding situation using the robot's camera and LIDAR sensor. Next, the generative AI generates action code for picking up the book and has the robot execute the code. This causes the robot to pick up the book from the table. This system enables the robot to flexibly respond to user requests, even if it has not previously learned the action. This system can be used in a variety of situations, such as household chores and factory work. Furthermore, because the generative AI grasps the surrounding situation, the robot can operate safely. This allows the robot control system to realize robot movements according to the user's requests. For example, it can be used in a variety of situations, such as household chores or factory work. In addition, the generation AI can grasp the surrounding situation, allowing the robot to operate safely.

[0077] A robot control system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a control unit. The reception unit receives a user's voice input. Examples of the user's voice input include, but are not limited to, voice input using a microphone or a smartphone. The reception unit receives the user's voice in real time using, for example, a microphone. The reception unit can also receive voice using the voice input function of a smartphone. The reception unit can also convert the voice input into text data using voice recognition technology. For example, the reception unit converts the voice into text using voice recognition software and transmits the text to the analysis unit. The analysis unit analyzes the voice input and grasps the surrounding situation using a camera and a LIDAR sensor. For example, the analysis unit analyzes the voice input using natural language processing technology. The analysis unit can also acquire image data of the surrounding area using a camera and acquire distance data of the surrounding area using a LIDAR sensor. For example, the analysis unit can analyze image data acquired by the camera using image recognition technology to identify the position and shape of an object. The LIDAR sensor uses laser light to acquire distance data about the surroundings and grasp the position and shape of objects in three dimensions. The generation unit uses a generation AI to generate Python code that enables the robot to operate in response to a request, based on the surrounding conditions grasped by the analysis unit. The generation unit generates the Python code using, for example, a generation AI (e.g., a Transformer model). The generation unit can also train the generation AI using deep learning technology. For example, the generation unit trains the generation AI with a large amount of code data to generate code according to the request. The generation unit inputs a prompt to the generation AI, such as "Please generate code to pick up the book on the table," and obtains the generated code. The control unit sends the Python code generated by the generation unit to the robot's control system and executes it. For example, the control unit sends the generated code to the robot in real time to control the robot's operation. The control unit can also monitor the execution results of the generated code and correct it as necessary. For example, the control unit monitors the robot's operation in real time and generates and sends correction code if an abnormality occurs.As a result, the robot control system according to the embodiment can realize robot operations according to user requests. For example, the robot control system can flexibly respond to user requests and can be used in a variety of situations, such as household chores and factory work. Furthermore, because the generation AI understands the surrounding situation, the robot can operate safely.

[0078] The generation unit can generate Python code using a generation AI. The generation unit generates Python code using, for example, a generation AI (e.g., a Transformer model). The generation AI has learned a large amount of code data and has advanced natural language processing capabilities. The generation unit inputs a prompt to the generation AI, such as "Please generate code to pick up the book on the table," and obtains the generated code. The generation unit can also train the generation AI using deep learning technology. For example, the generation unit trains the generation AI with a large amount of code data and generates code according to the request. This makes it possible to generate Python code using the generation AI. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI and obtains the generated code.

[0079] The analysis unit can grasp the surrounding situation using a camera and a LIDAR sensor. The analysis unit acquires image data of the surroundings using, for example, a camera. Examples of cameras include, but are not limited to, an RGB camera and a depth camera. The analysis unit analyzes the image data acquired by the camera using image recognition technology to identify the position and shape of an object. The analysis unit can also acquire distance data of the surroundings using a LIDAR sensor. Examples of LIDAR sensors include, but are not limited to, a rotary LIDAR and a fixed LIDAR. The analysis unit analyzes the distance data acquired by the LIDAR sensor to grasp the position and shape of an object in three dimensions. For example, the analysis unit identifies the position of an object using image data acquired by the camera, and grasps the shape of the object in three dimensions using the distance data acquired by the LIDAR sensor. In this way, the surrounding situation can be accurately grasped by using the camera and the LIDAR sensor. Some or all of the above-mentioned processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input image data acquired by a camera into AI and have the AI ​​identify the position and shape of an object.

[0080] The control unit can send the generated Python code to the robot's control system and execute it. For example, the control unit can send the generated code to the robot in real time and control the robot's operation. The control unit can also monitor the execution results of the generated code and correct it as necessary. For example, the control unit can monitor the robot's operation in real time and generate and send correction code if an abnormality occurs. The control unit can also record the execution results of the generated code as a log and analyze it later. For example, the control unit can collect the robot's operation log and evaluate the accuracy and efficiency of the operation. By doing so, the robot can execute the generated Python code to realize operation according to the user's request. Some or all of the above-mentioned processing in the control unit may be performed using AI or without AI. For example, the control unit can input the generated code to AI and have the AI ​​control the robot's operation.

[0081] The robot control system includes a monitoring unit that monitors the execution results of the generated code and corrects them as necessary. The monitoring unit monitors the execution results of the generated code and corrects them as necessary. For example, the monitoring unit monitors the execution results of the generated code in real time. The monitoring unit can also record the execution results of the generated code as a log and analyze it later. For example, the monitoring unit collects robot operation logs and evaluates the accuracy and efficiency of the operation. The monitoring unit can also generate correction codes based on the execution results of the generated code and send them to the robot. For example, the monitoring unit generates and sends correction codes when an abnormality occurs in the robot's operation. This allows the execution results of the generated code to be monitored and corrected as necessary, thereby improving the robot's operation accuracy. Some or all of the above-described processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input the execution results of the generated code into AI and have the AI ​​generate correction codes.

[0082] The generation unit can learn using deep learning. For example, the generation unit trains the generation AI using deep learning technology. Deep learning includes, but is not limited to, CNN (convolutional neural network) and RNN (recurrent neural network). The generation unit trains the generation AI with a large amount of code data to generate a code according to a request. For example, the generation unit inputs a prompt to the generation AI, such as "Please generate a code to pick up a book on the table," and obtains the generated code. The generation unit can also continuously provide learning data to the generation AI to improve generation accuracy. For example, the generation unit periodically trains the generation AI with new code data to generate code that corresponds to the latest technology. In this way, deep learning improves the learning accuracy of the generation unit. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit inputs a prompt to the generation AI and obtains the generated code.

[0083] The reception unit can estimate the user's emotion and adjust the timing of receiving the voice input based on the estimated user emotion. For example, when the user is stressed, the reception unit can shorten the timing of receiving the voice input to quickly receive the request. Furthermore, when the user is relaxed, the reception unit can extend the timing of receiving the voice input to quickly receive the request. Furthermore, when the user is in a hurry, the reception unit can immediately receive the voice input to quickly receive the request. By adjusting the timing of receiving the voice input according to the user's emotion, the voice input can be received at a more appropriate timing. The 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 reception unit can be performed using AI, or without AI. For example, the reception unit can input the user's voice data to the generation AI and have the generation AI perform emotion estimation.

[0084] The reception unit can analyze the user's past voice input history and select an appropriate reception method. For example, the reception unit prioritizes reception of voice commands that the user has frequently used in the past. The reception unit can also predict and accept commands to be used in a specific time period based on the user's past voice input history. Furthermore, the reception unit can analyze the user's past voice input history and suggest the most efficient reception method. In this way, the optimal reception method can be selected by analyzing the past voice input history. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's voice input history data into AI and have the AI ​​select the optimal reception method.

[0085] The reception unit can perform filtering based on the user's current situation and environment when receiving voice input. For example, when the user is in a noisy environment, the reception unit applies noise cancellation to receive the voice input. The reception unit can also receive normal voice input when the user is in a quiet environment. Furthermore, when the user is moving, the reception unit can adjust the sensitivity of the voice input before receiving the voice input. This allows the voice input to be filtered according to the user's situation and environment, thereby receiving more appropriate voice input. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's environmental data into AI and have the AI ​​perform filtering of the voice input.

[0086] When receiving a voice input, the reception unit can select an appropriate reception means according to the user's input method. For example, if the user selects voice input, the reception unit receives the voice input using voice recognition. Furthermore, if the user selects text input, the reception unit can also receive the voice input using text analysis. Furthermore, if the user selects gesture input, the reception unit can also receive the voice input using gesture recognition. This allows for more appropriate voice input to be received by selecting the optimal reception means according to the user's input method. Some or all of the above-described processing in the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's input method data into AI and have the AI ​​select the optimal reception means.

[0087] The reception unit can estimate the user's emotions and determine the priority of the voice inputs to be received based on the estimated user emotions. For example, when the user is nervous, the reception unit can prioritize receiving important voice inputs. Furthermore, when the user is relaxed, the reception unit can also prioritize receiving detailed voice inputs. Furthermore, when the user is in a hurry, the reception unit can also prioritize receiving quick voice inputs. Thus, by determining the priority of voice inputs according to the user's emotions, more appropriate voice inputs can be received. The 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 reception unit can be performed using AI, or without AI. For example, the reception unit can input the user's voice data to the generation AI and have the generation AI perform emotion estimation.

[0088] When receiving a voice input, the reception unit can prioritize receiving a highly relevant input by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit can prioritize receiving a voice input related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving a voice input related to the user's destination. Furthermore, when the user is at home, the reception unit can also prioritize receiving a voice input related to the user's home. In this way, by preferentially receiving a highly relevant voice input based on the user's geographical location information, more appropriate voice input is received. Some or all of the above-described processing in the reception unit may be performed using AI or without AI. For example, the reception unit can input the user's geographical location information data to AI and cause the AI ​​to select a highly relevant voice input.

[0089] When receiving a voice input, the reception unit can analyze the user's social media activity and receive related input. For example, the reception unit can preferentially receive voice input related to places where the user has checked in on social media. The reception unit can also analyze the content of the user's social media posts and receive related voice input. Furthermore, the reception unit can also receive related voice input by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity, related voice input is preferentially received. Some or all of the above-described processing by the reception unit may be performed using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data into AI and have the AI ​​select related voice input.

[0090] The reception unit can customize the reception method by reflecting the user's past feedback when receiving voice input. For example, the reception unit can suggest an optimal voice input reception method based on feedback provided by the user in the past. The reception unit can also preferentially accept a specific voice input method based on the user's past feedback. Furthermore, the reception unit can analyze the user's past feedback and suggest the most efficient voice input reception method. In this way, the optimal voice input reception method is provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using AI or without AI. For example, the reception unit can input the user's feedback data into AI and have the AI ​​customize the reception method.

[0091] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, if the user is nervous, the analysis unit provides simple, highly visible analysis results. The analysis unit can also provide detailed analysis results if the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can provide analysis results that focus on the main points. This allows for more appropriate analysis results to be provided by adjusting the way the analysis is presented according to the user's emotions. Emotion estimation is achieved 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 AI, or may be performed without AI. For example, the analysis unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0092] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the surrounding situation. For example, if the surrounding situation is an emergency, the analysis unit performs a detailed analysis. Furthermore, if the surrounding situation is normal, the analysis unit can also perform a standard analysis. Furthermore, if the surrounding situation is low-risk, the analysis unit can also perform a simplified analysis. In this way, by adjusting the level of detail of the analysis according to the importance of the surrounding situation, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​adjust the level of detail of the analysis.

[0093] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the surrounding situation. For example, when the surrounding situation is indoors, the analysis unit applies an analysis algorithm specifically for indoor use. Furthermore, when the surrounding situation is outdoors, the analysis unit can also apply an analysis algorithm specifically for outdoors. Furthermore, when the surrounding situation is inside a factory, the analysis unit can also apply an analysis algorithm specifically for factories. In this way, by applying different analysis algorithms depending on the category of the surrounding situation, more appropriate analysis results are provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​select an analysis algorithm.

[0094] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the current analysis accuracy based on the user's past analysis results. The analysis unit can also extract specific patterns from the user's past analysis results to improve the analysis accuracy. Furthermore, the analysis unit can analyze the user's past analysis results and suggest the most efficient analysis method. In this way, the analysis accuracy is improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's past analysis result data into AI and have the AI ​​improve the analysis accuracy.

[0095] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can perform a short, to-the-point analysis. The analysis unit can also perform a detailed analysis if the user is relaxed. Furthermore, if the user is excited, the analysis unit can perform a visually stimulating analysis. This allows for adjusting the length of the analysis according to the user's emotions, thereby providing more appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, such as 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 can be performed using AI, or without AI. For example, the analysis unit can input the user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0096] During analysis, the analysis unit can determine the priority of analysis based on changes in the surrounding situation. For example, if the surrounding situation suddenly changes, the analysis unit performs analysis with the highest priority. The analysis unit can also perform analysis with normal priority if the surrounding situation is stable. Furthermore, if the surrounding situation is low risk, the analysis unit can postpone analysis. In this way, by determining the priority of analysis based on changes in the surrounding situation, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding situation data into AI and have the AI ​​determine the priority of analysis.

[0097] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the surrounding circumstances. For example, if the surrounding circumstances are highly relevant, the analysis unit performs analysis with the highest priority. Furthermore, if the surrounding circumstances are medium relevance, the analysis unit can also perform analysis in the normal order. Furthermore, if the surrounding circumstances are low relevance, the analysis unit can postpone analysis. In this way, by adjusting the order of analysis based on the relevance of the surrounding circumstances, more appropriate analysis results can be provided. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input surrounding circumstances data into AI and have the AI ​​adjust the order of analysis.

[0098] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit can provide analysis results that use a lot of technical terminology. Furthermore, if the user has general knowledge, the analysis unit can also provide analysis results that use less technical terminology. Furthermore, if the user is a beginner, the analysis unit can provide analysis results that do not use technical terminology at all. This allows for more appropriate analysis results to be provided by adjusting the use of technical terminology in the analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology.

[0099] The generation unit can estimate the user's emotions and adjust the expression method of the generated chords based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate chords that progress at a leisurely pace. Furthermore, if the user is in a hurry, the generation unit can generate chords that emphasize the shortest route. Furthermore, if the user is excited, the generation unit can generate chords that add visually stimulating effects. By adjusting the expression method of the generated chords according to the user's emotions, more appropriate chords can be generated. 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 these examples. Some or all of the above-described processing in the generation unit can be performed using the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the expression method of the chords.

[0100] When generating code, the generation unit can adjust the level of detail of the code to be generated based on the importance of the request. For example, if the request is of high importance, the generation unit generates detailed code. Furthermore, if the request is of medium importance, the generation unit can also generate standard code. Furthermore, if the request is of low importance, the generation unit can also generate simplified code. In this way, by adjusting the level of detail of the code to be generated based on the importance of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input data on the importance of the request into the generation AI and cause the generation AI to adjust the level of detail of the code.

[0101] When generating a code, the generation unit can apply different generation algorithms depending on the category of the request. For example, if the request is for home work, the generation unit can apply a generation algorithm specifically for home use. Furthermore, if the request is for factory work, the generation unit can also apply a generation algorithm specifically for factories. Furthermore, if the request is for outdoor work, the generation unit can also apply a generation algorithm specifically for outdoor use. In this way, by applying different generation algorithms depending on the category of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input request category data into the generation AI and have the generation AI select a generation algorithm.

[0102] When generating code, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit improves the current generation accuracy based on the user's past generation results. The generation unit can also extract specific patterns from the user's past generation results to improve the generation accuracy. Furthermore, the generation unit can analyze the user's past generation results and suggest the most efficient generation method. In this way, the generation accuracy is improved by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the user's past generation result data into the generation AI and have the generation AI improve the generation accuracy.

[0103] The generation unit can estimate the user's emotions and adjust the length of the generated chord based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate short, concise chords. If the user is relaxed, the generation unit can also generate longer chords with detailed explanations. Furthermore, if the user is excited, the generation unit can generate chords with visually stimulating effects. This allows for the generation of more appropriate chords by adjusting the length of the generated chords according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as 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 generation unit can be performed using the generation AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the chord length.

[0104] When generating code, the generation unit can determine the generation priority based on the time of request submission. For example, if the request is urgent, the generation unit generates code with the highest priority. Also, if the request is normal, the generation unit can generate code with standard priority. Furthermore, if the request is low priority, the generation unit can generate code at a later date. In this way, by determining the generation priority based on the time of request submission, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit inputs data on the time of request submission into the generation AI and causes the generation AI to determine the generation priority.

[0105] When generating code, the generation unit can adjust the generation order based on the relevance of the request. For example, if the request is highly relevant, the generation unit generates the code with the highest priority. Furthermore, if the request is medium relevance, the generation unit can also generate the code in the normal order. Furthermore, if the request is low relevance, the generation unit can also generate the code later. In this way, by adjusting the generation order based on the relevance of the request, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit is performed using a generation AI. For example, the generation unit can input the relevance data of the request into the generation AI and cause the generation AI to adjust the generation order.

[0106] When generating code, the generation unit can adjust the use of technical terminology in the generated code according to the user's level of expertise. For example, if the user has technical expertise, the generation unit can generate code that uses a lot of technical terminology. Alternatively, if the user has general knowledge, the generation unit can generate code that uses less technical terminology. Furthermore, if the user is a beginner, the generation unit can generate code that does not use technical terminology at all. In this way, by adjusting the use of technical terminology in the generated code according to the user's level of expertise, more appropriate code is generated. Some or all of the above-mentioned processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to use technical terminology.

[0107] The control unit can estimate the user's emotions and adjust the control method based on the estimated user's emotions. For example, if the user is nervous, the control unit can provide a simple and highly visible control method. Furthermore, if the user is relaxed, the control unit can provide a detailed control method. Furthermore, if the user is in a hurry, the control unit can provide a control method that focuses on the key points. This allows for more appropriate control by adjusting the control method according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input the user's emotion data into the generation AI and have the generation AI adjust the control method.

[0108] During control, the control unit can adjust the level of detail of control based on the importance of the generated code. For example, if the generated code is of high importance, the control unit performs detailed control. Furthermore, if the generated code is of medium importance, the control unit can also perform standard control. Furthermore, if the generated code is of low importance, the control unit can also perform simplified control. In this way, by adjusting the level of detail of control based on the importance of the generated code, more appropriate control is performed. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input importance data of the generated code to AI and have the AI ​​adjust the level of detail of control.

[0109] During control, the control unit can apply different control algorithms depending on the category of the generated code. For example, if the generated code is for home work, the control unit applies a control algorithm specifically for home use. Furthermore, if the generated code is for factory work, the control unit can also apply a control algorithm specifically for factory use. Furthermore, if the generated code is for outdoor work, the control unit can also apply a control algorithm specifically for outdoor use. By applying different control algorithms depending on the category of the generated code, more appropriate control can be achieved. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input category data of the generated code into AI and have the AI ​​select a control algorithm.

[0110] During control, the control unit can improve the accuracy of control by referring to the user's past control results. The control unit, for example, improves the current control accuracy based on the user's past control results. The control unit can also extract specific patterns from the user's past control results and improve the control accuracy. Furthermore, the control unit can analyze the user's past control results and suggest the most efficient control method. In this way, the control accuracy is improved by referring to the user's past control results. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input the user's past control result data into AI and have the AI ​​improve the control accuracy.

[0111] The control unit can estimate the user's emotions and determine control priorities based on the estimated user emotions. For example, if the user is nervous, the control unit can prioritize important control. Furthermore, if the user is relaxed, the control unit can prioritize detailed control. Furthermore, if the user is in a hurry, the control unit can prioritize quick control. Thus, by determining control priorities according to the user's emotions, more appropriate control is performed. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input the user's emotion data into the generation AI and have the generation AI determine the control priorities.

[0112] During control, the control unit can determine the priority of control based on the submission time of the generated code. For example, if the generated code is urgent, the control unit performs control with the highest priority. Furthermore, if the generated code is normal, the control unit can also perform control with standard priority. Furthermore, if the generated code is low priority, the control unit can perform control at a later date. In this way, by determining the priority of control based on the submission time of the generated code, more appropriate control is performed. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input data on the submission time of the generated code into AI and have the AI ​​determine the priority of control.

[0113] During control, the control unit can adjust the order of control based on the relevance of the generated code. For example, if the generated code has high relevance, the control unit performs control with the highest priority. Furthermore, if the generated code has medium relevance, the control unit can also perform control in the normal order. Furthermore, if the generated code has low relevance, the control unit can perform control later. In this way, by adjusting the order of control based on the relevance of the generated code, more appropriate control is performed. Some or all of the above-described processing in the control unit may be performed using AI, or may be performed without using AI. For example, the control unit can input relevance data of the generated code to AI and have the AI ​​adjust the order of control.

[0114] During control, the control unit can adjust the use of technical terminology in the control according to the user's level of expertise. For example, if the user has technical expertise, the control unit can provide a control method that uses a lot of technical terminology. Furthermore, if the user has general knowledge, the control unit can provide a control method that uses less technical terminology. Furthermore, if the user is a beginner, the control unit can provide a control method that does not use technical terminology at all. In this way, more appropriate control is performed by adjusting the use of technical terminology in the control unit according to the user's level of expertise. Some or all of the above-mentioned processing in the control unit may be performed using AI, or may be performed without AI. For example, the control unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology.

[0115] The monitoring unit can estimate the user's emotions and adjust the monitoring method based on the estimated user emotions. For example, if the user is nervous, the monitoring unit can provide a simple, highly visible monitoring method. Furthermore, if the user is relaxed, the monitoring unit can provide a detailed monitoring method. Furthermore, if the user is in a hurry, the monitoring unit can provide a monitoring method that focuses on the key points. This allows for more appropriate monitoring by adjusting the monitoring method according to the user's emotions. The 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 monitoring unit can be performed using AI, or without AI. For example, the monitoring unit can input the user's emotion data into the generation AI and have the generation AI adjust the monitoring method.

[0116] During monitoring, the monitoring unit can adjust the level of monitoring detail based on the importance of the execution result of the generated code. For example, if the execution result of the generated code is of high importance, the monitoring unit can perform detailed monitoring. Furthermore, if the execution result of the generated code is of medium importance, the monitoring unit can also perform standard monitoring. Furthermore, if the execution result of the generated code is of low importance, the monitoring unit can also perform simplified monitoring. In this way, by adjusting the level of monitoring detail based on the importance of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input importance data of the execution result of the generated code to AI and have the AI ​​adjust the level of monitoring detail.

[0117] During monitoring, the monitoring unit can apply different monitoring algorithms depending on the category of the execution result of the generated code. For example, if the execution result of the generated code is a domestic task, the monitoring unit applies a monitoring algorithm specifically for domestic use. Furthermore, if the execution result of the generated code is a factory task, the monitoring unit can also apply a monitoring algorithm specifically for factories. Furthermore, if the execution result of the generated code is an outdoor task, the monitoring unit can also apply a monitoring algorithm specifically for outdoor use. In this way, by applying different monitoring algorithms depending on the category of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input category data of the execution result of the generated code into AI and have the AI ​​select a monitoring algorithm.

[0118] During monitoring, the monitoring unit can improve the accuracy of monitoring by referring to the user's past monitoring results. The monitoring unit, for example, improves the current monitoring accuracy based on the user's past monitoring results. The monitoring unit can also extract specific patterns from the user's past monitoring results to improve the monitoring accuracy. Furthermore, the monitoring unit can analyze the user's past monitoring results and suggest the most efficient monitoring method. In this way, the monitoring accuracy is improved by referring to the user's past monitoring results. Some or all of the above-mentioned processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input the user's past monitoring result data into AI and have the AI ​​improve the monitoring accuracy.

[0119] The monitoring unit can estimate the user's emotions and determine monitoring priorities based on the estimated user emotions. For example, if the user is nervous, the monitoring unit can prioritize important monitoring. Furthermore, if the user is relaxed, the monitoring unit can prioritize detailed monitoring. Furthermore, if the user is in a hurry, the monitoring unit can prioritize quick monitoring. This allows for more appropriate monitoring by determining monitoring priorities according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as 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 monitoring unit can be performed using AI, or without AI. For example, the monitoring unit can input the user's emotion data into the generation AI and have the generation AI determine the monitoring priorities.

[0120] During monitoring, the monitoring unit can determine the monitoring priority based on the submission time of the execution result of the generated code. For example, if the execution result of the generated code is urgent, the monitoring unit performs monitoring with the highest priority. In addition, if the execution result of the generated code is normal, the monitoring unit can also perform monitoring with a standard priority. Furthermore, if the execution result of the generated code is low priority, the monitoring unit can also perform monitoring at a later date. In this way, more appropriate monitoring is performed by determining the monitoring priority based on the submission time of the execution result of the generated code. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input data on the submission time of the execution result of the generated code to AI and have the AI ​​determine the monitoring priority.

[0121] During monitoring, the monitoring unit can adjust the monitoring order based on the relevance of the execution results of the generated code. For example, if the execution result of the generated code is highly relevant, the monitoring unit performs monitoring as a top priority. Furthermore, if the execution result of the generated code is medium relevance, the monitoring unit can also perform monitoring in a normal order. Furthermore, if the execution result of the generated code is low relevance, the monitoring unit can also perform monitoring at a later date. In this way, by adjusting the monitoring order based on the relevance of the execution result of the generated code, more appropriate monitoring can be performed. Some or all of the above-described processing in the monitoring unit may be performed using AI, or may be performed without using AI. For example, the monitoring unit can input relevance data of the execution result of the generated code to AI and have the AI ​​adjust the monitoring order.

[0122] During monitoring, the monitoring unit can adjust the use of technical terminology in the monitoring according to the user's level of expertise. For example, if the user has technical expertise, the monitoring unit can provide a monitoring method that uses a lot of technical terminology. Furthermore, if the user has general knowledge, the monitoring unit can provide a monitoring method that uses less technical terminology. Furthermore, if the user is a beginner, the monitoring unit can provide a monitoring method that does not use technical terminology at all. In this way, more appropriate monitoring can be performed by adjusting the use of technical terminology in the monitoring according to the user's level of expertise. Some or all of the above-mentioned processing in the monitoring unit may be performed using AI or without AI. For example, the monitoring unit can input the user's level of expertise data into AI and have the AI ​​execute the use of technical terminology. === Hard Collateral 1-1 === Each of the multiple elements, including the above-described reception unit, analysis unit, generation unit, control unit, and monitoring unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit can receive the user's voice in real time using the microphone 38B of the smart device 14. The analysis unit can grasp the surrounding situation using the camera 42 and LIDAR sensor of the smart device 14. The generation unit can generate Python code using generation AI by the specific processing unit 290 of the data processing device 12. The control unit can transmit the generated Python code to the control unit 46A of the smart device 14 and execute it. The monitoring unit can monitor the execution result of the code generated by the control unit 46A of the smart device 14 in real time and correct it as necessary. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, control unit, and monitoring unit is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive the user's voice in real time using the microphone 238 of the smart glasses 214. The analysis unit can grasp the surrounding situation using the camera 42 and LIDAR sensor of the smart glasses 214. The generation unit can generate Python code using generation AI by the specific processing unit 290 of the data processing device 12. The control unit can transmit the generated Python code to the control unit 46A of the smart glasses 214 for execution. The monitoring unit can monitor the execution result of the code generated by the control unit 46A of the smart glasses 214 in real time and correct it as necessary. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, control unit, and monitoring unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit can receive the user's voice in real time using the microphone 238 of the headset type terminal 314. The analysis unit can grasp the surrounding situation using the camera 42 and LIDAR sensor of the headset type terminal 314. The generation unit can generate Python code using generation AI by the specific processing unit 290 of the data processing device 12. The control unit can transmit the generated Python code to the control unit 46A of the headset type terminal 314 and execute it. The monitoring unit can monitor the execution result of the code generated by the control unit 46A of the headset type terminal 314 in real time and correct it as necessary. === Hard Collateral 1-4 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, control unit, and monitoring unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive the user's voice in real time using the microphone 238 of the robot 414. The analysis unit can grasp the surrounding situation using the camera 42 and LIDAR sensor of the robot 414. The generation unit can generate Python code using generation AI by the specific processing unit 290 of the data processing device 12. The control unit can transmit the generated Python code to the control unit 46A of the robot 414 and execute it. The monitoring unit can monitor the execution result of the code generated by the control unit 46A of the robot 414 in real time and correct it as necessary.

[0123] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0124] The reception unit can not only receive voice input from the user, but also accept gesture input from the user. For example, when the user raises their hand, the camera detects the gesture and transmits it to the reception unit as gesture input. The reception unit can also analyze the user's gesture input and combine it with the voice input to more accurately understand the user's request. Furthermore, the reception unit can analyze the user's gesture input in real time and respond immediately. In this way, by combining voice input and gesture input, the user's request can be more accurately understood and flexibly responded to.

[0125] The generation unit not only generates Python code using the generation AI, but can also generate code in other programming languages ​​according to user requests. For example, if a user requests "generate code in JavaScript," the generation AI generates JavaScript code. The generation unit can also simultaneously generate code in multiple programming languages ​​according to user requests. Furthermore, the generation unit can optimize the generated code to provide efficient code. This allows the generation unit to flexibly respond to user requests and generate code in various programming languages.

[0126] The analysis unit not only uses the camera and LIDAR sensor to understand the surrounding situation, but also uses the audio sensor to understand the surrounding sound environment. For example, the analysis unit acquires surrounding audio data and analyzes it using voice recognition technology. The analysis unit also uses the audio data to complement the surrounding situation, allowing for a more accurate understanding of the situation. Furthermore, the analysis unit can analyze the audio data in real time and respond immediately. As a result, by using the audio sensor in addition to the camera and LIDAR sensor, the surrounding situation can be understood more accurately.

[0127] The control unit not only sends the generated Python code to the robot's control system and executes it, but also receives user feedback to improve the control method. For example, when a user provides feedback on the robot's operation, the control unit analyzes the feedback and improves the control method. The control unit can also receive user feedback in real time and immediately modify the control method. Furthermore, the control unit can accumulate user feedback and use it to improve the control method over the long term. This allows the control method to be continuously improved by utilizing user feedback, resulting in more appropriate control.

[0128] The monitoring unit not only monitors the execution results of the generated code and corrects them as necessary, but also monitors the user's health condition. For example, the monitoring unit acquires biometric data such as the user's heart rate and body temperature and analyzes the health condition. The monitoring unit can also adjust the robot's operation according to the user's health condition. Furthermore, the monitoring unit can monitor the user's health condition in real time and issue an alert if an abnormality occurs. This allows the monitoring unit to adjust the robot's operation taking the user's health condition into consideration, thereby achieving safe and appropriate operation.

[0129] The generation unit can not only learn using deep learning, but also estimate the user's emotions and adjust the training data based on the estimated emotions. For example, if the user is feeling stressed, the generation unit can reduce the training data to lighten the learning load. Also, if the user is relaxed, the generation unit can increase the training data to improve learning accuracy. Furthermore, the generation unit can change the type of training data depending on the user's emotions. This allows the generation unit to adjust the training data according to the user's emotions and perform more appropriate training.

[0130] The reception unit can estimate the user's emotions and adjust the timing of receiving voice input based on the estimated user's emotions, as well as filter the content of the voice input according to the user's emotions. For example, if the user is angry, offensive words can be filtered out to prevent the user from receiving them. Also, if the user is sad, comforting words can be given priority. Furthermore, if the user is excited, words that will calm the user can be given priority. This allows the content of the voice input to be filtered according to the user's emotions, allowing for more appropriate responses.

[0131] The reception unit can analyze the user's past voice input history and select an appropriate reception method, as well as analyze and predict the user's past behavioral patterns. For example, if a user repeatedly makes a specific request during a specific time period, the reception unit can predict and prepare for that request during that time period. Also, if a user makes a specific request at a specific location, the reception unit can predict and prepare for that request when the user arrives at that location. Furthermore, the reception unit can analyze the user's past behavioral patterns to predict future requests and respond in advance. This allows for faster and more appropriate responses to be made by utilizing the user's past behavioral patterns.

[0132] When receiving voice input, the receiving unit not only filters the voice input based on the user's current situation and environment, but also prioritizes the voice input based on the user's current activity. For example, if the user is driving, voice input related to driving can be prioritized. Also, if the user is cooking, voice input related to cooking can be prioritized. Furthermore, if the user is exercising, voice input related to exercise can be prioritized. This allows the priority of voice input to be determined based on the user's current activity, allowing for more appropriate responses.

[0133] When receiving a voice input, the receiving unit not only selects an appropriate receiving means according to the user's input method, but also provides feedback according to the user's input method. For example, if the user selects voice input, the receiving unit provides feedback by voice. Also, if the user selects text input, the receiving unit can provide feedback by text. Furthermore, if the user selects gesture input, the receiving unit can provide visual feedback. This allows the receiving unit to provide appropriate feedback according to the user's input method and take a more appropriate action.

[0134] The processing flow of the second embodiment will be briefly explained below.

[0135] Step 1: The reception unit receives a user's voice input. The user's voice input includes, for example, voice input using a microphone or voice input via a smartphone. The reception unit converts the voice input into text data using voice recognition technology and sends it to the analysis unit. Step 2: The analysis unit analyzes the voice input received by the reception unit and grasps the surrounding situation using the camera and LIDAR sensor. The analysis unit analyzes the voice input using natural language processing technology and analyzes the image data acquired by the camera using image recognition technology. It also acquires distance data about the surrounding area using the LIDAR sensor and grasps the position and shape of objects in three dimensions. Step 3: The generator generates Python code that enables the robot to operate in response to requests based on the surrounding situation grasped by the analyzer. The generator generates the Python code using a generation AI (e.g., GPT-3 or BERT), and can also train the generation AI using deep learning technology. Step 4: The control unit sends the Python code generated by the generation unit to the robot's control system and executes it. The control unit sends the generated code to the robot in real time and controls the robot's operation. The control unit can also monitor the execution results of the generated code and correct it if necessary.

[0136] 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.

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

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0141] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0157] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0187] 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.

[0188] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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).

[0193] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0194] 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."

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Explanation of symbols]

[0208] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives voice input from a user; an analysis unit that analyzes the voice input received by the reception unit and grasps the surrounding situation using a camera and a LIDAR sensor; a generating unit that generates a Python code that realizes a robot operation to respond to a request based on the surrounding situation grasped by the analyzing unit; a control unit that transmits the Python code generated by the generation unit to a robot control system and executes the code. A system characterized by:

2. The generation unit Generate Python code using generative AI The system of claim 1 .

3. The analysis unit Understand the surroundings using cameras and LIDAR sensors The system of claim 1 .

4. The control unit Send the generated Python code to the robot's control system for execution. The system of claim 1 .

5. It has a monitoring section that monitors the execution results of the generated code and makes corrections as necessary. The system of claim 1 .

6. The generation unit Learn using deep learning The system of claim 1 .

7. The reception unit Estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated user emotions. The system of claim 1 .

8. The reception unit Analyze the user's past voice input history and select the appropriate reception method The system of claim 1 .

Images