system

Abstract

The system according to this embodiment aims to quickly generate and provide illustration cards for visual assistance. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives keywords to be visually supported. The analysis unit analyzes the keywords entered by the reception unit. The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The provision unit provides the illustration cards generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it takes time to create an illustration card for visual assistance and it is difficult to respond promptly on the spot.

[0005] The system according to the embodiment aims to quickly generate and provide an illustration card for visual assistance.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives keywords to be used for visual support. The analysis unit analyzes the keywords entered by the reception unit. The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The provision unit provides the illustration cards generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can quickly generate and provide illustration cards for visual assistance. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The visual support system according to an embodiment of the present invention is a product using a generative AI for visual support, targeting supporters of children with developmental disabilities (parents, special needs school teachers, and teachers at child development centers and after-school day services). This visual support system provides a mechanism in which a generative AI trained for visual support generates illustration cards simply by inputting keywords for visual support. This allows supporters to provide visual support on the spot without any effort, enabling effective support for children with developmental disabilities. For example, when a supporter inputs keywords such as "wash hands" or "do homework," the generative AI analyzes those keywords and generates illustration cards for visual support. The generated illustration cards are provided to the supporter, who can use them to visually communicate things to the child with developmental disabilities. This mechanism allows supporters to generate illustration cards for visual support without any effort and communicate what comes to mind immediately. This enables effective support for children with developmental disabilities. In short, the visual support system allows supporters of children with developmental disabilities to provide visual support on the spot without any effort, enabling effective support for children with developmental disabilities.

[0029] The visual support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives keywords from the supporter who wants visual support. The keywords entered by the supporter include specific actions or tasks such as "wash your hands" or "do your homework." The reception unit can receive keywords using, for example, keyboard input or voice input. The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. The analysis unit decomposes the keywords using morphological analysis, analyzes the structure of the keywords using grammatical analysis, and understands the meaning of the keywords using semantic analysis. The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual support using, for example, a generation AI. The generation AI includes, for example, a GAN (Generative Opposite Network) and a VAE (Variational Autoencoder). The generation unit generates illustrations based on keywords using, for example, GANs and generates variations of the illustrations using VAEs. The provision unit provides the illustration cards generated by the generation unit. The provision unit provides the illustration cards in, for example, digital format. Digital formats include PDF, JPEG, PNG, etc. The provision unit saves the generated illustration cards in PDF format and provides them to the supporter. The provision unit can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The provision unit saves the generated illustration cards in PDF format so that the supporter can print them. As a result, the visual support system according to the embodiment automatically generates illustration cards for visual support, allowing supporters to provide visual support on the spot without any effort. Some or all of the above-described processes in the visual support system may be performed using, for example, AI, or not using AI. For example, the reception unit can input keywords entered by the supporter into the AI ​​and have the AI ​​perform keyword analysis.The analysis unit can analyze keywords using AI, the generation unit can generate illustration cards using AI, and the provision unit can provide illustration cards using AI.

[0030] The reception desk receives keywords from the support worker who wants to provide visual assistance. These keywords include specific actions and tasks, such as "wash hands" or "do homework." The reception desk can accept keywords via keyboard input or voice input. Specifically, for keyboard input, the support worker uses a computer or tablet keyboard to enter the keywords. For voice input, the support worker speaks the keywords through a microphone, and speech recognition technology converts them into text. Speech recognition technology includes processes such as extracting speech features, breaking them down into phonemes, and converting them into text. This allows support workers to easily input keywords and facilitates the use of the visual assistance system. Furthermore, the reception desk has a function to temporarily store the entered keywords and send them to the analysis department. This ensures that the entered keywords are reliably passed to the analysis department, allowing for smoother processing. The reception desk also features a user interface design that is intuitive for support workers to use. For example, voice input can be started simply by clicking the microphone icon. It also includes a feedback function to verify whether the entered keywords are accurately recognized, allowing support workers to review their input and make corrections as needed. This allows the reception desk to provide an environment where support staff can easily and accurately input keywords, thereby improving the usability of the visual support system.

[0031] The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing (NLP) techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Specifically, it uses morphological analysis to break down keywords, grammatical analysis to analyze the structure of keywords, and semantic analysis to understand the meaning of keywords. For example, if the keyword "wash your hands" is entered, morphological analysis breaks it down into words such as "hands," "to," and "wash." Next, grammatical analysis analyzes the relationships between these words to identify the action of "washing hands." Finally, semantic analysis understands the specific meaning of the action of "washing hands." Based on these analysis results, the analysis unit can accurately grasp the intent of the keyword. Furthermore, the analysis unit can utilize past data and contextual information to gain a deeper understanding of the keyword's meaning. For example, by considering the analysis results from when the keyword "wash your hands" was entered in the past, and its relationship to other keywords entered by the same supporter, more accurate analysis becomes possible. The analysis unit passes these analysis results to the generation unit, preparing for the next processing to proceed smoothly. By utilizing AI technology, the analysis unit can perform keyword analysis quickly and accurately, thereby improving the performance of the visual assistance system.

[0032] The generation unit generates illustration cards based on keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual assistance using, for example, generation AI. Generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). Specifically, it uses GANs to generate illustrations based on keywords and VAEs to generate variations of the illustrations. For example, if the keyword "wash hands" is analyzed, the GAN generates an illustration depicting the action of washing hands. The generated illustration includes specific visual elements such as the shape of hands, the flow of water, and soap bubbles. Furthermore, by using VAEs, illustrations from different angles and styles are generated, allowing the supporter to select from them. The generation unit generates these illustrations in high resolution and provides them in a visually easy-to-understand format. In addition, the generation unit adjusts the color tone, brightness, and contrast of the generated illustration cards to improve their visual quality. By utilizing AI technology, the generation unit can respond quickly and accurately to keywords entered by the supporter and automatically generate illustration cards for visual assistance. This allows supporters to provide visual assistance on the spot without effort, increasing the convenience and effectiveness of the visual assistance system.

[0033] The provider unit provides illustration cards generated by the generator unit. The provider unit provides illustration cards in digital format, for example. Digital formats include PDF, JPEG, PNG, etc. Specifically, it saves the generated illustration cards in PDF format and provides them to the supporter. The provider unit can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. For example, it saves the generated illustration cards in PDF format so that the supporter can print them. Furthermore, the provider unit can save the generated illustration cards in cloud storage, making them accessible to the supporter at any time. This allows the supporter to easily obtain the necessary illustration cards when needed. The provider unit is designed so that supporters can easily view, download, and print the generated illustration cards through a user interface. For example, supporters can access the provider unit through a web browser, view a list of generated illustration cards, select the necessary cards, and download them. The provider unit also has a function that allows supporters to customize the illustration cards, for example, by adding text or changing colors. This allows the provider unit to provide an environment in which supporters can effectively use illustration cards for visual assistance, improving the convenience and flexibility of the visual assistance system.

[0034] The generation unit can generate illustration cards for visual assistance using a generation AI. The generation unit generates illustration cards for visual assistance using a generation AI, for example. The generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). The generation unit generates illustrations based on keywords using a GAN, for example, and generates variations of illustrations using a VAE. In this way, the generation of illustration cards for visual assistance is automated by using a generation AI. Some or all of the above-described processes in the generation unit may be performed using an AI, for example, or without an AI. For example, the generation unit can input keywords into the generation AI and have the generation AI execute the generation of illustration cards.

[0035] The analysis unit can analyze keywords using natural language processing techniques. For example, the analysis unit analyzes keywords using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit decomposes keywords using morphological analysis, analyzes the structure of keywords using grammatical analysis, and understands the meaning of keywords using semantic analysis. As a result, the accuracy of keyword analysis is improved by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keywords into AI and have the AI ​​perform keyword analysis using natural language processing techniques.

[0036] The service provider can provide the generated illustration cards in digital format. For example, the service provider can provide the generated illustration cards in digital format. Digital formats include PDF, JPEG, PNG, etc. For example, the service provider can save the generated illustration cards in PDF format and provide them to supporters. This makes it easy for supporters to use the illustration cards by providing them in digital format. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the generated illustration cards into AI and have the AI ​​perform the digital provision.

[0037] The service provider can provide the generated illustration cards in a printable format. For example, the service provider can provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The service provider can, for example, save the generated illustration cards in PDF format so that supporters can print them. This allows supporters to create physical illustration cards by providing them in a printable format. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the generated illustration cards into AI and have the AI ​​perform the task of providing them in a printable format.

[0038] The reception unit can receive keywords entered by the support worker. For example, the support worker enters keywords for which they want visual support. The keywords entered by the support worker include specific actions or tasks, such as "wash your hands" or "do your homework." The reception unit can receive keywords using, for example, keyboard input or voice input. By receiving the keywords entered by the support worker, the reception unit can obtain information for generating illustration cards for visual support. Some or all of the above processing in the reception unit may be performed using, for example, AI, or not using AI. For example, the reception unit can input the keywords entered by the support worker into the AI ​​and have the AI ​​perform the keyword reception.

[0039] The reception desk can analyze the supporter's past input history and suggest the optimal keyword input method. For example, the reception desk can automatically display keywords that the supporter has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the supporter has used in the past. Furthermore, the reception desk can predict and suggest keywords to be used during specific time periods based on the supporter's past input history. In this way, by analyzing past input history, the reception desk can suggest the optimal input method for the supporter. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the supporter's past input history data into AI and have the AI ​​suggest the optimal keyword input method.

[0040] The reception desk can present input suggestions based on the supporter's current situation and needs when keywords are entered. For example, the reception desk can prioritize presenting relevant keywords according to the supporter's current situation. The reception desk can also provide customized keyword suggestions based on the supporter's needs. Furthermore, the reception desk can suggest keywords related to the supporter's current activities in real time. This enables efficient keyword input by presenting input suggestions that match the supporter's situation and needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the supporter's current situation data into the AI ​​and have the AI ​​perform the task of presenting input suggestions.

[0041] The reception desk can prioritize and present highly relevant keywords when keywords are entered, taking into account the supporter's geographical location. For example, the reception desk can prioritize relevant keywords based on the supporter's current location. The reception desk can also suggest region-specific keywords, taking into account the supporter's geographical location. Furthermore, the reception desk can present the most suitable keywords, taking into account the distance from the supporter's current location. This allows for the priority presentation of highly relevant keywords by considering geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the supporter's geographical location information into the AI ​​and have the AI ​​perform the task of presenting highly relevant keywords.

[0042] The reception desk can analyze the supporter's social media activity when keywords are entered and suggest relevant keywords. For example, the reception desk can extract and suggest relevant keywords from the supporter's social media activity. The reception desk can also prioritize displaying keywords that the supporter frequently uses on social media. Furthermore, the reception desk can analyze the supporter's social media activity and suggest keywords based on trends. In this way, relevant keywords can be suggested by analyzing social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the supporter's social media activity data into AI and have the AI ​​suggest relevant keywords.

[0043] The analysis unit can optimize its analysis algorithm by referring to past analysis data during keyword analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. The analysis unit can also improve the accuracy of the analysis by referring to past analysis data. Furthermore, the analysis unit can analyze past analysis data and optimize the analysis algorithm. This allows the analysis algorithm to be optimized by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input past analysis data into AI and have the AI ​​perform the optimization of the analysis algorithm.

[0044] The analysis unit can apply different analysis methods depending on the keyword category during keyword analysis. For example, the analysis unit can select the optimal analysis method according to the keyword category. The analysis unit can also apply different analysis algorithms based on the keyword category. Furthermore, the analysis unit can customize the analysis method according to the keyword category. This improves the accuracy of the analysis by applying an analysis method appropriate to the keyword category. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keyword category data into the AI ​​and have the AI ​​perform the application of the analysis method.

[0045] The analysis unit can determine the priority of keyword analysis based on the submission date of the keywords. For example, the analysis unit can determine the priority of analysis based on the submission date of the keywords. The analysis unit can also prioritize the analysis of older keywords. Furthermore, the analysis unit can also prioritize the analysis of newer keywords. This enables efficient analysis by determining the priority of analysis based on the submission date. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keyword submission date data into AI and have the AI ​​perform the determination of the analysis priority.

[0046] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and data during keyword analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant literature. Furthermore, the analysis unit can also improve the accuracy of its analysis based on relevant data. In addition, the analysis unit can analyze literature and data and optimize its analysis algorithm. This improves the accuracy of the analysis by referring to relevant literature and data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input relevant literature and data into AI and have the AI ​​perform the analysis accuracy improvement.

[0047] The generation unit can adjust the level of detail generated based on the importance of keywords when generating illustration cards. For example, the generation unit can generate detailed illustration cards for important keywords. It can also generate simple illustration cards for less important keywords. Furthermore, the generation unit can customize the level of detail generated according to the importance of the keywords. This allows for the generation of more appropriate illustration cards by adjusting the level of detail generated according to the importance of the keywords. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword importance data into AI and have the AI ​​perform the adjustment of the level of detail generated.

[0048] The generation unit can apply different generation algorithms depending on the keyword category when generating illustration cards. For example, the generation unit can select the optimal generation algorithm depending on the keyword category. The generation unit can also apply different generation algorithms based on the keyword category. Furthermore, the generation unit can customize the generation algorithm depending on the keyword category. This improves the accuracy of generation by applying a generation algorithm that matches the keyword category. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword category data into AI and have AI perform the application of the generation algorithm.

[0049] The generation unit can determine the generation priority based on the keyword submission date when generating illustration cards. For example, the generation unit can determine the generation priority based on the keyword submission date. The generation unit can also prioritize the generation of older keywords. Furthermore, the generation unit can also prioritize the generation of newer keywords. This enables efficient illustration card generation by determining the generation priority based on the submission date. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword submission date data into AI and have the AI ​​perform the determination of the generation priority.

[0050] The generation unit can improve the accuracy of illustration card generation by referring to related images and data. For example, the generation unit can improve the accuracy of generation by referring to related images. The generation unit can also improve the accuracy of generation based on related data. Furthermore, the generation unit can analyze images and data and optimize the generation algorithm. This improves the accuracy of generation by referring to related images and data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input related images and data into AI and have the AI ​​perform the improvement of generation accuracy.

[0051] The distribution unit can select the optimal distribution method when providing illustration cards by referring to the supporter's past usage history. For example, the distribution unit can select the optimal distribution method based on the distribution methods the supporter has used in the past. The distribution unit can also select the most efficient distribution method from the supporter's past usage history. Furthermore, the distribution unit can analyze the supporter's past usage history and optimize the distribution method. This allows the optimal distribution method to be selected by referring to past usage history. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input the supporter's past usage history data into AI and have the AI ​​select the optimal distribution method.

[0052] The delivery unit can customize the delivery method based on the supporter's current situation when providing illustration cards. For example, the delivery unit can select the most suitable delivery method according to the supporter's current situation. Furthermore, if the supporter is in a hurry, the delivery unit can select a method that allows for quick delivery. Additionally, if the supporter is relaxed, the delivery unit can select a delivery method that includes detailed explanations. This allows for the provision of more appropriate illustration cards by customizing the delivery method according to the supporter's current situation. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input data on the supporter's current situation into the AI ​​and have the AI ​​perform the customization of the delivery method.

[0053] The distribution unit can select the optimal distribution method when providing illustration cards, taking into account the supporter's geographical location information. For example, the distribution unit can select the optimal distribution method based on the supporter's current location. The distribution unit can also propose region-specific distribution methods, taking into account the supporter's geographical location information. Furthermore, the distribution unit can select the optimal distribution method by considering the distance from the supporter's current location. In this way, the optimal distribution method can be selected by considering geographical location information. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without using AI. For example, the distribution unit can input the supporter's geographical location information into AI and have the AI ​​select the optimal distribution method.

[0054] The distribution unit can analyze the supporter's social media activity and propose distribution methods when providing illustration cards. For example, the distribution unit can propose the most suitable distribution method based on the supporter's social media activity. The distribution unit can also prioritize proposing distribution methods that supporters frequently use on social media. Furthermore, the distribution unit can analyze the supporter's social media activity and propose distribution methods based on trends. In this way, the optimal distribution method can be proposed by analyzing social media activity. Some or all of the above processing in the distribution unit may be performed using AI, for example, or not using AI. For example, the distribution unit can input supporter's social media activity data into AI and have the AI ​​propose distribution methods.

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

[0056] The reception desk can suggest relevant video content based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the reception desk can suggest a video demonstrating the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," the reception desk can suggest a video explaining how to complete homework. Furthermore, the reception desk can automatically search for and suggest educational video content related to the keywords entered by the supporter. This allows the visual support system to provide more diverse support through video content, in addition to visual illustration cards.

[0057] The analysis unit can generate relevant audio guides based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the analysis unit can generate an audio guide explaining the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," it can generate an audio guide explaining how to proceed with homework. Furthermore, the analysis unit can automatically generate and provide audio guides related to keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through audio guides.

[0058] The generation unit can generate relevant 3D models based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the generation unit can generate a 3D model showing the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," the unit can generate a 3D model explaining how to proceed with homework. Furthermore, the generation unit can automatically generate and provide 3D models related to keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through 3D models.

[0059] The service provider can deliver relevant interactive content based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash hands," the service provider can provide interactive content that teaches the handwashing procedure. Similarly, if the supporter enters the keyword "do homework," the service provider can provide interactive content that teaches how to complete homework. Furthermore, the service provider can automatically generate and deliver interactive content related to the keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through interactive content.

[0060] The service provider can select the optimal service delivery method by referring to the supporter's past usage history. For example, it can select the optimal delivery method based on the methods the supporter has used in the past. It can also select the most efficient delivery method from the supporter's past usage history. Furthermore, it can analyze the supporter's past usage history and optimize the delivery method. In this way, the optimal delivery method can be selected by referring to past usage history.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception desk receives keywords from the support worker that they would like to provide visual support for. These keywords may include specific actions or tasks, such as "wash your hands" or "do your homework." The reception desk can accept keywords using methods such as keyboard input or voice input. Step 2: The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit breaks down the keywords using morphological analysis, analyzes the structure of the keywords using grammatical analysis, and understands the meaning of the keywords using semantic analysis. Step 3: The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual assistance using, for example, a generation AI. The generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). The generation unit generates illustrations based on keywords using a GAN and generates variations of the illustrations using a VAE. Step 4: The provider provides the illustration cards generated by the generator. The provider provides the illustration cards in digital format, for example. Digital formats include PDF, JPEG, PNG, etc. The provider saves the generated illustration cards in PDF format and provides them to the supporter, for example. The provider can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The provider saves the generated illustration cards in PDF format so that the supporter can print them, for example.

[0063] (Example of form 2) The visual support system according to an embodiment of the present invention is a product using a generative AI for visual support, targeting supporters of children with developmental disabilities (parents, special needs school teachers, and teachers at child development centers and after-school day services). This visual support system provides a mechanism in which a generative AI trained for visual support generates illustration cards simply by inputting keywords for visual support. This allows supporters to provide visual support on the spot without any effort, enabling effective support for children with developmental disabilities. For example, when a supporter inputs keywords such as "wash hands" or "do homework," the generative AI analyzes those keywords and generates illustration cards for visual support. The generated illustration cards are provided to the supporter, who can use them to visually communicate things to the child with developmental disabilities. This mechanism allows supporters to generate illustration cards for visual support without any effort and communicate what comes to mind immediately. This enables effective support for children with developmental disabilities. In short, the visual support system allows supporters of children with developmental disabilities to provide visual support on the spot without any effort, enabling effective support for children with developmental disabilities.

[0064] The visual support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a provision unit. The reception unit receives keywords from the supporter who wants visual support. The keywords entered by the supporter include specific actions or tasks such as "wash your hands" or "do your homework." The reception unit can receive keywords using, for example, keyboard input or voice input. The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. The analysis unit decomposes the keywords using morphological analysis, analyzes the structure of the keywords using grammatical analysis, and understands the meaning of the keywords using semantic analysis. The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual support using, for example, a generation AI. The generation AI includes, for example, a GAN (Generative Opposite Network) and a VAE (Variational Autoencoder). The generation unit generates illustrations based on keywords using, for example, GANs and generates variations of the illustrations using VAEs. The provision unit provides the illustration cards generated by the generation unit. The provision unit provides the illustration cards in, for example, digital format. Digital formats include PDF, JPEG, PNG, etc. The provision unit saves the generated illustration cards in PDF format and provides them to the supporter. The provision unit can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The provision unit saves the generated illustration cards in PDF format so that the supporter can print them. As a result, the visual support system according to the embodiment automatically generates illustration cards for visual support, allowing supporters to provide visual support on the spot without any effort. Some or all of the above-described processes in the visual support system may be performed using, for example, AI, or not using AI. For example, the reception unit can input keywords entered by the supporter into the AI ​​and have the AI ​​perform keyword analysis.The analysis unit can analyze keywords using AI, the generation unit can generate illustration cards using AI, and the provision unit can provide illustration cards using AI.

[0065] The reception desk receives keywords from the support worker who wants to provide visual assistance. These keywords include specific actions and tasks, such as "wash hands" or "do homework." The reception desk can accept keywords via keyboard input or voice input. Specifically, for keyboard input, the support worker uses a computer or tablet keyboard to enter the keywords. For voice input, the support worker speaks the keywords through a microphone, and speech recognition technology converts them into text. Speech recognition technology includes processes such as extracting speech features, breaking them down into phonemes, and converting them into text. This allows support workers to easily input keywords and facilitates the use of the visual assistance system. Furthermore, the reception desk has a function to temporarily store the entered keywords and send them to the analysis department. This ensures that the entered keywords are reliably passed to the analysis department, allowing for smoother processing. The reception desk also features a user interface design that is intuitive for support workers to use. For example, voice input can be started simply by clicking the microphone icon. It also includes a feedback function to verify whether the entered keywords are accurately recognized, allowing support workers to review their input and make corrections as needed. This allows the reception desk to provide an environment where support staff can easily and accurately input keywords, thereby improving the usability of the visual support system.

[0066] The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing (NLP) techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. Specifically, it uses morphological analysis to break down keywords, grammatical analysis to analyze the structure of keywords, and semantic analysis to understand the meaning of keywords. For example, if the keyword "wash your hands" is entered, morphological analysis breaks it down into words such as "hands," "to," and "wash." Next, grammatical analysis analyzes the relationships between these words to identify the action of "washing hands." Finally, semantic analysis understands the specific meaning of the action of "washing hands." Based on these analysis results, the analysis unit can accurately grasp the intent of the keyword. Furthermore, the analysis unit can utilize past data and contextual information to gain a deeper understanding of the keyword's meaning. For example, by considering the analysis results from when the keyword "wash your hands" was entered in the past, and its relationship to other keywords entered by the same supporter, more accurate analysis becomes possible. The analysis unit passes these analysis results to the generation unit, preparing for the next processing to proceed smoothly. By utilizing AI technology, the analysis unit can perform keyword analysis quickly and accurately, thereby improving the performance of the visual assistance system.

[0067] The generation unit generates illustration cards based on keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual assistance using, for example, generation AI. Generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). Specifically, it uses GANs to generate illustrations based on keywords and VAEs to generate variations of the illustrations. For example, if the keyword "wash hands" is analyzed, the GAN generates an illustration depicting the action of washing hands. The generated illustration includes specific visual elements such as the shape of hands, the flow of water, and soap bubbles. Furthermore, by using VAEs, illustrations from different angles and styles are generated, allowing the supporter to select from them. The generation unit generates these illustrations in high resolution and provides them in a visually easy-to-understand format. In addition, the generation unit adjusts the color tone, brightness, and contrast of the generated illustration cards to improve their visual quality. By utilizing AI technology, the generation unit can respond quickly and accurately to keywords entered by the supporter and automatically generate illustration cards for visual assistance. This allows supporters to provide visual assistance on the spot without effort, increasing the convenience and effectiveness of the visual assistance system.

[0068] The provider unit provides illustration cards generated by the generator unit. The provider unit provides illustration cards in digital format, for example. Digital formats include PDF, JPEG, PNG, etc. Specifically, it saves the generated illustration cards in PDF format and provides them to the supporter. The provider unit can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. For example, it saves the generated illustration cards in PDF format so that the supporter can print them. Furthermore, the provider unit can save the generated illustration cards in cloud storage, making them accessible to the supporter at any time. This allows the supporter to easily obtain the necessary illustration cards when needed. The provider unit is designed so that supporters can easily view, download, and print the generated illustration cards through a user interface. For example, supporters can access the provider unit through a web browser, view a list of generated illustration cards, select the necessary cards, and download them. The provider unit also has a function that allows supporters to customize the illustration cards, for example, by adding text or changing colors. This allows the provider unit to provide an environment in which supporters can effectively use illustration cards for visual assistance, improving the convenience and flexibility of the visual assistance system.

[0069] The generation unit can generate illustration cards for visual assistance using a generation AI. The generation unit generates illustration cards for visual assistance using a generation AI, for example. The generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). The generation unit generates illustrations based on keywords using a GAN, for example, and generates variations of illustrations using a VAE. In this way, the generation of illustration cards for visual assistance is automated by using a generation AI. Some or all of the above-described processes in the generation unit may be performed using an AI, for example, or without an AI. For example, the generation unit can input keywords into the generation AI and have the generation AI execute the generation of illustration cards.

[0070] The analysis unit can analyze keywords using natural language processing techniques. For example, the analysis unit analyzes keywords using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit decomposes keywords using morphological analysis, analyzes the structure of keywords using grammatical analysis, and understands the meaning of keywords using semantic analysis. As a result, the accuracy of keyword analysis is improved by using natural language processing techniques. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keywords into AI and have the AI ​​perform keyword analysis using natural language processing techniques.

[0071] The service provider can provide the generated illustration cards in digital format. For example, the service provider can provide the generated illustration cards in digital format. Digital formats include PDF, JPEG, PNG, etc. For example, the service provider can save the generated illustration cards in PDF format and provide them to supporters. This makes it easy for supporters to use the illustration cards by providing them in digital format. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the generated illustration cards into AI and have the AI ​​perform the digital provision.

[0072] The service provider can provide the generated illustration cards in a printable format. For example, the service provider can provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The service provider can, for example, save the generated illustration cards in PDF format so that supporters can print them. This allows supporters to create physical illustration cards by providing them in a printable format. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input the generated illustration cards into AI and have the AI ​​perform the task of providing them in a printable format.

[0073] The reception unit can receive keywords entered by the support worker. For example, the support worker enters keywords for which they want visual support. The keywords entered by the support worker include specific actions or tasks, such as "wash your hands" or "do your homework." The reception unit can receive keywords using, for example, keyboard input or voice input. By receiving the keywords entered by the support worker, the reception unit can obtain information for generating illustration cards for visual support. Some or all of the above processing in the reception unit may be performed using, for example, AI, or not using AI. For example, the reception unit can input the keywords entered by the support worker into the AI ​​and have the AI ​​perform the keyword reception.

[0074] The reception desk can estimate the supporter's emotions and adjust the keyword input interface based on the estimated emotions. For example, if the supporter is stressed, the reception desk can provide a simple interface and minimize the input steps. If the supporter is relaxed, the reception desk can also provide detailed input options and suggest customizable input methods. Furthermore, if the supporter is in a hurry, the reception desk can prioritize voice input to allow for quick keyword entry. This provides a more user-friendly system by adjusting the input interface according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input supporter emotion data into an AI and have the AI ​​perform emotion estimation.

[0075] The reception desk can analyze the supporter's past input history and suggest the optimal keyword input method. For example, the reception desk can automatically display keywords that the supporter has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the supporter has used in the past. Furthermore, the reception desk can predict and suggest keywords to be used during specific time periods based on the supporter's past input history. In this way, by analyzing past input history, the reception desk can suggest the optimal input method for the supporter. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the supporter's past input history data into AI and have the AI ​​suggest the optimal keyword input method.

[0076] The reception desk can present input suggestions based on the supporter's current situation and needs when keywords are entered. For example, the reception desk can prioritize presenting relevant keywords according to the supporter's current situation. The reception desk can also provide customized keyword suggestions based on the supporter's needs. Furthermore, the reception desk can suggest keywords related to the supporter's current activities in real time. This enables efficient keyword input by presenting input suggestions that match the supporter's situation and needs. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the supporter's current situation data into the AI ​​and have the AI ​​perform the task of presenting input suggestions.

[0077] The reception desk can estimate the supporter's emotions and determine the priority of the entered keywords based on the estimated emotions. For example, if the supporter is nervous, the reception desk may prioritize displaying important keywords. It may also prioritize displaying detailed keywords if the supporter is relaxed. Furthermore, if the supporter is in a hurry, it may prioritize displaying keywords that can be entered quickly. This allows for priority processing of important keywords by prioritizing them according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the reception desk may be performed using AI or not. For example, the reception desk can input supporter emotion data into an AI and have the AI ​​determine the keyword priorities.

[0078] The reception desk can prioritize and present highly relevant keywords when keywords are entered, taking into account the supporter's geographical location. For example, the reception desk can prioritize relevant keywords based on the supporter's current location. The reception desk can also suggest region-specific keywords, taking into account the supporter's geographical location. Furthermore, the reception desk can present the most suitable keywords, taking into account the distance from the supporter's current location. This allows for the priority presentation of highly relevant keywords by considering geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the supporter's geographical location information into the AI ​​and have the AI ​​perform the task of presenting highly relevant keywords.

[0079] The reception desk can analyze the supporter's social media activity when keywords are entered and suggest relevant keywords. For example, the reception desk can extract and suggest relevant keywords from the supporter's social media activity. The reception desk can also prioritize displaying keywords that the supporter frequently uses on social media. Furthermore, the reception desk can analyze the supporter's social media activity and suggest keywords based on trends. In this way, relevant keywords can be suggested by analyzing social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the supporter's social media activity data into AI and have the AI ​​suggest relevant keywords.

[0080] The analysis unit can estimate the supporter's emotions and adjust the accuracy of keyword analysis based on the estimated emotions. For example, if the supporter is relaxed, the analysis unit can perform a detailed analysis. It can also perform a rapid analysis if the supporter is in a hurry. Furthermore, if the supporter is stressed, the analysis unit can perform a simpler analysis. This allows for more appropriate analysis results by adjusting the accuracy of the analysis according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can input supporter emotion data into an AI and have the AI ​​adjust the accuracy of keyword analysis.

[0081] The analysis unit can optimize its analysis algorithm by referring to past analysis data during keyword analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. The analysis unit can also improve the accuracy of the analysis by referring to past analysis data. Furthermore, the analysis unit can analyze past analysis data and optimize the analysis algorithm. This allows the analysis algorithm to be optimized by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input past analysis data into AI and have the AI ​​perform the optimization of the analysis algorithm.

[0082] The analysis unit can apply different analysis methods depending on the keyword category during keyword analysis. For example, the analysis unit can select the optimal analysis method according to the keyword category. The analysis unit can also apply different analysis algorithms based on the keyword category. Furthermore, the analysis unit can customize the analysis method according to the keyword category. This improves the accuracy of the analysis by applying an analysis method appropriate to the keyword category. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keyword category data into the AI ​​and have the AI ​​perform the application of the analysis method.

[0083] The analysis unit can estimate the supporter's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the supporter is nervous, the analysis unit can provide a simple and highly visible display method. If the supporter is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the supporter is in a hurry, the analysis unit can provide a concise display method. By adjusting the display method according to the supporter's emotions, more easily understandable analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the supporter's emotion data into AI and have the AI ​​adjust the display method of the analysis results.

[0084] The analysis unit can determine the priority of keyword analysis based on the submission date of the keywords. For example, the analysis unit can determine the priority of analysis based on the submission date of the keywords. The analysis unit can also prioritize the analysis of older keywords. Furthermore, the analysis unit can also prioritize the analysis of newer keywords. This enables efficient analysis by determining the priority of analysis based on the submission date. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input keyword submission date data into AI and have the AI ​​perform the determination of the analysis priority.

[0085] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and data during keyword analysis. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant literature. Furthermore, the analysis unit can also improve the accuracy of its analysis based on relevant data. In addition, the analysis unit can analyze literature and data and optimize its analysis algorithm. This improves the accuracy of the analysis by referring to relevant literature and data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input relevant literature and data into AI and have the AI ​​perform the analysis accuracy improvement.

[0086] The generation unit can estimate the supporter's emotions and adjust the illustration card design based on the estimated emotions. For example, if the supporter is relaxed, the generation unit can generate an illustration card with soft colors. It can also generate a simple, highly visible illustration card if the supporter is in a hurry. Furthermore, if the supporter is stressed, the generation unit can generate an illustration card with a calm design. This allows for the generation of more appropriate illustration cards by adjusting the design according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, such as 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 processes in the generation unit may be performed using AI, or not. For example, the generation unit can input supporter emotion data into an AI and have the AI ​​perform the illustration card design adjustments.

[0087] The generation unit can adjust the level of detail generated based on the importance of keywords when generating illustration cards. For example, the generation unit can generate detailed illustration cards for important keywords. It can also generate simple illustration cards for less important keywords. Furthermore, the generation unit can customize the level of detail generated according to the importance of the keywords. This allows for the generation of more appropriate illustration cards by adjusting the level of detail generated according to the importance of the keywords. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword importance data into AI and have the AI ​​perform the adjustment of the level of detail generated.

[0088] The generation unit can apply different generation algorithms depending on the keyword category when generating illustration cards. For example, the generation unit can select the optimal generation algorithm depending on the keyword category. The generation unit can also apply different generation algorithms based on the keyword category. Furthermore, the generation unit can customize the generation algorithm depending on the keyword category. This improves the accuracy of generation by applying a generation algorithm that matches the keyword category. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword category data into AI and have AI perform the application of the generation algorithm.

[0089] The generation unit can estimate the supporter's emotions and adjust the length and content of the illustration card based on the estimated emotions. For example, if the supporter is relaxed, the generation unit can generate a longer illustration card with a detailed explanation. If the supporter is in a hurry, the generation unit can also generate a short, concise illustration card. Furthermore, if the supporter is stressed, the generation unit can generate a simple, highly visual illustration card. This allows for the generation of more appropriate illustration cards by adjusting the length and content according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input supporter emotion data into the AI ​​and have the AI ​​adjust the length and content of the illustration card.

[0090] The generation unit can determine the generation priority based on the keyword submission date when generating illustration cards. For example, the generation unit can determine the generation priority based on the keyword submission date. The generation unit can also prioritize the generation of older keywords. Furthermore, the generation unit can also prioritize the generation of newer keywords. This enables efficient illustration card generation by determining the generation priority based on the submission date. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input keyword submission date data into AI and have the AI ​​perform the determination of the generation priority.

[0091] The generation unit can improve the accuracy of illustration card generation by referring to related images and data. For example, the generation unit can improve the accuracy of generation by referring to related images. The generation unit can also improve the accuracy of generation based on related data. Furthermore, the generation unit can analyze images and data and optimize the generation algorithm. This improves the accuracy of generation by referring to related images and data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input related images and data into AI and have the AI ​​perform the improvement of generation accuracy.

[0092] The delivery unit can estimate the supporter's emotions and adjust the method of providing the illustration cards based on the estimated emotions. For example, if the supporter is relaxed, the delivery unit may select a delivery method that includes detailed explanations. If the supporter is in a hurry, the delivery unit may select a method that allows for quick delivery. Furthermore, if the supporter is stressed, the delivery unit may select a simple and highly visible delivery method. By adjusting the delivery method according to the supporter's emotions, more appropriate illustration cards can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input supporter emotion data into AI and have the AI ​​adjust the delivery method.

[0093] The distribution unit can select the optimal distribution method when providing illustration cards by referring to the supporter's past usage history. For example, the distribution unit can select the optimal distribution method based on the distribution methods the supporter has used in the past. The distribution unit can also select the most efficient distribution method from the supporter's past usage history. Furthermore, the distribution unit can analyze the supporter's past usage history and optimize the distribution method. This allows the optimal distribution method to be selected by referring to past usage history. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without AI. For example, the distribution unit can input the supporter's past usage history data into AI and have the AI ​​select the optimal distribution method.

[0094] The delivery unit can customize the delivery method based on the supporter's current situation when providing illustration cards. For example, the delivery unit can select the most suitable delivery method according to the supporter's current situation. Furthermore, if the supporter is in a hurry, the delivery unit can select a method that allows for quick delivery. Additionally, if the supporter is relaxed, the delivery unit can select a delivery method that includes detailed explanations. This allows for the provision of more appropriate illustration cards by customizing the delivery method according to the supporter's current situation. Some or all of the above processing in the delivery unit may be performed using AI, for example, or without AI. For example, the delivery unit can input data on the supporter's current situation into the AI ​​and have the AI ​​perform the customization of the delivery method.

[0095] The distribution unit can estimate the supporter's emotions and determine the order in which to provide the illustration cards based on the estimated emotions. For example, if the supporter is nervous, the distribution unit may prioritize providing important illustration cards. It may also prioritize providing detailed illustration cards if the supporter is relaxed. Furthermore, if the supporter is in a hurry, the distribution unit may prioritize providing illustration cards that can be provided quickly. This allows for the priority of providing important illustration cards by determining the order of provision according to the supporter's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the distribution unit may be performed using AI, or not. For example, the distribution unit can input supporter emotion data into an AI and have the AI ​​determine the order of provision.

[0096] The distribution unit can select the optimal distribution method when providing illustration cards, taking into account the supporter's geographical location information. For example, the distribution unit can select the optimal distribution method based on the supporter's current location. The distribution unit can also propose region-specific distribution methods, taking into account the supporter's geographical location information. Furthermore, the distribution unit can select the optimal distribution method by considering the distance from the supporter's current location. In this way, the optimal distribution method can be selected by considering geographical location information. Some or all of the above processing in the distribution unit may be performed using AI, for example, or without using AI. For example, the distribution unit can input the supporter's geographical location information into AI and have the AI ​​select the optimal distribution method.

[0097] The distribution unit can analyze the supporter's social media activity and propose distribution methods when providing illustration cards. For example, the distribution unit can propose the most suitable distribution method based on the supporter's social media activity. The distribution unit can also prioritize proposing distribution methods that supporters frequently use on social media. Furthermore, the distribution unit can analyze the supporter's social media activity and propose distribution methods based on trends. In this way, the optimal distribution method can be proposed by analyzing social media activity. Some or all of the above processing in the distribution unit may be performed using AI, for example, or not using AI. For example, the distribution unit can input supporter's social media activity data into AI and have the AI ​​propose distribution methods.

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

[0099] The reception desk can suggest relevant video content based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the reception desk can suggest a video demonstrating the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," the reception desk can suggest a video explaining how to complete homework. Furthermore, the reception desk can automatically search for and suggest educational video content related to the keywords entered by the supporter. This allows the visual support system to provide more diverse support through video content, in addition to visual illustration cards.

[0100] The analysis unit can generate relevant audio guides based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the analysis unit can generate an audio guide explaining the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," it can generate an audio guide explaining how to proceed with homework. Furthermore, the analysis unit can automatically generate and provide audio guides related to keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through audio guides.

[0101] The generation unit can generate relevant 3D models based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash your hands," the generation unit can generate a 3D model showing the handwashing procedure. Similarly, if the supporter enters the keyword "do your homework," the unit can generate a 3D model explaining how to proceed with homework. Furthermore, the generation unit can automatically generate and provide 3D models related to keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through 3D models.

[0102] The service provider can deliver relevant interactive content based on keywords entered by the supporter. For example, if the supporter enters the keyword "wash hands," the service provider can provide interactive content that teaches the handwashing procedure. Similarly, if the supporter enters the keyword "do homework," the service provider can provide interactive content that teaches how to complete homework. Furthermore, the service provider can automatically generate and deliver interactive content related to the keywords entered by the supporter. This allows the visual support system to provide more diverse support not only through visual illustration cards but also through interactive content.

[0103] The reception desk can estimate the supporter's emotions and customize the keyword input method based on that estimation. For example, if the supporter is stressed, the reception desk can provide a simple interface and minimize the input steps. If the supporter is relaxed, it can provide detailed input options and suggest a customizable input method. Furthermore, if the supporter is in a hurry, voice input can be prioritized to allow for quick keyword entry. This allows for a more user-friendly system by customizing the input method according to the supporter's emotions.

[0104] The analysis unit can estimate the supporter's emotions and adjust the accuracy of keyword analysis based on the estimated emotions. For example, if the supporter is relaxed, a detailed analysis can be performed. If the supporter is in a hurry, a rapid analysis can be performed. Furthermore, if the supporter is stressed, a simpler analysis can be performed. By adjusting the accuracy of the analysis according to the supporter's emotions, more appropriate analysis results can be obtained.

[0105] The generation unit can estimate the supporter's emotions and adjust the illustration card design based on those emotions. For example, if the supporter is relaxed, it can generate an illustration card with soft colors. If the supporter is in a hurry, it can generate a simple and highly visible illustration card. Furthermore, if the supporter is stressed, it can generate an illustration card with a calm design. In this way, by adjusting the design according to the supporter's emotions, it can generate more appropriate illustration cards.

[0106] The distribution unit can estimate the supporter's emotions and adjust the method of providing the illustration cards based on those estimates. For example, if the supporter is relaxed, it can select a distribution method that includes detailed explanations. If the supporter is in a hurry, it can select a method that allows for quick distribution. Furthermore, if the supporter is stressed, it can select a simple and highly visible distribution method. By adjusting the distribution method according to the supporter's emotions, it is possible to provide more appropriate illustration cards.

[0107] The distribution unit can estimate the supporter's emotions and determine the order in which to provide the illustration cards based on those emotions. For example, if the supporter is nervous, important illustration cards can be provided preferentially. If the supporter is relaxed, detailed illustration cards can be provided preferentially. Furthermore, if the supporter is in a hurry, illustration cards that can be provided quickly can be provided preferentially. In this way, by determining the order of provision according to the supporter's emotions, important illustration cards can be provided preferentially.

[0108] The service provider can select the optimal service delivery method by referring to the supporter's past usage history. For example, it can select the optimal delivery method based on the methods the supporter has used in the past. It can also select the most efficient delivery method from the supporter's past usage history. Furthermore, it can analyze the supporter's past usage history and optimize the delivery method. In this way, the optimal delivery method can be selected by referring to past usage history.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The reception desk receives keywords from the support worker that they would like to provide visual support for. These keywords may include specific actions or tasks, such as "wash your hands" or "do your homework." The reception desk can accept keywords using methods such as keyboard input or voice input. Step 2: The analysis unit analyzes the keywords entered by the reception unit. The analysis unit analyzes the keywords using, for example, natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit breaks down the keywords using morphological analysis, analyzes the structure of the keywords using grammatical analysis, and understands the meaning of the keywords using semantic analysis. Step 3: The generation unit generates illustration cards based on the keywords analyzed by the analysis unit. The generation unit generates illustration cards for visual assistance using, for example, a generation AI. The generation AI includes, for example, GANs (Generative Opposite Networks) and VAEs (Variational Autoencoders). The generation unit generates illustrations based on keywords using a GAN and generates variations of the illustrations using a VAE. Step 4: The provider provides the illustration cards generated by the generator. The provider provides the illustration cards in digital format, for example. Digital formats include PDF, JPEG, PNG, etc. The provider saves the generated illustration cards in PDF format and provides them to the supporter, for example. The provider can also provide the generated illustration cards in a printable format. Printable formats include PDF, DOCX, etc. The provider saves the generated illustration cards in PDF format so that the supporter can print them, for example.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit allows the supporter to input keywords using the reception device 38 of the smart device 14. The analysis unit analyzes the keywords using the identification processing unit 290 of the data processing unit 12. The generation unit generates an illustration card using the generation AI via the identification processing unit 290 of the data processing unit 12. The provision unit can provide the generated illustration card to the supporter using the output device 40 of the smart device 14. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

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

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

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit allows the supporter to voice input keywords using the microphone 238 of the smart glasses 214. The analysis unit analyzes the keywords using the identification processing unit 290 of the data processing unit 12. The generation unit generates an illustration card using the generation AI via the identification processing unit 290 of the data processing unit 12. The provision unit can provide the generated illustration card to the supporter using the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit allows the supporter to voice input keywords using the microphone 238 of the headset terminal 314. The analysis unit analyzes the keywords using the identification processing unit 290 of the data processing unit 12. The generation unit generates an illustration card using the generation AI via the identification processing unit 290 of the data processing unit 12. The provision unit can provide the generated illustration card to the supporter using the display 343 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the reception unit allows the supporter to voice input keywords using the microphone 238 of the robot 414. The analysis unit analyzes the keywords using the identification processing unit 290 of the data processing unit 12. The generation unit generates an illustration card using the generation AI via the identification processing unit 290 of the data processing unit 12. The provision unit can provide the generated illustration card to the supporter using the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

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

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) A reception desk where you enter keywords for visual support, An analysis unit analyzes the keywords entered by the reception unit, A generation unit that generates an illustration card based on keywords analyzed by the aforementioned analysis unit, The system includes a providing unit that provides the illustration cards generated by the generation unit. A system characterized by the following features. (Note 2) The generating unit is AI generates illustration cards for visual assistance. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Analyze keywords using natural language processing techniques. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, The generated illustration cards will be provided in digital format. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Provide the generated illustration cards in a printable format. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is We accept keywords entered by supporters. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the supporter's emotions and adjusts the keyword input interface based on the estimated supporter's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze the supporter's past input history and suggest the optimal keyword input method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When keywords are entered, suggestions are presented based on the supporter's current situation and needs. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is The system estimates the emotions of supporters and prioritizes the entered keywords based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When keywords are entered, the system prioritizes displaying highly relevant keywords, taking into account the supporter's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When you enter keywords, the system analyzes the social media activity of supporters and suggests relevant keywords. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the emotions of supporters and adjusts the accuracy of keyword analysis based on the estimated emotions of the supporters. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During keyword analysis, the analysis algorithm is optimized by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing keywords, different analysis methods are applied depending on the keyword category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the emotions of the supporters and adjusts how the analysis results are displayed based on the estimated emotions of the supporters. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing keywords, the priority of the analysis is determined based on when the keywords were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When performing keyword analysis, we improve the accuracy of the analysis by referring to relevant literature and data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is The system estimates the emotions of supporters and adjusts the design of the illustration cards based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating illustration cards, adjust the level of detail based on the importance of the keywords. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating illustration cards, different generation algorithms are applied depending on the keyword category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is The system estimates the supporter's emotions and adjusts the length and content of the illustration cards based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating illustration cards, the generation priority is determined based on the timing of keyword submission. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating illustration cards, we improve the accuracy of the generation by referencing related images and data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, The system estimates the emotions of supporters and adjusts the method of providing illustration cards based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing illustration cards, the optimal delivery method is selected by referring to the supporter's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing illustration cards, customize the delivery method based on the supporter's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, The system estimates the emotions of the supporters and determines the order in which the illustration cards are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing illustration cards, the optimal delivery method will be selected considering the geographical location information of the supporter. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing illustration cards, we analyze the supporters' social media activity and propose delivery methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk where you enter keywords for visual support, An analysis unit analyzes the keywords entered by the reception unit, A generation unit that generates illustration cards based on keywords analyzed by the analysis unit, The system includes a providing unit that provides the illustration cards generated by the generation unit. A system characterized by the following features.

2. The generating unit is Generates illustration cards for visual assistance using AI. The system according to feature 1.

3. The aforementioned analysis unit, Analyze keywords using natural language processing techniques. The system according to feature 1.

4. The aforementioned supply unit is, The generated illustration cards will be provided in digital format. The system according to feature 1.

5. The aforementioned supply unit is, Provide the generated illustration cards in a printable format. The system according to feature 1.

6. The aforementioned reception unit is We accept keywords entered by supporters. The system according to feature 1.

7. The aforementioned reception unit is It estimates the supporter's emotions and adjusts the keyword input interface based on the estimated supporter's emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze the supporter's past input history and suggest the optimal keyword input method. The system according to feature 1.

Images