System

Abstract

An object of a system according to an embodiment is to automatically add a context for clarifying an intention and a background of a prompt input by a user.SOLUTION: A system according to an embodiment comprises a prompt analyzer, a context generator, and a context adder. The prompt analysis unit analyzes a prompt input by a user. The context generation unit generates a context for clarifying an intention or a background of the prompt analyzed by the prompt analysis unit. The context adding unit adds the context generated by the context generating unit to the prompt.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to appropriately add context to clarify the intent and background of a prompt entered by a user.

[0005] The system according to the embodiment aims to automatically add context to clarify the intent and background of a prompt input by a user. [Means for solving the problem]

[0006] A system according to an embodiment includes a prompt analysis unit, a context generation unit, and a context addition unit. The prompt analysis unit analyzes a prompt input by a user. The context generation unit generates a context to clarify the intention or background of the prompt analyzed by the prompt analysis unit. The context addition unit adds the context generated by the context generation unit to the prompt. [Effects of the Invention]

[0007] The system according to the embodiment can automatically add context to clarify the intent and background of a prompt entered by a user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The automatic context addition system according to an embodiment of the present invention analyzes a prompt entered by a user, generates a context using a generation AI, and automatically adds the context to the prompt. This allows the automatic context addition system to automatically add context to the user's prompt, providing more specific and useful information.

[0029] An automatic context addition system according to an embodiment includes a prompt analysis unit, a context generation unit, and a context addition unit. The prompt analysis unit analyzes a prompt input by a user. For example, the prompt analysis unit analyzes the intent and background of the prompt using natural language processing technology. The prompt analysis unit can also analyze the content of the prompt using a machine learning algorithm. The prompt analysis unit can also analyze prompts in different formats, such as text, audio, and image. For example, the prompt analysis unit analyzes a text prompt to clarify its intent. An audio prompt is converted into text using speech recognition technology and then analyzed. An image prompt's content is analyzed using image analysis technology. The context generation unit generates a context to clarify the intent and background of the prompt analyzed by the prompt analysis unit. For example, the context generation unit generates information to clarify the intent and background of the prompt using a generation AI. The context generation unit can also generate a more personalized context by reflecting the user's past behavioral history and preferences. The context generation unit can also reflect external data collected in real time (for example, news and social media trends). For example, the generation AI analyzes a user's past search history and browsing history and generates personalized context based on that. It analyzes LINE (registered trademark) chat data and Yahoo search data to generate context that reflects the user's interests and trends. The context addition unit adds the context generated by the context generation unit to the prompt. For example, the context addition unit automatically adds the context generated by the generation AI to the prompt and provides it as the final output. The context addition unit can also incorporate user feedback into the context generated by the generation AI and introduce a mechanism for continuous improvement. For example, it can automatically add visual data (e.g., graphs and charts) related to the context generated by the generation AI.As a result, the automatic context addition system according to the embodiment can automatically add context to a user's prompt and provide more specific and useful information. For example, if a user inputs, "I would like to create a proposal for a new project," the generation AI analyzes the prompt and adds context such as the project's objectives, target market, and competitive analysis. If a user inputs, "I would like to come up with a new marketing strategy," the generation AI adds context such as market analysis and target demographic information to the prompt and provides it to the user.

[0030] The context generation unit can provide a more personalized context by reflecting the user's past behavioral history or preferences. For example, the context generation unit uses a generation AI to analyze the user's past search history and browsing history and generate a personalized context based on the results. For example, it reflects information about keywords the user has previously searched for and websites they have visited. The context generation unit can also analyze the user's past chat history and message content and generate a context based on the results. For example, it can use LINE (registered trademark) chat data to reflect topics and themes that interest the user. The context generation unit can also analyze the user's past purchase history and usage history and generate a context based on the results. For example, it can use Yahoo! Shopping purchase data to provide information related to products and services that the user is interested in. This allows the context generation unit to provide a more personalized context by reflecting the user's past behavioral history and preferences.

[0031] The context generation unit can provide a context that reflects the latest trends or topics by reflecting external data collected in real time. For example, the context generation unit generates a context that reflects the latest trends and topics by having a generation AI analyze news data collected in real time. For example, the context generation unit adds a context based on the latest news articles or topics. The context generation unit also collects trend data from social media in real time, and the generation AI analyzes the data and reflects it in the context. For example, the context generation unit provides information that is likely to interest users based on trending words and hashtags on Twitter (registered trademark). The context generation unit also analyzes market data and economic indicators collected in real time from external data sources and generates a context based on the data. For example, the context generation unit provides a context that reflects the latest stock price information and economic trends. This allows the context generation unit to provide a context that reflects the latest trends and topics by reflecting external data collected in real time.

[0032] The context generation unit can generate contexts that provide new perspectives by combining data from different industries or fields. For example, the context generation unit uses a generation AI to analyze data from different industries and combine it to generate contexts. For example, data from the medical and technology fields can be combined to provide context related to new medical technologies. The context generation unit can also generate contexts that provide new perspectives by combining data from different fields. For example, data from the education and entertainment fields can be combined to provide context related to educational games. The context generation unit can also combine trend data from different industries to generate contexts that provide users with new perspectives. For example, trends from the fashion and technology industries can be combined to provide context related to smartwear. In this way, contexts that provide new perspectives can be generated by combining data from different industries or fields.

[0033] The context generation unit can add information based on specific keywords or themes specified by the user. For example, the context generation unit has the generation AI collect related information based on keywords specified by the user and add it to the context. For example, if the user specifies "environmental protection," the latest data on environmental protection will be provided. The context generation unit also has the generation AI analyze related information based on the theme specified by the user and reflect it in the context. For example, if the user specifies "artificial intelligence," the AI ​​will provide information on the latest AI technology. The context generation unit also has the generation AI collect related news articles and research papers based on keywords or themes specified by the user and add them to the context. For example, if the user specifies "health," the AI ​​will provide the latest research results on health. This allows information based on specific keywords or themes specified by the user to be added.

[0034] The prompt analysis unit can generate more accurate context by referencing the user's past input history. For example, the prompt analysis unit allows the generation AI to analyze the user's past input history and generate context that clarifies the intent and background of the prompt based on that. For example, it learns the patterns of prompts entered in the past and provides appropriate context for similar prompts. The prompt analysis unit also refers to the user's past input history and generates context that allows the generation AI to more accurately understand the intent of the prompt. For example, it analyzes the relationship between past prompts and the current prompt and provides background information. The prompt analysis unit also generates context that allows the generation AI to clarify the intent and background of the prompt based on the user's past input history. For example, it provides appropriate context by referring to keywords and phrases used in past prompts. In this way, more accurate context can be generated by referencing the user's past input history.

[0035] The prompt analysis unit can generate a more specialized context by referring to related expertise or industry information. For example, when the generation AI analyzes a prompt, the prompt analysis unit references related expertise and industry information to generate a specialized context. For example, for a prompt in the medical field, the prompt analysis unit provides the latest medical research and technical information. Furthermore, when the generation AI analyzes a prompt, the prompt analysis unit references databases and specialized books in the related industry to generate a specialized context. For example, for a prompt in the financial industry, the prompt analysis unit provides the latest market trends and economic indicators. Furthermore, when the generation AI analyzes a prompt, the prompt analysis unit references opinions and papers of experts with related expertise to generate a specialized context. For example, for a prompt in the technology field, the prompt analysis unit provides the latest technological trends and research results. In this way, a more specialized context can be generated by referring to related expertise and industry information.

[0036] The prompt analysis unit supports input in different languages ​​and can generate multilingual context. For example, the generation AI supports prompt input in different languages ​​and generates multilingual context. For example, the prompt analysis unit provides appropriate context for prompts input in multiple languages, such as English, French, and Chinese. Furthermore, when analyzing a prompt, the generation AI uses an automatic translation function to analyze prompts in different languages ​​and generate multilingual context. For example, the prompt analysis unit translates a prompt input in Japanese into English and provides English context. Furthermore, the generation AI references databases in different languages ​​to generate multilingual context. For example, the generation AI uses a database containing technical terms and phrases in each language to provide appropriate context. This allows input in different languages ​​to be supported and multilingual context to be generated.

[0037] The prompt analysis unit can generate a context based on a specific format specified by the user. For example, the generation AI generates a context based on a specific format specified by the user. For example, for a report-format prompt, the prompt analysis unit provides a context including appropriate chapter headings and items. Furthermore, when analyzing a prompt, the prompt analysis unit generates a context based on the presentation format specified by the user. For example, it provides a context including the content and visual elements of each slide. Furthermore, the prompt analysis unit generates a context to clarify the intent and background of the prompt based on the specific format specified by the user. For example, for a business plan-format prompt, it provides a context including appropriate market analysis and competitive analysis. In this way, it is possible to generate a context based on a specific format specified by the user.

[0038] The context adding unit can incorporate a mechanism for reflecting user feedback on the context generated by the generation AI and continuously improving it. For example, the context adding unit incorporates a mechanism for collecting user feedback on the context generated by the generation AI and continuously improving the context based on that feedback. For example, the context adding unit analyzes the feedback provided by the user and adjusts the generation AI's algorithm. The context adding unit also constructs an interface that allows the user to provide feedback on the generated context in real time and improves the context based on that feedback. For example, the user can delete unnecessary information or enter additional information. The context adding unit also incorporates a mechanism for the generation AI to learn user feedback and automatically improve the context based on that feedback. For example, the feedback provided by the user can be reflected in the next context generation. This makes it possible to incorporate a mechanism for reflecting user feedback on the context generated by the generation AI and continuously improving it.

[0039] The context adding unit can automatically add visual data related to the context generated by the generation AI. The context adding unit automatically adds visual data related to the context generated by the generation AI. For example, it provides graphs showing the progress of a project or diagrams showing market analysis. The context adding unit also automatically generates visual data related to the context and provides it to the user. For example, it adds charts showing demographic data of a target market or matrices for competitive analysis. The context adding unit also collects visual data related to the context by the generation AI and automatically incorporates it into the context. For example, it provides graphs showing the latest economic indicators or diagrams showing technological trends. In this way, visual data related to the context generated by the generation AI can be automatically added.

[0040] The context adding unit can output the context generated by the generation AI in a format that can be shared on different platforms. The context adding unit outputs the context generated by the generation AI in a format that can be shared on different platforms, such as email or social media. For example, the context adding unit automatically generates and sends the context as the body of an email. The context adding unit also automatically generates the context in a social media posting format, allowing users to easily share it. For example, the context adding unit provides a context that matches the posting format of Twitter (registered trademark) or Facebook (registered trademark). The context adding unit also provides an interface for outputting the context generated by the generation AI in a format that can be shared on different platforms. For example, the context can be converted into a format that can be shared by simply copying and pasting. This allows the context generated by the generation AI to be output in a format that can be shared on different platforms.

[0041] The context adding unit can directly output the context generated by the generation AI to a specific application specified by the user. For example, the context adding unit directly outputs the context generated by the generation AI to a word processor specified by the user. For example, the context adding unit automatically inserts the context into Microsoft Word or Google (registered trademark) Docs. The context adding unit also automatically generates the context in a spreadsheet format and outputs it directly to an application specified by the user. For example, the context adding unit automatically inputs data into Microsoft Excel or Google (registered trademark) Sheets. The context adding unit also provides an interface for directly outputting the context generated by the generation AI to a specific application specified by the user. For example, the context adding unit sends data to the application using an API. This allows the context generated by the generation AI to be directly output to a specific application specified by the user.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The automatic context addition system can also use the user's geographical information to generate a context that is specific to the region. For example, if the user is in a particular city, the system can add the latest event information and weather forecast for that city to the context. If the user is traveling, the system can provide information about tourist attractions and restaurants in the user's destination. Furthermore, based on the user's geographical information, the system can also incorporate information about local culture and customs into the context. This makes it possible to provide a more personalized context based on the user's location information.

[0044] The automatic context addition system can also use information about the user's device to generate contexts optimized for that device. For example, if the user is using a smartphone, it can provide a mobile-friendly context. If the user is using a desktop, it can provide a detailed context suitable for a large screen. It can also adjust the display format and content of the context according to the capabilities and settings of the user's device. This makes it possible to provide a more user-friendly context that is optimized for the user's device.

[0045] The automatic context addition system can also generate timely context by utilizing the user's schedule information. For example, it can analyze the user's calendar information and provide information related to the user's schedule. If the user is in a meeting, it can add materials and notes related to the meeting to the context. It can also provide reminders about important events and deadlines based on the user's schedule. This allows it to provide more timely and useful context that is tailored to the user's schedule.

[0046] The automatic context addition system can also generate health-related context using the user's health data. For example, it can analyze data obtained from the user's fitness tracker or smartwatch to provide health advice. It can also provide information on nutritional balance and exercise plans based on the user's diet and exercise history. It can also provide information on relaxation techniques and stress management based on the user's health status. This allows for more personalized health information to be provided based on the user's health data.

[0047] The automatic context addition system can also generate shopping-related contexts using a user's purchasing history. For example, it can provide recommendations for related products based on the user's past purchases. If a user frequently purchases products in a particular category, it can also provide the latest trend information related to that category. It can also provide sale information and coupons for specific brands or stores based on the user's purchasing history. This makes it possible to provide more personalized shopping information based on the user's purchasing history.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The prompt analyzer analyzes the prompt entered by the user. For example, the prompt analyzer analyzes the intent and background of the prompt using natural language processing technology. The prompt analyzer can also analyze the content of the prompt using a machine learning algorithm. Furthermore, the prompt analyzer can analyze prompts in different formats, such as text, audio, and image. For example, the prompt analyzer analyzes a text prompt to clarify its intent. An audio prompt is converted into text using speech recognition technology and then analyzed. An image prompt's content is analyzed using image analysis technology. Step 2: The context generation unit generates a context to clarify the intent and background of the prompt analyzed by the prompt analysis unit. For example, the context generation unit uses generation AI to generate information to clarify the intent and background of the prompt. The context generation unit can also generate a more personalized context by reflecting the user's past behavioral history and preferences. Furthermore, the context generation unit can also reflect external data collected in real time (e.g., news and social media trends). Step 3: The context adding unit adds the context generated by the context generating unit to the prompt. For example, the context adding unit automatically adds the context generated by the generation AI to the prompt and provides it as the final output. The context adding unit can also incorporate user feedback into the context generated by the generation AI and introduce a mechanism for continuous improvement. Furthermore, it can automatically add visual data (e.g., graphs and charts) related to the context generated by the generation AI.

[0050] (Example 2) The automatic context addition system according to an embodiment of the present invention analyzes a prompt entered by a user, generates a context using a generation AI, and automatically adds the context to the prompt. This allows the automatic context addition system to automatically add context to the user's prompt, providing more specific and useful information.

[0051] An automatic context addition system according to an embodiment includes a prompt analysis unit, a context generation unit, and a context addition unit. The prompt analysis unit analyzes a prompt input by a user. For example, the prompt analysis unit analyzes the intent and background of the prompt using natural language processing technology. The prompt analysis unit can also analyze the content of the prompt using a machine learning algorithm. The prompt analysis unit can also analyze prompts in different formats, such as text, audio, and image. For example, the prompt analysis unit analyzes a text prompt to clarify its intent. An audio prompt is converted into text using speech recognition technology and then analyzed. An image prompt's content is analyzed using image analysis technology. The context generation unit generates a context to clarify the intent and background of the prompt analyzed by the prompt analysis unit. For example, the context generation unit generates information to clarify the intent and background of the prompt using a generation AI. The context generation unit can also generate a more personalized context by reflecting the user's past behavioral history and preferences. The context generation unit can also reflect external data collected in real time (for example, news and social media trends). For example, the generation AI analyzes a user's past search history and browsing history and generates personalized context based on that. It analyzes LINE (registered trademark) chat data and Yahoo search data to generate context that reflects the user's interests and trends. The context addition unit adds the context generated by the context generation unit to the prompt. For example, the context addition unit automatically adds the context generated by the generation AI to the prompt and provides it as the final output. The context addition unit can also incorporate user feedback into the context generated by the generation AI and introduce a mechanism for continuous improvement. For example, it can automatically add visual data (e.g., graphs and charts) related to the context generated by the generation AI.As a result, the automatic context addition system according to the embodiment can automatically add context to a user's prompt and provide more specific and useful information. For example, if a user inputs, "I would like to create a proposal for a new project," the generation AI analyzes the prompt and adds context such as the project's objectives, target market, and competitive analysis. If a user inputs, "I would like to come up with a new marketing strategy," the generation AI adds context such as market analysis and target demographic information to the prompt and provides it to the user.

[0052] The context generation unit can provide a more personalized context by reflecting the user's past behavioral history or preferences. For example, the context generation unit uses a generation AI to analyze the user's past search history and browsing history and generate a personalized context based on the results. For example, it reflects information about keywords the user has previously searched for and websites they have visited. The context generation unit can also analyze the user's past chat history and message content and generate a context based on the results. For example, it can use LINE (registered trademark) chat data to reflect topics and themes that interest the user. The context generation unit can also analyze the user's past purchase history and usage history and generate a context based on the results. For example, it can use Yahoo! Shopping purchase data to provide information related to products and services that the user is interested in. This allows the context generation unit to provide a more personalized context by reflecting the user's past behavioral history and preferences.

[0053] The context generation unit can provide a context that reflects the latest trends or topics by reflecting external data collected in real time. For example, the context generation unit generates a context that reflects the latest trends and topics by having a generation AI analyze news data collected in real time. For example, the context generation unit adds a context based on the latest news articles or topics. The context generation unit also collects trend data from social media in real time, and the generation AI analyzes the data and reflects it in the context. For example, the context generation unit provides information that is likely to interest users based on trending words and hashtags on Twitter (registered trademark). The context generation unit also analyzes market data and economic indicators collected in real time from external data sources and generates a context based on the data. For example, the context generation unit provides a context that reflects the latest stock price information and economic trends. This allows the context generation unit to provide a context that reflects the latest trends and topics by reflecting external data collected in real time.

[0054] The context generation unit uses the emotion estimation function to generate a context according to the user's emotional state and provide it in the form most acceptable to the user. For example, the context generation unit uses a generation AI to analyze the user's emotional state at the time of input and generate a context accordingly. For example, if the user is feeling positive, optimistic information is provided. The context generation unit also uses the emotion estimation function to generate a context based on the user's emotional state. For example, if the user is feeling stressed, information or advice that will help them relax is provided. The context generation unit also monitors the user's emotional state in real time and adjusts the context accordingly. For example, if the user is feeling anxious, information that gives a sense of security is provided. This allows the context generation unit to generate a context according to the user's emotional state and provide it in the form most acceptable to the user.

[0055] The context generation unit can generate contexts that provide new perspectives by combining data from different industries or fields. For example, the context generation unit uses a generation AI to analyze data from different industries and combine it to generate contexts. For example, data from the medical and technology fields can be combined to provide context related to new medical technologies. The context generation unit can also generate contexts that provide new perspectives by combining data from different fields. For example, data from the education and entertainment fields can be combined to provide context related to educational games. The context generation unit can also combine trend data from different industries to generate contexts that provide users with new perspectives. For example, trends from the fashion and technology industries can be combined to provide context related to smartwear. In this way, contexts that provide new perspectives can be generated by combining data from different industries or fields.

[0056] The context generation unit can add information based on specific keywords or themes specified by the user. For example, the context generation unit has the generation AI collect related information based on keywords specified by the user and add it to the context. For example, if the user specifies "environmental protection," the latest data on environmental protection will be provided. The context generation unit also has the generation AI analyze related information based on the theme specified by the user and reflect it in the context. For example, if the user specifies "artificial intelligence," the AI ​​will provide information on the latest AI technology. The context generation unit also has the generation AI collect related news articles and research papers based on keywords or themes specified by the user and add them to the context. For example, if the user specifies "health," the AI ​​will provide the latest research results on health. This allows information based on specific keywords or themes specified by the user to be added.

[0057] The context generation unit can use the emotion estimation function to suggest the optimal context based on the emotional reaction to the prompt entered by the user. For example, the context generation unit uses the emotion estimation function to analyze the emotional reaction to the prompt entered by the user and suggests the optimal context based on that. For example, if the user is excited, positive information is provided. The context generation unit also uses the generation AI to generate the optimal context based on the user's emotional reaction. For example, if the user is feeling anxious, information that gives a sense of security is provided. The context generation unit also uses the emotion estimation function to monitor the user's emotional reaction in real time and adjust the context accordingly. For example, if the user is feeling depressed, an encouraging message is provided. This makes it possible to suggest the optimal context based on the emotional reaction to the prompt entered by the user.

[0058] The prompt analysis unit can generate more accurate context by referencing the user's past input history. For example, the prompt analysis unit allows the generation AI to analyze the user's past input history and generate context that clarifies the intent and background of the prompt based on that. For example, it learns the patterns of prompts entered in the past and provides appropriate context for similar prompts. The prompt analysis unit also refers to the user's past input history and generates context that allows the generation AI to more accurately understand the intent of the prompt. For example, it analyzes the relationship between past prompts and the current prompt and provides background information. The prompt analysis unit also generates context that allows the generation AI to clarify the intent and background of the prompt based on the user's past input history. For example, it provides appropriate context by referring to keywords and phrases used in past prompts. In this way, more accurate context can be generated by referencing the user's past input history.

[0059] The prompt analysis unit can generate a more specialized context by referring to related expertise or industry information. For example, when the generation AI analyzes a prompt, the prompt analysis unit references related expertise and industry information to generate a specialized context. For example, for a prompt in the medical field, the prompt analysis unit provides the latest medical research and technical information. Furthermore, when the generation AI analyzes a prompt, the prompt analysis unit references databases and specialized books in the related industry to generate a specialized context. For example, for a prompt in the financial industry, the prompt analysis unit provides the latest market trends and economic indicators. Furthermore, when the generation AI analyzes a prompt, the prompt analysis unit references opinions and papers of experts with related expertise to generate a specialized context. For example, for a prompt in the technology field, the prompt analysis unit provides the latest technological trends and research results. In this way, a more specialized context can be generated by referring to related expertise and industry information.

[0060] The prompt analysis unit can use the emotion estimation function to analyze the user's emotional state and generate a context according to that emotion. For example, the prompt analysis unit uses the emotion estimation function to analyze the user's emotional state and generate a context according to that emotion. For example, if the user is feeling positive, optimistic information is provided. The prompt analysis unit also uses a generation AI to analyze the user's emotional state and generate a context based on that emotion. For example, if the user is feeling stressed, information or advice that will help them relax is provided. The prompt analysis unit also uses the emotion estimation function to monitor the user's emotional state in real time and adjust the context accordingly. For example, if the user is feeling anxious, information that gives a sense of security is provided. This makes it possible to analyze the user's emotional state and generate a context according to that emotion.

[0061] The prompt analysis unit supports input in different languages ​​and can generate multilingual context. For example, the generation AI supports prompt input in different languages ​​and generates multilingual context. For example, the prompt analysis unit provides appropriate context for prompts input in multiple languages, such as English, French, and Chinese. Furthermore, when analyzing a prompt, the generation AI uses an automatic translation function to analyze prompts in different languages ​​and generate multilingual context. For example, the prompt analysis unit translates a prompt input in Japanese into English and provides English context. Furthermore, the generation AI references databases in different languages ​​to generate multilingual context. For example, the generation AI uses a database containing technical terms and phrases in each language to provide appropriate context. This allows input in different languages ​​to be supported and multilingual context to be generated.

[0062] The prompt analysis unit can generate a context based on a specific format specified by the user. For example, the generation AI generates a context based on a specific format specified by the user. For example, for a report-format prompt, the prompt analysis unit provides a context including appropriate chapter headings and items. Furthermore, when analyzing a prompt, the prompt analysis unit generates a context based on the presentation format specified by the user. For example, it provides a context including the content and visual elements of each slide. Furthermore, the prompt analysis unit generates a context to clarify the intent and background of the prompt based on the specific format specified by the user. For example, for a business plan-format prompt, it provides a context including appropriate market analysis and competitive analysis. In this way, it is possible to generate a context based on a specific format specified by the user.

[0063] The prompt analysis unit can use the emotion estimation function to analyze prompts based on the user's emotions and generate a context that corresponds to the emotions. For example, the prompt analysis unit uses the emotion estimation function to analyze prompts based on the user's emotions and generate a context that corresponds to the emotions. For example, if the user has positive emotions, optimistic information is provided. The prompt analysis unit also uses a generation AI to analyze the user's emotional state, analyze prompts based on the emotions, and generate an appropriate context. For example, if the user is feeling stressed, information or advice that will help the user relax is provided. The prompt analysis unit also uses the emotion estimation function to monitor the user's emotional state in real time, analyze prompts accordingly, and adjust the context. For example, if the user is feeling anxious, information that provides a sense of security is provided. This makes it possible to analyze prompts based on the user's emotions and generate a context that corresponds to the emotions.

[0064] The context adding unit can incorporate a mechanism for reflecting user feedback on the context generated by the generation AI and continuously improving it. For example, the context adding unit incorporates a mechanism for collecting user feedback on the context generated by the generation AI and continuously improving the context based on that feedback. For example, the context adding unit analyzes the feedback provided by the user and adjusts the generation AI's algorithm. The context adding unit also constructs an interface that allows the user to provide feedback on the generated context in real time and improves the context based on that feedback. For example, the user can delete unnecessary information or enter additional information. The context adding unit also incorporates a mechanism for the generation AI to learn user feedback and automatically improve the context based on that feedback. For example, the feedback provided by the user can be reflected in the next context generation. This makes it possible to incorporate a mechanism for reflecting user feedback on the context generated by the generation AI and continuously improving it.

[0065] The context adding unit can automatically add visual data related to the context generated by the generation AI. The context adding unit automatically adds visual data related to the context generated by the generation AI. For example, it provides graphs showing the progress of a project or diagrams showing market analysis. The context adding unit also automatically generates visual data related to the context and provides it to the user. For example, it adds charts showing demographic data of a target market or matrices for competitive analysis. The context adding unit also collects visual data related to the context by the generation AI and automatically incorporates it into the context. For example, it provides graphs showing the latest economic indicators or diagrams showing technological trends. In this way, visual data related to the context generated by the generation AI can be automatically added.

[0066] The context adding unit can use the emotion estimation function to adjust the output format of the context according to the user's emotion and provide it in an optimal form. For example, the context adding unit uses the emotion estimation function to adjust the output format of the context according to the user's emotion. For example, if the user has positive emotions, the context is provided in bright colors and an optimistic tone. The context adding unit also uses the generation AI to analyze the user's emotional state and adjust the output format of the context based on that analysis. For example, if the user is feeling stressed, the context is provided in relaxing colors and tones. The context adding unit also uses the emotion estimation function to monitor the user's emotional state in real time and adjust the output format of the context accordingly. For example, if the user is feeling anxious, the context is provided in a format that gives a sense of security. This allows the output format of the context to be adjusted according to the user's emotion and provided in an optimal form.

[0067] The context adding unit can output the context generated by the generation AI in a format that can be shared on different platforms. The context adding unit outputs the context generated by the generation AI in a format that can be shared on different platforms, such as email or social media. For example, the context adding unit automatically generates and sends the context as the body of an email. The context adding unit also automatically generates the context in a social media posting format, allowing users to easily share it. For example, the context adding unit provides a context that matches the posting format of Twitter (registered trademark) or Facebook (registered trademark). The context adding unit also provides an interface for outputting the context generated by the generation AI in a format that can be shared on different platforms. For example, the context can be converted into a format that can be shared by simply copying and pasting. This allows the context generated by the generation AI to be output in a format that can be shared on different platforms.

[0068] The context adding unit can directly output the context generated by the generation AI to a specific application specified by the user. For example, the context adding unit directly outputs the context generated by the generation AI to a word processor specified by the user. For example, the context adding unit automatically inserts the context into Microsoft Word or Google (registered trademark) Docs. The context adding unit also automatically generates the context in a spreadsheet format and outputs it directly to an application specified by the user. For example, the context adding unit automatically inputs data into Microsoft Excel or Google (registered trademark) Sheets. The context adding unit also provides an interface for directly outputting the context generated by the generation AI to a specific application specified by the user. For example, the context adding unit sends data to the application using an API. This allows the context generated by the generation AI to be directly output to a specific application specified by the user.

[0069] The context adding unit can use the emotion estimation function to adjust the timing of context output based on the user's emotion and provide it at the optimal timing. The context adding unit, for example, uses the emotion estimation function to adjust the timing of context output based on the user's emotion. For example, if the user has positive emotions, it provides the context immediately. The context adding unit also analyzes the user's emotional state using the generation AI and adjusts the timing of context output based on that. For example, if the user is feeling stressed, it provides the context at a timing that will help the user relax. The context adding unit also uses the emotion estimation function to monitor the user's emotional state in real time and adjust the timing of context output accordingly. For example, if the user is feeling anxious, it provides the context at a timing that will give the user a sense of security. This allows the timing of context output based on the user's emotion to be adjusted and provided at the optimal timing.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The automatic context addition system can also use the user's geographical information to generate a context that is specific to the region. For example, if the user is in a particular city, the system can add the latest event information and weather forecast for that city to the context. If the user is traveling, the system can provide information about tourist attractions and restaurants in the user's destination. Furthermore, based on the user's geographical information, the system can also incorporate information about local culture and customs into the context. This makes it possible to provide a more personalized context based on the user's location information.

[0072] The automatic context addition system can also use information about the user's device to generate contexts optimized for that device. For example, if the user is using a smartphone, it can provide a mobile-friendly context. If the user is using a desktop, it can provide a detailed context suitable for a large screen. It can also adjust the display format and content of the context according to the capabilities and settings of the user's device. This makes it possible to provide a more user-friendly context that is optimized for the user's device.

[0073] The automatic context addition system can also generate timely context by utilizing the user's schedule information. For example, it can analyze the user's calendar information and provide information related to the user's schedule. If the user is in a meeting, it can add materials and notes related to the meeting to the context. It can also provide reminders about important events and deadlines based on the user's schedule. This allows it to provide more timely and useful context that is tailored to the user's schedule.

[0074] The automatic context addition system can also generate health-related context using the user's health data. For example, it can analyze data obtained from the user's fitness tracker or smartwatch to provide health advice. It can also provide information on nutritional balance and exercise plans based on the user's diet and exercise history. It can also provide information on relaxation techniques and stress management based on the user's health status. This allows for more personalized health information to be provided based on the user's health data.

[0075] The automatic context addition system can also generate shopping-related contexts using a user's purchasing history. For example, it can provide recommendations for related products based on the user's past purchases. If a user frequently purchases products in a particular category, it can also provide the latest trend information related to that category. It can also provide sale information and coupons for specific brands or stores based on the user's purchasing history. This makes it possible to provide more personalized shopping information based on the user's purchasing history.

[0076] The automatic context addition system can use emotion estimation to generate music and entertainment contexts based on the user's emotions. For example, if a user feels like relaxing, it can provide recommendations for relaxing music and movies. If a user feels like cheering up, it can also provide recommendations for energetic music and action movies. It can also provide information on specific artists and genres depending on the user's emotional state. This allows for more personalized entertainment information based on the user's emotions.

[0077] The automatic context addition system can use its emotion estimation function to generate learning and educational contexts based on the user's emotions. For example, if a user feels like they want to improve their concentration, it can provide learning methods and materials to improve that concentration. Also, if a user feels like they want to relax, it can provide content that allows them to learn while relaxing. Furthermore, it can adjust the method of providing feedback on learning progress and results depending on the user's emotional state. This makes it possible to provide more effective learning and educational contexts based on the user's emotions.

[0078] The automatic context addition system can use its emotion estimation function to generate communication contexts based on the user's emotions. For example, if the user is feeling positive, it can provide fun topics and jokes. If the user is feeling negative, it can provide encouraging messages and advice. It can also adjust the tone and style of communication depending on the user's emotional state. This makes it possible to provide a more appropriate communication context based on the user's emotions.

[0079] The automatic context addition system can use its emotion estimation function to generate feedback and evaluation contexts based on the user's emotions. For example, if the user has positive emotions, it can provide positive feedback and evaluations. If the user has negative emotions, it can also provide constructive advice and suggestions for improvement. Furthermore, it can adjust the content and format of feedback depending on the user's emotional state. This makes it possible to provide more effective feedback and evaluation contexts based on the user's emotions.

[0080] The automatic context addition system can use emotion estimation to generate contexts for reminders and notifications based on the user's emotions. For example, if a user is feeling stressed, it can provide a reminder to take a break to relax. Also, if a user has positive emotions, it can provide a notification that motivates them to tackle the next task. Furthermore, it can adjust the timing and content of reminders and notifications according to the user's emotional state. This allows it to provide more appropriate contexts for reminders and notifications based on the user's emotions.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The prompt analyzer analyzes the prompt entered by the user. For example, the prompt analyzer analyzes the intent and background of the prompt using natural language processing technology. The prompt analyzer can also analyze the content of the prompt using a machine learning algorithm. Furthermore, the prompt analyzer can analyze prompts in different formats, such as text, audio, and image. For example, the prompt analyzer analyzes a text prompt to clarify its intent. An audio prompt is converted into text using speech recognition technology and then analyzed. An image prompt's content is analyzed using image analysis technology. Step 2: The context generation unit generates a context to clarify the intent and background of the prompt analyzed by the prompt analysis unit. For example, the context generation unit uses generation AI to generate information to clarify the intent and background of the prompt. The context generation unit can also generate a more personalized context by reflecting the user's past behavioral history and preferences. Furthermore, the context generation unit can also reflect external data collected in real time (e.g., news and social media trends). Step 3: The context adding unit adds the context generated by the context generating unit to the prompt. For example, the context adding unit automatically adds the context generated by the generation AI to the prompt and provides it as the final output. The context adding unit can also incorporate user feedback into the context generated by the generation AI and introduce a mechanism for continuous improvement. Furthermore, it can automatically add visual data (e.g., graphs and charts) related to the context generated by the generation AI.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 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.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 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.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] 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.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a prompt analysis unit that analyzes a prompt input by a user; a context generation unit that generates a context for clarifying the intent or background of the prompt analyzed by the prompt analysis unit; a context adding unit that adds the context generated by the context generating unit to the prompt. A system characterized by:

2. The context generation unit Providing more personalized context by reflecting the user's past behavior or preferences 2. The system of claim 1.

3. The context generation unit Incorporating external data collected in real time to provide context that reflects the latest trends or topics 2. The system of claim 1.

4. The context generation unit A context is generated according to the emotional state of the user, and is provided in a form most acceptable to the user.

2. The system of claim 1.

5. The context generation unit Combining data from different industries or sectors to create context that provides new perspectives 2. The system of claim 1.

6. The context generation unit Add information based on specific keywords or themes specified by the user.

2. The system of claim 1.

7. The context generation unit Suggesting the most appropriate context based on the user's emotional response to the prompt 2. The system of claim 1.

8. The prompt analysis unit Refer to the user's past input history to generate a more accurate context 2. The system of claim 1.

Images