System

Abstract

An object of the system according to the embodiment is to extract necessary materials and cooking procedures from a cooking moving image and convert the materials and the cooking procedures into text.SOLUTION: A system includes an analysis unit, an extraction unit, and a text generation unit. The analysis unit analyzes the cooking moving image. The extraction part extracts necessary materials and cooking procedures on the basis of the information analyzed by the analysis part. The text generation unit generates text from the information extracted by the extraction unit.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 technology has faced the challenge of making it difficult to efficiently extract the necessary ingredients and cooking steps from cooking videos and convert them into text.

[0005] The system according to the embodiment aims to extract necessary ingredients and cooking steps from cooking videos and convert them into text. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an extraction unit, and a text conversion unit. The analysis unit analyzes cooking videos. The extraction unit extracts necessary ingredients and cooking steps based on the information analyzed by the analysis unit. The text conversion unit converts the information extracted by the extraction unit into text. [Effects of the Invention]

[0007] The system according to the embodiment can extract the necessary ingredients and cooking steps from cooking videos and convert them into text. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention analyzes cooking videos, extracts necessary ingredients and cooking steps, and converts them into text. This system provides value to both viewers and creators by analyzing cooking videos, extracting necessary ingredients and cooking steps, and converting them into text. For example, the system analyzes cooking videos and identifies necessary ingredients and cooking steps from the audio and video in the videos. Next, it organizes the identified ingredients and steps in a list format and converts them into text. This allows viewers to easily provide high-quality videos and creators to supplement information missing from cooking videos. This allows viewers to check necessary ingredients and cooking steps while watching cooking videos, making it easier to recreate dishes. Creators can also provide more information to viewers by converting into text parts of cooking videos that are insufficiently explained or points that viewers tend to overlook.

[0029] A cooking video analysis system according to an embodiment includes an analysis unit, an extraction unit, and a text generation unit. The analysis unit analyzes cooking videos. Examples of cooking videos include, but are not limited to, home cooking, professional cooking, and specific cooking genres. The analysis unit identifies necessary ingredients and cooking steps from audio and video within the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit may analyze audio within the video using speech recognition technology to identify ingredients and cooking utensils used. The analysis unit may also analyze video within the video using image recognition technology to identify cooking steps. Furthermore, the analysis unit may use text analysis technology to analyze subtitle information within the video to complement the identification of ingredients and steps. The extraction unit extracts the ingredients and steps identified by the analysis unit. The extraction is performed using techniques such as keyword extraction and pattern recognition. For example, the extraction unit organizes the ingredients and steps identified by the analysis unit in a list format. Examples of list formats include, but are not limited to, bulleted lists and numbered lists. The text conversion unit converts the information extracted by the extraction unit into text. The text conversion is performed using, for example, techniques such as natural language generation and format conversion. For example, the text conversion unit organizes the extracted ingredients and steps in a list format and provides it to viewers and creators. This allows the cooking video analysis system according to the embodiment to provide value to both viewers and creators.

[0030] Furthermore, the cooking video analysis system includes a providing unit that provides the information extracted by the extraction unit to viewers and creators. The providing unit provides the information extracted by the extraction unit to viewers and creators. The information is provided, for example, via a website, an app, email, or other methods. For example, the providing unit provides the extracted information to viewers via a website. The providing unit can also provide the extracted information to creators via a dedicated app. Furthermore, the providing unit can send the extracted information to viewers and creators via email. In this way, by providing the extracted information to viewers and creators, value can be provided to both.

[0031] The analysis unit can identify the necessary ingredients and cooking steps from the audio or video in the video. The analysis unit, for example, uses voice recognition technology to analyze the audio in the video and identify the ingredients and cooking utensils used. For example, the analysis unit uses voice filtering technology to remove background sounds and improve the accuracy of voice recognition. The analysis unit can also analyze the video in the video and identify the cooking steps using image recognition technology. For example, the analysis unit can use video analysis technology to identify how to use cooking utensils. The analysis unit can also use text analysis technology to analyze subtitle information in the video and supplement the identification of ingredients and steps. For example, the analysis unit analyzes subtitle information to supplement the identification of ingredients. In this way, the necessary ingredients and cooking steps can be accurately identified by analyzing the audio and video in the video.

[0032] The extraction unit can organize the identified materials and steps in a list format. For example, the extraction unit organizes the materials and steps identified by the analysis unit in a list format. Examples of list formats include, but are not limited to, bulleted lists and numbered lists. For example, the extraction unit organizes the identified materials in bulleted lists. The extraction unit can also organize the identified steps in a numbered list. Furthermore, the extraction unit can combine the materials and steps and organize them in a list format. For example, the extraction unit combines the materials and steps and organizes them in a format that is easy for viewers to understand. By organizing the identified materials and steps in a list format, it is possible to provide them to viewers and creators in an easy-to-understand manner.

[0033] The text conversion unit can convert information organized in a list format into text. For example, the text conversion unit organizes the materials and procedures extracted by the extraction unit into a list format and converts the information into text. The text conversion is performed using techniques such as natural language generation and format conversion. For example, the text conversion unit organizes the extracted materials and procedures in a list format and provides them to viewers and creators. The text conversion unit can also output the textual information in different formats. For example, the text conversion unit outputs the textual information in PDF format or HTML format. In this way, by converting the information organized in a list format into text, it is possible to provide viewers and creators with information that is easy to understand.

[0034] The analysis unit can remove background sounds and noise from the video to improve the accuracy of the analysis. For example, the analysis unit can filter background sounds in the video to improve the accuracy of speech recognition. Examples of background sounds include, but are not limited to, environmental sounds and unnecessary sounds. For example, the analysis unit can remove background sounds from the video using noise filtering technology. The analysis unit can also remove noise from the video to improve the accuracy of video analysis. Examples of noise include, but are not limited to, white noise and environmental sounds. For example, the analysis unit can remove unnecessary sounds from the video using noise removal technology to accurately identify necessary materials and steps. In this way, the accuracy of the analysis can be improved by removing background sounds and noise.

[0035] The analysis unit can analyze each frame of the video and identify changes in material and procedures in detail. The analysis unit, for example, analyzes each frame of the video and identifies changes in material. The frame-by-frame analysis includes, but is not limited to, frame rate and analysis algorithm. For example, the analysis unit uses an algorithm for identifying changes in material for each frame. The analysis unit can also analyze each frame of the video and identify changes in procedures. For example, the analysis unit uses an algorithm for identifying changes in procedures for each frame. Furthermore, the analysis unit can analyze each frame of the video and identify detailed changes in material and procedures. For example, the analysis unit uses an algorithm for identifying changes in material and procedures for each frame. In this way, by performing the analysis for each frame, it is possible to identify changes in material and procedures in detail.

[0036] The analysis unit can use subtitle information in the video for analysis to complement the identification of materials and procedures. The analysis unit, for example, analyzes subtitle information in the video to complement the identification of materials. Subtitle information includes, for example, text analysis and timestamp analysis, but is not limited to these examples. For example, the analysis unit can analyze subtitle information using text analysis technology to complement the identification of materials. The analysis unit can also analyze subtitle information using timestamp analysis technology to complement the identification of procedures. For example, the analysis unit can analyze timestamps in the subtitle information to complement the identification of procedures. Furthermore, the analysis unit can analyze subtitle information in the video to complement the identification of materials and procedures. For example, the analysis unit can analyze subtitle information to complement the identification of materials and procedures. In this way, the identification of materials and procedures can be complemented by using subtitle information in the analysis.

[0037] The analysis unit can adjust the accuracy of the analysis based on the shooting environment of the video. The analysis unit, for example, takes into account the lighting conditions of the video and adjusts the accuracy of the analysis. Lighting conditions include, but are not limited to, brightness and light direction. For example, the analysis unit analyzes the lighting conditions to achieve optimal analysis accuracy. The analysis unit can also adjust the accuracy of the analysis by taking into account the camera angle of the video. Camera angles include, but are not limited to, shooting angles and zoom levels. For example, the analysis unit analyzes the camera angle to achieve optimal analysis accuracy. Furthermore, the analysis unit can also adjust the accuracy of the analysis by taking into account the entire shooting environment of the video. For example, the analysis unit analyzes the entire shooting environment to achieve optimal analysis accuracy. In this way, the analysis accuracy can be improved by taking the shooting environment into account.

[0038] The analysis unit can improve the accuracy of the analysis by adjusting the playback speed of the video. The analysis unit can improve the accuracy of the analysis by, for example, slowing down the playback speed of the video. The playback speed can include, but is not limited to, slow motion and double-speed playback. For example, the analysis unit can perform a detailed analysis using slow-motion playback. The analysis unit can also improve the efficiency of the analysis by increasing the playback speed of the video. For example, the analysis unit can perform a quick analysis by using double-speed playback. Furthermore, the analysis unit can adjust the playback speed of the video to achieve optimal analysis accuracy. For example, the analysis unit can adjust the playback speed to achieve optimal analysis accuracy. In this way, adjusting the playback speed can improve the accuracy of the analysis.

[0039] The analysis unit can use the results of speech recognition within the video in the analysis to complement the identification of materials and procedures. The analysis unit, for example, analyzes the results of speech recognition within the video to complement the identification of materials. The speech recognition results include, but are not limited to, for example, speech-to-text conversion and keyword extraction. For example, the analysis unit can analyze the speech recognition results using speech-to-text conversion technology to complement the identification of materials. The analysis unit can also analyze the speech recognition results using keyword extraction technology to complement the identification of procedures. For example, the analysis unit can analyze keywords extracted from the speech recognition results to complement the identification of procedures. Furthermore, the analysis unit can analyze the results of speech recognition within the video to complement the identification of materials and procedures. For example, the analysis unit can analyze the results of speech recognition to complement the identification of materials and procedures. In this way, the identification of materials and procedures can be complemented by using the results of speech recognition in the analysis.

[0040] The extraction unit can optimize the list by taking into account the relevance of materials and procedures. The extraction unit optimizes the list by taking into account, for example, the relevance between materials and procedures. Techniques such as co-occurrence analysis and correlation analysis are used to evaluate the relevance, but are not limited to these examples. For example, the extraction unit analyzes the co-occurrence relationship between materials and procedures to optimize the list. The extraction unit can also optimize the list by taking into account the relevance of materials. For example, the extraction unit analyzes the correlation between materials to optimize the list. Furthermore, the extraction unit can also optimize the list by taking into account the relevance of procedures. For example, the extraction unit analyzes the co-occurrence relationship between procedures to optimize the list. In this way, it is possible to realize list optimization by taking into account the relevance of materials and procedures.

[0041] The extraction unit can improve the accuracy of extraction by referring to past analysis results. The extraction unit, for example, refers to past analysis results to improve the accuracy of extraction. Techniques such as database reference and history analysis are used to utilize past analysis results, but are not limited to these examples. For example, the extraction unit references past analysis results from a database to improve the accuracy of extraction. The extraction unit can also improve the accuracy of material extraction based on past analysis results. For example, the extraction unit performs historical analysis of past analysis results to improve the accuracy of material extraction. Furthermore, the extraction unit can also improve the accuracy of procedure extraction based on past analysis results. For example, the extraction unit performs historical analysis of past analysis results to improve the accuracy of procedure extraction. In this way, the accuracy of extraction can be improved by referring to past analysis results.

[0042] The extraction unit can adjust the list by taking into account the quantity and frequency of materials and procedures. The extraction unit adjusts the list by taking into account, for example, the quantity and frequency of materials. Techniques such as the number of appearances and the amount of use are used to evaluate the quantity and frequency, but are not limited to such examples. For example, the extraction unit analyzes the number of appearances of materials and adjusts the list. The extraction unit can also adjust the list by taking into account the quantity and frequency of procedures. For example, the extraction unit analyzes the amount of use of procedures and adjusts the list. Furthermore, the extraction unit can adjust the list by taking into account the quantity and frequency of materials and procedures. For example, the extraction unit analyzes the number of appearances of materials and procedures and adjusts the list. In this way, it is possible to adjust the list by taking into account the quantity and frequency of materials and procedures.

[0043] The extraction unit can change the extraction algorithm depending on the genre or theme of the video. The extraction unit changes the extraction algorithm depending on, for example, the genre of the video. Genre classifications include, but are not limited to, cooking genres and theme-based classifications. For example, the extraction unit changes the extraction algorithm depending on the cooking genre. The extraction unit can also change the extraction algorithm depending on the theme of the video. For example, the extraction unit changes the extraction algorithm based on the theme-based classification. Furthermore, the extraction unit can change the extraction algorithm depending on the genre and theme of the video. For example, the extraction unit changes the extraction algorithm taking both the genre and theme into consideration. In this way, by changing the extraction algorithm depending on the genre and theme of the video, more appropriate information can be provided.

[0044] The extraction unit can adjust the level of extraction detail based on the length and content of the video. The extraction unit adjusts the level of extraction detail based on, for example, the length of the video. The evaluation of the length includes, for example, but is not limited to, the playback time of the video. For example, the extraction unit adjusts the level of extraction detail based on the playback time. The extraction unit can also adjust the level of extraction detail based on the content of the video. The evaluation of the content includes, for example, the level of detail and the amount of information in the video, for example, but is not limited to, the level of extraction detail. For example, the extraction unit adjusts the level of extraction detail based on the length and content of the video. For example, the extraction unit adjusts the level of extraction detail taking into account the playback time and the level of detail of the content. In this way, by adjusting the level of extraction detail based on the length and content of the video, more appropriate information can be provided.

[0045] The extraction unit can focus on analyzing specific scenes in a video to extract materials and procedures. For example, the extraction unit can focus on analyzing specific scenes in a video to extract materials. Identifying specific scenes includes, but is not limited to, using a scene detection algorithm or a definition of a key scene. For example, the extraction unit can analyze specific scenes using a scene detection algorithm to extract materials. The extraction unit can also focus on analyzing specific scenes in a video to extract procedures. For example, the extraction unit can analyze specific scenes based on the definition of a key scene to extract procedures. Furthermore, the extraction unit can focus on analyzing specific scenes in a video to extract materials and procedures. For example, the extraction unit can combine a scene detection algorithm and a definition of a key scene to analyze specific scenes and extract materials and procedures. In this way, by focusing on analyzing specific scenes, more detailed materials and procedures can be extracted.

[0046] The text generation unit can adjust the level of detail of the text based on the importance of the material and the procedure. The text generation unit adjusts the level of detail of the text based on, for example, the importance of the material. Evaluation of the importance includes, for example, comprehensiveness of information and detailed description, but is not limited to these examples. For example, the text generation unit adjusts the level of detail of the text based on the comprehensiveness of the information of the material. The text generation unit can also adjust the level of detail of the text based on the importance of the procedure. For example, the text generation unit adjusts the level of detail of the text based on the detailed description of the procedure. Furthermore, the text generation unit can adjust the level of detail of the text based on the importance of the material and the procedure. For example, the text generation unit adjusts the level of detail of the text taking into account the comprehensiveness and detailed description of the information of the material and the procedure. In this way, by adjusting the level of detail of the text based on the importance of the material and the procedure, more appropriate information can be provided.

[0047] The text conversion unit may add a translation function to support different languages. The text conversion unit, for example, automatically translates the text information and provides it in different languages. Examples of the translation function include, but are not limited to, machine translation and supported language types. For example, the text conversion unit may automatically translate the text information using machine translation technology and provide it in different languages. The text conversion unit may also translate text based on a language selected by a user. For example, the text conversion unit may translate and provide text based on a language selected by a user. Furthermore, the text conversion unit may support multiple languages ​​and provide text in multiple languages. For example, the text conversion unit may support multiple languages ​​and provide text in multiple languages. This allows information to be provided to a larger number of users by supporting different languages.

[0048] The text conversion unit can improve the accuracy of the text by reflecting the user's past feedback. The text conversion unit improves the accuracy of the text, for example, based on the user's past feedback. Use of past feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the text conversion unit analyzes the user's past feedback and improves the accuracy of the text. Furthermore, the text conversion unit can reflect the user's feedback and improve the content of the text. For example, the text conversion unit reflects the user's feedback and improves the content of the text. Furthermore, the text conversion unit can analyze the past feedback and improve the accuracy of the text. For example, the text conversion unit analyzes the past feedback and improves the accuracy of the text. In this way, the accuracy of the text can be improved by reflecting the past feedback.

[0049] The text conversion unit can customize the content of the text by referring to the video viewing history. The text conversion unit customizes the content of the text based on, for example, the content of videos that the user has viewed in the past. Use of the viewing history includes, for example, but is not limited to, the videos viewed in the past and the viewing time. For example, the text conversion unit can refer to the user's viewing history to provide text that reflects the user's preferred materials and procedures. The text conversion unit can also analyze the user's viewing history and suggest optimal text content. For example, the text conversion unit can analyze the viewing history and suggest optimal text content. In this way, optimal text content can be provided to the user by referring to the viewing history.

[0050] The text conversion unit can enable output in different formats. For example, the text conversion unit outputs the textual information in a PDF format. The different formats include, but are not limited to, PDF, HTML, and text files. For example, the text conversion unit outputs the textual information in a PDF format. The text conversion unit can also output the textual information in an HTML format. For example, the text conversion unit outputs the textual information in an HTML format. Furthermore, the text conversion unit can output text in different formats according to a user's selection. For example, the text conversion unit outputs text in a PDF format or an HTML format according to a user's selection. This enables output in different formats, thereby improving user convenience.

[0051] The text conversion unit may adjust the use of technical terms in the text according to the user's level of expertise. For example, if the user is a beginner, the text conversion unit may provide the text in simple language. The evaluation of the level of expertise may include, but is not limited to, the definition and frequency of use of technical terms. For example, the text conversion unit may adjust the content of the text based on the definition of technical terms. Furthermore, if the user is an intermediate learner, the text conversion unit may provide the text using appropriate technical terms. For example, the text conversion unit may adjust the content of the text based on the frequency of use of technical terms. Furthermore, if the user is an advanced learner, the text conversion unit may provide the text using detailed technical terms. For example, the text conversion unit may adjust the content of the text taking into account the definition and frequency of use of technical terms. In this way, more appropriate information may be provided by adjusting the content of the text according to the user's level of expertise.

[0052] The providing unit can provide optimal information by referring to the user's past usage history. The providing unit provides optimal information based on, for example, the user's past usage history. Use of past usage history includes, for example, past search history and usage frequency, but is not limited to these examples. For example, the providing unit refers to the user's past usage history and provides preferred information preferentially. The providing unit can also analyze the user's usage history and suggest optimal information. For example, the providing unit analyzes the usage history and suggests optimal information. In this way, optimal information can be provided to the user by referring to the past usage history.

[0053] The providing unit can provide information in an optimal format taking into account device information of the user. For example, if the user is using a smartphone, the providing unit provides information in a format that matches the screen size. Device information includes, but is not limited to, the type of device, screen size, and OS. For example, the providing unit provides information in a format that matches the screen size of the smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide information in a format optimized for a large screen. For example, the providing unit provides information in a format optimized for the tablet screen size. Furthermore, if the user is using a personal computer, the providing unit can also provide information in a format suitable for a desktop. For example, the providing unit provides information in a format suitable for a desktop. In this way, information can be provided in an optimal format for the user by taking into account device information.

[0054] The providing unit can improve the providing method by reflecting user feedback. The providing unit improves the providing method based on, for example, user feedback. Use of feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the providing unit analyzes user feedback and improves the providing method. The providing unit can also reflect past user feedback and propose an optimal providing method. For example, the providing unit analyzes past feedback and propose an optimal providing method. Furthermore, the providing unit can reflect user feedback and improve the quality of the information to be provided. For example, the providing unit reflects feedback and improves the quality of the information to be provided. In this way, by reflecting feedback, the providing method can be improved and more appropriate information can be provided.

[0055] The providing unit can provide highly relevant information by taking into account the geographical location information of the user. The providing unit provides highly relevant information, for example, based on the user's current location. Geographical location information includes, but is not limited to, GPS data and location information services. For example, the providing unit identifies the user's current location using GPS data and provides highly relevant information. The providing unit can also obtain the user's location information using a location information service and provide optimal information. For example, the providing unit obtains the user's location information using a location information service and provides relevant information preferentially. This makes it possible to provide highly relevant information to the user by taking into account the geographical location information.

[0056] The providing unit can analyze the user's social media activity and provide related information. The providing unit, for example, analyzes the user's social media activity and provides related information. Social media activity includes, for example, but is not limited to, the content of posts, the number of likes, the number of followers, etc. For example, the providing unit analyzes the content of posts by the user and provides related information. The providing unit can also provide related information by referring to the activities of the user's friends. For example, the providing unit analyzes the activities of the user's friends and provides related information. In this way, it is possible to provide information related to the user by analyzing social media activity.

[0057] The providing unit can customize the provision method by reflecting the user's past feedback. The providing unit customizes the provision method based on, for example, the user's past feedback. Use of past feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the providing unit analyzes the user's past feedback and customizes the provision method. The providing unit can also reflect the user's feedback and propose an optimal provision method. For example, the providing unit analyzes the past feedback and proposes an optimal provision method. Furthermore, the providing unit can reflect the user's past feedback and improve the provision method. For example, the providing unit reflects the feedback and improves the provision method. In this way, the provision method can be customized by reflecting the past feedback, and more appropriate information can be provided.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] In addition to analyzing cooking videos, the analysis unit can also refer to the user's past cooking history to customize the analysis results. For example, the analysis unit can provide analysis results tailored to the user's preferences and skill level based on the cooking videos the user has watched and the history of dishes the user has created. The analysis unit can also analyze the user's past cooking history to suggest similar dishes or new recipes. Furthermore, the analysis unit can refer to the user's past cooking history to provide detailed information about specific ingredients and cooking methods. This makes it possible to provide more personalized analysis results by utilizing the user's past cooking history.

[0060] In addition to analyzing cooking videos, the analysis unit can also provide analysis results in real time. For example, the analysis unit can identify ingredients and steps in real time while the video is playing and display them to the user. The analysis unit can also support the user as they cook while watching the video based on the real-time analysis results. Furthermore, the analysis unit can also provide immediate answers to questions the user has based on the real-time analysis results. This can improve user convenience by providing analysis results in real time.

[0061] The text generation unit can also customize recipes according to the user's preferences based on the analysis results of the cooking video. For example, if a user prefers a particular ingredient, the text generation unit can preferentially provide recipes using that ingredient. Also, if a user prefers a particular cooking method, the text generation unit can provide recipes using that cooking method. Furthermore, if a user prefers a particular cooking genre, the text generation unit can provide recipes related to that genre. In this way, by customizing recipes according to the user's preferences, it is possible to provide information that is more satisfying.

[0062] In addition to analyzing cooking videos, the analysis unit can also provide analysis results that take into account the user's health condition. For example, if the user has a specific allergy, the analysis unit can exclude ingredients that are related to that allergy. Also, if the user needs a specific nutrient, the analysis unit can preferentially provide ingredients that contain that nutrient. Furthermore, the analysis unit can suggest cooking methods that take the user's health condition into account. In this way, healthier cooking can be achieved by providing analysis results that take the user's health condition into account.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The analysis unit analyzes the cooking video. Cooking videos include home cooking, professional cooking, and specific cooking genres. The analysis unit uses technologies such as image analysis, audio analysis, and text analysis to identify the necessary ingredients and cooking steps from the audio and video in the video. For example, it can use voice recognition technology to analyze the audio in the video and identify the ingredients and cooking utensils used. It can also use image recognition technology to analyze the video in the video and identify the cooking steps. It can also use text analysis technology to analyze the subtitle information in the video to complement the identification of ingredients and steps. Step 2: The extraction unit extracts the materials and procedures identified by the analysis unit. This extraction is done using techniques such as keyword extraction and pattern recognition. For example, the materials and procedures identified by the analysis unit are organized in a list format. List formats include bulleted lists and numbered lists. Step 3: The text converter converts the information extracted by the extractor into text using techniques such as natural language generation and format conversion. For example, the extracted materials and procedures are organized in a list format and provided to viewers and creators.

[0065] (Example 2) A system according to an embodiment of the present invention analyzes cooking videos, extracts necessary ingredients and cooking steps, and converts them into text. This system provides value to both viewers and creators by analyzing cooking videos, extracting necessary ingredients and cooking steps, and converting them into text. For example, the system analyzes cooking videos and identifies necessary ingredients and cooking steps from the audio and video in the videos. Next, it organizes the identified ingredients and steps in a list format and converts them into text. This allows viewers to easily provide high-quality videos and creators to supplement information missing from cooking videos. This allows viewers to check necessary ingredients and cooking steps while watching cooking videos, making it easier to recreate dishes. Creators can also provide more information to viewers by converting into text parts of cooking videos that are insufficiently explained or points that viewers tend to overlook.

[0066] A cooking video analysis system according to an embodiment includes an analysis unit, an extraction unit, and a text generation unit. The analysis unit analyzes cooking videos. Examples of cooking videos include, but are not limited to, home cooking, professional cooking, and specific cooking genres. The analysis unit identifies necessary ingredients and cooking steps from audio and video within the video using techniques such as image analysis, audio analysis, and text analysis. For example, the analysis unit may analyze audio within the video using speech recognition technology to identify ingredients and cooking utensils used. The analysis unit may also analyze video within the video using image recognition technology to identify cooking steps. Furthermore, the analysis unit may use text analysis technology to analyze subtitle information within the video to complement the identification of ingredients and steps. The extraction unit extracts the ingredients and steps identified by the analysis unit. The extraction is performed using techniques such as keyword extraction and pattern recognition. For example, the extraction unit organizes the ingredients and steps identified by the analysis unit in a list format. Examples of list formats include, but are not limited to, bulleted lists and numbered lists. The text conversion unit converts the information extracted by the extraction unit into text. The text conversion is performed using, for example, techniques such as natural language generation and format conversion. For example, the text conversion unit organizes the extracted ingredients and steps in a list format and provides it to viewers and creators. This allows the cooking video analysis system according to the embodiment to provide value to both viewers and creators.

[0067] Furthermore, the cooking video analysis system includes a providing unit that provides the information extracted by the extraction unit to viewers and creators. The providing unit provides the information extracted by the extraction unit to viewers and creators. The information is provided, for example, via a website, an app, email, or other methods. For example, the providing unit provides the extracted information to viewers via a website. The providing unit can also provide the extracted information to creators via a dedicated app. Furthermore, the providing unit can send the extracted information to viewers and creators via email. In this way, by providing the extracted information to viewers and creators, value can be provided to both.

[0068] The analysis unit can identify the necessary ingredients and cooking steps from the audio or video in the video. The analysis unit, for example, uses voice recognition technology to analyze the audio in the video and identify the ingredients and cooking utensils used. For example, the analysis unit uses voice filtering technology to remove background sounds and improve the accuracy of voice recognition. The analysis unit can also analyze the video in the video and identify the cooking steps using image recognition technology. For example, the analysis unit can use video analysis technology to identify how to use cooking utensils. The analysis unit can also use text analysis technology to analyze subtitle information in the video and supplement the identification of ingredients and steps. For example, the analysis unit analyzes subtitle information to supplement the identification of ingredients. In this way, the necessary ingredients and cooking steps can be accurately identified by analyzing the audio and video in the video.

[0069] The extraction unit can organize the identified materials and steps in a list format. For example, the extraction unit organizes the materials and steps identified by the analysis unit in a list format. Examples of list formats include, but are not limited to, bulleted lists and numbered lists. For example, the extraction unit organizes the identified materials in bulleted lists. The extraction unit can also organize the identified steps in a numbered list. Furthermore, the extraction unit can combine the materials and steps and organize them in a list format. For example, the extraction unit combines the materials and steps and organizes them in a format that is easy for viewers to understand. By organizing the identified materials and steps in a list format, it is possible to provide them to viewers and creators in an easy-to-understand manner.

[0070] The text conversion unit can convert information organized in a list format into text. For example, the text conversion unit organizes the materials and procedures extracted by the extraction unit into a list format and converts the information into text. The text conversion is performed using techniques such as natural language generation and format conversion. For example, the text conversion unit organizes the extracted materials and procedures in a list format and provides them to viewers and creators. The text conversion unit can also output the textual information in different formats. For example, the text conversion unit outputs the textual information in PDF format or HTML format. In this way, by converting the information organized in a list format into text, it is possible to provide viewers and creators with information that is easy to understand.

[0071] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice tone analysis. For example, if the user is excited, the analysis unit can increase the accuracy of the analysis to identify detailed materials and procedures. Alternatively, if the user is relaxed, the analysis unit can maintain the accuracy of the analysis at normal levels and identify standard materials and procedures. Furthermore, if the user is stressed, the analysis unit can adjust the accuracy of the analysis to identify concise and easy-to-understand materials and procedures. This allows for more appropriate analysis results by adjusting the accuracy of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0072] The analysis unit can remove background sounds and noise from the video to improve the accuracy of the analysis. For example, the analysis unit can filter background sounds in the video to improve the accuracy of speech recognition. Examples of background sounds include, but are not limited to, environmental sounds and unnecessary sounds. For example, the analysis unit can remove background sounds from the video using noise filtering technology. The analysis unit can also remove noise from the video to improve the accuracy of video analysis. Examples of noise include, but are not limited to, white noise and environmental sounds. For example, the analysis unit can remove unnecessary sounds from the video using noise removal technology to accurately identify necessary materials and steps. In this way, the accuracy of the analysis can be improved by removing background sounds and noise.

[0073] The analysis unit can analyze each frame of the video and identify changes in material and procedures in detail. The analysis unit, for example, analyzes each frame of the video and identifies changes in material. The frame-by-frame analysis includes, but is not limited to, frame rate and analysis algorithm. For example, the analysis unit uses an algorithm for identifying changes in material for each frame. The analysis unit can also analyze each frame of the video and identify changes in procedures. For example, the analysis unit uses an algorithm for identifying changes in procedures for each frame. Furthermore, the analysis unit can analyze each frame of the video and identify detailed changes in material and procedures. For example, the analysis unit uses an algorithm for identifying changes in material and procedures for each frame. In this way, by performing the analysis for each frame, it is possible to identify changes in material and procedures in detail.

[0074] The analysis unit can use subtitle information in the video for analysis to complement the identification of materials and procedures. The analysis unit, for example, analyzes subtitle information in the video to complement the identification of materials. Subtitle information includes, for example, text analysis and timestamp analysis, but is not limited to these examples. For example, the analysis unit can analyze subtitle information using text analysis technology to complement the identification of materials. The analysis unit can also analyze subtitle information using timestamp analysis technology to complement the identification of procedures. For example, the analysis unit can analyze timestamps in the subtitle information to complement the identification of procedures. Furthermore, the analysis unit can analyze subtitle information in the video to complement the identification of materials and procedures. For example, the analysis unit can analyze subtitle information to complement the identification of materials and procedures. In this way, the identification of materials and procedures can be complemented by using subtitle information in the analysis.

[0075] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis results based on the estimated user emotion. The user's emotion is estimated using technologies such as facial expression recognition and voice tone analysis. For example, the analysis unit displays detailed analysis results when the user is excited. The analysis unit can also display standard analysis results when the user is relaxed. Furthermore, the analysis unit can display concise and easy-to-understand analysis results when the user is stressed. This allows for more appropriate information to be provided by adjusting the display method of the analysis results according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0076] The analysis unit can adjust the accuracy of the analysis based on the shooting environment of the video. The analysis unit, for example, takes into account the lighting conditions of the video and adjusts the accuracy of the analysis. Lighting conditions include, but are not limited to, brightness and light direction. For example, the analysis unit analyzes the lighting conditions to achieve optimal analysis accuracy. The analysis unit can also adjust the accuracy of the analysis by taking into account the camera angle of the video. Camera angles include, but are not limited to, shooting angles and zoom levels. For example, the analysis unit analyzes the camera angle to achieve optimal analysis accuracy. Furthermore, the analysis unit can also adjust the accuracy of the analysis by taking into account the entire shooting environment of the video. For example, the analysis unit analyzes the entire shooting environment to achieve optimal analysis accuracy. In this way, the analysis accuracy can be improved by taking the shooting environment into account.

[0077] The analysis unit can improve the accuracy of the analysis by adjusting the playback speed of the video. The analysis unit can improve the accuracy of the analysis by, for example, slowing down the playback speed of the video. The playback speed can include, but is not limited to, slow motion and double-speed playback. For example, the analysis unit can perform a detailed analysis using slow-motion playback. The analysis unit can also improve the efficiency of the analysis by increasing the playback speed of the video. For example, the analysis unit can perform a quick analysis by using double-speed playback. Furthermore, the analysis unit can adjust the playback speed of the video to achieve optimal analysis accuracy. For example, the analysis unit can adjust the playback speed to achieve optimal analysis accuracy. In this way, adjusting the playback speed can improve the accuracy of the analysis.

[0078] The analysis unit can use the results of speech recognition within the video in the analysis to complement the identification of materials and procedures. The analysis unit, for example, analyzes the results of speech recognition within the video to complement the identification of materials. The speech recognition results include, but are not limited to, for example, speech-to-text conversion and keyword extraction. For example, the analysis unit can analyze the speech recognition results using speech-to-text conversion technology to complement the identification of materials. The analysis unit can also analyze the speech recognition results using keyword extraction technology to complement the identification of procedures. For example, the analysis unit can analyze keywords extracted from the speech recognition results to complement the identification of procedures. Furthermore, the analysis unit can analyze the results of speech recognition within the video to complement the identification of materials and procedures. For example, the analysis unit can analyze the results of speech recognition to complement the identification of materials and procedures. In this way, the identification of materials and procedures can be complemented by using the results of speech recognition in the analysis.

[0079] The extraction unit can estimate the user's emotions and determine the priority of materials and procedures to be extracted based on the estimated user emotions. The extraction unit, for example, estimates the user's emotions and determines the priority of materials and procedures to be extracted based on the estimated user emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice tone analysis. For example, the extraction unit can prioritize detailed materials and procedures when the user is excited. The extraction unit can also prioritize standard materials and procedures when the user is relaxed. Furthermore, the extraction unit can prioritize concise and easy-to-understand materials and procedures when the user is stressed. This allows for more appropriate information to be provided by prioritizing materials and procedures according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The extraction unit can optimize the list by taking into account the relevance of materials and procedures. The extraction unit optimizes the list by taking into account, for example, the relevance between materials and procedures. Techniques such as co-occurrence analysis and correlation analysis are used to evaluate the relevance, but are not limited to these examples. For example, the extraction unit analyzes the co-occurrence relationship between materials and procedures to optimize the list. The extraction unit can also optimize the list by taking into account the relevance of materials. For example, the extraction unit analyzes the correlation between materials to optimize the list. Furthermore, the extraction unit can also optimize the list by taking into account the relevance of procedures. For example, the extraction unit analyzes the co-occurrence relationship between procedures to optimize the list. In this way, it is possible to realize list optimization by taking into account the relevance of materials and procedures.

[0081] The extraction unit can improve the accuracy of extraction by referring to past analysis results. The extraction unit, for example, refers to past analysis results to improve the accuracy of extraction. Techniques such as database reference and history analysis are used to utilize past analysis results, but are not limited to these examples. For example, the extraction unit references past analysis results from a database to improve the accuracy of extraction. The extraction unit can also improve the accuracy of material extraction based on past analysis results. For example, the extraction unit performs historical analysis of past analysis results to improve the accuracy of material extraction. Furthermore, the extraction unit can also improve the accuracy of procedure extraction based on past analysis results. For example, the extraction unit performs historical analysis of past analysis results to improve the accuracy of procedure extraction. In this way, the accuracy of extraction can be improved by referring to past analysis results.

[0082] The extraction unit can adjust the list by taking into account the quantity and frequency of materials and procedures. The extraction unit adjusts the list by taking into account, for example, the quantity and frequency of materials. Techniques such as the number of appearances and the amount of use are used to evaluate the quantity and frequency, but are not limited to such examples. For example, the extraction unit analyzes the number of appearances of materials and adjusts the list. The extraction unit can also adjust the list by taking into account the quantity and frequency of procedures. For example, the extraction unit analyzes the amount of use of procedures and adjusts the list. Furthermore, the extraction unit can adjust the list by taking into account the quantity and frequency of materials and procedures. For example, the extraction unit analyzes the number of appearances of materials and procedures and adjusts the list. In this way, it is possible to adjust the list by taking into account the quantity and frequency of materials and procedures.

[0083] The extraction unit can estimate the user's emotion and adjust the display method of the extraction result based on the estimated user emotion. The extraction unit, for example, estimates the user's emotion and adjusts the display method of the extraction result based on the estimated user emotion. The user's emotion is estimated using technologies such as facial expression recognition and voice tone analysis. For example, the extraction unit displays detailed extraction results when the user is excited. The extraction unit can also display standard extraction results when the user is relaxed. Furthermore, the extraction unit can display concise and easy-to-understand extraction results when the user is stressed. This allows for more appropriate information to be provided by adjusting the display method of the extraction result according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0084] The extraction unit can change the extraction algorithm depending on the genre or theme of the video. The extraction unit changes the extraction algorithm depending on, for example, the genre of the video. Genre classifications include, but are not limited to, cooking genres and theme-based classifications. For example, the extraction unit changes the extraction algorithm depending on the cooking genre. The extraction unit can also change the extraction algorithm depending on the theme of the video. For example, the extraction unit changes the extraction algorithm based on the theme-based classification. Furthermore, the extraction unit can change the extraction algorithm depending on the genre and theme of the video. For example, the extraction unit changes the extraction algorithm taking both the genre and theme into consideration. In this way, by changing the extraction algorithm depending on the genre and theme of the video, more appropriate information can be provided.

[0085] The extraction unit can adjust the level of extraction detail based on the length and content of the video. The extraction unit adjusts the level of extraction detail based on, for example, the length of the video. The evaluation of the length includes, for example, but is not limited to, the playback time of the video. For example, the extraction unit adjusts the level of extraction detail based on the playback time. The extraction unit can also adjust the level of extraction detail based on the content of the video. The evaluation of the content includes, for example, the level of detail and the amount of information in the video, for example, but is not limited to, the level of extraction detail. For example, the extraction unit adjusts the level of extraction detail based on the length and content of the video. For example, the extraction unit adjusts the level of extraction detail taking into account the playback time and the level of detail of the content. In this way, by adjusting the level of extraction detail based on the length and content of the video, more appropriate information can be provided.

[0086] The extraction unit can focus on analyzing specific scenes in a video to extract materials and procedures. For example, the extraction unit can focus on analyzing specific scenes in a video to extract materials. Identifying specific scenes includes, but is not limited to, using a scene detection algorithm or a definition of a key scene. For example, the extraction unit can analyze specific scenes using a scene detection algorithm to extract materials. The extraction unit can also focus on analyzing specific scenes in a video to extract procedures. For example, the extraction unit can analyze specific scenes based on the definition of a key scene to extract procedures. Furthermore, the extraction unit can focus on analyzing specific scenes in a video to extract materials and procedures. For example, the extraction unit can combine a scene detection algorithm and a definition of a key scene to analyze specific scenes and extract materials and procedures. In this way, by focusing on analyzing specific scenes, more detailed materials and procedures can be extracted.

[0087] The text conversion unit can estimate the user's emotion and adjust the text expression method based on the estimated user's emotion. The text conversion unit, for example, estimates the user's emotion and adjusts the text expression method based on the estimated user's emotion. The user's emotion is estimated using technologies such as facial expression recognition and voice tone analysis. For example, the text conversion unit can provide detailed text when the user is excited. The text conversion unit can also provide standard text when the user is relaxed. Furthermore, the text conversion unit can provide concise and easy-to-understand text when the user is stressed. This allows for more appropriate information to be provided by adjusting the text expression method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0088] The text generation unit can adjust the level of detail of the text based on the importance of the material and the procedure. The text generation unit adjusts the level of detail of the text based on, for example, the importance of the material. Evaluation of the importance includes, for example, comprehensiveness of information and detailed description, but is not limited to these examples. For example, the text generation unit adjusts the level of detail of the text based on the comprehensiveness of the information of the material. The text generation unit can also adjust the level of detail of the text based on the importance of the procedure. For example, the text generation unit adjusts the level of detail of the text based on the detailed description of the procedure. Furthermore, the text generation unit can adjust the level of detail of the text based on the importance of the material and the procedure. For example, the text generation unit adjusts the level of detail of the text taking into account the comprehensiveness and detailed description of the information of the material and the procedure. In this way, by adjusting the level of detail of the text based on the importance of the material and the procedure, more appropriate information can be provided.

[0089] The text conversion unit may add a translation function to support different languages. The text conversion unit, for example, automatically translates the text information and provides it in different languages. Examples of the translation function include, but are not limited to, machine translation and supported language types. For example, the text conversion unit may automatically translate the text information using machine translation technology and provide it in different languages. The text conversion unit may also translate text based on a language selected by a user. For example, the text conversion unit may translate and provide text based on a language selected by a user. Furthermore, the text conversion unit may support multiple languages ​​and provide text in multiple languages. For example, the text conversion unit may support multiple languages ​​and provide text in multiple languages. This allows information to be provided to a larger number of users by supporting different languages.

[0090] The text conversion unit can improve the accuracy of the text by reflecting the user's past feedback. The text conversion unit improves the accuracy of the text, for example, based on the user's past feedback. Use of past feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the text conversion unit analyzes the user's past feedback and improves the accuracy of the text. Furthermore, the text conversion unit can reflect the user's feedback and improve the content of the text. For example, the text conversion unit reflects the user's feedback and improves the content of the text. Furthermore, the text conversion unit can analyze the past feedback and improve the accuracy of the text. For example, the text conversion unit analyzes the past feedback and improves the accuracy of the text. In this way, the accuracy of the text can be improved by reflecting the past feedback.

[0091] The text conversion unit can estimate the user's emotion and adjust the length of the text based on the estimated user's emotion. The text conversion unit, for example, estimates the user's emotion and adjusts the length of the text based on the estimated user's emotion. The user's emotion is estimated using techniques such as facial expression recognition and voice tone analysis. For example, the text conversion unit can provide detailed text when the user is excited. The text conversion unit can also provide standard text when the user is relaxed. Furthermore, the text conversion unit can provide concise and easy-to-understand text when the user is stressed. This allows for more appropriate information to be provided by adjusting the length of the text according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] The text conversion unit can customize the content of the text by referring to the video viewing history. The text conversion unit customizes the content of the text based on, for example, the content of videos that the user has viewed in the past. Use of the viewing history includes, for example, but is not limited to, the videos viewed in the past and the viewing time. For example, the text conversion unit can refer to the user's viewing history to provide text that reflects the user's preferred materials and procedures. The text conversion unit can also analyze the user's viewing history and suggest optimal text content. For example, the text conversion unit can analyze the viewing history and suggest optimal text content. In this way, optimal text content can be provided to the user by referring to the viewing history.

[0093] The text conversion unit can enable output in different formats. For example, the text conversion unit outputs the textual information in a PDF format. The different formats include, but are not limited to, PDF, HTML, and text files. For example, the text conversion unit outputs the textual information in a PDF format. The text conversion unit can also output the textual information in an HTML format. For example, the text conversion unit outputs the textual information in an HTML format. Furthermore, the text conversion unit can output text in different formats according to a user's selection. For example, the text conversion unit outputs text in a PDF format or an HTML format according to a user's selection. This enables output in different formats, thereby improving user convenience.

[0094] The text conversion unit may adjust the use of technical terms in the text according to the user's level of expertise. For example, if the user is a beginner, the text conversion unit may provide the text in simple language. The evaluation of the level of expertise may include, but is not limited to, the definition and frequency of use of technical terms. For example, the text conversion unit may adjust the content of the text based on the definition of technical terms. Furthermore, if the user is an intermediate learner, the text conversion unit may provide the text using appropriate technical terms. For example, the text conversion unit may adjust the content of the text based on the frequency of use of technical terms. Furthermore, if the user is an advanced learner, the text conversion unit may provide the text using detailed technical terms. For example, the text conversion unit may adjust the content of the text taking into account the definition and frequency of use of technical terms. In this way, more appropriate information may be provided by adjusting the content of the text according to the user's level of expertise.

[0095] The providing unit can estimate the user's emotions and determine the priority of information to be provided based on the estimated user emotions. The providing unit, for example, estimates the user's emotions and determines the priority of information to be provided based on the estimated user emotions. The user's emotions are estimated using technologies such as facial expression recognition and voice tone analysis. For example, the providing unit can prioritize providing detailed information when the user is excited. The providing unit can also prioritize providing standard information when the user is relaxed. Furthermore, the providing unit can prioritize providing concise and easy-to-understand information when the user is stressed. This allows more appropriate information to be provided by determining the priority of information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] The providing unit can provide optimal information by referring to the user's past usage history. The providing unit provides optimal information based on, for example, the user's past usage history. Use of past usage history includes, for example, past search history and usage frequency, but is not limited to these examples. For example, the providing unit refers to the user's past usage history and provides preferred information preferentially. The providing unit can also analyze the user's usage history and suggest optimal information. For example, the providing unit analyzes the usage history and suggests optimal information. In this way, optimal information can be provided to the user by referring to the past usage history.

[0097] The providing unit can provide information in an optimal format taking into account device information of the user. For example, if the user is using a smartphone, the providing unit provides information in a format that matches the screen size. Device information includes, but is not limited to, the type of device, screen size, and OS. For example, the providing unit provides information in a format that matches the screen size of the smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide information in a format optimized for a large screen. For example, the providing unit provides information in a format optimized for the tablet screen size. Furthermore, if the user is using a personal computer, the providing unit can also provide information in a format suitable for a desktop. For example, the providing unit provides information in a format suitable for a desktop. In this way, information can be provided in an optimal format for the user by taking into account device information.

[0098] The providing unit can improve the providing method by reflecting user feedback. The providing unit improves the providing method based on, for example, user feedback. Use of feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the providing unit analyzes user feedback and improves the providing method. The providing unit can also reflect past user feedback and propose an optimal providing method. For example, the providing unit analyzes past feedback and propose an optimal providing method. Furthermore, the providing unit can reflect user feedback and improve the quality of the information to be provided. For example, the providing unit reflects feedback and improves the quality of the information to be provided. In this way, by reflecting feedback, the providing method can be improved and more appropriate information can be provided.

[0099] The providing unit can estimate the user's emotion and adjust the display method of the information to be provided based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the display method of the information to be provided based on the estimated user's emotion. The user's emotion is estimated using, for example, techniques such as facial expression recognition or voice tone analysis. For example, the providing unit can provide a detailed display method when the user is excited. The providing unit can also provide a standard display method when the user is relaxed. Furthermore, the providing unit can also provide a simple and easy-to-understand display method when the user is stressed. This allows the information display method to be adjusted according to the user's emotion, thereby providing more appropriate information. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0100] The providing unit can provide highly relevant information by taking into account the geographical location information of the user. The providing unit provides highly relevant information, for example, based on the user's current location. Geographical location information includes, but is not limited to, GPS data and location information services. For example, the providing unit identifies the user's current location using GPS data and provides highly relevant information. The providing unit can also obtain the user's location information using a location information service and provide optimal information. For example, the providing unit obtains the user's location information using a location information service and provides relevant information preferentially. This makes it possible to provide highly relevant information to the user by taking into account the geographical location information.

[0101] The providing unit can analyze the user's social media activity and provide related information. The providing unit, for example, analyzes the user's social media activity and provides related information. Social media activity includes, for example, but is not limited to, the content of posts, the number of likes, the number of followers, etc. For example, the providing unit analyzes the content of posts by the user and provides related information. The providing unit can also provide related information by referring to the activities of the user's friends. For example, the providing unit analyzes the activities of the user's friends and provides related information. In this way, it is possible to provide information related to the user by analyzing social media activity.

[0102] The providing unit can customize the provision method by reflecting the user's past feedback. The providing unit customizes the provision method based on, for example, the user's past feedback. Use of past feedback includes, for example, user reviews and evaluation comments, but is not limited to these examples. For example, the providing unit analyzes the user's past feedback and customizes the provision method. The providing unit can also reflect the user's feedback and propose an optimal provision method. For example, the providing unit analyzes the past feedback and proposes an optimal provision method. Furthermore, the providing unit can reflect the user's past feedback and improve the provision method. For example, the providing unit reflects the feedback and improves the provision method. In this way, the provision method can be customized by reflecting the past feedback, and more appropriate information can be provided. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned analysis unit, extraction unit, text conversion unit, and provision unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit can analyze a cooking video using the camera 42 and microphone 38B of the smart device 14 to identify necessary ingredients and cooking steps. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, organizes the identified ingredients and steps in list format. The text conversion unit, realized, for example, by the control unit 46A of the smart device 14, converts the extracted information into text. The provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides information to viewers and creators via a website or app. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned analysis unit, extraction unit, text conversion unit, and provision unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit can analyze cooking videos using the camera 42 and microphone 238 of the smart glasses 214 to identify necessary ingredients and cooking steps. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, organizes the identified ingredients and steps in list format. The text conversion unit, realized, for example, by the control unit 46A of the smart glasses 214, converts the extracted information into text. The provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides information to viewers and creators via a website or app. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, extraction unit, text conversion unit, and provision unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit can analyze a cooking video using the camera 42 and microphone 238 of the headset-type terminal 314 to identify necessary ingredients and cooking steps. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and organizes the identified ingredients and steps in list format. The text conversion unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and converts the extracted information into text. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides information to viewers and creators via a website or app. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, extraction unit, text conversion unit, and provision unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the analysis unit can analyze cooking videos using the camera 42 and microphone 238 of the robot 414 to identify necessary ingredients and cooking steps. The extraction unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and organizes the identified ingredients and steps in list form. The text conversion unit is realized, for example, by the control unit 46A of the robot 414 and converts the extracted information into text. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides information to viewers and creators via a website or app.

[0103] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0104] In addition to analyzing cooking videos, the analysis unit can also refer to the user's past cooking history to customize the analysis results. For example, the analysis unit can provide analysis results tailored to the user's preferences and skill level based on the cooking videos the user has watched and the history of dishes the user has created. The analysis unit can also analyze the user's past cooking history to suggest similar dishes or new recipes. Furthermore, the analysis unit can refer to the user's past cooking history to provide detailed information about specific ingredients and cooking methods. This makes it possible to provide more personalized analysis results by utilizing the user's past cooking history.

[0105] The providing unit can also estimate the user's emotions and adjust the format of the information to be provided based on the estimated user's emotions. For example, if the user is excited, the providing unit can provide information in a visually appealing infographic format. If the user is relaxed, the providing unit can provide information in a detailed text format. Furthermore, if the user is stressed, the providing unit can provide information in a concise and easy-to-understand bullet point format. This makes it possible to provide more appropriate information by adjusting the format of information according to the user's emotions.

[0106] In addition to analyzing cooking videos, the analysis unit can also provide analysis results in real time. For example, the analysis unit can identify ingredients and steps in real time while the video is playing and display them to the user. The analysis unit can also support the user as they cook while watching the video based on the real-time analysis results. Furthermore, the analysis unit can also provide immediate answers to questions the user has based on the real-time analysis results. This can improve user convenience by providing analysis results in real time.

[0107] The extraction unit can also estimate the user's emotions and adjust the level of detail of the extracted materials and procedures based on the estimated user's emotions. For example, if the user is excited, the extraction unit can extract detailed materials and procedures. If the user is relaxed, the extraction unit can also extract standard materials and procedures. Furthermore, if the user is feeling stressed, the extraction unit can extract concise and easy-to-understand materials and procedures. This makes it possible to provide more appropriate information by adjusting the level of detail of the materials and procedures according to the user's emotions.

[0108] The text generation unit can also customize recipes according to the user's preferences based on the analysis results of the cooking video. For example, if a user prefers a particular ingredient, the text generation unit can preferentially provide recipes using that ingredient. Also, if a user prefers a particular cooking method, the text generation unit can provide recipes using that cooking method. Furthermore, if a user prefers a particular cooking genre, the text generation unit can provide recipes related to that genre. In this way, by customizing recipes according to the user's preferences, it is possible to provide information that is more satisfying.

[0109] The analysis unit can also estimate the user's emotions and provide feedback of the analysis results based on the estimated user emotions. For example, if the user is excited, the analysis unit can provide positive feedback to increase the user's motivation. If the user is relaxed, the analysis unit can also provide feedback to maintain a relaxed atmosphere. Furthermore, if the user is feeling stressed, the analysis unit can also provide feedback to reduce stress. In this way, by providing feedback according to the user's emotions, a better user experience can be achieved.

[0110] In addition to analyzing cooking videos, the analysis unit can also provide analysis results that take into account the user's health condition. For example, if the user has a specific allergy, the analysis unit can exclude ingredients that are related to that allergy. Also, if the user needs a specific nutrient, the analysis unit can preferentially provide ingredients that contain that nutrient. Furthermore, the analysis unit can suggest cooking methods that take the user's health condition into account. In this way, healthier cooking can be achieved by providing analysis results that take the user's health condition into account.

[0111] The extraction unit can also estimate the user's emotions based on the analysis results of the cooking video and customize the extraction results based on the estimated emotions. For example, if the user is excited, the extraction unit can extract detailed ingredients and steps. If the user is relaxed, the extraction unit can also extract standard ingredients and steps. Furthermore, if the user is stressed, the extraction unit can extract concise and easy-to-understand ingredients and steps. In this way, by customizing the extraction results according to the user's emotions, more appropriate information can be provided.

[0112] The text generation unit can also estimate the user's emotions based on the analysis results of the cooking video and adjust the tone of the text based on the estimated emotions. For example, if the user is excited, the text generation unit can provide text with a positive and energetic tone. If the user is relaxed, the text generation unit can provide text with a calm and relaxed tone. Furthermore, if the user is stressed, the text generation unit can provide text with a reassuring tone. In this way, by adjusting the tone of the text according to the user's emotions, more appropriate information can be provided.

[0113] The providing unit can also estimate the user's emotions based on the analysis results of the cooking video and determine the priority of information to be provided based on the estimated emotions. For example, if the user is excited, the providing unit can prioritize providing detailed information. Also, if the user is relaxed, the providing unit can prioritize providing standard information. Furthermore, if the user is feeling stressed, the providing unit can prioritize providing concise and easy-to-understand information. In this way, by determining the priority of information according to the user's emotions, more appropriate information can be provided.

[0114] The processing flow of the second embodiment will be briefly explained below.

[0115] Step 1: The analysis unit analyzes the cooking video. Cooking videos include home cooking, professional cooking, and specific cooking genres. The analysis unit uses technologies such as image analysis, audio analysis, and text analysis to identify the necessary ingredients and cooking steps from the audio and video in the video. For example, it can use voice recognition technology to analyze the audio in the video and identify the ingredients and cooking utensils used. It can also use image recognition technology to analyze the video in the video and identify the cooking steps. It can also use text analysis technology to analyze the subtitle information in the video to complement the identification of ingredients and steps. Step 2: The extraction unit extracts the materials and procedures identified by the analysis unit. This extraction is done using techniques such as keyword extraction and pattern recognition. For example, the materials and procedures identified by the analysis unit are organized in a list format. List formats include bulleted lists and numbered lists. Step 3: The text converter converts the information extracted by the extractor into text using techniques such as natural language generation and format conversion. For example, the extracted materials and procedures are organized in a list format and provided to viewers and creators.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0120] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0121] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0137] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] [Explanation of symbols]

[0188] 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. An analysis unit that analyzes cooking videos, an extraction unit that extracts necessary ingredients and cooking procedures based on the information analyzed by the analysis unit; a text conversion unit that converts the information extracted by the extraction unit into text; Equipped with A system characterized by:

2. Equipped with a provider that provides content to viewers and creators 2. The system of claim 1.

3. The analysis unit Identify the ingredients and cooking steps needed from the audio or visual information in the video 2. The system of claim 1.

4. The extraction unit Organize the identified materials and procedures in a list format 2. The system of claim 1.

5. The text conversion unit Convert information organized in list format into text 2. The system of claim 1.

6. The analysis unit Estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions.

2. The system of claim 1.

7. The analysis unit Remove background sounds and noise from the video to improve analysis accuracy 2. The system of claim 1.

8. The analysis unit Analyzes each frame of video to identify detailed changes in materials and procedures 2. The system of claim 1.

9. The analysis unit Use subtitle information in the video for analysis to complement the identification of materials and procedures 2. The system of claim 1.

Images