system

Abstract

We provide the system. [Solution] Means of obtaining the source code, A means of analyzing the acquired source code to extract operational functions and error conditions, A natural language generation method that automatically generates user manuals and FAQs based on the generated data, A rich content generation means that automatically generates images and videos of operating procedures, A means of integrating the generated content into a management system and distributing it, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Generally, every time software is released or updated, the creation and update of user manuals and FAQs are required, but the manual work involved is a heavy burden. This work requires labor and time, and in addition, there is a possibility of impairing the user experience due to the delay in providing the latest information. Furthermore, in an environment where changes are frequently made, it is difficult to maintain the accuracy of information, and rapid updates are required. Against this background, there is a demand for a system that can automatically generate and update manuals and FAQs based on source code information.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating user manuals and FAQs by acquiring and analyzing source code to extract operational functions and error conditions. Furthermore, it constructs comprehensive documentation by documenting the generated data using natural language generation means and creating operation videos and images using rich content generation means. This reduces the effort required to create documentation during releases and updates, while always providing users with the latest and most accurate information. It also provides a system that enables efficient operation by automatically detecting changes in source code and updating only the relevant parts of the information as needed.

[0006] "Source code" refers to text written in a programming language to control the operation of software.

[0007] "Means of acquisition" refers to the method or process for retrieving specific data or information from an external repository or database.

[0008] "Means of analysis" refers to methods or techniques for analyzing given data or information to extract useful information or understand specific meanings.

[0009] "Extraction methods" refer to processes or methods used to extract only the necessary parts from a large amount of data.

[0010] "Natural language generation methods" refer to technologies and algorithms that enable computers to automatically generate natural language text that is easy for humans to understand.

[0011] A "rich content generation method" is a method of creating content that conveys information visually and audibly using various media formats such as images, videos, and audio.

[0012] "Methods for integrating and distributing data into a management system" refers to methods for consolidating generated data and content into a single system and then appropriately distributing it to users from there. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system for effectively and efficiently generating and updating manuals and FAQs for software products. This system extracts necessary information from source code, processes and formats it, and provides it to the user.

[0035] First, the server accesses the source code repository to retrieve the latest code. This ensures that the latest features and changes are always reflected. Next, the server uses static analysis tools to analyze the retrieved source code and extract features available to the user and possible error conditions. Based on this analysis information, the server uses a generative AI model to generate natural language text and create manuals and FAQs in a user-friendly format.

[0036] For example, it can automatically generate operating procedures for specific functions, including explanations of potential errors users might encounter. Furthermore, the server utilizes rich content generation technology to create images and videos to complement the instructions. This allows for visual communication, aiding user understanding.

[0037] The generated manuals and FAQs are ultimately distributed to a web portal and documentation site managed by the server. This ensures that users always have access to the latest documentation. Furthermore, users can utilize the provided information to use the product more effectively and submit feedback. The server then uses this feedback to make further improvements and updates.

[0038] As a concrete example, when a new software version is released, the relevant manual sections can be automatically updated based only on the code changes, and the updated content can be visualized and provided in a video with narration. In this way, the traditional manual documentation creation and updating work can be significantly reduced, and users can always access the latest information.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server accesses the source code repository and clones the latest source code from a specific repository or branch. This allows it to obtain the most up-to-date version of the code to be analyzed.

[0042] Step 2:

[0043] The server analyzes the retrieved source code using static analysis tools. In this process, it reads function and class definitions and documentation comments to understand the features available to the user and the overall structure of the system.

[0044] Step 3:

[0045] The server extracts a list of functions and error conditions from the analysis results. This includes identifying what inputs a function requires, what outputs it produces, and what errors may occur.

[0046] Step 4:

[0047] The server uses a generative AI model to generate natural language documentation based on extracted functionality and error information. This includes the process of creating user manuals and FAQs.

[0048] Step 5:

[0049] The server generates images and videos to visually represent the operating procedures based on the generated text content. This uses screen capture and animation creation technologies.

[0050] Step 6:

[0051] The server integrates the generated documents and rich content into the management system and distributes them to web portals and document sites. This process ensures that users have access to the latest information.

[0052] Step 7:

[0053] The server monitors changes to the source code, and if a change is detected, it reparses only the affected sections of the manual and updates only the necessary parts.

[0054] Step 8:

[0055] Users can learn how to use the product by viewing the publicly available manuals and FAQs. Furthermore, they can submit feedback regarding the manual content to the system.

[0056] Step 9:

[0057] The server receives feedback from users, analyzes it, and then uses the results to further improve the content of manuals and FAQs, which will be reflected in the next update.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] Creating and updating manuals and FAQs for traditional software products is largely a manual process, requiring considerable time and effort. Furthermore, the information may not always be up-to-date, potentially preventing the provision of adequate support to users. Additionally, it is difficult to quickly incorporate user feedback and continuously improve the quality of the documentation.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operational functions and error conditions, and means for inputting prompts to a generated AI model based on the extracted information. This enables the automatic generation and updating of manuals and FAQs, as well as the provision of visually rich content.

[0063] "Source code" refers to a set of text-based instructions written by a programmer to specify the structure and functionality of a program.

[0064] "Analysis" is the process by which a system identifies specific elements or structures within source code and extracts information from them.

[0065] A "generative AI model" refers to a machine learning algorithm trained to generate natural language text and has the ability to create documents based on prompts.

[0066] A "prompt" is text data containing information and instructions that are input to a generative AI model, including questions and commands to obtain the desired output.

[0067] "Rich content" refers to multimedia information that includes not only static text but also visual elements such as images and videos.

[0068] "Feedback" refers to information provided by users, including opinions and requests for improvement, which is used to improve the system.

[0069] This invention relates to a system for effectively and automatically generating and updating user manuals and FAQs for software products, with a server playing a central role in achieving this.

[0070] First, the server accesses the source code repository (e.g., version control system) to retrieve the latest source code. During this process, the server utilizes a stable network connection to ensure that the latest software changes are reflected. The retrieved source code is then analyzed using known static analysis tools (e.g., SonarQube, ESLint). Through this analysis, the server extracts user-available functions and potential error conditions from the source code.

[0071] Next, the server generates prompts to input into the AI ​​model (e.g., a natural language generation algorithm). Based on the generated prompts, the AI ​​model generates the text necessary for creating user manuals and FAQs in natural language. Through this process, the server can provide documents that are easy for users without specialized technical knowledge to understand. For example, it might generate a prompt such as, "Please explain the specific operating procedure for new feature X. This feature is designed to simplify data filtering."

[0072] Furthermore, the server uses image and video editing software to create rich content based on the generated text. This rich content includes screencast videos explaining operating procedures and infographics illustrating important functions. By creating rich content, users can more easily grasp information visually, and understanding complex operations and errors is facilitated.

[0073] Ultimately, the server integrates and distributes the generated manuals and rich content into a dedicated web portal and document management system. This system allows the server to continuously provide users with the most up-to-date information. Users can refer to these documents to effectively utilize the product and send feedback to the server. This feedback is used by the server to make further improvements.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server accesses the source code repository to retrieve the latest source code. It uses the repository URL and access key as input. The retrieved source code is stored as a dataset and used as the basis for the next analysis step. The server automates this process and ensures data up-to-dateness by recording timestamps.

[0077] Step 2:

[0078] The server analyzes the acquired source code using a static analysis tool. This step uses the acquired source code as input. During the analysis, the server detects functions and classes within the code and extracts their operational functions and error conditions. The output is a set of extracted information for use in the next step. This information provides the data necessary for the automatic generation of user manuals and FAQs.

[0079] Step 3:

[0080] The server generates prompts for input into the generated AI model based on the analysis results. The input here is the analysis data from step 2. The server creates prompts expressed in natural language, taking into account the detected functions and error conditions. The output is a text-based prompt statement used in the next step. This prompt serves as a guideline for determining the content of the user manual and FAQ.

[0081] Step 4:

[0082] The server passes the generated prompts to an AI model to produce user manuals and FAQ documents. The input is the prompt text, and the output is a document expressed as natural language text. In this step, the server, with the help of the generative AI model, creates explanatory text in a format easily understandable even to users without technical knowledge. The generated text includes operating procedures and error handling.

[0083] Step 5:

[0084] The server creates rich content based on the generated text. The input is the text information obtained in step 4. The server uses image and video editing tools to create diagrams and screencasts to visually supplement the text explanations. The output is rich content that includes this visual information, improving the quality of information provided to the user. This content is incorporated into user manuals and FAQs.

[0085] Step 6:

[0086] The server delivers all generated content to the web portal and document management system. The input consists of all documents, including the rich content generated in step 5. The output is published in a user-accessible format, and an interface for receiving feedback is also provided. This allows the server to continuously update and improve the content based on user feedback.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In traditional software products, creating user manuals and FAQs was often done manually, leading to slow updates and making it difficult to provide users with the latest information. Similarly, updating product information and instruction manuals on e-commerce sites was time-consuming, making it difficult to provide customers with up-to-date information. This resulted in users being unable to obtain accurate information, hindering improvements in the user experience and causing delays in customer service for businesses.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for acquiring software code, means for analyzing the acquired software code to extract operation functions and error patterns, and natural language generation means for automatically generating documents and Q&A collections based on the generated data. This enables the automatic generation and updating of documents during software updates, making it possible to quickly provide users with the latest and most accurate information. Furthermore, the automatic generation of instruction manuals based on product data on e-commerce sites speeds up customer service and improves user convenience.

[0092] "Software code" is a set of instructions written in a computer language to dictate the operation of a computer program.

[0093] "Operational functions" refer to the means by which users perform specific actions and tasks through software.

[0094] An "error pattern" refers to typical examples or characteristics of abnormal conditions or malfunctions that can occur in the operation of software.

[0095] "Natural language generation means" refers to a method or apparatus for generating natural-sounding, human-readable text from structured data using computer technology.

[0096] A "rich media generation means" is a method or apparatus for generating advanced content (e.g., images and videos) that combines visual and auditory elements.

[0097] "Product data" refers to a collection of information including product attributes and specifications, which forms the basis for instruction manuals and Q&A.

[0098] "Opinions" refer to feedback provided by users, including their experiences, impressions, and suggestions for product improvement.

[0099] A "wide-area communication network" refers to a communication infrastructure that connects over a wide area, such as the internet.

[0100] The system for realizing this invention consists of a server, a user terminal, and a wide-area communication network. The server's primary role is to acquire software code. It establishes an access point in the data management system and retrieves the software code from the code repository. Next, the server uses a static analysis tool to analyze the acquired code. This analysis extracts the functionality of the operations and error patterns. Using this analysis data, a generative AI model generates natural language text. This automatically generates user manuals and FAQs.

[0101] The server also utilizes rich media generation capabilities to create diagrams and videos illustrating operating procedures. The generated content is integrated into a management system on the server and distributed to users' terminals via a wide-area communication network. This ensures that users always have access to the latest information.

[0102] As a concrete example, for newly introduced home appliances, the server automatically generates an instruction manual based on the product's technical data. In this case, an example of a prompt message would be: "Product Name: Smart Cooker\nDescription: Multifunctional cooking device\nFunctions: Temperature control function, built-in timer function." This allows users to quickly obtain detailed information about the product.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server accesses the software code repository via a wide-area network to retrieve the latest software code. During this process, the server periodically monitors the repository to detect new code commits. The input is the latest software code, and this code is downloaded to the server as output.

[0106] Step 2:

[0107] The server performs static analysis on the acquired software code. Using a static analysis tool, it analyzes the code and extracts operational functions and error patterns. In this process, the input is the acquired software code, and the output is a list of operational functions and error patterns.

[0108] Step 3:

[0109] The server uses a generative AI model to generate natural language text based on a list of functions and error patterns obtained from static analysis. Prompts are used to instruct the AI ​​model to generate the text. The input is a list of functions and error patterns, and the output is text such as a user manual or FAQ.

[0110] Step 4:

[0111] The server uses a rich media generation tool to generate diagrams and videos that visually explain the operating procedures. Visual materials are created using image processing and video generation technologies. The input is the content and procedure details of the user manual, and the output is the generated diagrams and videos.

[0112] Step 5:

[0113] The server integrates the generated natural language text and rich media into the management system. At this stage, the server organizes the content metadata and converts it into a deliverable format. The input is the generated text and rich media, and the output is the content integrated within the management system.

[0114] Step 6:

[0115] The server distributes content integrated into the management system to user terminals via a wide-area network. It efficiently distributes content, taking into account display and access on user terminals. The input is content integrated into the management system, and the output is information provided in a format accessible to the user's terminal.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] This invention improves the user experience in a system for generating and updating user manuals and FAQs by incorporating an emotion engine that recognizes user emotions. This system acquires and analyzes source code, automatically generates user manuals and FAQs, and simultaneously recognizes user emotions in real time using the emotion engine.

[0118] First, the server retrieves the latest code from the source code repository and analyzes it using static analysis tools. This extracts operational functions and error conditions, which are then used to generate user manuals and FAQs in natural language. Furthermore, rich content including images and videos is also generated, enabling the provision of easy-to-understand information to users.

[0119] Next, the server uses an emotion engine to recognize the user's emotions while viewing the documents. Based on this emotion data, the content of manuals and FAQs is dynamically adjusted. Specifically, if the user expresses anxiety or confusion, more detailed explanations or additional examples are provided. In this way, flexible information can be provided in response to the user's emotions.

[0120] For example, if the AI ​​detects stress from the user's facial expressions or voice while they are viewing a manual on their device, the server will automatically display relevant FAQs and hints, and suggest video tutorials to help the user understand. This allows users to solve problems more smoothly and improves their product experience.

[0121] In addition, the server accumulates user feedback based on emotions, and over the long term, this data is analyzed to continuously improve and optimize the content of manuals and FAQs. This will enable the provision of more appropriate content in future updates.

[0122] By combining these functions, the present invention can provide personalized information tailored to user needs and improve product satisfaction.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server selects a specific branch from the source code repository and downloads the latest source code. This allows the server to obtain the development progress that forms the basis for analysis.

[0126] Step 2:

[0127] The server analyzes the retrieved source code using a static analysis tool. This analysis extracts the structure of functions and classes within the code, the features available to the user, and the conditions under which errors may occur.

[0128] Step 3:

[0129] The server inputs the extracted information into a generation AI model, which automatically generates a user manual and FAQ in natural language. During this generation process, paragraph structure and terminology explanations are also included to ensure user comprehension.

[0130] Step 4:

[0131] The server automatically generates images and videos using a rich content generation tool to visually illustrate operating procedures. This makes it possible to add visual aids to the manual.

[0132] Step 5:

[0133] The server uploads the generated manuals and rich content to the management system and distributes them to the documentation site and portal. This ensures that users can always access the latest information.

[0134] Step 6:

[0135] When users view manuals or FAQs on their devices, an emotion engine is activated to monitor their emotions in real time. It analyzes the user's emotions from their facial expressions and voice input, and sends that data to a server.

[0136] Step 7:

[0137] The server analyzes emotional data and dynamically adjusts the content of manuals and FAQs based on the user's emotional state. For example, it provides additional explanations or tutorial videos where the user finds something difficult.

[0138] Step 8:

[0139] Users refer to the tailored manual and use support content to resolve any issues they encounter while using the product. By sending feedback to the server, the system collects data for continuous improvement.

[0140] Step 9:

[0141] The server collects user feedback based on emotions and analyzes long-term trends to help optimize future manuals and FAQs. The results of the emotion data analysis will be reflected in the next content update.

[0142] (Example 2)

[0143] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0144] Traditional user manual and FAQ generation systems lacked the ability to automatically adapt and improve content based on source code updates and user feedback. Furthermore, they lacked mechanisms to provide information tailored to individual user emotional states, making them insufficient for improving the quality of the user experience. As a result, they failed to effectively address user problems, leading to decreased product satisfaction.

[0145] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0146] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operation functions and error conditions, means for automatically generating a user manual and FAQ in natural language based on the generated data, means for automatically generating visual information and videos of operation procedures, means for integrating and supplying the generated content to an information management means, means for recognizing the user's emotional state, and means for dynamically adjusting the content based on the emotional state. This enables the flexible provision of information based on the user's emotional state and the generation of adaptive content that utilizes feedback.

[0147] "Source code" is a text-based description of a program that explains how software works.

[0148] "Means of acquisition" refers to the process or function of retrieving source code from a repository using networks or other data transfer technologies.

[0149] "Means of analysis" refers to the function of statically inspecting software code and extracting information such as operational functions and error conditions.

[0150] "Methods for automatically generating text in natural language" refers to a function that outputs text such as documents in natural language that humans can understand.

[0151] "Means for automatically generating visual information and videos" refers to a function that generates media content, including images and audio, to make the operating procedures easier to understand.

[0152] "Information management means" refers to the process or function for organizing generated content and appropriately maintaining and distributing it within the system.

[0153] "Means of recognition" refers to technologies or functions that perceive and analyze a user's facial expressions, voice, and other elements to identify their emotional state.

[0154] "Dynamic adjustment" refers to a function that changes and optimizes the content presented in real time in response to the user's emotional state and feedback.

[0155] This invention is a system that automatically generates user manuals and FAQs and dynamically adjusts the content according to the user's emotions. This system consists of the following main components.

[0156] The server retrieves the latest source code from a source code management system (e.g., a version control system) via network communication. The retrieved source code is analyzed using static analysis tools such as SonarQube and ESLint to extract information such as operational functions and error conditions. Based on this information, a generative AI model such as OpenAI's GPT-3 (registered trademark) is used to automatically generate a user manual and FAQ in natural language. It is also possible to generate images and videos that visually demonstrate the operating procedures using media editing software such as Adobe Premiere Pro.

[0157] The device uses its camera and microphone to collect facial and audio data as the user views content, and uses this data to recognize the user's emotions. This utilizes emotion recognition technologies such as Microsoft® Azure®'s Emotion API. Based on this emotion data, the displayed content can be adjusted in real time. If the user is confused, more detailed explanations or visual examples are presented.

[0158] A concrete example of this is when a user is using a cooking app. If the user shows difficulty with the instructions while referring to the manual, the emotion engine recognizes this emotion, and the server immediately displays relevant FAQs or step-by-step video tutorials. This makes it easier for the user to understand the cooking process smoothly, improving the app's user experience.

[0159] As an example of a prompt, using the sentence, "Generate what kind of explanations and video content would be helpful when a user is looking at a cake recipe in a cooking app," allows the generative AI model to adopt a stance of generating appropriate information and content.

[0160] This system enables flexible information delivery tailored to the user's emotions, significantly improving the product user experience.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server retrieves the latest source code from the source code management system. It uses the repository URL and authentication information as input and downloads the source code using Git or other version control tools. The output is a complete set of source code extracted to a local directory.

[0164] Step 2:

[0165] The server analyzes the acquired source code using a static analysis tool. Using analysis tools such as SonarQube or ESLint, it takes the source code as input and extracts code operation functions and error conditions. The output is obtained as an analysis report and extracted information. This is formatted as a function list and error list and passed on to the next process.

[0166] Step 3:

[0167] The server automatically generates user manuals and FAQs using a generative AI model. The input consists of the analysis information obtained in step 2 and the prompt "Please write a description of the functions and errors encountered." The generative AI model constructs a description in natural language, and the output is a user manual and FAQ in a human-readable format. This result is saved as a document file.

[0168] Step 4:

[0169] The server automatically generates visual information and videos of operating procedures. Input includes detailed information about functions and operating procedures, as well as media editing software such as Adobe Premiere Pro. An automated script creates videos and images based on the operating procedures. The output is a visually rich content file, allowing users to understand the operations more intuitively.

[0170] Step 5:

[0171] The device recognizes emotions as the user views a document. It acquires audio and facial expression data via the camera and microphone as input and sends it to an emotion recognition API. The output is data on the user's current emotional state. Based on this data, the content is dynamically adjusted in the next step.

[0172] Step 6:

[0173] The server dynamically adjusts content based on the user's emotional state. It takes state information from an emotion recognition API as input and presents corresponding additional information or video tutorials. The output is displayed on the device as adjusted content, allowing users to feel secure and efficiently access the information they need.

[0174] Through this series of processes, the system provides information tailored to user needs in real time, improving the overall user experience. Furthermore, the accumulated feedback data is used for future improvements.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] Traditional user manuals and FAQs are static, making it difficult to provide information tailored to the user's emotions and level of understanding. In particular, when purchasing products in physical stores, users often experience anxiety and confusion if they are unsure how to use the product, which negatively impacts their satisfaction with the product.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0179] In this invention, the server includes means for obtaining source code, means for analyzing the obtained source code to extract operation functions and error conditions, means for natural language generation to automatically generate user guides and FAQs based on the generated data, and means for dynamically adjusting content using an emotion engine that recognizes the user's emotions. This enables the provision of personalized information in accordance with the user's emotions, thereby improving user satisfaction with the product.

[0180] "Source code" is a set of instructions in text format that describes how a computer program works.

[0181] "Analysis" is the process of breaking down data and information to reveal their characteristics and relationships.

[0182] "Operational functions" refer to the basic actions and roles that users can utilize when using software.

[0183] An "error condition" refers to a specific situation or input that prevents the software from functioning correctly.

[0184] "Generation" is the process of creating new content or deliverables using data and information.

[0185] "Natural language generation" is a technology that allows computers to create text that is readable in human language.

[0186] "Rich content" refers to content that includes a variety of media elements, such as text, images, and videos.

[0187] A "management system" is software used to organize information and data in an orderly manner and to utilize them as needed.

[0188] An "emotion engine" is a software technology used to analyze and recognize a user's emotions.

[0189] "Dynamic adjustment" means changing the content or operation in real time according to specific conditions.

[0190] "Feedback" refers to the opinions and evaluations received from users, and is information used to improve products and services.

[0191] "Personalization" means optimizing content to provide experiences and services tailored to individual users.

[0192] Embodiments of this invention utilize a system that combines specific elements to improve the user experience. First, a server retrieves source code from a database and uses an analysis tool to extract operation functions and error conditions. Next, based on the extracted information, natural language generation software is used to generate a user manual and FAQ. This also includes a rich content generation tool, which automatically generates images and videos related to the operation procedures.

[0193] In addition, an emotion engine operates on the device side, using the camera and microphone to recognize emotions from the user's facial expressions and vocalizations while they are viewing the manual. This emotion data is sent to the server in real time, and the server dynamically adjusts the content based on this data. For example, if the user is confused, it will be presented with relevant FAQs or additional video tutorials.

[0194] The hardware and software used by the server for emotion recognition include the smartphone's camera and microphone. The emotion engine utilizes Microsoft Azure's Emotion API. OpenAI's GPT-3 is used as the generative AI model. This allows the system to generate responses that correspond to the user's emotions.

[0195] A concrete example is when a user is using a coffee maker purchased from a physical store and becomes confused when the machine doesn't work properly. In this case, the application on the device automatically displays a video guide with detailed operating instructions.

[0196] An example of a prompt for a generative AI model is, "Explain how to use a modern coffee maker step-by-step for beginners."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server retrieves the latest source code from the source code repository. The input is source code data from the repository, and the output is the retrieved source code. Specifically, the server accesses the repository via a network connection and downloads the source code using authentication credentials.

[0200] Step 2:

[0201] The server analyzes the source code it has retrieved. The input is the retrieved source code, and the output is the operational functions and error conditions as a result of the analysis. Specifically, the server uses a static analysis tool to scan the code and extract the usage of specific APIs and functions from it.

[0202] Step 3:

[0203] The server generates a user manual and FAQ in natural language based on the analysis results. The input is the analysis results, and the output is manual and FAQ content in natural language format. Specifically, the server uses a generation AI model to explain the operating procedures in natural language and create the FAQ.

[0204] Step 4:

[0205] The server generates rich content. The input is the analysis results, and the output is rich content in the form of images and videos. Specifically, the server uses image generation tools and video editing software to automatically generate content that visually explains the procedure.

[0206] Step 5:

[0207] The device recognizes the user's emotions. The input is the user's facial expressions and voice data, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to record the user's facial expressions and capture their voice. Then, an emotion engine analyzes this data to determine the user's emotions.

[0208] Step 6:

[0209] The server dynamically adjusts content based on the emotion data it recognizes. The input is emotion data, and the output is the adjusted content. Specifically, the server sends a prompt message to the generating AI model, "If the user is anxious, provide a detailed tutorial," and then provides the resulting content.

[0210] Step 7:

[0211] The device displays content tailored to the user. The input is the tailored content, and the output is information provided to the user. Specifically, the device launches a video playback application and displays a tutorial video received from the server.

[0212] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0213] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0228] This invention is a system for effectively and efficiently generating and updating manuals and FAQs for software products. This system extracts necessary information from source code, processes and formats it, and provides it to the user.

[0229] First, the server accesses the source code repository to retrieve the latest code. This ensures that the latest features and changes are always reflected. Next, the server uses static analysis tools to analyze the retrieved source code and extract features available to the user and possible error conditions. Based on this analysis information, the server uses a generative AI model to generate natural language text and create manuals and FAQs in a user-friendly format.

[0230] For example, it can automatically generate operating procedures for specific functions, including explanations of potential errors users might encounter. Furthermore, the server utilizes rich content generation technology to create images and videos to complement the instructions. This allows for visual communication, aiding user understanding.

[0231] The generated manuals and FAQs are ultimately distributed to a web portal and documentation site managed by the server. This ensures that users always have access to the latest documentation. Furthermore, users can utilize the provided information to use the product more effectively and submit feedback. The server then uses this feedback to make further improvements and updates.

[0232] As a concrete example, when a new software version is released, the relevant manual sections can be automatically updated based only on the code changes, and the updated content can be visualized and provided in a video with narration. In this way, the traditional manual documentation creation and updating work can be significantly reduced, and users can always access the latest information.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The server accesses the source code repository and clones the latest source code from a specific repository or branch. This allows it to obtain the most up-to-date version of the code to be analyzed.

[0236] Step 2:

[0237] The server analyzes the retrieved source code using static analysis tools. In this process, it reads function and class definitions and documentation comments to understand the features available to the user and the overall structure of the system.

[0238] Step 3:

[0239] The server extracts a list of functions and error conditions from the analysis results. This includes identifying what inputs a function requires, what outputs it produces, and what errors may occur.

[0240] Step 4:

[0241] The server uses a generative AI model to generate natural language documentation based on extracted functionality and error information. This includes the process of creating user manuals and FAQs.

[0242] Step 5:

[0243] The server generates images and videos to visually represent the operating procedures based on the generated text content. This uses screen capture and animation creation technologies.

[0244] Step 6:

[0245] The server integrates the generated documents and rich content into the management system and distributes them to web portals and document sites. This process ensures that users have access to the latest information.

[0246] Step 7:

[0247] The server monitors changes to the source code, and if a change is detected, it reparses only the affected sections of the manual and updates only the necessary parts.

[0248] Step 8:

[0249] Users can learn how to use the product by viewing the publicly available manuals and FAQs. Furthermore, they can submit feedback regarding the manual content to the system.

[0250] Step 9:

[0251] The server receives feedback from users, analyzes it, and then uses the results to further improve the content of manuals and FAQs, which will be reflected in the next update.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] Creating and updating manuals and FAQs for traditional software products is largely a manual process, requiring considerable time and effort. Furthermore, the information may not always be up-to-date, potentially preventing the provision of adequate support to users. Additionally, it is difficult to quickly incorporate user feedback and continuously improve the quality of the documentation.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operational functions and error conditions, and means for inputting prompts to a generated AI model based on the extracted information. This enables the automatic generation and updating of manuals and FAQs, as well as the provision of visually rich content.

[0257] "Source code" refers to a set of text-based instructions written by a programmer to specify the structure and functionality of a program.

[0258] "Analysis" is the process by which a system identifies specific elements or structures within source code and extracts information from them.

[0259] A "generative AI model" refers to a machine learning algorithm trained to generate natural language text and has the ability to create documents based on prompts.

[0260] A "prompt" is text data containing information and instructions that are input to a generative AI model, including questions and commands to obtain the desired output.

[0261] "Rich content" refers to multimedia information that includes not only static text but also visual elements such as images and videos.

[0262] "Feedback" refers to information provided by users, including opinions and requests for improvement, which is used to improve the system.

[0263] This invention relates to a system for effectively and automatically generating and updating user manuals and FAQs for software products, with a server playing a central role in achieving this.

[0264] First, the server accesses the source code repository (e.g., version control system) to retrieve the latest source code. During this process, the server utilizes a stable network connection to ensure that the latest software changes are reflected. The retrieved source code is then analyzed using known static analysis tools (e.g., SonarQube, ESLint). Through this analysis, the server extracts user-available functions and potential error conditions from the source code.

[0265] Next, the server generates prompts to input into the AI ​​model (e.g., a natural language generation algorithm). Based on the generated prompts, the AI ​​model generates the text necessary for creating user manuals and FAQs in natural language. Through this process, the server can provide documents that are easy for users without specialized technical knowledge to understand. For example, it might generate a prompt such as, "Please explain the specific operating procedure for new feature X. This feature is designed to simplify data filtering."

[0266] Furthermore, the server uses image and video editing software to create rich content based on the generated text. This rich content includes screencast videos explaining operating procedures and infographics illustrating important functions. By creating rich content, users can more easily grasp information visually, and understanding complex operations and errors is facilitated.

[0267] Ultimately, the server integrates and distributes the generated manuals and rich content into a dedicated web portal and document management system. This system allows the server to continuously provide users with the most up-to-date information. Users can refer to these documents to effectively utilize the product and send feedback to the server. This feedback is used by the server to make further improvements.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server accesses the source code repository to retrieve the latest source code. It uses the repository URL and access key as input. The retrieved source code is stored as a dataset and used as the basis for the next analysis step. The server automates this process and ensures data up-to-dateness by recording timestamps.

[0271] Step 2:

[0272] The server analyzes the acquired source code using a static analysis tool. This step uses the acquired source code as input. During the analysis, the server detects functions and classes within the code and extracts their operational functions and error conditions. The output is a set of extracted information for use in the next step. This information provides the data necessary for the automatic generation of user manuals and FAQs.

[0273] Step 3:

[0274] The server generates prompts for input into the generated AI model based on the analysis results. The input here is the analysis data from step 2. The server creates prompts expressed in natural language, taking into account the detected functions and error conditions. The output is a text-based prompt statement used in the next step. This prompt serves as a guideline for determining the content of the user manual and FAQ.

[0275] Step 4:

[0276] The server passes the generated prompts to an AI model to produce user manuals and FAQ documents. The input is the prompt text, and the output is a document expressed as natural language text. In this step, the server, with the help of the generative AI model, creates explanatory text in a format easily understandable even to users without technical knowledge. The generated text includes operating procedures and error handling.

[0277] Step 5:

[0278] The server creates rich content based on the generated text. The input is the text information obtained in step 4. The server uses image and video editing tools to create diagrams and screencasts to visually supplement the text explanations. The output is rich content that includes this visual information, improving the quality of information provided to the user. This content is incorporated into user manuals and FAQs.

[0279] Step 6:

[0280] The server delivers all generated content to the web portal and document management system. The input consists of all documents, including the rich content generated in step 5. The output is published in a user-accessible format, and an interface for receiving feedback is also provided. This allows the server to continuously update and improve the content based on user feedback.

[0281] (Application Example 1)

[0282] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0283] In the creation of user manuals and FAQs in conventional software products, it was often done manually and was prone to delays in updates, making it difficult to provide users with the latest information. Also, in mail-order sites, updating product information and handling instructions was laborious, and it was difficult to provide customers with the latest information. As a result, users could not obtain accurate information, making it difficult to improve the user experience, and there was a problem of delays in the company's response to customers.

[0284] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0285] In this invention, the server includes means for acquiring software code, means for analyzing the acquired software code to extract operation functions and error patterns, and natural language generation means for automatically generating documents and Q&A sets based on the generated data. As a result, it becomes possible to automatically generate and update documents at the time of software update, and it is possible to quickly provide users with always the latest and accurate information. Also, by automatically generating handling instructions based on product data in a mail-order site, customer response is speeded up and user convenience is improved.

[0286] "Software code" is a set of instructions in a computer language described to instruct the operation of a computer program.

[0287] "Operation function" is a means for realizing specific actions and tasks that a user performs through software.

[0288] "Error pattern" is a typical example and feature of abnormal states and malfunctions that can occur in the operation of software.

[0289] "Natural language generation means" is a method or apparatus for generating natural sentences understandable by humans from structured data using computer technology.

[0290] A "rich media generation means" is a method or apparatus for generating advanced content (e.g., images and videos) that combines visual and auditory elements.

[0291] "Product data" refers to a collection of information including product attributes and specifications, which forms the basis for instruction manuals and Q&A.

[0292] "Opinions" refer to feedback provided by users, including their experiences, impressions, and suggestions for product improvement.

[0293] A "wide-area communication network" refers to a communication infrastructure that connects over a wide area, such as the internet.

[0294] The system for realizing this invention consists of a server, a user terminal, and a wide-area communication network. The server's primary role is to acquire software code. It establishes an access point in the data management system and retrieves the software code from the code repository. Next, the server uses a static analysis tool to analyze the acquired code. This analysis extracts the functionality of the operations and error patterns. Using this analysis data, a generative AI model generates natural language text. This automatically generates user manuals and FAQs.

[0295] The server also utilizes rich media generation capabilities to create diagrams and videos illustrating operating procedures. The generated content is integrated into a management system on the server and distributed to users' terminals via a wide-area communication network. This ensures that users always have access to the latest information.

[0296] As a concrete example, for newly introduced home appliances, the server automatically generates an instruction manual based on the product's technical data. In this case, an example of a prompt message would be: "Product Name: Smart Cooker\nDescription: Multifunctional cooking device\nFunctions: Temperature control function, built-in timer function." This allows users to quickly obtain detailed information about the product.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server accesses the software code repository via a wide-area network to retrieve the latest software code. During this process, the server periodically monitors the repository to detect new code commits. The input is the latest software code, and this code is downloaded to the server as output.

[0300] Step 2:

[0301] The server performs static analysis on the acquired software code. Using a static analysis tool, it analyzes the code and extracts operational functions and error patterns. In this process, the input is the acquired software code, and the output is a list of operational functions and error patterns.

[0302] Step 3:

[0303] The server uses a generative AI model to generate natural language text based on a list of functions and error patterns obtained from static analysis. Prompts are used to instruct the AI ​​model to generate the text. The input is a list of functions and error patterns, and the output is text such as a user manual or FAQ.

[0304] Step 4:

[0305] The server uses a rich media generation tool to generate diagrams and videos that visually explain the operation procedures. Visual materials are created through image processing and video generation technologies. The input is the content of the user manual and the details of the procedures, and the output is the generated diagrams and videos.

[0306] Step 5:

[0307] The server integrates the generated natural language sentences and rich media into the management system. At this stage, the server sorts out the metadata of the content and converts it into a distributable format. The input is the generated sentences and rich media, and the output is the content integrated into the management system.

[0308] Step 6:

[0309] The server distributes the content integrated into the management system to the user's terminal via a wide area network. Considering the display and access on the user terminal, the content is distributed efficiently. The input is the content integrated into the management system, and the output is to provide information in a form accessible by the user on the terminal.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0311] The present invention improves the user experience by incorporating an emotion engine that recognizes the user's emotion in a system for generating and updating user manuals and FAQs. This system acquires, analyzes the source code, and automatically generates user manuals and FAQs, and at the same time, uses the emotion engine to recognize the user's emotion in real time.

[0312] First, the server retrieves the latest code from the source code repository and analyzes it using static analysis tools. This extracts operational functions and error conditions, which are then used to generate user manuals and FAQs in natural language. Furthermore, rich content including images and videos is also generated, enabling the provision of easy-to-understand information to users.

[0313] Next, the server uses an emotion engine to recognize the user's emotions while viewing the documents. Based on this emotion data, the content of manuals and FAQs is dynamically adjusted. Specifically, if the user expresses anxiety or confusion, more detailed explanations or additional examples are provided. In this way, flexible information can be provided in response to the user's emotions.

[0314] For example, if the AI ​​detects stress from the user's facial expressions or voice while they are viewing a manual on their device, the server will automatically display relevant FAQs and hints, and suggest video tutorials to help the user understand. This allows users to solve problems more smoothly and improves their product experience.

[0315] In addition, the server accumulates user feedback based on emotions, and over the long term, this data is analyzed to continuously improve and optimize the content of manuals and FAQs. This will enable the provision of more appropriate content in future updates.

[0316] By combining these functions, the present invention can provide personalized information tailored to user needs and improve product satisfaction.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The server selects a specific branch from the source code repository and downloads the latest source code. This allows the server to obtain the development progress that forms the basis for analysis.

[0320] Step 2:

[0321] The server analyzes the retrieved source code using a static analysis tool. This analysis extracts the structure of functions and classes within the code, the features available to the user, and the conditions under which errors may occur.

[0322] Step 3:

[0323] The server inputs the extracted information into a generation AI model, which automatically generates a user manual and FAQ in natural language. During this generation process, paragraph structure and terminology explanations are also included to ensure user comprehension.

[0324] Step 4:

[0325] The server automatically generates images and videos using a rich content generation tool to visually illustrate operating procedures. This makes it possible to add visual aids to the manual.

[0326] Step 5:

[0327] The server uploads the generated manuals and rich content to the management system and distributes them to the documentation site and portal. This ensures that users can always access the latest information.

[0328] Step 6:

[0329] When users view manuals or FAQs on their devices, an emotion engine is activated to monitor their emotions in real time. It analyzes the user's emotions from their facial expressions and voice input, and sends that data to a server.

[0330] Step 7:

[0331] The server analyzes emotional data and dynamically adjusts the content of manuals and FAQs based on the user's emotional state. For example, it provides additional explanations or tutorial videos where the user finds something difficult.

[0332] Step 8:

[0333] Users refer to the tailored manual and use support content to resolve any issues they encounter while using the product. By sending feedback to the server, the system collects data for continuous improvement.

[0334] Step 9:

[0335] The server collects user feedback based on emotions and analyzes long-term trends to help optimize future manuals and FAQs. The results of the emotion data analysis will be reflected in the next content update.

[0336] (Example 2)

[0337] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0338] Traditional user manual and FAQ generation systems lacked the ability to automatically adapt and improve content based on source code updates and user feedback. Furthermore, they lacked mechanisms to provide information tailored to individual user emotional states, making them insufficient for improving the quality of the user experience. As a result, they failed to effectively address user problems, leading to decreased product satisfaction.

[0339] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0340] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operation functions and error conditions, means for automatically generating a user manual and FAQ in natural language based on the generated data, means for automatically generating visual information and videos of operation procedures, means for integrating and supplying the generated content to an information management means, means for recognizing the user's emotional state, and means for dynamically adjusting the content based on the emotional state. This enables the flexible provision of information based on the user's emotional state and the generation of adaptive content that utilizes feedback.

[0341] "Source code" is a text-based description of a program that explains how software works.

[0342] "Means of acquisition" refers to the process or function of retrieving source code from a repository using networks or other data transfer technologies.

[0343] "Means of analysis" refers to the function of statically inspecting software code and extracting information such as operational functions and error conditions.

[0344] "Methods for automatically generating text in natural language" refers to a function that outputs text such as documents in natural language that humans can understand.

[0345] "Means for automatically generating visual information and videos" refers to a function that generates media content, including images and audio, to make the operating procedures easier to understand.

[0346] "Information management means" refers to the process or function for organizing generated content and appropriately maintaining and distributing it within the system.

[0347] "Means of recognition" refers to technologies or functions that perceive and analyze a user's facial expressions, voice, and other elements to identify their emotional state.

[0348] "Dynamic adjustment" refers to a function that changes and optimizes the content presented in real time in response to the user's emotional state and feedback.

[0349] This invention is a system that automatically generates user manuals and FAQs and dynamically adjusts the content according to the user's emotions. This system consists of the following main components.

[0350] The server retrieves the latest source code from a source code management system (e.g., a version control system) via network communication. The retrieved source code is analyzed using static analysis tools such as SonarQube or ESLint to extract information such as operational functions and error conditions. Based on this information, a generative AI model such as OpenAI's GPT-3 is used to automatically generate a user manual and FAQ in natural language. It is also possible to generate images and videos that visually demonstrate the operating procedures using media editing software such as Adobe Premiere Pro.

[0351] The device uses its camera and microphone to collect facial and audio data as the user views content, and uses this data to recognize the user's emotions. This utilizes emotion recognition technologies such as Microsoft Azure's Emotion API. Based on this emotion data, the displayed content can be adjusted in real time. If the user appears confused, more detailed explanations or visual examples are presented.

[0352] A concrete example of this is when a user is using a cooking app. If the user shows difficulty with the instructions while referring to the manual, the emotion engine recognizes this emotion, and the server immediately displays relevant FAQs or step-by-step video tutorials. This makes it easier for the user to understand the cooking process smoothly, improving the app's user experience.

[0353] As an example of a prompt, using the sentence, "Generate what kind of explanations and video content would be helpful when a user is looking at a cake recipe in a cooking app," allows the generative AI model to adopt a stance of generating appropriate information and content.

[0354] This system enables flexible information delivery tailored to the user's emotions, significantly improving the product user experience.

[0355] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0356] Step 1:

[0357] The server retrieves the latest source code from the source code management system. It uses the repository URL and authentication information as input and downloads the source code using Git or other version control tools. The output is a complete set of source code extracted to a local directory.

[0358] Step 2:

[0359] The server analyzes the acquired source code using a static analysis tool. Using analysis tools such as SonarQube or ESLint, it takes the source code as input and extracts code operation functions and error conditions. The output is obtained as an analysis report and extracted information. This is formatted as a function list and error list and passed on to the next process.

[0360] Step 3:

[0361] The server automatically generates user manuals and FAQs using a generative AI model. The input consists of the analysis information obtained in step 2 and the prompt "Please write a description of the functions and errors encountered." The generative AI model constructs a description in natural language, and the output is a user manual and FAQ in a human-readable format. This result is saved as a document file.

[0362] Step 4:

[0363] The server automatically generates visual information and videos of operating procedures. Input includes detailed information about functions and operating procedures, as well as media editing software such as Adobe Premiere Pro. An automated script creates videos and images based on the operating procedures. The output is a visually rich content file, allowing users to understand the operations more intuitively.

[0364] Step 5:

[0365] The device recognizes emotions as the user views a document. It acquires audio and facial expression data via the camera and microphone as input and sends it to an emotion recognition API. The output is data on the user's current emotional state. Based on this data, the content is dynamically adjusted in the next step.

[0366] Step 6:

[0367] The server dynamically adjusts content based on the user's emotional state. It takes state information from an emotion recognition API as input and presents corresponding additional information or video tutorials. The output is displayed on the device as adjusted content, allowing users to feel secure and efficiently access the information they need.

[0368] Through this series of processes, the system provides information tailored to user needs in real time, improving the overall user experience. Furthermore, the accumulated feedback data is used for future improvements.

[0369] (Application Example 2)

[0370] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0371] Traditional user manuals and FAQs are static, making it difficult to provide information tailored to the user's emotions and level of understanding. In particular, when purchasing products in physical stores, users often experience anxiety and confusion if they are unsure how to use the product, which negatively impacts their satisfaction with the product.

[0372] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0373] In this invention, the server includes means for obtaining source code, means for analyzing the obtained source code to extract operation functions and error conditions, means for natural language generation to automatically generate user guides and FAQs based on the generated data, and means for dynamically adjusting content using an emotion engine that recognizes the user's emotions. This enables the provision of personalized information in accordance with the user's emotions, thereby improving user satisfaction with the product.

[0374] "Source code" is a set of instructions in text format that describes how a computer program works.

[0375] "Analysis" is the process of breaking down data and information to reveal their characteristics and relationships.

[0376] "Operational functions" refer to the basic actions and roles that users can utilize when using software.

[0377] An "error condition" refers to a specific situation or input that prevents the software from functioning correctly.

[0378] "Generation" is the process of creating new content or deliverables using data and information.

[0379] "Natural language generation" is a technology that allows computers to create text that is readable in human language.

[0380] "Rich content" refers to content that includes a variety of media elements, such as text, images, and videos.

[0381] A "management system" is software used to organize information and data in an orderly manner and to utilize them as needed.

[0382] An "emotion engine" is a software technology used to analyze and recognize a user's emotions.

[0383] "Dynamic adjustment" means changing the content or operation in real time according to specific conditions.

[0384] "Feedback" refers to the opinions and evaluations received from users, and is information used to improve products and services.

[0385] "Personalization" means optimizing content to provide experiences and services tailored to individual users.

[0386] Embodiments of this invention utilize a system that combines specific elements to improve the user experience. First, a server retrieves source code from a database and uses an analysis tool to extract operation functions and error conditions. Next, based on the extracted information, natural language generation software is used to generate a user manual and FAQ. This also includes a rich content generation tool, which automatically generates images and videos related to the operation procedures.

[0387] In addition, an emotion engine operates on the device side, using the camera and microphone to recognize emotions from the user's facial expressions and vocalizations while they are viewing the manual. This emotion data is sent to the server in real time, and the server dynamically adjusts the content based on this data. For example, if the user is confused, it will be presented with relevant FAQs or additional video tutorials.

[0388] The hardware and software used by the server for emotion recognition include the smartphone's camera and microphone. The emotion engine utilizes Microsoft Azure's Emotion API. OpenAI's GPT-3 is used as the generative AI model. This allows the system to generate responses that correspond to the user's emotions.

[0389] A concrete example is when a user is using a coffee maker purchased from a physical store and becomes confused when the machine doesn't work properly. In this case, the application on the device automatically displays a video guide with detailed operating instructions.

[0390] An example of a prompt for a generative AI model is, "Explain how to use a modern coffee maker step-by-step for beginners."

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The server retrieves the latest source code from the source code repository. The input is source code data from the repository, and the output is the retrieved source code. Specifically, the server accesses the repository via a network connection and downloads the source code using authentication credentials.

[0394] Step 2:

[0395] The server analyzes the source code it has retrieved. The input is the retrieved source code, and the output is the operational functions and error conditions as a result of the analysis. Specifically, the server uses a static analysis tool to scan the code and extract the usage of specific APIs and functions from it.

[0396] Step 3:

[0397] The server generates a user manual and FAQ in natural language based on the analysis results. The input is the analysis results, and the output is manual and FAQ content in natural language format. Specifically, the server uses a generation AI model to explain the operating procedures in natural language and create the FAQ.

[0398] Step 4:

[0399] The server generates rich content. The input is the analysis results, and the output is rich content in the form of images and videos. Specifically, the server uses image generation tools and video editing software to automatically generate content that visually explains the procedure.

[0400] Step 5:

[0401] The device recognizes the user's emotions. The input is the user's facial expressions and voice data, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to record the user's facial expressions and capture their voice. Then, an emotion engine analyzes this data to determine the user's emotions.

[0402] Step 6:

[0403] The server dynamically adjusts content based on the emotion data it recognizes. The input is emotion data, and the output is the adjusted content. Specifically, the server sends a prompt message to the generating AI model, "If the user is anxious, provide a detailed tutorial," and then provides the resulting content.

[0404] Step 7:

[0405] The device displays content tailored to the user. The input is the tailored content, and the output is information provided to the user. Specifically, the device launches a video playback application and displays a tutorial video received from the server.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0407] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0412] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0414] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0416] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0417] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0418] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0421] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0422] This invention is a system for effectively and efficiently generating and updating manuals and FAQs for software products. This system extracts necessary information from source code, processes and formats it, and provides it to the user.

[0423] First, the server accesses the source code repository to retrieve the latest code. This ensures that the latest features and changes are always reflected. Next, the server uses static analysis tools to analyze the retrieved source code and extract features available to the user and possible error conditions. Based on this analysis information, the server uses a generative AI model to generate natural language text and create manuals and FAQs in a user-friendly format.

[0424] For example, it can automatically generate operating procedures for specific functions, including explanations of potential errors users might encounter. Furthermore, the server utilizes rich content generation technology to create images and videos to complement the instructions. This allows for visual communication, aiding user understanding.

[0425] The generated manuals and FAQs are ultimately distributed to a web portal and documentation site managed by the server. This ensures that users always have access to the latest documentation. Furthermore, users can utilize the provided information to use the product more effectively and submit feedback. The server then uses this feedback to make further improvements and updates.

[0426] As a concrete example, when a new software version is released, the relevant manual sections can be automatically updated based only on the code changes, and the updated content can be visualized and provided in a video with narration. In this way, the traditional manual documentation creation and updating work can be significantly reduced, and users can always access the latest information.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The server accesses the source code repository and clones the latest source code from a specific repository or branch. This allows it to obtain the most up-to-date version of the code to be analyzed.

[0430] Step 2:

[0431] The server analyzes the retrieved source code using static analysis tools. In this process, it reads function and class definitions and documentation comments to understand the features available to the user and the overall structure of the system.

[0432] Step 3:

[0433] The server extracts a list of functions and error conditions from the analysis results. This includes identifying what inputs a function requires, what outputs it produces, and what errors may occur.

[0434] Step 4:

[0435] The server uses a generative AI model to generate natural language documentation based on extracted functionality and error information. This includes the process of creating user manuals and FAQs.

[0436] Step 5:

[0437] The server generates images and videos to visually represent the operating procedures based on the generated text content. This uses screen capture and animation creation technologies.

[0438] Step 6:

[0439] The server integrates the generated documents and rich content into the management system and distributes them to web portals and document sites. This process ensures that users have access to the latest information.

[0440] Step 7:

[0441] The server monitors changes to the source code, and if a change is detected, it reparses only the affected sections of the manual and updates only the necessary parts.

[0442] Step 8:

[0443] Users can learn how to use the product by viewing the publicly available manuals and FAQs. Furthermore, they can submit feedback regarding the manual content to the system.

[0444] Step 9:

[0445] The server receives feedback from users, analyzes it, and then uses the results to further improve the content of manuals and FAQs, which will be reflected in the next update.

[0446] (Example 1)

[0447] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0448] Creating and updating manuals and FAQs for traditional software products is largely a manual process, requiring considerable time and effort. Furthermore, the information may not always be up-to-date, potentially preventing the provision of adequate support to users. Additionally, it is difficult to quickly incorporate user feedback and continuously improve the quality of the documentation.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operational functions and error conditions, and means for inputting prompts to a generated AI model based on the extracted information. This enables the automatic generation and updating of manuals and FAQs, as well as the provision of visually rich content.

[0451] "Source code" refers to a set of text-based instructions written by a programmer to specify the structure and functionality of a program.

[0452] "Analysis" is the process by which a system identifies specific elements or structures within source code and extracts information from them.

[0453] A "generative AI model" refers to a machine learning algorithm trained to generate natural language text and has the ability to create documents based on prompts.

[0454] A "prompt" is text data containing information and instructions that are input to a generative AI model, including questions and commands to obtain the desired output.

[0455] "Rich content" refers to multimedia information that includes not only static text but also visual elements such as images and videos.

[0456] "Feedback" refers to information provided by users, including opinions and requests for improvement, which is used to improve the system.

[0457] This invention relates to a system for effectively and automatically generating and updating user manuals and FAQs for software products, with a server playing a central role in achieving this.

[0458] First, the server accesses the source code repository (e.g., version control system) to retrieve the latest source code. During this process, the server utilizes a stable network connection to ensure that the latest software changes are reflected. The retrieved source code is then analyzed using known static analysis tools (e.g., SonarQube, ESLint). Through this analysis, the server extracts user-available functions and potential error conditions from the source code.

[0459] Next, the server generates prompts to input into the AI ​​model (e.g., a natural language generation algorithm). Based on the generated prompts, the AI ​​model generates the text necessary for creating user manuals and FAQs in natural language. Through this process, the server can provide documents that are easy for users without specialized technical knowledge to understand. For example, it might generate a prompt such as, "Please explain the specific operating procedure for new feature X. This feature is designed to simplify data filtering."

[0460] Furthermore, the server uses image and video editing software to create rich content based on the generated text. This rich content includes screencast videos explaining operating procedures and infographics illustrating important functions. By creating rich content, users can more easily grasp information visually, and understanding complex operations and errors is facilitated.

[0461] Ultimately, the server integrates and distributes the generated manuals and rich content into a dedicated web portal and document management system. This system allows the server to continuously provide users with the most up-to-date information. Users can refer to these documents to effectively utilize the product and send feedback to the server. This feedback is used by the server to make further improvements.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The server accesses the source code repository to retrieve the latest source code. It uses the repository URL and access key as input. The retrieved source code is stored as a dataset and used as the basis for the next analysis step. The server automates this process and ensures data up-to-dateness by recording timestamps.

[0465] Step 2:

[0466] The server analyzes the acquired source code using a static analysis tool. This step uses the acquired source code as input. During the analysis, the server detects functions and classes within the code and extracts their operational functions and error conditions. The output is a set of extracted information for use in the next step. This information provides the data necessary for the automatic generation of user manuals and FAQs.

[0467] Step 3:

[0468] The server generates prompts for input into the generated AI model based on the analysis results. The input here is the analysis data from step 2. The server creates prompts expressed in natural language, taking into account the detected functions and error conditions. The output is a text-based prompt statement used in the next step. This prompt serves as a guideline for determining the content of the user manual and FAQ.

[0469] Step 4:

[0470] The server passes the generated prompts to an AI model to produce user manuals and FAQ documents. The input is the prompt text, and the output is a document expressed as natural language text. In this step, the server, with the help of the generative AI model, creates explanatory text in a format easily understandable even to users without technical knowledge. The generated text includes operating procedures and error handling.

[0471] Step 5:

[0472] The server creates rich content based on the generated text. The input is the text information obtained in step 4. The server uses image and video editing tools to create diagrams and screencasts to visually supplement the text explanations. The output is rich content that includes this visual information, improving the quality of information provided to the user. This content is incorporated into user manuals and FAQs.

[0473] Step 6:

[0474] The server delivers all generated content to the web portal and document management system. The input consists of all documents, including the rich content generated in step 5. The output is published in a user-accessible format, and an interface for receiving feedback is also provided. This allows the server to continuously update and improve the content based on user feedback.

[0475] (Application Example 1)

[0476] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0477] In traditional software products, creating user manuals and FAQs was often done manually, leading to slow updates and making it difficult to provide users with the latest information. Similarly, updating product information and instruction manuals on e-commerce sites was time-consuming, making it difficult to provide customers with up-to-date information. This resulted in users being unable to obtain accurate information, hindering improvements in the user experience and causing delays in customer service for businesses.

[0478] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0479] In this invention, the server includes means for acquiring software code, means for analyzing the acquired software code to extract operation functions and error patterns, and natural language generation means for automatically generating documents and Q&A collections based on the generated data. This enables the automatic generation and updating of documents during software updates, making it possible to quickly provide users with the latest and most accurate information. Furthermore, the automatic generation of instruction manuals based on product data on e-commerce sites speeds up customer service and improves user convenience.

[0480] "Software code" is a set of instructions written in a computer language to dictate the operation of a computer program.

[0481] "Operational functions" refer to the means by which users perform specific actions and tasks through software.

[0482] An "error pattern" refers to typical examples or characteristics of abnormal conditions or malfunctions that can occur in the operation of software.

[0483] "Natural language generation means" refers to a method or apparatus for generating natural-sounding, human-readable text from structured data using computer technology.

[0484] A "rich media generation means" is a method or apparatus for generating advanced content (e.g., images and videos) that combines visual and auditory elements.

[0485] "Product data" refers to a collection of information including product attributes and specifications, which forms the basis for instruction manuals and Q&A.

[0486] "Opinions" refer to feedback provided by users, including their experiences, impressions, and suggestions for product improvement.

[0487] A "wide-area communication network" refers to a communication infrastructure that connects over a wide area, such as the internet.

[0488] The system for realizing this invention consists of a server, a user terminal, and a wide-area communication network. The server's primary role is to acquire software code. It establishes an access point in the data management system and retrieves the software code from the code repository. Next, the server uses a static analysis tool to analyze the acquired code. This analysis extracts the functionality of the operations and error patterns. Using this analysis data, a generative AI model generates natural language text. This automatically generates user manuals and FAQs.

[0489] The server also utilizes rich media generation capabilities to create diagrams and videos illustrating operating procedures. The generated content is integrated into a management system on the server and distributed to users' terminals via a wide-area communication network. This ensures that users always have access to the latest information.

[0490] As a concrete example, for newly introduced home appliances, the server automatically generates an instruction manual based on the product's technical data. In this case, an example of a prompt message would be: "Product Name: Smart Cooker\nDescription: Multifunctional cooking device\nFunctions: Temperature control function, built-in timer function." This allows users to quickly obtain detailed information about the product.

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The server accesses the software code repository via a wide-area network to retrieve the latest software code. During this process, the server periodically monitors the repository to detect new code commits. The input is the latest software code, and this code is downloaded to the server as output.

[0494] Step 2:

[0495] The server performs static analysis on the acquired software code. Using a static analysis tool, it analyzes the code and extracts operational functions and error patterns. In this process, the input is the acquired software code, and the output is a list of operational functions and error patterns.

[0496] Step 3:

[0497] The server uses a generative AI model to generate natural language text based on a list of functions and error patterns obtained from static analysis. Prompts are used to instruct the AI ​​model to generate the text. The input is a list of functions and error patterns, and the output is text such as a user manual or FAQ.

[0498] Step 4:

[0499] The server uses a rich media generation tool to generate diagrams and videos that visually explain the operating procedures. Visual materials are created using image processing and video generation technologies. The input is the content and procedure details of the user manual, and the output is the generated diagrams and videos.

[0500] Step 5:

[0501] The server integrates the generated natural language text and rich media into the management system. At this stage, the server organizes the content metadata and converts it into a deliverable format. The input is the generated text and rich media, and the output is the content integrated within the management system.

[0502] Step 6:

[0503] The server distributes content integrated into the management system to user terminals via a wide-area network. It efficiently distributes content, taking into account display and access on user terminals. The input is content integrated into the management system, and the output is information provided in a format accessible to the user's terminal.

[0504] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0505] This invention improves the user experience in a system for generating and updating user manuals and FAQs by incorporating an emotion engine that recognizes user emotions. This system acquires and analyzes source code, automatically generates user manuals and FAQs, and simultaneously recognizes user emotions in real time using the emotion engine.

[0506] First, the server retrieves the latest code from the source code repository and analyzes it using static analysis tools. This extracts operational functions and error conditions, which are then used to generate user manuals and FAQs in natural language. Furthermore, rich content including images and videos is also generated, enabling the provision of easy-to-understand information to users.

[0507] Next, the server uses an emotion engine to recognize the user's emotions while viewing the documents. Based on this emotion data, the content of manuals and FAQs is dynamically adjusted. Specifically, if the user expresses anxiety or confusion, more detailed explanations or additional examples are provided. In this way, flexible information can be provided in response to the user's emotions.

[0508] For example, if the AI ​​detects stress from the user's facial expressions or voice while they are viewing a manual on their device, the server will automatically display relevant FAQs and hints, and suggest video tutorials to help the user understand. This allows users to solve problems more smoothly and improves their product experience.

[0509] In addition, the server accumulates user feedback based on emotions, and over the long term, this data is analyzed to continuously improve and optimize the content of manuals and FAQs. This will enable the provision of more appropriate content in future updates.

[0510] By combining these functions, the present invention can provide personalized information tailored to user needs and improve product satisfaction.

[0511] The following describes the processing flow.

[0512] Step 1:

[0513] The server selects a specific branch from the source code repository and downloads the latest source code. This allows the server to obtain the development progress that forms the basis for analysis.

[0514] Step 2:

[0515] The server analyzes the retrieved source code using a static analysis tool. This analysis extracts the structure of functions and classes within the code, the features available to the user, and the conditions under which errors may occur.

[0516] Step 3:

[0517] The server inputs the extracted information into a generation AI model, which automatically generates a user manual and FAQ in natural language. During this generation process, paragraph structure and terminology explanations are also included to ensure user comprehension.

[0518] Step 4:

[0519] The server automatically generates images and videos using a rich content generation tool to visually illustrate operating procedures. This makes it possible to add visual aids to the manual.

[0520] Step 5:

[0521] The server uploads the generated manuals and rich content to the management system and distributes them to the documentation site and portal. This ensures that users can always access the latest information.

[0522] Step 6:

[0523] When users view manuals or FAQs on their devices, an emotion engine is activated to monitor their emotions in real time. It analyzes the user's emotions from their facial expressions and voice input, and sends that data to a server.

[0524] Step 7:

[0525] The server analyzes emotional data and dynamically adjusts the content of manuals and FAQs based on the user's emotional state. For example, it provides additional explanations or tutorial videos where the user finds something difficult.

[0526] Step 8:

[0527] Users refer to the tailored manual and use support content to resolve any issues they encounter while using the product. By sending feedback to the server, the system collects data for continuous improvement.

[0528] Step 9:

[0529] The server collects user feedback based on emotions and analyzes long-term trends to help optimize future manuals and FAQs. The results of the emotion data analysis will be reflected in the next content update.

[0530] (Example 2)

[0531] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0532] Traditional user manual and FAQ generation systems lacked the ability to automatically adapt and improve content based on source code updates and user feedback. Furthermore, they lacked mechanisms to provide information tailored to individual user emotional states, making them insufficient for improving the quality of the user experience. As a result, they failed to effectively address user problems, leading to decreased product satisfaction.

[0533] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0534] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operation functions and error conditions, means for automatically generating a user manual and FAQ in natural language based on the generated data, means for automatically generating visual information and videos of operation procedures, means for integrating and supplying the generated content to an information management means, means for recognizing the user's emotional state, and means for dynamically adjusting the content based on the emotional state. This enables the flexible provision of information based on the user's emotional state and the generation of adaptive content that utilizes feedback.

[0535] "Source code" is a text-based description of a program that explains how software works.

[0536] "Means of acquisition" refers to the process or function of retrieving source code from a repository using networks or other data transfer technologies.

[0537] "Means of analysis" refers to the function of statically inspecting software code and extracting information such as operational functions and error conditions.

[0538] "Methods for automatically generating text in natural language" refers to a function that outputs text such as documents in natural language that humans can understand.

[0539] "Means for automatically generating visual information and videos" refers to a function that generates media content, including images and audio, to make the operating procedures easier to understand.

[0540] "Information management means" refers to the process or function for organizing generated content and appropriately maintaining and distributing it within the system.

[0541] "Means of recognition" refers to technologies or functions that perceive and analyze a user's facial expressions, voice, and other elements to identify their emotional state.

[0542] "Dynamic adjustment" refers to a function that changes and optimizes the content presented in real time in response to the user's emotional state and feedback.

[0543] This invention is a system that automatically generates user manuals and FAQs and dynamically adjusts the content according to the user's emotions. This system consists of the following main components.

[0544] The server retrieves the latest source code from a source code management system (e.g., a version control system) via network communication. The retrieved source code is analyzed using static analysis tools such as SonarQube or ESLint to extract information such as operational functions and error conditions. Based on this information, a generative AI model such as OpenAI's GPT-3 is used to automatically generate a user manual and FAQ in natural language. It is also possible to generate images and videos that visually demonstrate the operating procedures using media editing software such as Adobe Premiere Pro.

[0545] The device uses its camera and microphone to collect facial and audio data as the user views content, and uses this data to recognize the user's emotions. This utilizes emotion recognition technologies such as Microsoft Azure's Emotion API. Based on this emotion data, the displayed content can be adjusted in real time. If the user appears confused, more detailed explanations or visual examples are presented.

[0546] A concrete example of this is when a user is using a cooking app. If the user shows difficulty with the instructions while referring to the manual, the emotion engine recognizes this emotion, and the server immediately displays relevant FAQs or step-by-step video tutorials. This makes it easier for the user to understand the cooking process smoothly, improving the app's user experience.

[0547] As an example of a prompt, using the sentence, "Generate what kind of explanations and video content would be helpful when a user is looking at a cake recipe in a cooking app," allows the generative AI model to adopt a stance of generating appropriate information and content.

[0548] This system enables flexible information delivery tailored to the user's emotions, significantly improving the product user experience.

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] The server retrieves the latest source code from the source code management system. It uses the repository URL and authentication information as input and downloads the source code using Git or other version control tools. The output is a complete set of source code extracted to a local directory.

[0552] Step 2:

[0553] The server analyzes the acquired source code using a static analysis tool. Using analysis tools such as SonarQube or ESLint, it takes the source code as input and extracts code operation functions and error conditions. The output is obtained as an analysis report and extracted information. This is formatted as a function list and error list and passed on to the next process.

[0554] Step 3:

[0555] The server automatically generates user manuals and FAQs using a generative AI model. The input consists of the analysis information obtained in step 2 and the prompt "Please write a description of the functions and errors encountered." The generative AI model constructs a description in natural language, and the output is a user manual and FAQ in a human-readable format. This result is saved as a document file.

[0556] Step 4:

[0557] The server automatically generates visual information and videos of operating procedures. Input includes detailed information about functions and operating procedures, as well as media editing software such as Adobe Premiere Pro. An automated script creates videos and images based on the operating procedures. The output is a visually rich content file, allowing users to understand the operations more intuitively.

[0558] Step 5:

[0559] The device recognizes emotions as the user views a document. It acquires audio and facial expression data via the camera and microphone as input and sends it to an emotion recognition API. The output is data on the user's current emotional state. Based on this data, the content is dynamically adjusted in the next step.

[0560] Step 6:

[0561] The server dynamically adjusts content based on the user's emotional state. It takes state information from an emotion recognition API as input and presents corresponding additional information or video tutorials. The output is displayed on the device as adjusted content, allowing users to feel secure and efficiently access the information they need.

[0562] Through this series of processes, the system provides information tailored to user needs in real time, improving the overall user experience. Furthermore, the accumulated feedback data is used for future improvements.

[0563] (Application Example 2)

[0564] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] Traditional user manuals and FAQs are static, making it difficult to provide information tailored to the user's emotions and level of understanding. In particular, when purchasing products in physical stores, users often experience anxiety and confusion if they are unsure how to use the product, which negatively impacts their satisfaction with the product.

[0566] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0567] In this invention, the server includes means for obtaining source code, means for analyzing the obtained source code to extract operation functions and error conditions, means for natural language generation to automatically generate user guides and FAQs based on the generated data, and means for dynamically adjusting content using an emotion engine that recognizes the user's emotions. This enables the provision of personalized information in accordance with the user's emotions, thereby improving user satisfaction with the product.

[0568] "Source code" is a set of instructions in text format that describes how a computer program works.

[0569] "Analysis" is the process of breaking down data and information to reveal their characteristics and relationships.

[0570] "Operational functions" refer to the basic actions and roles that users can utilize when using software.

[0571] An "error condition" refers to a specific situation or input that prevents the software from functioning correctly.

[0572] "Generation" is the process of creating new content or deliverables using data and information.

[0573] "Natural language generation" is a technology that allows computers to create text that is readable in human language.

[0574] "Rich content" refers to content that includes a variety of media elements, such as text, images, and videos.

[0575] A "management system" is software used to organize information and data in an orderly manner and to utilize them as needed.

[0576] An "emotion engine" is a software technology used to analyze and recognize a user's emotions.

[0577] "Dynamic adjustment" means changing the content or operation in real time according to specific conditions.

[0578] "Feedback" refers to the opinions and evaluations received from users, and is information used to improve products and services.

[0579] "Personalization" means optimizing content to provide experiences and services tailored to individual users.

[0580] Embodiments of this invention utilize a system that combines specific elements to improve the user experience. First, a server retrieves source code from a database and uses an analysis tool to extract operation functions and error conditions. Next, based on the extracted information, natural language generation software is used to generate a user manual and FAQ. This also includes a rich content generation tool, which automatically generates images and videos related to the operation procedures.

[0581] In addition, an emotion engine operates on the device side, using the camera and microphone to recognize emotions from the user's facial expressions and vocalizations while they are viewing the manual. This emotion data is sent to the server in real time, and the server dynamically adjusts the content based on this data. For example, if the user is confused, it will be presented with relevant FAQs or additional video tutorials.

[0582] The hardware and software used by the server for emotion recognition include the smartphone's camera and microphone. The emotion engine utilizes Microsoft Azure's Emotion API. OpenAI's GPT-3 is used as the generative AI model. This allows the system to generate responses that correspond to the user's emotions.

[0583] A concrete example is when a user is using a coffee maker purchased from a physical store and becomes confused when the machine doesn't work properly. In this case, the application on the device automatically displays a video guide with detailed operating instructions.

[0584] An example of a prompt for a generative AI model is, "Explain how to use a modern coffee maker step-by-step for beginners."

[0585] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0586] Step 1:

[0587] The server retrieves the latest source code from the source code repository. The input is source code data from the repository, and the output is the retrieved source code. Specifically, the server accesses the repository via a network connection and downloads the source code using authentication credentials.

[0588] Step 2:

[0589] The server analyzes the source code it has retrieved. The input is the retrieved source code, and the output is the operational functions and error conditions as a result of the analysis. Specifically, the server uses a static analysis tool to scan the code and extract the usage of specific APIs and functions from it.

[0590] Step 3:

[0591] The server generates a user manual and FAQ in natural language based on the analysis results. The input is the analysis results, and the output is manual and FAQ content in natural language format. Specifically, the server uses a generation AI model to explain the operating procedures in natural language and create the FAQ.

[0592] Step 4:

[0593] The server generates rich content. The input is the analysis results, and the output is rich content in the form of images and videos. Specifically, the server uses image generation tools and video editing software to automatically generate content that visually explains the procedure.

[0594] Step 5:

[0595] The device recognizes the user's emotions. The input is the user's facial expressions and voice data, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to record the user's facial expressions and capture their voice. Then, an emotion engine analyzes this data to determine the user's emotions.

[0596] Step 6:

[0597] The server dynamically adjusts content based on the emotion data it recognizes. The input is emotion data, and the output is the adjusted content. Specifically, the server sends a prompt message to the generating AI model, "If the user is anxious, provide a detailed tutorial," and then provides the resulting content.

[0598] Step 7:

[0599] The device displays content tailored to the user. The input is the tailored content, and the output is information provided to the user. Specifically, the device launches a video playback application and displays a tutorial video received from the server.

[0600] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0601] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0602] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0603] [Fourth Embodiment]

[0604] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0605] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0606] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0607] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0608] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0609] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0610] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0611] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0612] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0613] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0614] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0615] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0616] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0617] This invention is a system for effectively and efficiently generating and updating manuals and FAQs for software products. This system extracts necessary information from source code, processes and formats it, and provides it to the user.

[0618] First, the server accesses the source code repository to retrieve the latest code. This ensures that the latest features and changes are always reflected. Next, the server uses static analysis tools to analyze the retrieved source code and extract features available to the user and possible error conditions. Based on this analysis information, the server uses a generative AI model to generate natural language text and create manuals and FAQs in a user-friendly format.

[0619] For example, it can automatically generate operating procedures for specific functions, including explanations of potential errors users might encounter. Furthermore, the server utilizes rich content generation technology to create images and videos to complement the instructions. This allows for visual communication, aiding user understanding.

[0620] The generated manuals and FAQs are ultimately distributed to a web portal and documentation site managed by the server. This ensures that users always have access to the latest documentation. Furthermore, users can utilize the provided information to use the product more effectively and submit feedback. The server then uses this feedback to make further improvements and updates.

[0621] As a concrete example, when a new software version is released, the relevant manual sections can be automatically updated based only on the code changes, and the updated content can be visualized and provided in a video with narration. In this way, the traditional manual documentation creation and updating work can be significantly reduced, and users can always access the latest information.

[0622] The following describes the processing flow.

[0623] Step 1:

[0624] The server accesses the source code repository and clones the latest source code from a specific repository or branch. This allows it to obtain the most up-to-date version of the code to be analyzed.

[0625] Step 2:

[0626] The server analyzes the retrieved source code using static analysis tools. In this process, it reads function and class definitions and documentation comments to understand the features available to the user and the overall structure of the system.

[0627] Step 3:

[0628] The server extracts a list of functions and error conditions from the analysis results. This includes identifying what inputs a function requires, what outputs it produces, and what errors may occur.

[0629] Step 4:

[0630] The server uses a generative AI model to generate natural language documentation based on extracted functionality and error information. This includes the process of creating user manuals and FAQs.

[0631] Step 5:

[0632] The server generates images and videos to visually represent the operating procedures based on the generated text content. This uses screen capture and animation creation technologies.

[0633] Step 6:

[0634] The server integrates the generated documents and rich content into the management system and distributes them to web portals and document sites. This process ensures that users have access to the latest information.

[0635] Step 7:

[0636] The server monitors changes to the source code, and if a change is detected, it reparses only the affected sections of the manual and updates only the necessary parts.

[0637] Step 8:

[0638] Users can learn how to use the product by viewing the publicly available manuals and FAQs. Furthermore, they can submit feedback regarding the manual content to the system.

[0639] Step 9:

[0640] The server receives feedback from users, analyzes it, and then uses the results to further improve the content of manuals and FAQs, which will be reflected in the next update.

[0641] (Example 1)

[0642] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] Creating and updating manuals and FAQs for traditional software products is largely a manual process, requiring considerable time and effort. Furthermore, the information may not always be up-to-date, potentially preventing the provision of adequate support to users. Additionally, it is difficult to quickly incorporate user feedback and continuously improve the quality of the documentation.

[0644] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0645] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operational functions and error conditions, and means for inputting prompts to a generated AI model based on the extracted information. This enables the automatic generation and updating of manuals and FAQs, as well as the provision of visually rich content.

[0646] "Source code" refers to a set of text-based instructions written by a programmer to specify the structure and functionality of a program.

[0647] "Analysis" is the process by which a system identifies specific elements or structures within source code and extracts information from them.

[0648] A "generative AI model" refers to a machine learning algorithm trained to generate natural language text and has the ability to create documents based on prompts.

[0649] A "prompt" is text data containing information and instructions that are input to a generative AI model, including questions and commands to obtain the desired output.

[0650] "Rich content" refers to multimedia information that includes not only static text but also visual elements such as images and videos.

[0651] "Feedback" refers to information provided by users, including opinions and requests for improvement, which is used to improve the system.

[0652] This invention relates to a system for effectively and automatically generating and updating user manuals and FAQs for software products, with a server playing a central role in achieving this.

[0653] First, the server accesses the source code repository (e.g., version control system) to retrieve the latest source code. During this process, the server utilizes a stable network connection to ensure that the latest software changes are reflected. The retrieved source code is then analyzed using known static analysis tools (e.g., SonarQube, ESLint). Through this analysis, the server extracts user-available functions and potential error conditions from the source code.

[0654] Next, the server generates prompts to input into the AI ​​model (e.g., a natural language generation algorithm). Based on the generated prompts, the AI ​​model generates the text necessary for creating user manuals and FAQs in natural language. Through this process, the server can provide documents that are easy for users without specialized technical knowledge to understand. For example, it might generate a prompt such as, "Please explain the specific operating procedure for new feature X. This feature is designed to simplify data filtering."

[0655] Furthermore, the server uses image and video editing software to create rich content based on the generated text. This rich content includes screencast videos explaining operating procedures and infographics illustrating important functions. By creating rich content, users can more easily grasp information visually, and understanding complex operations and errors is facilitated.

[0656] Ultimately, the server integrates and distributes the generated manuals and rich content into a dedicated web portal and document management system. This system allows the server to continuously provide users with the most up-to-date information. Users can refer to these documents to effectively utilize the product and send feedback to the server. This feedback is used by the server to make further improvements.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The server accesses the source code repository to retrieve the latest source code. It uses the repository URL and access key as input. The retrieved source code is stored as a dataset and used as the basis for the next analysis step. The server automates this process and ensures data up-to-dateness by recording timestamps.

[0660] Step 2:

[0661] The server analyzes the acquired source code using a static analysis tool. This step uses the acquired source code as input. During the analysis, the server detects functions and classes within the code and extracts their operational functions and error conditions. The output is a set of extracted information for use in the next step. This information provides the data necessary for the automatic generation of user manuals and FAQs.

[0662] Step 3:

[0663] The server generates prompts for input into the generated AI model based on the analysis results. The input here is the analysis data from step 2. The server creates prompts expressed in natural language, taking into account the detected functions and error conditions. The output is a text-based prompt statement used in the next step. This prompt serves as a guideline for determining the content of the user manual and FAQ.

[0664] Step 4:

[0665] The server passes the generated prompts to an AI model to produce user manuals and FAQ documents. The input is the prompt text, and the output is a document expressed as natural language text. In this step, the server, with the help of the generative AI model, creates explanatory text in a format easily understandable even to users without technical knowledge. The generated text includes operating procedures and error handling.

[0666] Step 5:

[0667] The server creates rich content based on the generated text. The input is the text information obtained in step 4. The server uses image and video editing tools to create diagrams and screencasts to visually supplement the text explanations. The output is rich content that includes this visual information, improving the quality of information provided to the user. This content is incorporated into user manuals and FAQs.

[0668] Step 6:

[0669] The server delivers all generated content to the web portal and document management system. The input consists of all documents, including the rich content generated in step 5. The output is published in a user-accessible format, and an interface for receiving feedback is also provided. This allows the server to continuously update and improve the content based on user feedback.

[0670] (Application Example 1)

[0671] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0672] In traditional software products, creating user manuals and FAQs was often done manually, leading to slow updates and making it difficult to provide users with the latest information. Similarly, updating product information and instruction manuals on e-commerce sites was time-consuming, making it difficult to provide customers with up-to-date information. This resulted in users being unable to obtain accurate information, hindering improvements in the user experience and causing delays in customer service for businesses.

[0673] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0674] In this invention, the server includes means for acquiring software code, means for analyzing the acquired software code to extract operation functions and error patterns, and natural language generation means for automatically generating documents and Q&A collections based on the generated data. This enables the automatic generation and updating of documents during software updates, making it possible to quickly provide users with the latest and most accurate information. Furthermore, the automatic generation of instruction manuals based on product data on e-commerce sites speeds up customer service and improves user convenience.

[0675] "Software code" is a set of instructions written in a computer language to dictate the operation of a computer program.

[0676] "Operational functions" refer to the means by which users perform specific actions and tasks through software.

[0677] An "error pattern" refers to typical examples or characteristics of abnormal conditions or malfunctions that can occur in the operation of software.

[0678] "Natural language generation means" refers to a method or apparatus for generating natural-sounding, human-readable text from structured data using computer technology.

[0679] A "rich media generation means" is a method or apparatus for generating advanced content (e.g., images and videos) that combines visual and auditory elements.

[0680] "Product data" refers to a collection of information including product attributes and specifications, which forms the basis for instruction manuals and Q&A.

[0681] "Opinions" refer to feedback provided by users, including their experiences, impressions, and suggestions for product improvement.

[0682] A "wide-area communication network" refers to a communication infrastructure that connects over a wide area, such as the internet.

[0683] The system for realizing this invention consists of a server, a user terminal, and a wide-area communication network. The server's primary role is to acquire software code. It establishes an access point in the data management system and retrieves the software code from the code repository. Next, the server uses a static analysis tool to analyze the acquired code. This analysis extracts the functionality of the operations and error patterns. Using this analysis data, a generative AI model generates natural language text. This automatically generates user manuals and FAQs.

[0684] The server also utilizes rich media generation capabilities to create diagrams and videos illustrating operating procedures. The generated content is integrated into a management system on the server and distributed to users' terminals via a wide-area communication network. This ensures that users always have access to the latest information.

[0685] As a concrete example, for newly introduced home appliances, the server automatically generates an instruction manual based on the product's technical data. In this case, an example of a prompt message would be: "Product Name: Smart Cooker\nDescription: Multifunctional cooking device\nFunctions: Temperature control function, built-in timer function." This allows users to quickly obtain detailed information about the product.

[0686] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0687] Step 1:

[0688] The server accesses the software code repository via a wide-area network to retrieve the latest software code. During this process, the server periodically monitors the repository to detect new code commits. The input is the latest software code, and this code is downloaded to the server as output.

[0689] Step 2:

[0690] The server performs static analysis on the acquired software code. Using a static analysis tool, it analyzes the code and extracts operational functions and error patterns. In this process, the input is the acquired software code, and the output is a list of operational functions and error patterns.

[0691] Step 3:

[0692] The server uses a generative AI model to generate natural language text based on a list of functions and error patterns obtained from static analysis. Prompts are used to instruct the AI ​​model to generate the text. The input is a list of functions and error patterns, and the output is text such as a user manual or FAQ.

[0693] Step 4:

[0694] The server uses a rich media generation tool to generate diagrams and videos that visually explain the operating procedures. Visual materials are created using image processing and video generation technologies. The input is the content and procedure details of the user manual, and the output is the generated diagrams and videos.

[0695] Step 5:

[0696] The server integrates the generated natural language text and rich media into the management system. At this stage, the server organizes the content metadata and converts it into a deliverable format. The input is the generated text and rich media, and the output is the content integrated within the management system.

[0697] Step 6:

[0698] The server distributes content integrated into the management system to user terminals via a wide-area network. It efficiently distributes content, taking into account display and access on user terminals. The input is content integrated into the management system, and the output is information provided in a format accessible to the user's terminal.

[0699] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0700] This invention improves the user experience in a system for generating and updating user manuals and FAQs by incorporating an emotion engine that recognizes user emotions. This system acquires and analyzes source code, automatically generates user manuals and FAQs, and simultaneously recognizes user emotions in real time using the emotion engine.

[0701] First, the server retrieves the latest code from the source code repository and analyzes it using static analysis tools. This extracts operational functions and error conditions, which are then used to generate user manuals and FAQs in natural language. Furthermore, rich content including images and videos is also generated, enabling the provision of easy-to-understand information to users.

[0702] Next, the server uses an emotion engine to recognize the user's emotions while viewing the documents. Based on this emotion data, the content of manuals and FAQs is dynamically adjusted. Specifically, if the user expresses anxiety or confusion, more detailed explanations or additional examples are provided. In this way, flexible information can be provided in response to the user's emotions.

[0703] For example, if the AI ​​detects stress from the user's facial expressions or voice while they are viewing a manual on their device, the server will automatically display relevant FAQs and hints, and suggest video tutorials to help the user understand. This allows users to solve problems more smoothly and improves their product experience.

[0704] In addition, the server accumulates user feedback based on emotions, and over the long term, this data is analyzed to continuously improve and optimize the content of manuals and FAQs. This will enable the provision of more appropriate content in future updates.

[0705] By combining these functions, the present invention can provide personalized information tailored to user needs and improve product satisfaction.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] The server selects a specific branch from the source code repository and downloads the latest source code. This allows the server to obtain the development progress that forms the basis for analysis.

[0709] Step 2:

[0710] The server analyzes the retrieved source code using a static analysis tool. This analysis extracts the structure of functions and classes within the code, the features available to the user, and the conditions under which errors may occur.

[0711] Step 3:

[0712] The server inputs the extracted information into a generation AI model, which automatically generates a user manual and FAQ in natural language. During this generation process, paragraph structure and terminology explanations are also included to ensure user comprehension.

[0713] Step 4:

[0714] The server automatically generates images and videos using a rich content generation tool to visually illustrate operating procedures. This makes it possible to add visual aids to the manual.

[0715] Step 5:

[0716] The server uploads the generated manuals and rich content to the management system and distributes them to the documentation site and portal. This ensures that users can always access the latest information.

[0717] Step 6:

[0718] When users view manuals or FAQs on their devices, an emotion engine is activated to monitor their emotions in real time. It analyzes the user's emotions from their facial expressions and voice input, and sends that data to a server.

[0719] Step 7:

[0720] The server analyzes emotional data and dynamically adjusts the content of manuals and FAQs based on the user's emotional state. For example, it provides additional explanations or tutorial videos where the user finds something difficult.

[0721] Step 8:

[0722] Users refer to the tailored manual and use support content to resolve any issues they encounter while using the product. By sending feedback to the server, the system collects data for continuous improvement.

[0723] Step 9:

[0724] The server collects user feedback based on emotions and analyzes long-term trends to help optimize future manuals and FAQs. The results of the emotion data analysis will be reflected in the next content update.

[0725] (Example 2)

[0726] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0727] Traditional user manual and FAQ generation systems lacked the ability to automatically adapt and improve content based on source code updates and user feedback. Furthermore, they lacked mechanisms to provide information tailored to individual user emotional states, making them insufficient for improving the quality of the user experience. As a result, they failed to effectively address user problems, leading to decreased product satisfaction.

[0728] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0729] In this invention, the server includes means for acquiring source code, means for analyzing the acquired source code to extract operation functions and error conditions, means for automatically generating a user manual and FAQ in natural language based on the generated data, means for automatically generating visual information and videos of operation procedures, means for integrating and supplying the generated content to an information management means, means for recognizing the user's emotional state, and means for dynamically adjusting the content based on the emotional state. This enables the flexible provision of information based on the user's emotional state and the generation of adaptive content that utilizes feedback.

[0730] "Source code" is a text-based description of a program that explains how software works.

[0731] "Means of acquisition" refers to the process or function of retrieving source code from a repository using networks or other data transfer technologies.

[0732] "Means of analysis" refers to the function of statically inspecting software code and extracting information such as operational functions and error conditions.

[0733] "Methods for automatically generating text in natural language" refers to a function that outputs text such as documents in natural language that humans can understand.

[0734] "Means for automatically generating visual information and videos" refers to a function that generates media content, including images and audio, to make the operating procedures easier to understand.

[0735] "Information management means" refers to the process or function for organizing generated content and appropriately maintaining and distributing it within the system.

[0736] "Means of recognition" refers to technologies or functions that perceive and analyze a user's facial expressions, voice, and other elements to identify their emotional state.

[0737] "Dynamic adjustment" refers to a function that changes and optimizes the content presented in real time in response to the user's emotional state and feedback.

[0738] This invention is a system that automatically generates user manuals and FAQs and dynamically adjusts the content according to the user's emotions. This system consists of the following main components.

[0739] The server retrieves the latest source code from a source code management system (e.g., a version control system) via network communication. The retrieved source code is analyzed using static analysis tools such as SonarQube or ESLint to extract information such as operational functions and error conditions. Based on this information, a generative AI model such as OpenAI's GPT-3 is used to automatically generate a user manual and FAQ in natural language. It is also possible to generate images and videos that visually demonstrate the operating procedures using media editing software such as Adobe Premiere Pro.

[0740] The device uses its camera and microphone to collect facial and audio data as the user views content, and uses this data to recognize the user's emotions. This utilizes emotion recognition technologies such as Microsoft Azure's Emotion API. Based on this emotion data, the displayed content can be adjusted in real time. If the user appears confused, more detailed explanations or visual examples are presented.

[0741] A concrete example of this is when a user is using a cooking app. If the user shows difficulty with the instructions while referring to the manual, the emotion engine recognizes this emotion, and the server immediately displays relevant FAQs or step-by-step video tutorials. This makes it easier for the user to understand the cooking process smoothly, improving the app's user experience.

[0742] As an example of a prompt, using the sentence, "Generate what kind of explanations and video content would be helpful when a user is looking at a cake recipe in a cooking app," allows the generative AI model to adopt a stance of generating appropriate information and content.

[0743] This system enables flexible information delivery tailored to the user's emotions, significantly improving the product user experience.

[0744] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0745] Step 1:

[0746] The server retrieves the latest source code from the source code management system. It uses the repository URL and authentication information as input and downloads the source code using Git or other version control tools. The output is a complete set of source code extracted to a local directory.

[0747] Step 2:

[0748] The server analyzes the acquired source code using a static analysis tool. Using analysis tools such as SonarQube or ESLint, it takes the source code as input and extracts code operation functions and error conditions. The output is obtained as an analysis report and extracted information. This is formatted as a function list and error list and passed on to the next process.

[0749] Step 3:

[0750] The server automatically generates user manuals and FAQs using a generative AI model. The input consists of the analysis information obtained in step 2 and the prompt "Please write a description of the functions and errors encountered." The generative AI model constructs a description in natural language, and the output is a user manual and FAQ in a human-readable format. This result is saved as a document file.

[0751] Step 4:

[0752] The server automatically generates visual information and videos of operating procedures. Input includes detailed information about functions and operating procedures, as well as media editing software such as Adobe Premiere Pro. An automated script creates videos and images based on the operating procedures. The output is a visually rich content file, allowing users to understand the operations more intuitively.

[0753] Step 5:

[0754] The device recognizes emotions as the user views a document. It acquires audio and facial expression data via the camera and microphone as input and sends it to an emotion recognition API. The output is data on the user's current emotional state. Based on this data, the content is dynamically adjusted in the next step.

[0755] Step 6:

[0756] The server dynamically adjusts content based on the user's emotional state. It takes state information from an emotion recognition API as input and presents corresponding additional information or video tutorials. The output is displayed on the device as adjusted content, allowing users to feel secure and efficiently access the information they need.

[0757] Through this series of processes, the system provides information tailored to user needs in real time, improving the overall user experience. Furthermore, the accumulated feedback data is used for future improvements.

[0758] (Application Example 2)

[0759] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0760] Traditional user manuals and FAQs are static, making it difficult to provide information tailored to the user's emotions and level of understanding. In particular, when purchasing products in physical stores, users often experience anxiety and confusion if they are unsure how to use the product, which negatively impacts their satisfaction with the product.

[0761] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0762] In this invention, the server includes means for obtaining source code, means for analyzing the obtained source code to extract operation functions and error conditions, means for natural language generation to automatically generate user guides and FAQs based on the generated data, and means for dynamically adjusting content using an emotion engine that recognizes the user's emotions. This enables the provision of personalized information in accordance with the user's emotions, thereby improving user satisfaction with the product.

[0763] "Source code" is a set of instructions in text format that describes how a computer program works.

[0764] "Analysis" is the process of breaking down data and information to reveal their characteristics and relationships.

[0765] "Operational functions" refer to the basic actions and roles that users can utilize when using software.

[0766] An "error condition" refers to a specific situation or input that prevents the software from functioning correctly.

[0767] "Generation" is the process of creating new content or deliverables using data and information.

[0768] "Natural language generation" is a technology that allows computers to create text that is readable in human language.

[0769] "Rich content" refers to content that includes a variety of media elements, such as text, images, and videos.

[0770] A "management system" is software used to organize information and data in an orderly manner and to utilize them as needed.

[0771] An "emotion engine" is a software technology used to analyze and recognize a user's emotions.

[0772] "Dynamic adjustment" means changing the content or operation in real time according to specific conditions.

[0773] "Feedback" refers to the opinions and evaluations received from users, and is information used to improve products and services.

[0774] "Personalization" means optimizing content to provide experiences and services tailored to individual users.

[0775] Embodiments of this invention utilize a system that combines specific elements to improve the user experience. First, a server retrieves source code from a database and uses an analysis tool to extract operation functions and error conditions. Next, based on the extracted information, natural language generation software is used to generate a user manual and FAQ. This also includes a rich content generation tool, which automatically generates images and videos related to the operation procedures.

[0776] In addition, an emotion engine operates on the device side, using the camera and microphone to recognize emotions from the user's facial expressions and vocalizations while they are viewing the manual. This emotion data is sent to the server in real time, and the server dynamically adjusts the content based on this data. For example, if the user is confused, it will be presented with relevant FAQs or additional video tutorials.

[0777] The hardware and software used by the server for emotion recognition include the smartphone's camera and microphone. The emotion engine utilizes Microsoft Azure's Emotion API. OpenAI's GPT-3 is used as the generative AI model. This allows the system to generate responses that correspond to the user's emotions.

[0778] A concrete example is when a user is using a coffee maker purchased from a physical store and becomes confused when the machine doesn't work properly. In this case, the application on the device automatically displays a video guide with detailed operating instructions.

[0779] An example of a prompt for a generative AI model is, "Explain how to use a modern coffee maker step-by-step for beginners."

[0780] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0781] Step 1:

[0782] The server retrieves the latest source code from the source code repository. The input is source code data from the repository, and the output is the retrieved source code. Specifically, the server accesses the repository via a network connection and downloads the source code using authentication credentials.

[0783] Step 2:

[0784] The server analyzes the source code it has retrieved. The input is the retrieved source code, and the output is the operational functions and error conditions as a result of the analysis. Specifically, the server uses a static analysis tool to scan the code and extract the usage of specific APIs and functions from it.

[0785] Step 3:

[0786] The server generates a user manual and FAQ in natural language based on the analysis results. The input is the analysis results, and the output is manual and FAQ content in natural language format. Specifically, the server uses a generation AI model to explain the operating procedures in natural language and create the FAQ.

[0787] Step 4:

[0788] The server generates rich content. The input is the analysis results, and the output is rich content in the form of images and videos. Specifically, the server uses image generation tools and video editing software to automatically generate content that visually explains the procedure.

[0789] Step 5:

[0790] The device recognizes the user's emotions. The input is the user's facial expressions and voice data, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to record the user's facial expressions and capture their voice. Then, an emotion engine analyzes this data to determine the user's emotions.

[0791] Step 6:

[0792] The server dynamically adjusts content based on the emotion data it recognizes. The input is emotion data, and the output is the adjusted content. Specifically, the server sends a prompt message to the generating AI model, "If the user is anxious, provide a detailed tutorial," and then provides the resulting content.

[0793] Step 7:

[0794] The device displays content tailored to the user. The input is the tailored content, and the output is information provided to the user. Specifically, the device launches a video playback application and displays a tutorial video received from the server.

[0795] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0796] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0797] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0798] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0799] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0800] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0801] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0802] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0803] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0804] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0805] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0806] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0807] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0808] 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.

[0809] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0810] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0811] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0812] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0813] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0814] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0815] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0816] The following is further disclosed regarding the embodiments described above.

[0817] (Claim 1)

[0818] Means of obtaining the source code,

[0819] A means of analyzing the acquired source code to extract operational functions and error conditions,

[0820] A natural language generation method that automatically generates user manuals and FAQs based on the generated data,

[0821] A rich content generation means that automatically generates images and videos of operating procedures,

[0822] A means of integrating the generated content into a management system and distributing it,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, further comprising means for detecting changes in source code and automatically updating the manual and FAQ based on the changes.

[0826] (Claim 3)

[0827] The system according to claim 1, further comprising means for receiving user feedback and analyzing that feedback to improve the manual and FAQ.

[0828] "Example 1"

[0829] (Claim 1)

[0830] Means of obtaining the source code,

[0831] A means of analyzing the acquired source code to extract operational functions and error conditions,

[0832] A means of inputting prompts to the generated AI model based on the extracted information,

[0833] A natural language generation method that automatically generates user manuals and FAQs based on prompts,

[0834] A rich content generation means that automatically generates images and videos of operating procedures based on the generated text,

[0835] A means of integrating the generated content into a management system and distributing it,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, which detects changes in source code and automatically updates the manual and FAQ based on the changes.

[0839] (Claim 3)

[0840] The system according to claim 1, which receives user feedback, analyzes that feedback, and uses it to improve the manual and FAQ.

[0841] "Application Example 1"

[0842] (Claim 1)

[0843] Means of obtaining software code,

[0844] A means of analyzing the acquired software code to extract the functions and error patterns of the operations,

[0845] A natural language generation method that automatically generates documents and Q&A collections based on generated data,

[0846] A rich media generation means that automatically generates diagrams and videos of operating procedures,

[0847] A means of integrating the generated content into a management system and distributing it over a wide-area communication network,

[0848] A means for acquiring product data and automatically generating documents and Q&A collections based on that data,

[0849] A means of registering acquired documents in a database and managing the information,

[0850] A system that includes this.

[0851] (Claim 2)

[0852] The system according to claim 1, further comprising means for detecting changes in software code and automatically updating documentation and question-and-answer collections based on the changes.

[0853] (Claim 3)

[0854] The system according to claim 1, further comprising means for receiving user feedback, analyzing that feedback, and improving documents and Q&A collections.

[0855] "Example 2 of combining an emotion engine"

[0856] (Claim 1)

[0857] Means of obtaining the source code,

[0858] A means of analyzing the acquired source code to extract operational functions and error conditions,

[0859] A means for automatically generating user manuals and FAQs in natural language based on the generated data,

[0860] A means for automatically generating visual information and videos of operating procedures,

[0861] A means for integrating and supplying the generated content to an information management system,

[0862] A means of recognizing the user's emotional state,

[0863] A means of dynamically adjusting content based on emotional state,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising means for detecting changes in source code and automatically updating the manual and FAQ based on the changes.

[0867] (Claim 3)

[0868] The system according to claim 1, further comprising means for receiving user feedback based on their emotional state and analyzing that feedback to improve the manual and FAQ.

[0869] "Application example 2 when combining with an emotional engine"

[0870] (Claim 1)

[0871] Means of obtaining the source code,

[0872] A means of analyzing the acquired source code to extract operational functions and error conditions,

[0873] A natural language generation method that automatically generates user guides and FAQs based on the generated data,

[0874] A rich content generation means that automatically generates images and videos of operating procedures,

[0875] A means of integrating the generated content into a management system and distributing it,

[0876] A means of dynamically adjusting content using an emotion engine that recognizes the user's emotions,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising means for detecting changes in source code and automatically updating guides and FAQs based on the changes.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising means for collecting user feedback and analyzing that feedback to improve guides and FAQs. [Explanation of symbols]

[0882] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining the source code, A means of analyzing the acquired source code to extract operational functions and error conditions, A natural language generation method that automatically generates user manuals and FAQs based on the generated data, A rich content generation means that automatically generates images and videos of operating procedures, A means of integrating the generated content into a management system and distributing it, A system that includes this.

2. The system according to claim 1, further comprising means for detecting changes in source code and automatically updating the manual and FAQ based on the changes.

3. The system according to claim 1, further comprising means for receiving user feedback and analyzing that feedback to improve the manual and FAQ.

Images