system

Abstract

We provide the system. [Solution] The information processing device includes means for receiving program code, A method for analyzing program code using a generative model and automatically generating specifications, Based on automatically generated specifications, a risk analysis is performed, and a method is proposed to identify the locations and methods for operational verification. A means of providing the generated specifications in a predetermined format, A system that includes this.

Description

Technical Field

[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] Many companies have a problem that a great deal of man-hours are required for creating and updating a specification document when newly creating or modifying program code. In addition, the creation of a specification document by a human hand may be inaccurate, consuming the company's resources wastefully and, as a result, imposing an unnecessary burden on developers. There is a demand for measures to streamline such a situation and ensure quality.

Means for Solving the Problems

[0005] This invention provides a system that uses an information processing device to receive program code, analyze it using a generative model, and automatically generate specifications. Based on the automatically generated specifications, a risk analysis is performed, and the system's operational verification points and implementation methods are proposed. Furthermore, by providing the generated specifications in a format that meets customer requirements, the system streamlines operations and optimizes resources.

[0006] An "information processing device" is a digital computer system that has the functions of receiving, processing, storing, and outputting data.

[0007] "Program code" refers to source code consisting of a set of instructions that a computer can execute, along with accompanying comments.

[0008] A "generative model" is an algorithm or program that uses machine learning techniques to automatically generate text or data.

[0009] "Analysis" is the process of examining given information or data in detail to understand its structure and meaning.

[0010] A "specification document" is a document that describes in detail the functions, structure, operation methods, and other technical information of a system or program.

[0011] "Automatic generation" refers to the process by which systems or software create data or documents without human intervention.

[0012] "Risk analysis" is a method for evaluating potential risks to a system or project and estimating their impact and likelihood of occurrence.

[0013] A "test area" is a specific region or section that requires testing to verify whether a system or program functions as intended.

[0014] "Implementation method" refers to the procedures and techniques for performing specific operations or processes.

[0015] "Predetermined format" refers to a specific structure, format, or form that has been previously agreed upon or determined.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying out the Invention

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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.

[0020] 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.

[0021] 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, etc.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system that uses an information processing device to analyze program code and automatically generate specifications based on that information. This system improves the efficiency of specification creation by performing a series of processes including code reception, analysis, specification generation, risk analysis, and proposal of operation verification methods.

[0038] The server receives program code uploaded by the user from their terminal. This code is analyzed using a generative model within the system. The generative model utilizes natural language processing technology to identify variable names, functions, comments, and control structures within the code, and automatically generates a specification document based on the analysis results. The generated specification document details the system's functions and operational specifications.

[0039] Furthermore, the server performs risk analysis using automatically generated specifications. This risk analysis evaluates the program's complexity and dependencies, identifying parts deemed high-risk. Based on this information, the server suggests areas requiring verification and how to perform them. This allows developers to conduct testing efficiently and effectively.

[0040] A concrete example is the code for an inventory management system. When a user uploads this code to the server, the server automatically generates detailed specifications for functions such as product registration, inventory adjustment, and shipping processing. Furthermore, it identifies processes where inventory discrepancies may occur as high-risk areas and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0041] This system allows users to obtain reliable specifications without hassle, resulting in improved system quality and reduced development time.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user uploads the program code to be analyzed to the server using their device. The server securely receives this code and prepares to store it in its database.

[0045] Step 2:

[0046] The server prepares the received program code for input into the generation model. Here, the code's format is checked and initial errors are performed to prepare it for analysis.

[0047] Step 3:

[0048] The server uses a generative model to analyze program code. The model employs natural language processing techniques to identify variable names, functions, comments, and control structures, and stores this information in a database.

[0049] Step 4:

[0050] The server automatically generates a specification document based on the analyzed data. The generated specification document includes details such as the program's function, structure, interactions, exception handling, and usage examples, and is written in natural language.

[0051] Step 5:

[0052] Based on automatically generated specifications, the server performs a risk analysis. This risk analysis identifies and evaluates parts of the program that contain complex logic or dependencies on external systems.

[0053] Step 6:

[0054] Based on the risk analysis results, the server extracts areas requiring operational verification and proposes specific test scenarios and methods. The proposed test information is reflected in the specifications and presented in a format easily accessible to users.

[0055] Step 7:

[0056] The server ultimately outputs the generated specifications in a format according to the customer's requirements, such as Markdown or PDF, and provides them to the user. This allows the user to effectively utilize the specifications in each phase of project management and development.

[0057] (Example 1)

[0058] 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."

[0059] Modern software development is becoming increasingly complex, making it time-consuming and laborious to create accurate and detailed specifications from program code. Furthermore, even with completed specifications, identifying potential risks and conducting appropriate testing remains challenging, hindering system quality improvement. Therefore, developers are required to efficiently produce high-quality software.

[0060] 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.

[0061] In this invention, the server includes means for an information processing device to receive program code, means for analyzing the program code using a generation AI model and automatically generating specifications using natural language processing technology, and means for evaluating the complexity and dependencies of the program based on the automatically generated specifications, performing risk analysis, and proposing operational verification points and specific implementation methods. As a result, the user can automatically obtain detailed specifications and have specific test cases proposed for high-risk areas.

[0062] An "information processing device" is a hardware or software system used to perform operations such as receiving, analyzing, storing, and outputting data.

[0063] A "generative AI model" is an artificial intelligence model that performs pattern recognition and inference based on given input data (in this case, program code) to execute a specific process (in this case, automatic generation of specifications).

[0064] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language, and is a technology that can efficiently perform language analysis and information extraction.

[0065] A "specification document" is a document that describes the design and operation of a system or software in detail, and serves as a guideline for development and operation.

[0066] "Risk analysis" is the process of identifying potential problems and hazards in a system or project, and evaluating the likelihood and impact of their occurrence.

[0067] A "database" is a system for efficiently storing, searching, and managing data, enabling the permanent retention and rapid retrieval of information.

[0068] This invention improves development efficiency by using an information processing system to analyze program code, automatically generate specifications, and propose risk analysis and operational verification.

[0069] The server receives program code uploaded by the user from their terminal. This code is then analyzed by a generative AI model on the server. The generative AI model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures within the code.

[0070] Next, the server automatically generates a specification document based on the analysis results. This specification document details the system's functions and operational specifications, providing developers with the information necessary to accurately understand the system. The generated specification document is not only stored in a database but also provided in a format easily accessible to users.

[0071] Furthermore, the server performs a risk analysis based on the specifications. This analysis identifies areas prone to bugs by evaluating the complexity and dependencies of the code. For high-risk areas, the server then proposes specific test cases.

[0072] As a concrete example, consider the case of uploading code for an inventory management system. The server generates detailed specifications for product registration, inventory adjustment, and shipping processing, identifies the risk of inventory discrepancies, and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0073] An example of a prompt message could be, "From the code of this inventory management system, please specify the necessary specifications and risk areas, and propose test cases." In this way, developers can obtain highly accurate specifications and concrete test proposals without much effort, resulting in improved system quality and reduced development time.

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

[0075] Step 1:

[0076] The server receives program code uploaded by the user from their terminal. The user sends a program file selected by the user as input to the server. The server temporarily stores this code in preparation for subsequent analysis. A simple validation is performed to ensure that the received code is stored correctly.

[0077] Step 2:

[0078] The server inputs the received program code into a generating AI model for analysis. The stored program code is used as input. The generating AI model uses natural language processing techniques to identify variable names, functions, comments, and control structures within the code. This results in a list of program components, which are extracted as analysis results. These analysis results form the basis for generating the specification document.

[0079] Step 3:

[0080] The server automatically generates a specification document based on the analysis results. In this step, the analysis results are provided as input. The server uses a template engine to convert the analysis data into natural language and generate the specification document text. The output is a specification document that describes the system's functions and operational specifications in detail. This specification document is stored in a database and provided in a format that users can access as needed.

[0081] Step 4:

[0082] The server performs a risk analysis based on the generated specifications. The generated specifications are used as input. This analysis identifies high-risk areas by evaluating the complexity of the program and the dependencies between modules. High-risk areas are identified through statistical analysis and comparison with known risk patterns. The output is a list of the areas where risks have been identified.

[0083] Step 5:

[0084] The server proposes specific operational verification methods for high-risk areas. The results of the risk analysis are used as input. Based on these results, the server automatically creates test cases. These test cases include specific operational verification procedures, such as "verify that the inventory count is greater than or equal to zero." The output provides developers with specific test proposals. This process allows developers to easily plan and execute tests for critical areas.

[0085] (Application Example 1)

[0086] 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."

[0087] In the inventory management process at a logistics center, when workers modify or develop new program data, it is necessary to quickly and accurately create design specifications and assess the associated risks. However, conventional methods are time-consuming and cumbersome, and suffer from inconsistent accuracy in specifications and reliability in risk assessments.

[0088] 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.

[0089] In this invention, the server includes means for an information processing unit to receive program data, means for automatically generating design specifications using a generative model, means for performing a risk assessment based on the automatically generated design specifications and indicating areas for functional verification, and means for presenting the design specifications and risk information to field workers in real time via a user interface. This makes it possible to carry out the inventory management process in a logistics center in an efficient and reliable manner.

[0090] An "information processing unit" is a device that has the ability to receive and analyze program data.

[0091] "Program data" refers to the code and scripts that a system analyzes.

[0092] A "generative model" is a mechanism that uses natural language processing technology to analyze program data and generate design specifications.

[0093] A "design specification" is a document that details the functions and operation of a system automatically generated by a generative model.

[0094] "Risk assessment" is the process of identifying potential problems and risks in a system based on the generated design specifications.

[0095] A "user interface" refers to the screens and operating environments used to present information to field workers.

[0096] A "structured database" is a digital recording medium used to systematically store generated design specifications.

[0097] This invention provides a system in which a server plays a central role in efficiently supporting inventory management in a logistics center. Program data is uploaded to the server by field workers from their terminals to initiate processing. The server utilizes an information processing unit to analyze the program data based on a generated AI model. Specifically, it uses natural language processing technology to identify elements within the data and automatically generates design specifications based on these elements.

[0098] The generated design specifications are immediately subjected to risk assessment to identify potential risks and areas for improvement in the system. This allows users to view the design specifications, including risk information, in real time through the user interface. Natural language processing technologies such as OpenAI® and spaCy are used in this process to generate specifications and perform risk assessment.

[0099] Furthermore, the server systematically stores the generated design specifications in a structured database, making them accessible to users at any time. By streamlining this entire process, workers can utilize data analysis results both online and offline to perform inventory management with greater accuracy.

[0100] As a concrete example, consider a script for a new inventory management system in a logistics center. When an employee uploads the script to the server using their smartphone, the server quickly generates a specification document and displays specific risk factors, such as "operation points where inventory counts may become inconsistent," in the user interface. This facilitates verification of behavior and implementation of necessary countermeasures.

[0101] Example of a prompt:

[0102] "Analyze the code for the new inventory management script, generate relevant specifications, and identify any risky areas. Please also suggest test cases if possible."

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

[0104] Step 1:

[0105] The user uploads program data from their terminal to the server. The input here is the program data prepared by the user, and this serves as the starting point for processing. The server receives this data and prepares for the next analysis process.

[0106] Step 2:

[0107] The server analyzes the received program data using natural language processing techniques. The input is the uploaded program data, and the output is the analyzed information. In this step, the generative AI model identifies variable names, functions, comments, control structures, etc., and extracts data.

[0108] Step 3:

[0109] The server automatically generates design specifications based on the analysis results. The input is the analyzed information obtained in step 2, and the output is the design specification document. The generation model automatically generates the design specifications in natural language based on the analysis information, clarifying the technical details.

[0110] Step 4:

[0111] The server performs a risk assessment based on the generated design specifications. The input is the design specifications generated in step 3, and the output is the result of the risk assessment. The process extracts high-risk areas and identifies parts that require special attention.

[0112] Step 5:

[0113] The server presents the user with design specifications and risk information generated through the user interface in real time. The input is the result of the risk assessment, and the output is the information displayed on the user interface. Based on this, the user can easily confirm the specific actions that should be taken.

[0114] Step 6:

[0115] The server saves the generated design specifications to a structured database. The input is the design specification document, and the output is the information stored in the database. In this step, the information is stored in a format that can be referenced long-term.

[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 combines a system that analyzes program code using an information processing device and automatically generates specifications based on the results with an emotion engine that recognizes user emotions. The aim of this system is to enable users to efficiently generate program specifications and optimize their user experience.

[0118] First, the user uploads the program code to be analyzed to the server using a terminal. The server receives this code and performs analysis using a generative model based on natural language processing technology. This analysis identifies variable names, functions, comments, and control structures within the code. Based on this information, the server automatically generates a specification document. This specification document details the program's functions, operating procedures, and potential risks.

[0119] Furthermore, the server is equipped with an emotion engine that recognizes user emotions and can determine the user's emotional state by analyzing their voice input. The emotion engine analyzes emotional data in real time as the user interacts with the system and adaptively optimizes the user interface based on this analysis. Through this process, the system can reduce user stress and provide a more user-friendly interface.

[0120] As a concrete example, consider a situation where a user is modifying a program while viewing a specification document. If the user expresses an emotion such as "This is troublesome" verbally, the emotion engine can recognize that emotion, and the server can either simplify the display of the specification document or suggest ways to streamline the process.

[0121] Thus, the present invention contributes to improving system quality and reducing development man-hours by deepening the understanding of programs and providing flexible operability that responds to emotions.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The user uses a terminal to upload the program code they wish to have analyzed to the server. The server receives this code correctly and stores it in a database to proceed to the next step.

[0125] Step 2:

[0126] The server prepares the received program code for input into the generation model. Here, it verifies that the code is in a format suitable for analysis and performs preprocessing as needed.

[0127] Step 3:

[0128] The server analyzes the program code using a generative model. At this stage, natural language processing techniques are used to identify variable names, functions, comments, and control structures within the code, and to obtain data that automatically generates specifications based on this information.

[0129] Step 4:

[0130] Based on the analysis data, the server automatically generates a detailed specification document that includes the program's functions, operating procedures, and potential risks. This specification document is written in natural language and is in a format that is easy for users to understand.

[0131] Step 5:

[0132] The emotion engine installed on the server accepts voice input from the user and recognizes their emotions. This engine analyzes the voice data and determines the emotional state in real time.

[0133] Step 6:

[0134] Based on emotional data recognized by the emotion engine, the server dynamically optimizes the user interface. For example, if it detects user stress or confusion, features such as simplifying operating procedures or providing advice are activated.

[0135] Step 7:

[0136] Finally, the server provides the user with the generated specifications. The specifications are output in the format specified by the user, and the user can view them on their terminal and use them for project management and development.

[0137] (Example 2)

[0138] 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".

[0139] When program analysis and specification creation are performed manually, the process is often time-consuming and inefficient. Furthermore, since work efficiency varies depending on the user's emotions, it is important to reduce the burden on users and provide a more user-friendly interface. To solve these problems, there is a need for a system that automates program code analysis and specification creation, and that also provides an optimal interface tailored to the user's emotions.

[0140] 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.

[0141] In this invention, the server includes means for receiving program code, means for analyzing the program code using a generative model and automatically generating specifications, means for analyzing voice data and determining the user's emotions, and means for optimizing the user's interface based on the results of the emotion determination. This enables the automation of program analysis and specification generation, as well as the provision of an optimal interface to the user.

[0142] An "information processing device" is a computer system that receives, analyzes, and outputs data.

[0143] "Program code" is a description of instructions given to a computer, and is usually written in a specific programming language.

[0144] A "generative model" is an algorithm or system that processes input data and automatically generates a specific output result.

[0145] A "specification document" is a written description of the functions, operation, and risks of a program or system.

[0146] "Risk analysis" is the process of identifying potential risks associated with a particular project or process and planning preventive measures and countermeasures based on those risks.

[0147] "Audio data" refers to data that records human voices in digital format.

[0148] "Emotional judgment" is the process of inferring a person's emotional state from audio data, facial expression analysis, and other sources.

[0149] An "interface" is a point of contact or means for information exchange between a system and a user, or between different systems.

[0150] This invention is a system that utilizes a server as an information processing device and a terminal as a user interface. The user uploads program code to the server using the terminal. In this process, the terminal software is equipped with a function that allows the user to select program files from their local drive and send them to the server.

[0151] The server analyzes the received program code using a generative AI model. This model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures from the code. Based on this analysis, the server automatically generates a specification document that includes the program's function, purpose, risks, and operating procedures.

[0152] Furthermore, the server uses an emotion engine to analyze voice data from the user and determine their emotions in real time. This emotion analysis allows the interface to adaptively optimize itself to reduce the stress and frustration the user experiences while using it. For example, if a user utters a voice command like "This is a hassle," the emotion engine recognizes this, and the server immediately suggests simplifying the specifications or improving the operation procedure to make it smoother.

[0153] For example, if a user enters a prompt such as, "Analyze this program code and automatically generate a specification document. Also, simplify the operating procedures that should be replaced," the server will perform the appropriate processing based on that prompt.

[0154] This invention provides an efficient work environment and reduces the burden on users by automating everything from program analysis and specification creation to optimizing interfaces based on emotions.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The user uses a terminal to select the program code to be analyzed and uploads it to the server. The input is the program file selected by the user, and the output is the transmission of that file to the server. In this process, the user uses a file selection menu to find the necessary file and then presses the "Upload" button.

[0158] Step 2:

[0159] The server receives the uploaded program code and begins analysis using a generative AI model. The input is the program code submitted by the user, and the output is the identification of variable names, functions, comments, and control structures within the code. The analysis is performed by reading the code line by line, and the generative AI model utilizes natural language processing techniques to understand the grammar and structure of the code.

[0160] Step 3:

[0161] The server initiates a process to automatically generate specifications based on the analysis results. The input is the analysis results obtained in step 2, and the output is a specification document describing the program's functions, objectives, risks, and operating procedures. At this stage, the server fills in a document template based on the analysis data and formats it into a document in the specified format.

[0162] Step 4:

[0163] The server has an emotion engine that receives voice input from the user. The input is the user's voice data, and the output is a judgment of their emotional state. Here, the server analyzes the voice data in real time and detects keywords that indicate an emotion such as "this is a hassle."

[0164] Step 5:

[0165] Based on the emotion assessment in the previous step, the server optimizes the user interface. The input is the emotion state determined in step 4, and the output is, for example, a simplified display of the specifications or suggestions for improving the operating procedures. In this process, the server automatically adjusts the interface settings and immediately reflects UI changes so that the user can use the system more comfortably.

[0166] (Application Example 2)

[0167] 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."

[0168] In modern industrial sectors, there is a demand for increased efficiency in program development and maintenance, as well as optimization of the user experience during software operation. However, conventional technologies require considerable effort to create specifications due to the complexity of the programs, and have not adequately achieved improvements in usability that respond to user emotions. This results in challenges such as inefficiency and user stress.

[0169] 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.

[0170] In this invention, the server includes means for receiving program content, means for analyzing the program content using a generative model and automatically generating a document, means for analyzing voice input and determining the emotional state, and means for dynamically optimizing the user interface based on the emotional state. This enables the automatic and efficient creation of program specifications and immediate UI adaptation to the user's emotions.

[0171] An "information processing system" is a device that receives program content, analyzes it, and performs dynamic interface optimization.

[0172] "Program content" refers to a collection of data that describes the instructions and processing procedures necessary for a machine to operate.

[0173] A "generative model" refers to an algorithm that analyzes program content and outputs it as a natural language document.

[0174] A "document" is a record of information generated to clearly explain the functions, operating procedures, risks, etc., of a program.

[0175] "Risk assessment" is the process of determining the potential for latent problems and defects within a program based on analyzed documents.

[0176] "Operational verification points" refer to the points where important operations during program execution should be checked and verified.

[0177] "Implementation method" refers to the specific procedures and methods related to verifying the program's operation and managing its functions.

[0178] "Voice input" refers to information obtained by converting the user's voice into digital data, making it recognizable by the system.

[0179] "Emotional state" refers to a linguistic or numerical representation of the psychological state inferred from the user's voice and actions.

[0180] "User interface" refers to the overall screens and operating methods that users encounter when interacting with a system.

[0181] "Dynamic optimization" is the process of adjusting the interface and functions in real time according to the user's situation and emotions.

[0182] This invention uses an information processing system as a component to achieve analysis of its program content, automatic generation of specifications, and optimization of the interface based on user emotions.

[0183] The server first receives the contents of robot control systems and other machine programs from the user's terminal. Next, it analyzes the received program contents using a generative AI model. This analysis uses Python's natural language processing libraries (e.g., NLTK, spaCy) to identify variables, functions, comments, and control structures within the code. Based on this information, it automatically generates a document that describes the program's functions and operating procedures in detail.

[0184] The generated documents are provided in LaTeX or Markdown format and stored in a structured database. This allows developers to quickly deepen their understanding of the program and perform development and maintenance efficiently.

[0185] Furthermore, the server uses TENSORFLOW® and other machine learning libraries to perform emotion recognition in real time to analyze voice input. Based on the emotional state, dynamic user interface optimization is performed using React.js. For example, if the user feels stressed, the screen display will be simplified, or specific assistance functions will be suggested.

[0186] As a concrete example, consider a scenario where a new robotic arm is introduced to a factory production line. While developers understand the program through specifications, they might react verbally to any unclear points. If the emotion recognition system detects an emotion like "I'm confused," it will display detailed tutorials and reference information accordingly. This improves the user's work efficiency.

[0187] As an example of a prompt, you could instruct the system to "generate a method to adjust the program specification display based on how the user describes the program's complexity using voice."

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server receives program content from the user's terminal. It receives the program code sent from the terminal as input and temporarily stores it in the database. This prepares the server for analysis.

[0191] Step 2:

[0192] The server analyzes the received program content using a generative AI model. Specifically, it uses natural language processing libraries (e.g., NLTK, spaCy) to identify components within the code (variables, functions, comments, control structures). The input is program code, and the output is structured data as a result of the analysis.

[0193] Step 3:

[0194] The server automatically generates documents based on the analyzed data. These documents include program functions, operating procedures, and risk information. The input is the analyzed data from step 2, and the output is a document in LaTeX or Markdown format. A document generation tool is used for generation.

[0195] Step 4:

[0196] The server stores the generated documents in a structured database. The input is the documents created in step 3, and saving them to the database makes them accessible at any time.

[0197] Step 5:

[0198] The server runs an emotion recognition model using TensorFlow to analyze the user's voice input in real time. The input is audio data from the microphone, and after digital conversion of the audio, it outputs data that numerically represents the emotional state.

[0199] Step 6:

[0200] The server dynamically optimizes the user interface based on the emotional state. It adjusts UI components using React.js based on the data. The input is the emotional state obtained in step 5, and the output is the UI change corresponding to that emotional state (e.g., simplify the screen, display additional information).

[0201] 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.

[0202] Data generation model 58 is a 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.

[0203] 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.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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".

[0217] This invention provides a system that uses an information processing device to analyze program code and automatically generate specifications based on that information. This system improves the efficiency of specification creation by performing a series of processes including code reception, analysis, specification generation, risk analysis, and proposal of operation verification methods.

[0218] The server receives program code uploaded by the user from their terminal. This code is analyzed using a generative model within the system. The generative model utilizes natural language processing technology to identify variable names, functions, comments, and control structures within the code, and automatically generates a specification document based on the analysis results. The generated specification document details the system's functions and operational specifications.

[0219] Furthermore, the server performs risk analysis using automatically generated specifications. This risk analysis evaluates the program's complexity and dependencies, identifying parts deemed high-risk. Based on this information, the server suggests areas requiring verification and how to perform them. This allows developers to conduct testing efficiently and effectively.

[0220] A concrete example is the code for an inventory management system. When a user uploads this code to the server, the server automatically generates detailed specifications for functions such as product registration, inventory adjustment, and shipping processing. Furthermore, it identifies processes where inventory discrepancies may occur as high-risk areas and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0221] This system allows users to obtain reliable specifications without hassle, resulting in improved system quality and reduced development time.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user uploads the program code to be analyzed to the server using their device. The server securely receives this code and prepares to store it in its database.

[0225] Step 2:

[0226] The server prepares the received program code for input into the generation model. Here, the code's format is checked and initial errors are performed to prepare it for analysis.

[0227] Step 3:

[0228] The server uses a generative model to analyze program code. The model employs natural language processing techniques to identify variable names, functions, comments, and control structures, and stores this information in a database.

[0229] Step 4:

[0230] The server automatically generates a specification document based on the analyzed data. The generated specification document includes details such as the program's function, structure, interactions, exception handling, and usage examples, and is written in natural language.

[0231] Step 5:

[0232] Based on automatically generated specifications, the server performs a risk analysis. This risk analysis identifies and evaluates parts of the program that contain complex logic or dependencies on external systems.

[0233] Step 6:

[0234] Based on the risk analysis results, the server extracts areas requiring operational verification and proposes specific test scenarios and methods. The proposed test information is reflected in the specifications and presented in a format easily accessible to users.

[0235] Step 7:

[0236] The server ultimately outputs the generated specifications in a format according to the customer's requirements, such as Markdown or PDF, and provides them to the user. This allows the user to effectively utilize the specifications in each phase of project management and development.

[0237] (Example 1)

[0238] 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."

[0239] Modern software development is becoming increasingly complex, making it time-consuming and laborious to create accurate and detailed specifications from program code. Furthermore, even with completed specifications, identifying potential risks and conducting appropriate testing remains challenging, hindering system quality improvement. Therefore, developers are required to efficiently produce high-quality software.

[0240] 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.

[0241] In this invention, the server includes means for an information processing device to receive program code, means for analyzing the program code using a generation AI model and automatically generating specifications using natural language processing technology, and means for evaluating the complexity and dependencies of the program based on the automatically generated specifications, performing risk analysis, and proposing operational verification points and specific implementation methods. As a result, the user can automatically obtain detailed specifications and have specific test cases proposed for high-risk areas.

[0242] An "information processing device" is a hardware or software system used to perform operations such as receiving, analyzing, storing, and outputting data.

[0243] A "generative AI model" is an artificial intelligence model that performs pattern recognition and inference based on given input data (in this case, program code) to execute a specific process (in this case, automatic generation of specifications).

[0244] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language, and is a technology that can efficiently perform language analysis and information extraction.

[0245] A "specification document" is a document that describes the design and operation of a system or software in detail, and serves as a guideline for development and operation.

[0246] "Risk analysis" is the process of identifying potential problems and hazards in a system or project, and evaluating the likelihood and impact of their occurrence.

[0247] A "database" is a system for efficiently storing, searching, and managing data, enabling the permanent retention and rapid retrieval of information.

[0248] This invention improves development efficiency by using an information processing system to analyze program code, automatically generate specifications, and propose risk analysis and operational verification.

[0249] The server receives program code uploaded by the user from their terminal. This code is then analyzed by a generative AI model on the server. The generative AI model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures within the code.

[0250] Next, the server automatically generates a specification document based on the analysis results. This specification document details the system's functions and operational specifications, providing developers with the information necessary to accurately understand the system. The generated specification document is not only stored in a database but also provided in a format easily accessible to users.

[0251] Furthermore, the server performs a risk analysis based on the specifications. This analysis identifies areas prone to bugs by evaluating the complexity and dependencies of the code. For high-risk areas, the server then proposes specific test cases.

[0252] As a concrete example, consider the case of uploading code for an inventory management system. The server generates detailed specifications for product registration, inventory adjustment, and shipping processing, identifies the risk of inventory discrepancies, and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0253] An example of a prompt message could be, "From the code of this inventory management system, please specify the necessary specifications and risk areas, and propose test cases." In this way, developers can obtain highly accurate specifications and concrete test proposals without much effort, resulting in improved system quality and reduced development time.

[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0255] Step 1:

[0256] The server receives program code uploaded by the user from their terminal. The user sends a program file selected by the user as input to the server. The server temporarily stores this code in preparation for subsequent analysis. A simple validation is performed to ensure that the received code is stored correctly.

[0257] Step 2:

[0258] The server inputs the received program code into a generating AI model for analysis. The stored program code is used as input. The generating AI model uses natural language processing techniques to identify variable names, functions, comments, and control structures within the code. This results in a list of program components, which are extracted as analysis results. These analysis results form the basis for generating the specification document.

[0259] Step 3:

[0260] The server automatically generates a specification document based on the analysis results. In this step, the analysis results are provided as input. The server uses a template engine to convert the analysis data into natural language and generate the specification document text. The output is a specification document that describes the system's functions and operational specifications in detail. This specification document is stored in a database and provided in a format that users can access as needed.

[0261] Step 4:

[0262] The server performs a risk analysis based on the generated specifications. The generated specifications are used as input. This analysis identifies high-risk areas by evaluating the complexity of the program and the dependencies between modules. High-risk areas are identified through statistical analysis and comparison with known risk patterns. The output is a list of the areas where risks have been identified.

[0263] Step 5:

[0264] The server proposes specific operational verification methods for high-risk areas. The results of the risk analysis are used as input. Based on these results, the server automatically creates test cases. These test cases include specific operational verification procedures, such as "verify that the inventory count is greater than or equal to zero." The output provides developers with specific test proposals. This process allows developers to easily plan and execute tests for critical areas.

[0265] (Application Example 1)

[0266] 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."

[0267] In the inventory management process at a logistics center, when workers modify or develop new program data, it is necessary to quickly and accurately create design specifications and assess the associated risks. However, conventional methods are time-consuming and cumbersome, and suffer from inconsistent accuracy in specifications and reliability in risk assessments.

[0268] 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.

[0269] In this invention, the server includes means for an information processing unit to receive program data, means for automatically generating design specifications using a generative model, means for performing a risk assessment based on the automatically generated design specifications and indicating areas for functional verification, and means for presenting the design specifications and risk information to field workers in real time via a user interface. This makes it possible to carry out the inventory management process in a logistics center in an efficient and reliable manner.

[0270] An "information processing unit" is a device that has the ability to receive and analyze program data.

[0271] "Program data" refers to the code and scripts that a system analyzes.

[0272] A "generative model" is a mechanism that uses natural language processing technology to analyze program data and generate design specifications.

[0273] A "design specification" is a document that details the functions and operation of a system automatically generated by a generative model.

[0274] "Risk assessment" is the process of identifying potential problems and risks in a system based on the generated design specifications.

[0275] A "user interface" refers to the screens and operating environments used to present information to field workers.

[0276] A "structured database" is a digital recording medium used to systematically store generated design specifications.

[0277] This invention provides a system in which a server plays a central role in efficiently supporting inventory management in a logistics center. Program data is uploaded to the server by field workers from their terminals to initiate processing. The server utilizes an information processing unit to analyze the program data based on a generated AI model. Specifically, it uses natural language processing technology to identify elements within the data and automatically generates design specifications based on these elements.

[0278] The generated design specifications are immediately subjected to risk assessment to identify potential risks and areas for improvement in the system. This allows users to view the design specifications, including risk information, in real time through the user interface. Natural language processing technologies such as OpenAI and spaCy are used in this process to generate specifications and perform risk assessment.

[0279] Furthermore, the server systematically stores the generated design specifications in a structured database, making them accessible to users at any time. By streamlining this entire process, workers can utilize data analysis results both online and offline to perform inventory management with greater accuracy.

[0280] As a concrete example, consider a script for a new inventory management system in a logistics center. When an employee uploads the script to the server using their smartphone, the server quickly generates a specification document and displays specific risk factors, such as "operation points where inventory counts may become inconsistent," in the user interface. This facilitates verification of behavior and implementation of necessary countermeasures.

[0281] Example of a prompt:

[0282] "Analyze the code of the new inventory management script, generate the relevant specification document, identify the risky parts, and if possible, propose test cases as well."

[0283] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0284] Step 1:

[0285] The user uploads program data from the terminal to the server. The input here is the program data prepared by the user, which serves as the starting point of the process. The server receives this data and prepares for the next analysis process.

[0286] Step 2:

[0287] The server analyzes the received program data using natural language processing technology. The input is the uploaded program data, and the output is the analyzed information. In this step, the generation AI model identifies variable names, functions, comments, control structures, etc., and performs operations to extract data.

[0288] Step 3:

[0289] The server automatically generates a design specification based on the analysis result. The input is the analyzed information obtained in Step 2, and the output is the design specification document. The generation model automatically generates the design specification in natural language based on the analysis information, clarifying the technical details.

[0290] Step 4:

[0291] The server performs a risk assessment based on the generated design specification. The input is the design specification generated in Step 3, and the output is the result of the risk assessment. A process is carried out to extract the high-risk parts and identify the parts that require special attention.

[0292] Step 5:

[0293] The server presents the user with design specifications and risk information generated through the user interface in real time. The input is the result of the risk assessment, and the output is the information displayed on the user interface. Based on this, the user can easily confirm the specific actions that should be taken.

[0294] Step 6:

[0295] The server saves the generated design specifications to a structured database. The input is the design specification document, and the output is the information stored in the database. In this step, the information is stored in a format that can be referenced long-term.

[0296] 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.

[0297] This invention combines a system that analyzes program code using an information processing device and automatically generates specifications based on the results with an emotion engine that recognizes user emotions. The aim of this system is to enable users to efficiently generate program specifications and optimize their user experience.

[0298] First, the user uploads the program code to be analyzed to the server using a terminal. The server receives this code and performs analysis using a generative model based on natural language processing technology. This analysis identifies variable names, functions, comments, and control structures within the code. Based on this information, the server automatically generates a specification document. This specification document details the program's functions, operating procedures, and potential risks.

[0299] Furthermore, the server is equipped with an emotion engine that can recognize the user's emotions and analyze the user's voice input to determine the emotional state. The emotion engine analyzes the emotional data in real time when the user operates the system and adaptively optimizes the user interface based on this. Through this process, the system can reduce the user's stress and provide a more user-friendly interface.

[0300] As a specific example, consider the situation where the user is modifying a program while viewing a specification document. At this time, if the user expresses emotions such as "it's troublesome" verbally, the emotion engine can recognize this emotion, and the server can propose to simplify the display of the specification document or smooth the process.

[0301] In this way, the present invention contributes to improving the quality of the system and reducing the development man-hours by deepening the understanding of the program and providing flexible operability according to emotions.

[0302] The following describes the processing flow.

[0303] Step 1:

[0304] The user uses the terminal to upload the program code to be analyzed to the server. The server correctly receives this code and saves it in the database to proceed with the next processing.

[0305] Step 2:

[0306] Prepare to input the program code received by the server into the generation model. Here, it is confirmed whether the code is in a format suitable for analysis, and preprocessing is performed if necessary.

[0307] Step 3:

[0308] The server analyzes the program code using a generative model. At this stage, natural language processing techniques are used to identify variable names, functions, comments, and control structures within the code, and to obtain data that automatically generates specifications based on this information.

[0309] Step 4:

[0310] Based on the analysis data, the server automatically generates a detailed specification document that includes the program's functions, operating procedures, and potential risks. This specification document is written in natural language and is in a format that is easy for users to understand.

[0311] Step 5:

[0312] The emotion engine installed on the server accepts voice input from the user and recognizes their emotions. This engine analyzes the voice data and determines the emotional state in real time.

[0313] Step 6:

[0314] Based on emotional data recognized by the emotion engine, the server dynamically optimizes the user interface. For example, if it detects user stress or confusion, features such as simplifying operating procedures or providing advice are activated.

[0315] Step 7:

[0316] Finally, the server provides the user with the generated specifications. The specifications are output in the format specified by the user, and the user can view them on their terminal and use them for project management and development.

[0317] (Example 2)

[0318] 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".

[0319] When program analysis and specification creation are performed manually, the process is often time-consuming and inefficient. Furthermore, since work efficiency varies depending on the user's emotions, it is important to reduce the burden on users and provide a more user-friendly interface. To solve these problems, there is a need for a system that automates program code analysis and specification creation, and that also provides an optimal interface tailored to the user's emotions.

[0320] 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.

[0321] In this invention, the server includes means for receiving program code, means for analyzing the program code using a generative model and automatically generating specifications, means for analyzing voice data and determining the user's emotions, and means for optimizing the user's interface based on the results of the emotion determination. This enables the automation of program analysis and specification generation, as well as the provision of an optimal interface to the user.

[0322] An "information processing device" is a computer system that receives, analyzes, and outputs data.

[0323] "Program code" is a description of instructions given to a computer, and is usually written in a specific programming language.

[0324] A "generative model" is an algorithm or system that processes input data and automatically generates a specific output result.

[0325] A "specification document" is a written description of the functions, operation, and risks of a program or system.

[0326] "Risk analysis" is the process of identifying potential risks associated with a particular project or process and planning preventive measures and countermeasures based on those risks.

[0327] "Audio data" refers to data that records human voices in digital format.

[0328] "Emotional judgment" is the process of inferring a person's emotional state from audio data, facial expression analysis, and other sources.

[0329] An "interface" is a point of contact or means for information exchange between a system and a user, or between different systems.

[0330] This invention is a system that utilizes a server as an information processing device and a terminal as a user interface. The user uploads program code to the server using the terminal. In this process, the terminal software is equipped with a function that allows the user to select program files from their local drive and send them to the server.

[0331] The server analyzes the received program code using a generative AI model. This model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures from the code. Based on this analysis, the server automatically generates a specification document that includes the program's function, purpose, risks, and operating procedures.

[0332] Furthermore, the server uses an emotion engine to analyze voice data from the user and determine their emotions in real time. This emotion analysis allows the interface to adaptively optimize itself to reduce the stress and frustration the user experiences while using it. For example, if a user utters a voice command like "This is a hassle," the emotion engine recognizes this, and the server immediately suggests simplifying the specifications or improving the operation procedure to make it smoother.

[0333] For example, if a user enters a prompt such as, "Analyze this program code and automatically generate a specification document. Also, simplify the operating procedures that should be replaced," the server will perform the appropriate processing based on that prompt.

[0334] This invention provides an efficient work environment and reduces the burden on users by automating everything from program analysis and specification creation to optimizing interfaces based on emotions.

[0335] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0336] Step 1:

[0337] The user uses a terminal to select the program code to be analyzed and uploads it to the server. The input is the program file selected by the user, and the output is the transmission of that file to the server. In this process, the user uses a file selection menu to find the necessary file and then presses the "Upload" button.

[0338] Step 2:

[0339] The server receives the uploaded program code and begins analysis using a generative AI model. The input is the program code submitted by the user, and the output is the identification of variable names, functions, comments, and control structures within the code. The analysis is performed by reading the code line by line, and the generative AI model utilizes natural language processing techniques to understand the grammar and structure of the code.

[0340] Step 3:

[0341] The server initiates a process to automatically generate specifications based on the analysis results. The input is the analysis results obtained in step 2, and the output is a specification document describing the program's functions, objectives, risks, and operating procedures. At this stage, the server fills in a document template based on the analysis data and formats it into a document in the specified format.

[0342] Step 4:

[0343] The server has an emotion engine that receives voice input from the user. The input is the user's voice data, and the output is a judgment of their emotional state. Here, the server analyzes the voice data in real time and detects keywords that indicate an emotion such as "this is a hassle."

[0344] Step 5:

[0345] Based on the emotion assessment in the previous step, the server optimizes the user interface. The input is the emotion state determined in step 4, and the output is, for example, a simplified display of the specifications or suggestions for improving the operating procedures. In this process, the server automatically adjusts the interface settings and immediately reflects UI changes so that the user can use the system more comfortably.

[0346] (Application Example 2)

[0347] 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."

[0348] In modern industrial sectors, there is a demand for increased efficiency in program development and maintenance, as well as optimization of the user experience during software operation. However, conventional technologies require considerable effort to create specifications due to the complexity of the programs, and have not adequately achieved improvements in usability that respond to user emotions. This results in challenges such as inefficiency and user stress.

[0349] 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.

[0350] In this invention, the server includes means for receiving program content, means for analyzing the program content using a generative model and automatically generating a document, means for analyzing voice input and determining the emotional state, and means for dynamically optimizing the user interface based on the emotional state. This enables the automatic and efficient creation of program specifications and immediate UI adaptation to the user's emotions.

[0351] An "information processing system" is a device that receives program content, analyzes it, and performs dynamic interface optimization.

[0352] "Program content" refers to a collection of data that describes the instructions and processing procedures necessary for a machine to operate.

[0353] A "generative model" refers to an algorithm that analyzes program content and outputs it as a natural language document.

[0354] A "document" is a record of information generated to clearly explain the functions, operating procedures, risks, etc., of a program.

[0355] "Risk assessment" is the process of determining the potential for latent problems and defects within a program based on analyzed documents.

[0356] "Operational verification points" refer to the points where important operations during program execution should be checked and verified.

[0357] "Implementation method" refers to the specific procedures and methods related to verifying the program's operation and managing its functions.

[0358] "Voice input" refers to information obtained by converting the user's voice into digital data, making it recognizable by the system.

[0359] "Emotional state" refers to a linguistic or numerical representation of the psychological state inferred from the user's voice and actions.

[0360] "User interface" refers to the overall screens and operating methods that users encounter when interacting with a system.

[0361] "Dynamic optimization" is the process of adjusting the interface and functions in real time according to the user's situation and emotions.

[0362] This invention uses an information processing system as a component to achieve analysis of its program content, automatic generation of specifications, and optimization of the interface based on user emotions.

[0363] The server first receives the contents of robot control systems and other machine programs from the user's terminal. Next, it analyzes the received program contents using a generative AI model. This analysis uses Python's natural language processing libraries (e.g., NLTK, spaCy) to identify variables, functions, comments, and control structures within the code. Based on this information, it automatically generates a document that describes the program's functions and operating procedures in detail.

[0364] The generated documents are provided in LaTeX or Markdown format and stored in a structured database. This allows developers to quickly deepen their understanding of the program and perform development and maintenance efficiently.

[0365] Furthermore, the server uses TensorFlow and other machine learning libraries to perform emotion recognition in order to analyze voice input in real time. Based on the emotional state, dynamic user interface optimization is performed using React.js. For example, if the user feels stressed, the screen display will be simplified, or specific assistance functions will be suggested.

[0366] As a concrete example, consider a scenario where a new robotic arm is introduced to a factory production line. While developers understand the program through specifications, they might react verbally to any unclear points. If the emotion recognition system detects an emotion like "I'm confused," it will display detailed tutorials and reference information accordingly. This improves the user's work efficiency.

[0367] As an example of a prompt, you could instruct the system to "generate a method to adjust the program specification display based on how the user describes the program's complexity using voice."

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] The server receives program content from the user's terminal. It receives the program code sent from the terminal as input and temporarily stores it in the database. This prepares the server for analysis.

[0371] Step 2:

[0372] The server analyzes the received program content using a generative AI model. Specifically, it uses natural language processing libraries (e.g., NLTK, spaCy) to identify components within the code (variables, functions, comments, control structures). The input is program code, and the output is structured data as a result of the analysis.

[0373] Step 3:

[0374] The server automatically generates documents based on the analyzed data. These documents include program functions, operating procedures, and risk information. The input is the analyzed data from step 2, and the output is a document in LaTeX or Markdown format. A document generation tool is used for generation.

[0375] Step 4:

[0376] The server stores the generated documents in a structured database. The input is the documents created in step 3, and saving them to the database makes them accessible at any time.

[0377] Step 5:

[0378] The server runs an emotion recognition model using TensorFlow to analyze the user's voice input in real time. The input is audio data from the microphone, and after digital conversion of the audio, it outputs data that numerically represents the emotional state.

[0379] Step 6:

[0380] The server dynamically optimizes the user interface based on the emotional state. It adjusts UI components using React.js based on the data. The input is the emotional state obtained in step 5, and the output is the UI change corresponding to that emotional state (e.g., simplify the screen, display additional information).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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".

[0397] This invention provides a system that uses an information processing device to analyze program code and automatically generate specifications based on that information. This system improves the efficiency of specification creation by performing a series of processes including code reception, analysis, specification generation, risk analysis, and proposal of operation verification methods.

[0398] The server receives program code uploaded by the user from their terminal. This code is analyzed using a generative model within the system. The generative model utilizes natural language processing technology to identify variable names, functions, comments, and control structures within the code, and automatically generates a specification document based on the analysis results. The generated specification document details the system's functions and operational specifications.

[0399] Furthermore, the server performs risk analysis using automatically generated specifications. This risk analysis evaluates the program's complexity and dependencies, identifying parts deemed high-risk. Based on this information, the server suggests areas requiring verification and how to perform them. This allows developers to conduct testing efficiently and effectively.

[0400] A concrete example is the code for an inventory management system. When a user uploads this code to the server, the server automatically generates detailed specifications for functions such as product registration, inventory adjustment, and shipping processing. Furthermore, it identifies processes where inventory discrepancies may occur as high-risk areas and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0401] This system allows users to obtain reliable specifications without hassle, resulting in improved system quality and reduced development time.

[0402] The following describes the processing flow.

[0403] Step 1:

[0404] The user uploads the program code to be analyzed to the server using their device. The server securely receives this code and prepares to store it in its database.

[0405] Step 2:

[0406] The server prepares the received program code for input into the generation model. Here, the code's format is checked and initial errors are performed to prepare it for analysis.

[0407] Step 3:

[0408] The server uses a generative model to analyze program code. The model employs natural language processing techniques to identify variable names, functions, comments, and control structures, and stores this information in a database.

[0409] Step 4:

[0410] The server automatically generates a specification document based on the analyzed data. The generated specification document includes details such as the program's function, structure, interactions, exception handling, and usage examples, and is written in natural language.

[0411] Step 5:

[0412] Based on automatically generated specifications, the server performs a risk analysis. This risk analysis identifies and evaluates parts of the program that contain complex logic or dependencies on external systems.

[0413] Step 6:

[0414] Based on the risk analysis results, the server extracts areas requiring operational verification and proposes specific test scenarios and methods. The proposed test information is reflected in the specifications and presented in a format easily accessible to users.

[0415] Step 7:

[0416] The server ultimately outputs the generated specifications in a format according to the customer's requirements, such as Markdown or PDF, and provides them to the user. This allows the user to effectively utilize the specifications in each phase of project management and development.

[0417] (Example 1)

[0418] 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."

[0419] Modern software development is becoming increasingly complex, making it time-consuming and laborious to create accurate and detailed specifications from program code. Furthermore, even with completed specifications, identifying potential risks and conducting appropriate testing remains challenging, hindering system quality improvement. Therefore, developers are required to efficiently produce high-quality software.

[0420] 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.

[0421] In this invention, the server includes means for an information processing device to receive program code, means for analyzing the program code using a generation AI model and automatically generating specifications using natural language processing technology, and means for evaluating the complexity and dependencies of the program based on the automatically generated specifications, performing risk analysis, and proposing operational verification points and specific implementation methods. As a result, the user can automatically obtain detailed specifications and have specific test cases proposed for high-risk areas.

[0422] An "information processing device" is a hardware or software system used to perform operations such as receiving, analyzing, storing, and outputting data.

[0423] A "generative AI model" is an artificial intelligence model that performs pattern recognition and inference based on given input data (in this case, program code) to execute a specific process (in this case, automatic generation of specifications).

[0424] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language, and is a technology that can efficiently perform language analysis and information extraction.

[0425] A "specification document" is a document that describes the design and operation of a system or software in detail, and serves as a guideline for development and operation.

[0426] "Risk analysis" is the process of identifying potential problems and hazards in a system or project, and evaluating the likelihood and impact of their occurrence.

[0427] A "database" is a system for efficiently storing, searching, and managing data, enabling the permanent retention and rapid retrieval of information.

[0428] This invention improves development efficiency by using an information processing system to analyze program code, automatically generate specifications, and propose risk analysis and operational verification.

[0429] The server receives program code uploaded by the user from their terminal. This code is then analyzed by a generative AI model on the server. The generative AI model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures within the code.

[0430] Next, the server automatically generates a specification document based on the analysis results. This specification document details the system's functions and operational specifications, providing developers with the information necessary to accurately understand the system. The generated specification document is not only stored in a database but also provided in a format easily accessible to users.

[0431] Furthermore, the server performs a risk analysis based on the specifications. This analysis identifies areas prone to bugs by evaluating the complexity and dependencies of the code. For high-risk areas, the server then proposes specific test cases.

[0432] As a concrete example, consider the case of uploading code for an inventory management system. The server generates detailed specifications for product registration, inventory adjustment, and shipping processing, identifies the risk of inventory discrepancies, and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0433] An example of a prompt message could be, "From the code of this inventory management system, please specify the necessary specifications and risk areas, and propose test cases." In this way, developers can obtain highly accurate specifications and concrete test proposals without much effort, resulting in improved system quality and reduced development time.

[0434] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0435] Step 1:

[0436] The server receives program code uploaded by the user from their terminal. The user sends a program file selected by the user as input to the server. The server temporarily stores this code in preparation for subsequent analysis. A simple validation is performed to ensure that the received code is stored correctly.

[0437] Step 2:

[0438] The server inputs the received program code into a generating AI model for analysis. The stored program code is used as input. The generating AI model uses natural language processing techniques to identify variable names, functions, comments, and control structures within the code. This results in a list of program components, which are extracted as analysis results. These analysis results form the basis for generating the specification document.

[0439] Step 3:

[0440] The server automatically generates a specification document based on the analysis results. In this step, the analysis results are provided as input. The server uses a template engine to convert the analysis data into natural language and generate the specification document text. The output is a specification document that describes the system's functions and operational specifications in detail. This specification document is stored in a database and provided in a format that users can access as needed.

[0441] Step 4:

[0442] The server performs a risk analysis based on the generated specifications. The generated specifications are used as input. This analysis identifies high-risk areas by evaluating the complexity of the program and the dependencies between modules. High-risk areas are identified through statistical analysis and comparison with known risk patterns. The output is a list of the areas where risks have been identified.

[0443] Step 5:

[0444] The server proposes specific operational verification methods for high-risk areas. The results of the risk analysis are used as input. Based on these results, the server automatically creates test cases. These test cases include specific operational verification procedures, such as "verify that the inventory count is greater than or equal to zero." The output provides developers with specific test proposals. This process allows developers to easily plan and execute tests for critical areas.

[0445] (Application Example 1)

[0446] 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."

[0447] In the inventory management process at a logistics center, when workers modify or develop new program data, it is necessary to quickly and accurately create design specifications and assess the associated risks. However, conventional methods are time-consuming and cumbersome, and suffer from inconsistent accuracy in specifications and reliability in risk assessments.

[0448] 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.

[0449] In this invention, the server includes means for an information processing unit to receive program data, means for automatically generating design specifications using a generative model, means for performing a risk assessment based on the automatically generated design specifications and indicating areas for functional verification, and means for presenting the design specifications and risk information to field workers in real time via a user interface. This makes it possible to carry out the inventory management process in a logistics center in an efficient and reliable manner.

[0450] An "information processing unit" is a device that has the ability to receive and analyze program data.

[0451] "Program data" refers to the code and scripts that a system analyzes.

[0452] A "generative model" is a mechanism that uses natural language processing technology to analyze program data and generate design specifications.

[0453] A "design specification" is a document that details the functions and operation of a system automatically generated by a generative model.

[0454] "Risk assessment" is the process of identifying potential problems and risks in a system based on the generated design specifications.

[0455] A "user interface" refers to the screens and operating environments used to present information to field workers.

[0456] A "structured database" is a digital recording medium used to systematically store generated design specifications.

[0457] This invention provides a system in which a server plays a central role in efficiently supporting inventory management in a logistics center. Program data is uploaded to the server by field workers from their terminals to initiate processing. The server utilizes an information processing unit to analyze the program data based on a generated AI model. Specifically, it uses natural language processing technology to identify elements within the data and automatically generates design specifications based on these elements.

[0458] The generated design specifications are immediately subjected to risk assessment to identify potential risks and areas for improvement in the system. This allows users to view the design specifications, including risk information, in real time through the user interface. Natural language processing technologies such as OpenAI and spaCy are used in this process to generate specifications and perform risk assessment.

[0459] Furthermore, the server systematically stores the generated design specifications in a structured database, making them accessible to users at any time. By streamlining this entire process, workers can utilize data analysis results both online and offline to perform inventory management with greater accuracy.

[0460] As a concrete example, consider a script for a new inventory management system in a logistics center. When an employee uploads the script to the server using their smartphone, the server quickly generates a specification document and displays specific risk factors, such as "operation points where inventory counts may become inconsistent," in the user interface. This facilitates verification of behavior and implementation of necessary countermeasures.

[0461] Example of a prompt:

[0462] "Analyze the code for the new inventory management script, generate relevant specifications, and identify any risky areas. Please also suggest test cases if possible."

[0463] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0464] Step 1:

[0465] The user uploads program data from their terminal to the server. The input here is the program data prepared by the user, and this serves as the starting point for processing. The server receives this data and prepares for the next analysis process.

[0466] Step 2:

[0467] The server analyzes the received program data using natural language processing techniques. The input is the uploaded program data, and the output is the analyzed information. In this step, the generative AI model identifies variable names, functions, comments, control structures, etc., and extracts data.

[0468] Step 3:

[0469] The server automatically generates design specifications based on the analysis results. The input is the analyzed information obtained in step 2, and the output is the design specification document. The generation model automatically generates the design specifications in natural language based on the analysis information, clarifying the technical details.

[0470] Step 4:

[0471] The server performs a risk assessment based on the generated design specifications. The input is the design specifications generated in step 3, and the output is the result of the risk assessment. The process extracts high-risk areas and identifies parts that require special attention.

[0472] Step 5:

[0473] The server presents the user with design specifications and risk information generated through the user interface in real time. The input is the result of the risk assessment, and the output is the information displayed on the user interface. Based on this, the user can easily confirm the specific actions that should be taken.

[0474] Step 6:

[0475] The server saves the generated design specifications to a structured database. The input is the design specification document, and the output is the information stored in the database. In this step, the information is stored in a format that can be referenced long-term.

[0476] 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.

[0477] This invention combines a system that analyzes program code using an information processing device and automatically generates specifications based on the results with an emotion engine that recognizes user emotions. The aim of this system is to enable users to efficiently generate program specifications and optimize their user experience.

[0478] First, the user uploads the program code to be analyzed to the server using a terminal. The server receives this code and performs analysis using a generative model based on natural language processing technology. This analysis identifies variable names, functions, comments, and control structures within the code. Based on this information, the server automatically generates a specification document. This specification document details the program's functions, operating procedures, and potential risks.

[0479] Furthermore, the server is equipped with an emotion engine that recognizes user emotions and can determine the user's emotional state by analyzing their voice input. The emotion engine analyzes emotional data in real time as the user interacts with the system and adaptively optimizes the user interface based on this analysis. Through this process, the system can reduce user stress and provide a more user-friendly interface.

[0480] As a concrete example, consider a situation where a user is modifying a program while viewing a specification document. If the user expresses an emotion such as "This is troublesome" verbally, the emotion engine can recognize that emotion, and the server can either simplify the display of the specification document or suggest ways to streamline the process.

[0481] Thus, the present invention contributes to improving system quality and reducing development man-hours by deepening the understanding of programs and providing flexible operability that responds to emotions.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] The user uses a terminal to upload the program code they wish to have analyzed to the server. The server receives this code correctly and stores it in a database to proceed to the next step.

[0485] Step 2:

[0486] The server prepares the received program code for input into the generation model. Here, it verifies that the code is in a format suitable for analysis and performs preprocessing as needed.

[0487] Step 3:

[0488] The server analyzes the program code using a generative model. At this stage, natural language processing techniques are used to identify variable names, functions, comments, and control structures within the code, and to obtain data that automatically generates specifications based on this information.

[0489] Step 4:

[0490] Based on the analysis data, the server automatically generates a detailed specification document that includes the program's functions, operating procedures, and potential risks. This specification document is written in natural language and is in a format that is easy for users to understand.

[0491] Step 5:

[0492] The emotion engine installed on the server accepts voice input from the user and recognizes their emotions. This engine analyzes the voice data and determines the emotional state in real time.

[0493] Step 6:

[0494] Based on emotional data recognized by the emotion engine, the server dynamically optimizes the user interface. For example, if it detects user stress or confusion, features such as simplifying operating procedures or providing advice are activated.

[0495] Step 7:

[0496] Finally, the server provides the user with the generated specifications. The specifications are output in the format specified by the user, and the user can view them on their terminal and use them for project management and development.

[0497] (Example 2)

[0498] 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."

[0499] When program analysis and specification creation are performed manually, the process is often time-consuming and inefficient. Furthermore, since work efficiency varies depending on the user's emotions, it is important to reduce the burden on users and provide a more user-friendly interface. To solve these problems, there is a need for a system that automates program code analysis and specification creation, and that also provides an optimal interface tailored to the user's emotions.

[0500] 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.

[0501] In this invention, the server includes means for receiving program code, means for analyzing the program code using a generative model and automatically generating specifications, means for analyzing voice data and determining the user's emotions, and means for optimizing the user's interface based on the results of the emotion determination. This enables the automation of program analysis and specification generation, as well as the provision of an optimal interface to the user.

[0502] An "information processing device" is a computer system that receives, analyzes, and outputs data.

[0503] "Program code" is a description of instructions given to a computer, and is usually written in a specific programming language.

[0504] A "generative model" is an algorithm or system that processes input data and automatically generates a specific output result.

[0505] A "specification document" is a written description of the functions, operation, and risks of a program or system.

[0506] "Risk analysis" is the process of identifying potential risks associated with a particular project or process and planning preventive measures and countermeasures based on those risks.

[0507] "Audio data" refers to data that records human voices in digital format.

[0508] "Emotional judgment" is the process of inferring a person's emotional state from audio data, facial expression analysis, and other sources.

[0509] An "interface" is a point of contact or means for information exchange between a system and a user, or between different systems.

[0510] This invention is a system that utilizes a server as an information processing device and a terminal as a user interface. The user uploads program code to the server using the terminal. In this process, the terminal software is equipped with a function that allows the user to select program files from their local drive and send them to the server.

[0511] The server analyzes the received program code using a generative AI model. This model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures from the code. Based on this analysis, the server automatically generates a specification document that includes the program's function, purpose, risks, and operating procedures.

[0512] Furthermore, the server uses an emotion engine to analyze voice data from the user and determine their emotions in real time. This emotion analysis allows the interface to adaptively optimize itself to reduce the stress and frustration the user experiences while using it. For example, if a user utters a voice command like "This is a hassle," the emotion engine recognizes this, and the server immediately suggests simplifying the specifications or improving the operation procedure to make it smoother.

[0513] For example, if a user enters a prompt such as, "Analyze this program code and automatically generate a specification document. Also, simplify the operating procedures that should be replaced," the server will perform the appropriate processing based on that prompt.

[0514] This invention provides an efficient work environment and reduces the burden on users by automating everything from program analysis and specification creation to optimizing interfaces based on emotions.

[0515] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0516] Step 1:

[0517] The user uses a terminal to select the program code to be analyzed and uploads it to the server. The input is the program file selected by the user, and the output is the transmission of that file to the server. In this process, the user uses a file selection menu to find the necessary file and then presses the "Upload" button.

[0518] Step 2:

[0519] The server receives the uploaded program code and begins analysis using a generative AI model. The input is the program code submitted by the user, and the output is the identification of variable names, functions, comments, and control structures within the code. The analysis is performed by reading the code line by line, and the generative AI model utilizes natural language processing techniques to understand the grammar and structure of the code.

[0520] Step 3:

[0521] The server initiates a process to automatically generate specifications based on the analysis results. The input is the analysis results obtained in step 2, and the output is a specification document describing the program's functions, objectives, risks, and operating procedures. At this stage, the server fills in a document template based on the analysis data and formats it into a document in the specified format.

[0522] Step 4:

[0523] The server has an emotion engine that receives voice input from the user. The input is the user's voice data, and the output is a judgment of their emotional state. Here, the server analyzes the voice data in real time and detects keywords that indicate an emotion such as "this is a hassle."

[0524] Step 5:

[0525] Based on the emotion assessment in the previous step, the server optimizes the user interface. The input is the emotion state determined in step 4, and the output is, for example, a simplified display of the specifications or suggestions for improving the operating procedures. In this process, the server automatically adjusts the interface settings and immediately reflects UI changes so that the user can use the system more comfortably.

[0526] (Application Example 2)

[0527] 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."

[0528] In modern industrial sectors, there is a demand for increased efficiency in program development and maintenance, as well as optimization of the user experience during software operation. However, conventional technologies require considerable effort to create specifications due to the complexity of the programs, and have not adequately achieved improvements in usability that respond to user emotions. This results in challenges such as inefficiency and user stress.

[0529] 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.

[0530] In this invention, the server includes means for receiving program content, means for analyzing the program content using a generative model and automatically generating a document, means for analyzing voice input and determining the emotional state, and means for dynamically optimizing the user interface based on the emotional state. This enables the automatic and efficient creation of program specifications and immediate UI adaptation to the user's emotions.

[0531] An "information processing system" is a device that receives program content, analyzes it, and performs dynamic interface optimization.

[0532] "Program content" refers to a collection of data that describes the instructions and processing procedures necessary for a machine to operate.

[0533] A "generative model" refers to an algorithm that analyzes program content and outputs it as a natural language document.

[0534] A "document" is a record of information generated to clearly explain the functions, operating procedures, risks, etc., of a program.

[0535] "Risk assessment" is the process of determining the potential for latent problems and defects within a program based on analyzed documents.

[0536] "Operational verification points" refer to the points where important operations during program execution should be checked and verified.

[0537] "Implementation method" refers to the specific procedures and methods related to verifying the program's operation and managing its functions.

[0538] "Voice input" refers to information obtained by converting the user's voice into digital data, making it recognizable by the system.

[0539] "Emotional state" refers to a linguistic or numerical representation of the psychological state inferred from the user's voice and actions.

[0540] "User interface" refers to the overall screens and operating methods that users encounter when interacting with a system.

[0541] "Dynamic optimization" is the process of adjusting the interface and functions in real time according to the user's situation and emotions.

[0542] This invention uses an information processing system as a component to achieve analysis of its program content, automatic generation of specifications, and optimization of the interface based on user emotions.

[0543] The server first receives the contents of robot control systems and other machine programs from the user's terminal. Next, it analyzes the received program contents using a generative AI model. This analysis uses Python's natural language processing libraries (e.g., NLTK, spaCy) to identify variables, functions, comments, and control structures within the code. Based on this information, it automatically generates a document that describes the program's functions and operating procedures in detail.

[0544] The generated documents are provided in LaTeX or Markdown format and stored in a structured database. This allows developers to quickly deepen their understanding of the program and perform development and maintenance efficiently.

[0545] Furthermore, the server uses TensorFlow and other machine learning libraries to perform emotion recognition in order to analyze voice input in real time. Based on the emotional state, dynamic user interface optimization is performed using React.js. For example, if the user feels stressed, the screen display will be simplified, or specific assistance functions will be suggested.

[0546] As a concrete example, consider a scenario where a new robotic arm is introduced to a factory production line. While developers understand the program through specifications, they might react verbally to any unclear points. If the emotion recognition system detects an emotion like "I'm confused," it will display detailed tutorials and reference information accordingly. This improves the user's work efficiency.

[0547] As an example of a prompt, you could instruct the system to "generate a method to adjust the program specification display based on how the user describes the program's complexity using voice."

[0548] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0549] Step 1:

[0550] The server receives program content from the user's terminal. It receives the program code sent from the terminal as input and temporarily stores it in the database. This prepares the server for analysis.

[0551] Step 2:

[0552] The server analyzes the received program content using a generative AI model. Specifically, it uses natural language processing libraries (e.g., NLTK, spaCy) to identify components within the code (variables, functions, comments, control structures). The input is program code, and the output is structured data as a result of the analysis.

[0553] Step 3:

[0554] The server automatically generates documents based on the analyzed data. These documents include program functions, operating procedures, and risk information. The input is the analyzed data from step 2, and the output is a document in LaTeX or Markdown format. A document generation tool is used for generation.

[0555] Step 4:

[0556] The server stores the generated documents in a structured database. The input is the documents created in step 3, and saving them to the database makes them accessible at any time.

[0557] Step 5:

[0558] The server runs an emotion recognition model using TensorFlow to analyze the user's voice input in real time. The input is audio data from the microphone, and after digital conversion of the audio, it outputs data that numerically represents the emotional state.

[0559] Step 6:

[0560] The server dynamically optimizes the user interface based on the emotional state. It adjusts UI components using React.js based on the data. The input is the emotional state obtained in step 5, and the output is the UI change corresponding to that emotional state (e.g., simplify the screen, display additional information).

[0561] 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.

[0562] 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.

[0563] 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.

[0564] [Fourth Embodiment]

[0565] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0566] 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.

[0567] 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).

[0568] 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.

[0569] 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.

[0570] 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).

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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".

[0578] This invention provides a system that uses an information processing device to analyze program code and automatically generate specifications based on that information. This system improves the efficiency of specification creation by performing a series of processes including code reception, analysis, specification generation, risk analysis, and proposal of operation verification methods.

[0579] The server receives program code uploaded by the user from their terminal. This code is analyzed using a generative model within the system. The generative model utilizes natural language processing technology to identify variable names, functions, comments, and control structures within the code, and automatically generates a specification document based on the analysis results. The generated specification document details the system's functions and operational specifications.

[0580] Furthermore, the server performs risk analysis using automatically generated specifications. This risk analysis evaluates the program's complexity and dependencies, identifying parts deemed high-risk. Based on this information, the server suggests areas requiring verification and how to perform them. This allows developers to conduct testing efficiently and effectively.

[0581] A concrete example is the code for an inventory management system. When a user uploads this code to the server, the server automatically generates detailed specifications for functions such as product registration, inventory adjustment, and shipping processing. Furthermore, it identifies processes where inventory discrepancies may occur as high-risk areas and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0582] This system allows users to obtain reliable specifications without hassle, resulting in improved system quality and reduced development time.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The user uploads the program code to be analyzed to the server using their device. The server securely receives this code and prepares to store it in its database.

[0586] Step 2:

[0587] The server prepares the received program code for input into the generation model. Here, the code's format is checked and initial errors are performed to prepare it for analysis.

[0588] Step 3:

[0589] The server uses a generative model to analyze program code. The model employs natural language processing techniques to identify variable names, functions, comments, and control structures, and stores this information in a database.

[0590] Step 4:

[0591] The server automatically generates a specification document based on the analyzed data. The generated specification document includes details such as the program's function, structure, interactions, exception handling, and usage examples, and is written in natural language.

[0592] Step 5:

[0593] Based on automatically generated specifications, the server performs a risk analysis. This risk analysis identifies and evaluates parts of the program that contain complex logic or dependencies on external systems.

[0594] Step 6:

[0595] Based on the risk analysis results, the server extracts areas requiring operational verification and proposes specific test scenarios and methods. The proposed test information is reflected in the specifications and presented in a format easily accessible to users.

[0596] Step 7:

[0597] The server ultimately outputs the generated specifications in a format according to the customer's requirements, such as Markdown or PDF, and provides them to the user. This allows the user to effectively utilize the specifications in each phase of project management and development.

[0598] (Example 1)

[0599] 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".

[0600] Modern software development is becoming increasingly complex, making it time-consuming and laborious to create accurate and detailed specifications from program code. Furthermore, even with completed specifications, identifying potential risks and conducting appropriate testing remains challenging, hindering system quality improvement. Therefore, developers are required to efficiently produce high-quality software.

[0601] 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.

[0602] In this invention, the server includes means for an information processing device to receive program code, means for analyzing the program code using a generation AI model and automatically generating specifications using natural language processing technology, and means for evaluating the complexity and dependencies of the program based on the automatically generated specifications, performing risk analysis, and proposing operational verification points and specific implementation methods. As a result, the user can automatically obtain detailed specifications and have specific test cases proposed for high-risk areas.

[0603] An "information processing device" is a hardware or software system used to perform operations such as receiving, analyzing, storing, and outputting data.

[0604] A "generative AI model" is an artificial intelligence model that performs pattern recognition and inference based on given input data (in this case, program code) to execute a specific process (in this case, automatic generation of specifications).

[0605] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language, and is a technology that can efficiently perform language analysis and information extraction.

[0606] A "specification document" is a document that describes the design and operation of a system or software in detail, and serves as a guideline for development and operation.

[0607] "Risk analysis" is the process of identifying potential problems and hazards in a system or project, and evaluating the likelihood and impact of their occurrence.

[0608] A "database" is a system for efficiently storing, searching, and managing data, enabling the permanent retention and rapid retrieval of information.

[0609] This invention improves development efficiency by using an information processing system to analyze program code, automatically generate specifications, and propose risk analysis and operational verification.

[0610] The server receives program code uploaded by the user from their terminal. This code is then analyzed by a generative AI model on the server. The generative AI model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures within the code.

[0611] Next, the server automatically generates a specification document based on the analysis results. This specification document details the system's functions and operational specifications, providing developers with the information necessary to accurately understand the system. The generated specification document is not only stored in a database but also provided in a format easily accessible to users.

[0612] Furthermore, the server performs a risk analysis based on the specifications. This analysis identifies areas prone to bugs by evaluating the complexity and dependencies of the code. For high-risk areas, the server then proposes specific test cases.

[0613] As a concrete example, consider the case of uploading code for an inventory management system. The server generates detailed specifications for product registration, inventory adjustment, and shipping processing, identifies the risk of inventory discrepancies, and proposes a test case to "verify that the inventory count is greater than or equal to zero."

[0614] An example of a prompt message could be, "From the code of this inventory management system, please specify the necessary specifications and risk areas, and propose test cases." In this way, developers can obtain highly accurate specifications and concrete test proposals without much effort, resulting in improved system quality and reduced development time.

[0615] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0616] Step 1:

[0617] The server receives program code uploaded by the user from their terminal. The user sends a program file selected by the user as input to the server. The server temporarily stores this code in preparation for subsequent analysis. A simple validation is performed to ensure that the received code is stored correctly.

[0618] Step 2:

[0619] The server inputs the received program code into a generating AI model for analysis. The stored program code is used as input. The generating AI model uses natural language processing techniques to identify variable names, functions, comments, and control structures within the code. This results in a list of program components, which are extracted as analysis results. These analysis results form the basis for generating the specification document.

[0620] Step 3:

[0621] The server automatically generates a specification document based on the analysis results. In this step, the analysis results are provided as input. The server uses a template engine to convert the analysis data into natural language and generate the specification document text. The output is a specification document that describes the system's functions and operational specifications in detail. This specification document is stored in a database and provided in a format that users can access as needed.

[0622] Step 4:

[0623] The server performs a risk analysis based on the generated specifications. The generated specifications are used as input. This analysis identifies high-risk areas by evaluating the complexity of the program and the dependencies between modules. High-risk areas are identified through statistical analysis and comparison with known risk patterns. The output is a list of the areas where risks have been identified.

[0624] Step 5:

[0625] The server proposes specific operational verification methods for high-risk areas. The results of the risk analysis are used as input. Based on these results, the server automatically creates test cases. These test cases include specific operational verification procedures, such as "verify that the inventory count is greater than or equal to zero." The output provides developers with specific test proposals. This process allows developers to easily plan and execute tests for critical areas.

[0626] (Application Example 1)

[0627] 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".

[0628] In the inventory management process at a logistics center, when workers modify or develop new program data, it is necessary to quickly and accurately create design specifications and assess the associated risks. However, conventional methods are time-consuming and cumbersome, and suffer from inconsistent accuracy in specifications and reliability in risk assessments.

[0629] 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.

[0630] In this invention, the server includes means for an information processing unit to receive program data, means for automatically generating design specifications using a generative model, means for performing a risk assessment based on the automatically generated design specifications and indicating areas for functional verification, and means for presenting the design specifications and risk information to field workers in real time via a user interface. This makes it possible to carry out the inventory management process in a logistics center in an efficient and reliable manner.

[0631] An "information processing unit" is a device that has the ability to receive and analyze program data.

[0632] "Program data" refers to the code and scripts that a system analyzes.

[0633] A "generative model" is a mechanism that uses natural language processing technology to analyze program data and generate design specifications.

[0634] A "design specification" is a document that details the functions and operation of a system automatically generated by a generative model.

[0635] "Risk assessment" is the process of identifying potential problems and risks in a system based on the generated design specifications.

[0636] A "user interface" refers to the screens and operating environments used to present information to field workers.

[0637] A "structured database" is a digital recording medium used to systematically store generated design specifications.

[0638] This invention provides a system in which a server plays a central role in efficiently supporting inventory management in a logistics center. Program data is uploaded to the server by field workers from their terminals to initiate processing. The server utilizes an information processing unit to analyze the program data based on a generated AI model. Specifically, it uses natural language processing technology to identify elements within the data and automatically generates design specifications based on these elements.

[0639] The generated design specifications are immediately subjected to risk assessment to identify potential risks and areas for improvement in the system. This allows users to view the design specifications, including risk information, in real time through the user interface. Natural language processing technologies such as OpenAI and spaCy are used in this process to generate specifications and perform risk assessment.

[0640] Furthermore, the server systematically stores the generated design specifications in a structured database, making them accessible to users at any time. By streamlining this entire process, workers can utilize data analysis results both online and offline to perform inventory management with greater accuracy.

[0641] As a concrete example, consider a script for a new inventory management system in a logistics center. When an employee uploads the script to the server using their smartphone, the server quickly generates a specification document and displays specific risk factors, such as "operation points where inventory counts may become inconsistent," in the user interface. This facilitates verification of behavior and implementation of necessary countermeasures.

[0642] Example of a prompt:

[0643] "Analyze the code for the new inventory management script, generate relevant specifications, and identify any risky areas. Please also suggest test cases if possible."

[0644] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0645] Step 1:

[0646] The user uploads program data from their terminal to the server. The input here is the program data prepared by the user, and this serves as the starting point for processing. The server receives this data and prepares for the next analysis process.

[0647] Step 2:

[0648] The server analyzes the received program data using natural language processing techniques. The input is the uploaded program data, and the output is the analyzed information. In this step, the generative AI model identifies variable names, functions, comments, control structures, etc., and extracts data.

[0649] Step 3:

[0650] The server automatically generates design specifications based on the analysis results. The input is the analyzed information obtained in step 2, and the output is the design specification document. The generation model automatically generates the design specifications in natural language based on the analysis information, clarifying the technical details.

[0651] Step 4:

[0652] The server performs a risk assessment based on the generated design specifications. The input is the design specifications generated in step 3, and the output is the result of the risk assessment. The process extracts high-risk areas and identifies parts that require special attention.

[0653] Step 5:

[0654] The server presents the user with design specifications and risk information generated through the user interface in real time. The input is the result of the risk assessment, and the output is the information displayed on the user interface. Based on this, the user can easily confirm the specific actions that should be taken.

[0655] Step 6:

[0656] The server saves the generated design specifications to a structured database. The input is the design specification document, and the output is the information stored in the database. In this step, the information is stored in a format that can be referenced long-term.

[0657] 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.

[0658] This invention combines a system that analyzes program code using an information processing device and automatically generates specifications based on the results with an emotion engine that recognizes user emotions. The aim of this system is to enable users to efficiently generate program specifications and optimize their user experience.

[0659] First, the user uploads the program code to be analyzed to the server using a terminal. The server receives this code and performs analysis using a generative model based on natural language processing technology. This analysis identifies variable names, functions, comments, and control structures within the code. Based on this information, the server automatically generates a specification document. This specification document details the program's functions, operating procedures, and potential risks.

[0660] Furthermore, the server is equipped with an emotion engine that recognizes user emotions and can determine the user's emotional state by analyzing their voice input. The emotion engine analyzes emotional data in real time as the user interacts with the system and adaptively optimizes the user interface based on this analysis. Through this process, the system can reduce user stress and provide a more user-friendly interface.

[0661] As a concrete example, consider a situation where a user is modifying a program while viewing a specification document. If the user expresses an emotion such as "This is troublesome" verbally, the emotion engine can recognize that emotion, and the server can either simplify the display of the specification document or suggest ways to streamline the process.

[0662] Thus, the present invention contributes to improving system quality and reducing development man-hours by deepening the understanding of programs and providing flexible operability that responds to emotions.

[0663] The following describes the processing flow.

[0664] Step 1:

[0665] The user uses a terminal to upload the program code they wish to have analyzed to the server. The server receives this code correctly and stores it in a database to proceed to the next step.

[0666] Step 2:

[0667] The server prepares the received program code for input into the generation model. Here, it verifies that the code is in a format suitable for analysis and performs preprocessing as needed.

[0668] Step 3:

[0669] The server analyzes the program code using a generative model. At this stage, natural language processing techniques are used to identify variable names, functions, comments, and control structures within the code, and to obtain data that automatically generates specifications based on this information.

[0670] Step 4:

[0671] Based on the analysis data, the server automatically generates a detailed specification document that includes the program's functions, operating procedures, and potential risks. This specification document is written in natural language and is in a format that is easy for users to understand.

[0672] Step 5:

[0673] The emotion engine installed on the server accepts voice input from the user and recognizes their emotions. This engine analyzes the voice data and determines the emotional state in real time.

[0674] Step 6:

[0675] Based on emotional data recognized by the emotion engine, the server dynamically optimizes the user interface. For example, if it detects user stress or confusion, features such as simplifying operating procedures or providing advice are activated.

[0676] Step 7:

[0677] Finally, the server provides the user with the generated specifications. The specifications are output in the format specified by the user, and the user can view them on their terminal and use them for project management and development.

[0678] (Example 2)

[0679] 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".

[0680] When program analysis and specification creation are performed manually, the process is often time-consuming and inefficient. Furthermore, since work efficiency varies depending on the user's emotions, it is important to reduce the burden on users and provide a more user-friendly interface. To solve these problems, there is a need for a system that automates program code analysis and specification creation, and that also provides an optimal interface tailored to the user's emotions.

[0681] 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.

[0682] In this invention, the server includes means for receiving program code, means for analyzing the program code using a generative model and automatically generating specifications, means for analyzing voice data and determining the user's emotions, and means for optimizing the user's interface based on the results of the emotion determination. This enables the automation of program analysis and specification generation, as well as the provision of an optimal interface to the user.

[0683] An "information processing device" is a computer system that receives, analyzes, and outputs data.

[0684] "Program code" is a description of instructions given to a computer, and is usually written in a specific programming language.

[0685] A "generative model" is an algorithm or system that processes input data and automatically generates a specific output result.

[0686] A "specification document" is a written description of the functions, operation, and risks of a program or system.

[0687] "Risk analysis" is the process of identifying potential risks associated with a particular project or process and planning preventive measures and countermeasures based on those risks.

[0688] "Audio data" refers to data that records human voices in digital format.

[0689] "Emotional judgment" is the process of inferring a person's emotional state from audio data, facial expression analysis, and other sources.

[0690] An "interface" is a point of contact or means for information exchange between a system and a user, or between different systems.

[0691] This invention is a system that utilizes a server as an information processing device and a terminal as a user interface. The user uploads program code to the server using the terminal. In this process, the terminal software is equipped with a function that allows the user to select program files from their local drive and send them to the server.

[0692] The server analyzes the received program code using a generative AI model. This model utilizes natural language processing techniques to identify variable names, functions, comments, and control structures from the code. Based on this analysis, the server automatically generates a specification document that includes the program's function, purpose, risks, and operating procedures.

[0693] Furthermore, the server uses an emotion engine to analyze voice data from the user and determine their emotions in real time. This emotion analysis allows the interface to adaptively optimize itself to reduce the stress and frustration the user experiences while using it. For example, if a user utters a voice command like "This is a hassle," the emotion engine recognizes this, and the server immediately suggests simplifying the specifications or improving the operation procedure to make it smoother.

[0694] For example, if a user enters a prompt such as, "Analyze this program code and automatically generate a specification document. Also, simplify the operating procedures that should be replaced," the server will perform the appropriate processing based on that prompt.

[0695] This invention provides an efficient work environment and reduces the burden on users by automating everything from program analysis and specification creation to optimizing interfaces based on emotions.

[0696] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0697] Step 1:

[0698] The user uses a terminal to select the program code to be analyzed and uploads it to the server. The input is the program file selected by the user, and the output is the transmission of that file to the server. In this process, the user uses a file selection menu to find the necessary file and then presses the "Upload" button.

[0699] Step 2:

[0700] The server receives the uploaded program code and begins analysis using a generative AI model. The input is the program code submitted by the user, and the output is the identification of variable names, functions, comments, and control structures within the code. The analysis is performed by reading the code line by line, and the generative AI model utilizes natural language processing techniques to understand the grammar and structure of the code.

[0701] Step 3:

[0702] The server initiates a process to automatically generate specifications based on the analysis results. The input is the analysis results obtained in step 2, and the output is a specification document describing the program's functions, objectives, risks, and operating procedures. At this stage, the server fills in a document template based on the analysis data and formats it into a document in the specified format.

[0703] Step 4:

[0704] The server has an emotion engine that receives voice input from the user. The input is the user's voice data, and the output is a judgment of their emotional state. Here, the server analyzes the voice data in real time and detects keywords that indicate an emotion such as "this is a hassle."

[0705] Step 5:

[0706] Based on the emotion assessment in the previous step, the server optimizes the user interface. The input is the emotion state determined in step 4, and the output is, for example, a simplified display of the specifications or suggestions for improving the operating procedures. In this process, the server automatically adjusts the interface settings and immediately reflects UI changes so that the user can use the system more comfortably.

[0707] (Application Example 2)

[0708] 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".

[0709] In modern industrial sectors, there is a demand for increased efficiency in program development and maintenance, as well as optimization of the user experience during software operation. However, conventional technologies require considerable effort to create specifications due to the complexity of the programs, and have not adequately achieved improvements in usability that respond to user emotions. This results in challenges such as inefficiency and user stress.

[0710] 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.

[0711] In this invention, the server includes means for receiving program content, means for analyzing the program content using a generative model and automatically generating a document, means for analyzing voice input and determining the emotional state, and means for dynamically optimizing the user interface based on the emotional state. This enables the automatic and efficient creation of program specifications and immediate UI adaptation to the user's emotions.

[0712] An "information processing system" is a device that receives program content, analyzes it, and performs dynamic interface optimization.

[0713] "Program content" refers to a collection of data that describes the instructions and processing procedures necessary for a machine to operate.

[0714] A "generative model" refers to an algorithm that analyzes program content and outputs it as a natural language document.

[0715] A "document" is a record of information generated to clearly explain the functions, operating procedures, risks, etc., of a program.

[0716] "Risk assessment" is the process of determining the potential for latent problems and defects within a program based on analyzed documents.

[0717] "Operational verification points" refer to the points where important operations during program execution should be checked and verified.

[0718] "Implementation method" refers to the specific procedures and methods related to verifying the program's operation and managing its functions.

[0719] "Voice input" refers to information obtained by converting the user's voice into digital data, making it recognizable by the system.

[0720] "Emotional state" refers to a linguistic or numerical representation of the psychological state inferred from the user's voice and actions.

[0721] "User interface" refers to the overall screens and operating methods that users encounter when interacting with a system.

[0722] "Dynamic optimization" is the process of adjusting the interface and functions in real time according to the user's situation and emotions.

[0723] This invention uses an information processing system as a component to achieve analysis of its program content, automatic generation of specifications, and optimization of the interface based on user emotions.

[0724] The server first receives the contents of robot control systems and other machine programs from the user's terminal. Next, it analyzes the received program contents using a generative AI model. This analysis uses Python's natural language processing libraries (e.g., NLTK, spaCy) to identify variables, functions, comments, and control structures within the code. Based on this information, it automatically generates a document that describes the program's functions and operating procedures in detail.

[0725] The generated documents are provided in LaTeX or Markdown format and stored in a structured database. This allows developers to quickly deepen their understanding of the program and perform development and maintenance efficiently.

[0726] Furthermore, the server uses TensorFlow and other machine learning libraries to perform emotion recognition in order to analyze voice input in real time. Based on the emotional state, dynamic user interface optimization is performed using React.js. For example, if the user feels stressed, the screen display will be simplified, or specific assistance functions will be suggested.

[0727] As a concrete example, consider a scenario where a new robotic arm is introduced to a factory production line. While developers understand the program through specifications, they might react verbally to any unclear points. If the emotion recognition system detects an emotion like "I'm confused," it will display detailed tutorials and reference information accordingly. This improves the user's work efficiency.

[0728] As an example of a prompt, you could instruct the system to "generate a method to adjust the program specification display based on how the user describes the program's complexity using voice."

[0729] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0730] Step 1:

[0731] The server receives program content from the user's terminal. It receives the program code sent from the terminal as input and temporarily stores it in the database. This prepares the server for analysis.

[0732] Step 2:

[0733] The server analyzes the received program content using a generative AI model. Specifically, it uses natural language processing libraries (e.g., NLTK, spaCy) to identify components within the code (variables, functions, comments, control structures). The input is program code, and the output is structured data as a result of the analysis.

[0734] Step 3:

[0735] The server automatically generates documents based on the analyzed data. These documents include program functions, operating procedures, and risk information. The input is the analyzed data from step 2, and the output is a document in LaTeX or Markdown format. A document generation tool is used for generation.

[0736] Step 4:

[0737] The server stores the generated documents in a structured database. The input is the documents created in step 3, and saving them to the database makes them accessible at any time.

[0738] Step 5:

[0739] The server runs an emotion recognition model using TensorFlow to analyze the user's voice input in real time. The input is audio data from the microphone, and after digital conversion of the audio, it outputs data that numerically represents the emotional state.

[0740] Step 6:

[0741] The server dynamically optimizes the user interface based on the emotional state. It adjusts UI components using React.js based on the data. The input is the emotional state obtained in step 5, and the output is the UI change corresponding to that emotional state (e.g., simplify the screen, display additional information).

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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."

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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 as being incorporated by reference.

[0763] The following is further disclosed regarding the embodiments described above.

[0764] (Claim 1)

[0765] The information processing device includes means for receiving program code,

[0766] A method for analyzing program code using a generative model and automatically generating specifications,

[0767] Based on automatically generated specifications, a risk analysis is performed, and a method is proposed to identify the locations and methods for operational verification.

[0768] A means of providing the generated specifications in a predetermined format,

[0769] A system that includes this.

[0770] (Claim 2)

[0771] The system according to claim 1, wherein the generative model uses natural language processing techniques.

[0772] (Claim 3)

[0773] The system according to claim 1, wherein the information processing device stores the generated specifications in a structured database.

[0774] "Example 1"

[0775] (Claim 1)

[0776] The information processing device includes means for receiving program code,

[0777] A method for analyzing program code using a generative AI model and automatically generating specifications using natural language processing technology,

[0778] Based on automatically generated specifications, this method evaluates the complexity and dependencies of the program, performs risk analysis, and proposes locations for operational verification and specific implementation methods.

[0779] A means of providing the generated specifications in a predetermined format,

[0780] A system that includes this.

[0781] (Claim 2)

[0782] The system according to claim 1, which automatically proposes specific test cases for high-risk areas using the generated specifications.

[0783] (Claim 3)

[0784] The system according to claim 1, wherein the information processing device stores the generated specifications in a database and provides them in a form that can be easily accessed by the user.

[0785] "Application Example 1"

[0786] (Claim 1)

[0787] The information processing unit has means for receiving program data,

[0788] A method for analyzing program data using a generative model and automatically generating design specifications,

[0789] A means of conducting a risk assessment based on automatically generated design specifications and presenting functional verification points and implementation methods,

[0790] A means of presenting design specifications and risk information to on-site workers in real time via a user interface,

[0791] A means for distributing the generated design specifications in a predetermined format,

[0792] A system that includes this.

[0793] (Claim 2)

[0794] The system according to claim 1, wherein the generative model uses natural language processing techniques.

[0795] (Claim 3)

[0796] The system according to claim 1, wherein the information processing unit stores the generated design specifications in a structured database.

[0797] "Example 2 of combining an emotion engine"

[0798] (Claim 1)

[0799] The information processing device includes means for receiving program code,

[0800] A method for analyzing program code using a generative model and automatically generating specifications,

[0801] Based on automatically generated specifications, a risk analysis is performed, and a method is proposed to identify the locations and methods for operational verification.

[0802] A means of providing the generated specifications in a predetermined format,

[0803] A method for analyzing voice data to determine the user's emotions,

[0804] A means of optimizing the user interface based on the results of emotional judgment,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, wherein the generative model uses natural language processing techniques.

[0808] (Claim 3)

[0809] The system according to claim 1, wherein the information processing device stores the generated specifications in a structured database.

[0810] "Application example 2 of combining emotional engines"

[0811] (Claim 1)

[0812] An information processing system includes means for receiving program content,

[0813] A means of analyzing program content using a generative model and automatically generating documents,

[0814] A means of conducting a risk assessment based on automatically generated documents and presenting the locations and methods for verifying functionality,

[0815] Means for providing the generated document in a predetermined format,

[0816] A method for analyzing voice input to determine emotional state,

[0817] A means of dynamically optimizing the user interface based on emotional state,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, wherein the generative model uses natural language processing techniques.

[0821] (Claim 3)

[0822] The system according to claim 1, wherein the information processing system stores the generated documents in a structured database. [Explanation of Symbols]

[0823] 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. The information processing device includes means for receiving program code, A method for analyzing program code using a generative model and automatically generating specifications, Based on automatically generated specifications, a risk analysis is performed, and a method is proposed to identify the locations and methods for operational verification. A means of providing the generated specifications in a predetermined format, A system that includes this.

2. The system according to claim 1, wherein the generative model uses natural language processing technology.

3. The system according to claim 1, wherein the information processing device stores the generated specifications in a structured database.

Images