System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing requirement data input from a user by using natural language processing; means for extracting relevance of the requirement data by using machine learning and displaying the extracted relevance as a graph; means for automatically generating a requirement document by using template generation artificial intelligence and performing grammar check; and means for establishing traceability of requirements, implementation, and test by utilizing a data mining technique and evaluating change influence.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Business departments considering systemization often face difficulties in defining requirements. Creating requirements definition documents and system requirement specifications can be a significant burden, especially when business personnel lack specialized knowledge of systems development. This can result in delays from the early stages of system development, hindering smooth progress throughout the project. Furthermore, inaccuracies and lack of traceability in the requirements definition stage can lead to rework in later stages. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, it provides a means for analyzing requirements data entered by a user using natural language processing. Next, it provides a means for extracting relevance of requirements data using machine learning and displaying it as a graph. It also provides a means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. It also provides a means for establishing traceability of requirements, implementation, and testing using data mining technology and evaluating the impact of changes. This makes the requirements definition process more efficient, improves the accuracy and traceability of requirements, and reduces the burden on business personnel.

[0006] "Natural language processing" is a technology that allows a computer to understand and analyze human language, and is used to analyze text data entered by a user and identify requirements.

[0007] "Machine learning" is a technology that allows computer systems to analyze data, recognize patterns, and learn automatically. It is a technology used to extract and display relationships between collected requirements data.

[0008] "Template generation AI" is a technology that uses artificial intelligence to generate document formats suitable for specific purposes, and is used to automatically generate requirements documents and perform grammar checks.

[0009] "Data mining" is a technique used to extract valuable information from large amounts of data, establish traceability of requirements, implementation and testing, and assess the impact of changes.

[0010] "Requirements traceability" is the ability to track how requirements are implemented and tested, mapping the relationships between requirements, implementations, and test cases in real time and assessing the impact of changes.

[0011] A "user interface" is an interface through which a user interacts with a system and is used by the user to interactively gather requirements.

[0012] An "online collaborative editing tool" is a tool that allows multiple users to edit documents simultaneously, enabling collaborative editing of requirements specifications in real time. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

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

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

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

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0034] The present invention describes a specific embodiment of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies to automate and streamline the requirements definition process.

[0035] 1. Requirements gathering support

[0036] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[0037] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[0038] 2. Requirements analysis support

[0039] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[0040] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[0041] 3. Support for requirements documentation

[0042] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and performs grammar checks during the document generation process.

[0043] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[0044] 4. Requirements tracing support

[0045] The server utilizes data mining techniques to establish traceability between collected requirements and implementations and test cases, enabling real-time tracking of how requirements were implemented and tested.

[0046] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[0047] ---

[0048] The advantages of this invention are realized by explaining the specific processing flow and clarifying the specific operations of the server, terminal, and user at each step, which automates the entire requirements definition process and dramatically improves efficiency and accuracy.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[0052] Step 2:

[0053] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[0054] Step 3:

[0055] The server analyzes the input requirements using natural language processing (NLP) technology. Specifically, it tokenizes the requirement sentence and extracts key keywords. For example, it extracts "customer," "order," "cancellation," and "function."

[0056] Step 4:

[0057] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[0058] Step 5:

[0059] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[0060] Step 6:

[0061] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[0062] Step 7:

[0063] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[0064] Step 8:

[0065] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[0066] Step 9:

[0067] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[0068] Step 10:

[0069] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[0070] Step 11:

[0071] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[0072] Step 12:

[0073] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[0074] Step 13:

[0075] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[0076] Step 14:

[0077] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[0078] Step 15:

[0079] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[0080] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of the present invention are realized, and the requirements definition process is automated and made more efficient.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] Conventional requirements definition processes require extensive manual operations and complex data analysis, resulting in issues with efficiency and accuracy. Furthermore, requirements collection, analysis, documentation, and traceability are often separated, making it difficult to maintain consistency of information across each process. The present invention aims to solve these issues by providing a system that automates the entire requirements definition process and improves efficiency and accuracy.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes: means for tokenizing requirements information entered by a user using natural language processing technology and extracting important keywords; means for calculating and classifying features of the requirements information using a machine learning algorithm and generating a graph that visualizes the relevance of the requirements information based on the features; means for automatically creating a requirements document based on the requirements information using template generation artificial intelligence and performing grammar checks using natural language processing technology; and means for establishing traceability between the requirements information, implementation code, and test cases using data mining technology, and automatically identifying and notifying affected parts when changes occur. This enables the automation and efficiency of the entire requirements definition process.

[0086] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[0087] "User" refers to a person who uses the system to input, check, and edit requirements information.

[0088] "Requirements information" is information that describes the functions and characteristics required of a system.

[0089] "Tokenization" is the process of breaking down natural language into its smallest units, such as words and phrases.

[0090] "Important keywords" refer to words or phrases that are considered to be particularly important in the requirements information.

[0091] A "machine learning algorithm" is a computational method for learning patterns and rules based on data and making predictions and classifications.

[0092] "Features" refer to the attributes and variables of data input into a machine learning model.

[0093] "Visualization" is the process of representing data and information in an intuitive and easy-to-understand way using graphs and charts.

[0094] "Template generation artificial intelligence" is an artificial intelligence technology that automatically creates documents and formats based on specified requirements.

[0095] "Grammar checking" is the process of detecting grammatical errors in a sentence and suggesting corrections.

[0096] "Data mining technology" is an analytical technique for extracting useful information from large amounts of data.

[0097] "Traceability" is the ability to trace the relationship from requirements to implementation to testing and identify the impact of any changes.

[0098] "Implementation code" refers to the actual program code written to meet the system requirements.

[0099] A "test case" refers to specific test conditions and procedures for verifying that specific functions or requirements of a system are implemented correctly.

[0100] "Notification" is the act of the system informing the user about a particular event or change.

[0101] MODE FOR CARRYING OUT THE INVENTION

[0102] This invention relates to a system that automates and streamlines the requirements definition process by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. This system aims to integrate and automate the entire process of requirements gathering, analysis, documentation, and traceability.

[0103] Requirements gathering support

[0104] First, the user inputs requirements information using the terminal's interactive collection GUI, which provides an interface that accepts natural language prompt input. For example, the user might input a requirement such as, "I need a feature that allows customers to cancel orders."

[0105] The server then uses natural language processing techniques (e.g., NLTK or spaCy) to tokenize the requirements and extract important keywords. For example, keywords like "customer," "order," and "cancellation" are extracted. Based on these keywords, the server determines the requirement category and matches it with an existing requirements database. This process detects similar, overlapping, or conflicting requirements.

[0106] If necessary, the server generates templates and samples and displays them on the terminal to help the user make decisions. For example, displaying a template for a "cancel function" used in a past project can help clarify requirements.

[0107] Requirements analysis support

[0108] The server analyzes the collected requirements information using machine learning algorithms (e.g., Scikit-Learn or TensorFlow). The collected requirements data is converted into features. For example, a dataset with features such as "customer," "order," and "cancellation" is generated.

[0109] Next, this dataset is fed into a machine learning model to classify requirements and analyze their relationships. As a result, the relationships between basic and derived requirements are identified. Based on the results of this analysis, the server generates a graph to visualize the relationships between requirements and displays it on the terminal. This provides users with requirement priorities and risk assessment information to support decision-making.

[0110] Requirements documentation support

[0111] The template generation AI automatically generates requirements documents based on collected and analyzed requirements information. Based on user input, it suggests appropriate document formats and performs grammar checks on the automatically generated documents.

[0112] Grammar checking is performed using the server's natural language processing technology (e.g., Grammarly API), and suggested corrections are presented to the user. Users can edit the requirements specification document in real time using an online collaborative editing tool (e.g., Google Docs). The server automatically updates the document when changes are made and manages the change history.

[0113] Requirement tracing support

[0114] Finally, the server uses data mining technology to establish traceability between the requirements information, the implementation code, and the test cases. Specifically, it analyzes and maps the relationships between the collected requirements, the implementation code, and the test cases.

[0115] The mapping results are displayed on the terminal, visualizing the relationships, allowing users to directly check the relationship between requirements and implementation. Furthermore, when changes occur, the server automatically identifies the affected implementation and tests, and notifies the user of the necessary modifications.

[0116] Specific examples

[0117] Example prompt sentence:

[0118] "We need the ability for customers to cancel their orders."

[0119] Using this system, the entire requirements definition process described above is automated, dramatically improving efficiency and accuracy.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The user uses the terminal's collection GUI to input requirement information. For example, they might input "I need a feature that allows customers to cancel orders." The input in this step is text information in natural language, and the output is raw data for the server to analyze.

[0123] Step 2:

[0124] The server analyzes the input requirements information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the requirements sentences and extracts important keywords. For example, tokens such as "customer," "order," and "cancellation" are generated. The input in this step is the raw requirements information, and the output is a tokenized keyword list.

[0125] Step 3:

[0126] The server determines the category of the requirement based on the extracted keywords and compares it with the existing requirements database. A specific operation here is to check whether "cancellation" belongs to "customer management functions." The input in this step is a keyword list, and the output is the category determination result and the database comparison result.

[0127] Step 4:

[0128] The server detects whether there are similar, overlapping, or conflicting requirements, and generates templates or samples as needed, which are then displayed on the device. For example, it displays a template for a "cancel function" used in a past project. The input in this step is the category determination results and matching results, and the output is the presentation of templates or samples.

[0129] Step 5:

[0130] The server analyzes the collected requirements information using a machine learning algorithm (e.g., Scikit-Learn or TensorFlow). The requirements data is converted into features and fed into the machine learning model. For example, features such as "customer," "order," and "cancellation" are calculated. The input in this step is the requirements data, and the output is a list of features and a classification result.

[0131] Step 6:

[0132] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The visualized graph includes requirement priority and risk assessment information. For example, a graph is generated showing that "cancellation function" is related to "order management function." The input in this step is the analysis results, and the output is the visualized graph.

[0133] Step 7:

[0134] The template generation AI automatically generates a requirements document based on requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and grammar checks are also performed during the document generation process. Specifically, it generates a requirement statement such as "We need a function that allows customers to cancel orders." The input in this step is requirements data, and the output is a requirements document.

[0135] Step 8:

[0136] The server checks the generated document for grammar using natural language processing technology (e.g., Grammarly API) and suggests corrections. Users can edit the document in real time using online collaborative editing tools (e.g., Google Docs). The input in this step is the requirements document, and the output is the grammar check results and suggested corrections.

[0137] Step 9:

[0138] The server automatically updates the document when changes are made and maintains the change history. For example, when a user adds or modifies a document, the changes are immediately reflected and recorded in the history. The input in this step is the edited document, and the output is the updated document and the change history.

[0139] Step 10:

[0140] The server uses data mining technology to establish traceability between requirements information, implementation code, and test cases. Specifically, it analyzes and maps the relationships between collected requirements, implementation code, and test cases. The input in this step is requirements information, and the output is the mapping results.

[0141] Step 11:

[0142] When a change occurs, the server automatically identifies the implementation and tests of the affected parts and notifies the user of the necessary modifications. For example, if there is a change to the "cancel function," other affected functions and test cases will be identified and notified. The input to this step is the changed requirements information, and the output is the impact analysis results and notification of the modifications.

[0143] (Application example 1)

[0144] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0145] In modern factories, improved work efficiency is required, as well as accuracy and speed in the requirements definition process. However, manually collecting requirements, analyzing them, documenting them, and establishing traceability is time-consuming and prone to errors. It is also difficult to manage work progress in real time, making it difficult to respond quickly when problems occur. Furthermore, a lack of visualization of work data and provision of related information can delay decision-making by workers and managers.

[0146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0147] In this invention, the server includes: means for analyzing requirements data entered by a user using natural language processing; means for extracting relevance of the requirements data using machine learning and displaying it as a graph; means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks; means for establishing traceability of requirements, implementation, and testing using data mining technology and evaluating the impact of changes; means for inputting work requirements by voice using a smart device and processing the data in real time; and means for visually presenting work progress and related information in real time and providing necessary corrections. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and enabling real-time work management and rapid response.

[0148] "Natural language processing" is the technology of using computers to understand, analyze, and generate human language.

[0149] "Machine learning" is an algorithm that allows a computer to make decisions by feeding it large amounts of data and automatically learning patterns.

[0150] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates sentences and documents based on a specified format.

[0151] "Data mining" is a technique for discovering useful information and relationships from large amounts of data.

[0152] A "smart device" is an advanced electronic device with internet connectivity and a variety of functions.

[0153] "Voice input" is a technology that inputs voice into a computer or device and converts it into text or commands.

[0154] "Real-time" means that data and information is processed and provided almost immediately.

[0155] "Work progress" is information that indicates how much work has progressed or been completed.

[0156] "Visually presented" means displaying information graphically and making it easy to understand.

[0157] The "requirements definition process" is a procedure for describing the requirements of a system or project in detail and achieving a common understanding.

[0158] This invention provides a system for automating and streamlining the requirements definition process in a factory by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. Specific embodiments are described below.

[0159] System Overview

[0160] The system consists of a smart device (smart glasses or head-mounted display) and a server. The smart device has the function of converting voice input into text data and sending it to the server. The server analyzes the received text data and executes an automated requirements definition process.

[0161] Hardware and Software Used

[0162] Smart Devices: Voice Input and Real-Time Notifications

[0163] Server: Data analysis and processing

[0164] Natural language processing software: SpaCy and NLTK

[0165] Machine learning frameworks: Scikit-learn and TensorFlow

[0166] Template generation AI: GPT-3

[0167] Data mining tools: Weka and RapidMiner

[0168] Details of the process

[0169] 1. Voice input and text conversion

[0170] The user uses the microphone in the smart glasses to input the task requirements by voice, and the smart glasses convert the voice data into text data using the Google Speech-to-Text API or similar.

[0171] The converted text data is sent from the smart device to the server.

[0172] 2. Requirements analysis and relevance assessment

[0173] The server tokenizes the received text data using natural language processing software (e.g., SpaCy or NLTK) and extracts important keywords.

[0174] Based on the extracted keywords, a machine learning framework (e.g., Scikit-learn or TensorFlow) is used to analyze the priority and risks of requirements.

[0175] The analysis results are visualized as a relevance graph and displayed in real time on smart devices.

[0176] 3. Requirements documentation

[0177] Using a template generation AI (e.g., GPT-3), a requirements specification document is automatically generated from the analysis results. Grammar checks are also performed during the document generation process.

[0178] The generated requirements specification document is provided to users and administrators and can be edited in real time through online collaborative editing tools.

[0179] 4. Requirements tracing and real-time notifications

[0180] The server uses data mining tools (e.g., Weka or RapidMiner) to establish traceability between requirements, implementation code, and test cases.

[0181] Work progress and related information are visually displayed on smart devices in real time, and if a problem occurs, you are immediately notified and provided with the necessary corrections.

[0182] Examples of specific examples and prompts

[0183] For example, a worker wearing smart glasses can input "The conveyor belt speed on line C4 needs to be increased by 30%" through voice input. The server receives and analyzes this information, and displays the associated risks and countermeasures on the smart glasses. The generated requirements specification document is provided to the manager, and work progress is updated in real time.

[0184] Example prompts for generative AI models

[0185] "We need to increase the speed of our factory conveyor belts by 30%. Please generate a requirements document for this requirement, including a risk assessment and associated work."

[0186] As a result, the present invention not only dramatically improves the efficiency and accuracy of factory work, but also enables quick response when problems occur.

[0187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0188] Step 1:

[0189] Voice input and text conversion

[0190] The user uses the microphone on the smart device to input the task requirements by voice, and the smart device converts the input voice data into text data using a speech recognition tool such as the Google Speech-to-Text API, which then sends the converted text data from the smart device to the server.

[0191] Input: Voice data from the user

[0192] Output: Text data

[0193] Specific operation: The smart device records voice, and the voice recognition engine analyzes the voice data and converts it into text.

[0194] Step 2:

[0195] Requirements analysis

[0196] The server receives the text data and uses natural language processing (NLP) software (e.g., SpaCy or NLTK) to tokenize the text data and extract important keywords.

[0197] Input: Text data converted from audio

[0198] Output: Keywords and tokenized text

[0199] What happens: The server breaks the text into tokens and performs text analysis to identify keywords.

[0200] Step 3:

[0201] Relevance assessment

[0202] The server uses machine learning algorithms (e.g., Scikit-learn or TensorFlow) based on the extracted keywords to evaluate the priority and risk of requirements. Based on the analysis results, it generates a relevance graph and displays it to the user.

[0203] Input: Extracted keywords

[0204] Output: Requirement priorities, risk assessment, and relationship graphs

[0205] How it works: The server feeds data into a machine learning model, calculates priorities and risks, and generates a visual graph.

[0206] Step 4:

[0207] Requirements documentation

[0208] The server uses template generation AI (e.g., GPT-3) to automatically generate a requirements specification document from the analysis results. It also performs grammar checks during document generation and provides the generated document to users and administrators.

[0209] Input: Parsed requirements data

[0210] Output: Automatically generated requirements specification

[0211] Specific operation: The server provides data to the template generation AI, generates a requirements specification document, and checks the grammar.

[0212] Step 5:

[0213] Requirement Tracing and Notifications

[0214] The server uses data mining tools (e.g., Weka and RapidMiner) to establish traceability between requirements, implementation code, and test cases. It visually displays work progress and related information in real time on smart devices, and immediately notifies users if any problems occur. It also provides necessary fixes.

[0215] Input: Requirements specification, implementation code, test cases

[0216] Output: Traceability map, real-time notifications, remediation guidelines

[0217] Specific operation: The server analyzes the relationship between requirements, implementation, and testing, generates notifications about progress and when problems occur, and sends them to the smart device.

[0218] As a result, the present invention automates and streamlines the requirements definition process in a factory, supporting appropriate work management and rapid response.

[0219] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0220] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[0221] 1. Requirements gathering support

[0222] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[0223] Furthermore, an emotion engine is used to recognize the user's emotions in real time as they input data. For example, if the user appears irritated, the server will change the content and presentation of the collection GUI to provide an environment that makes it easier for the user to input data.

[0224] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[0225] 2. Requirements analysis support

[0226] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[0227] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[0228] Furthermore, the system uses an emotion engine to dynamically adjust the priority and risk assessment of requirements analysis according to changes in the user's emotions. For example, if the user is feeling anxious, the system will review the most important requirements first, thereby reassuring the user.

[0229] 3. Support for requirements documentation

[0230] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to adjust specific expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it will use more gentle expressions and positive vocabulary.

[0231] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[0232] 4. Requirements tracing support

[0233] The server utilizes data mining techniques to establish traceability between collected requirements and implementation code and test cases, enabling real-time tracking of how requirements were implemented and tested.

[0234] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[0235] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of this invention are realized. The entire requirements definition process is automated, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[0236] The processing flow will be explained below.

[0237] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[0238] Step 1:

[0239] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[0240] Step 2:

[0241] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[0242] Step 3:

[0243] The device's built-in emotion engine recognizes the user's emotions in real time from their facial expressions and tone of voice. If the emotion is irritation or anxiety, the device will adjust the content and presentation method.

[0244] Step 4:

[0245] The server analyzes the input requirements using natural language processing (NLP) techniques. It tokenizes the requirement statements and extracts key keywords. For example, it extracts "customer", "order", "cancellation", and "function".

[0246] Step 5:

[0247] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[0248] Step 6:

[0249] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[0250] Step 7:

[0251] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[0252] Step 8:

[0253] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[0254] Step 9:

[0255] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[0256] Step 10:

[0257] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[0258] Step 11:

[0259] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[0260] Step 12:

[0261] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[0262] Step 13:

[0263] The server adjusts certain expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it uses softer expressions and more positive vocabulary.

[0264] Step 14:

[0265] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[0266] Step 15:

[0267] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[0268] Step 16:

[0269] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[0270] Step 17:

[0271] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[0272] By clarifying the specific process flow and the operations at each step, the advantages of this invention are realized, automating the entire requirements definition process, dramatically improving efficiency and accuracy, and taking user emotions into consideration to provide a more user-friendly experience.

[0273] Example 2

[0274] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0275] The traditional requirements definition process had problems such as ambiguity in user input and subjective bias, making it time-consuming and labor-intensive to collect and analyze requirements. It was also unclear how requirements would be tracked and changes managed during the implementation and testing phases, making traceability difficult. Furthermore, inconsistent UI / UX design that did not take user emotions into consideration often resulted in a poor user experience. Effective methods to resolve these issues are needed.

[0276] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0277] In this invention, the server includes means for analyzing requirements data entered by a user using natural language processing, means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[0278] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0279] "Machine learning" is a technique that trains algorithms based on data to make predictions and classifications.

[0280] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents based on a predefined format.

[0281] "Data mining technology" is a technique for extracting useful patterns and knowledge from large amounts of data.

[0282] An "emotion engine" is an algorithm that detects a user's emotions and changes behavior based on them.

[0283] "Traceability" means ensuring traceability of the entire process from requirements to implementation and testing.

[0284] An "interactive collection GUI" is a graphical user interface for collecting requirements data through user interaction.

[0285] An "online collaborative editing tool" is an online tool that allows multiple users to edit and update documents simultaneously.

[0286] This invention relates to a system that automates and streamlines the requirements definition process. The main hardware is a server and a terminal, and the software uses natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining technology, and an emotion engine.

[0287] 1. Requirements Gathering

[0288] First, the user inputs business requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. This interface can also include specific examples such as "We need a function that allows customers to cancel orders." The emotion engine recognizes the user's emotions in real time as they input their requirements. For example, if the user is showing irritation, the server adjusts the content and presentation method of the collection GUI, providing an environment that makes it easier for the user to input.

[0289] 2. Requirements analysis

[0290] The server analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. If necessary, it displays templates or samples on the device to support the user's decision-making.

[0291] 3. Requirements analysis

[0292] The server analyzes the collected requirements using a machine learning algorithm. The collected data is converted into features and input into a machine learning model. This identifies the relationships between basic and derived requirements. The analysis results are generated as graphs to visualize the relationship between requirements and are displayed on the terminal. They also include requirement priority and risk assessment information to support user decision-making. An emotion engine is used to dynamically adjust the analysis results in response to changes in the user's emotions, and requirements with high importance or high risk are displayed first.

[0293] 4. Requirements documentation

[0294] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to reflect the user's emotions, as recognized by the emotion engine, and adjust specific expressions and vocabulary. For example, if the user is nervous, it will use more soft, positive vocabulary. The server uses natural language processing technology to check grammar and suggests corrections. Users can edit requirements specifications in real time using an online collaborative editing tool. The server automatically updates the document when changes are made and manages the change history.

[0295] 5. Requirements Tracing

[0296] The server uses data mining technology to establish traceability between collected requirements and implementation code and test cases. This makes it possible to track how requirements have been implemented and tested in real time. Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. The mapping results are displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected implementation and tests and notifies the user of the necessary modifications.

[0297] Specific examples and prompt sentence examples

[0298] For example, if a user requests "a feature that allows customers to cancel orders," the terminal provides an interactive collection GUI, and if the emotion engine detects frustration with the user's input, the server adjusts the interface and displays a flexible input form. The requirement is checked for overlaps with existing databases and classified as "order management." The following prompt sentence is then input to the generative AI model based on this requirement:

[0299] One requirement input was for the ability for customers to cancel orders. Users were frustrated with some of the input. In this case, we flexed the interface presentation and categorized the requirement under "Order Management." We then checked our existing database for similar requirements to find any overlaps or inconsistencies.

[0300] This system automates the entire requirements definition process, dramatically improving efficiency and accuracy, and also takes user feelings into consideration to provide a more user-friendly environment.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1:

[0303] User enters requirements

[0304] The user inputs business requirements using an interactive collection GUI, including specific requirements such as "We need a function that allows customers to cancel orders." The input requirements data is then sent to the terminal.

[0305] Input: User's business requirements (natural language text)

[0306] Output: Collected requirements data

[0307] Step 2:

[0308] The device uses an emotion engine to recognize the user's emotions in real time.

[0309] The device analyzes the user's facial expressions and tone of voice when inputting, and uses an emotion engine to recognize emotions such as irritation or dissatisfaction in real time. For example, if the user shows irritation, the device will collect emotional data.

[0310] Input: User facial expression, voice tone

[0311] Output: User emotion data

[0312] Step 3:

[0313] The server analyzes the requirements

[0314] The server receives the requirements data sent from the device and analyzes it using natural language processing technology. The requirements sentences are tokenized and important keywords are extracted. For example, keywords such as "order" and "cancel" are extracted.

[0315] Input: Collected requirements data

[0316] Output: Extracted keywords and analysis results

[0317] Step 4:

[0318] The server performs categorization and matching

[0319] The server categorizes the requirements based on the extracted keywords and compares them with existing requirements databases, for example, categorizing them into categories such as "order management" and "cancellation function." It also checks for similar, overlapping, or conflicting requirements.

[0320] Input: Extracted keywords and analysis results

[0321] Output: Categorized requirements data and matching results

[0322] Step 5:

[0323] The device displays templates and examples

[0324] Based on the results of the analysis, the server displays requirement templates and samples on the terminal, allowing the user to determine more specific requirements based on the templates and samples they refer to.

[0325] Input: Categorized requirements data and matching results

[0326] Output: The template or sample to be displayed

[0327] Step 6:

[0328] The server uses machine learning algorithms to analyze requirements

[0329] The collected requirements data is converted into features and analyzed using a machine learning model to identify relationships between base and derived requirements. For example, we analyze how the cancellation function relates to other order management requirements.

[0330] Input: Categorized requirements data

[0331] Output: Requirements association and analysis results

[0332] Step 7:

[0333] The server visualizes the analysis results

[0334] The server visualizes the relationship between requirements based on the analysis results as a graph, including requirement priority and risk assessment information. For example, the importance and risk of the cancel function are visually displayed.

[0335] Input: Requirements associations and analysis results

[0336] Output: Visualized graph

[0337] Step 8:

[0338] The device displays the analysis results.

[0339] The terminal displays visualized graphs sent from the server to the user, clearly presenting requirement priorities and risk assessments.

[0340] Input: Visualized graph

[0341] Output: The analysis results to be displayed

[0342] Step 9:

[0343] The server uses an emotion engine to dynamically adjust the analysis results.

[0344] The server monitors changes in the user's emotions and dynamically adjusts the priority and risk assessment of requirements analysis according to the user's emotions. For example, if the user feels anxious, the server will prioritize reviewing requirements of high importance.

[0345] Input: User sentiment data, requirements analysis results

[0346] Output: Dynamically adjusted analysis results

[0347] Step 10:

[0348] The server automatically generates requirements documents using template generation AI.

[0349] Based on the collected and analyzed requirements data, requirements documents are automatically generated in the appropriate document format, and grammar checks are also performed.

[0350] Input: Requirement analysis results, categorized requirement data

[0351] Output: Auto-generated requirements document

[0352] Step 11:

[0353] The server performs a syntax check

[0354] The server uses natural language processing technology to check the grammar of the generated requirements document and suggests corrections.

[0355] Input: Auto-generated requirements document

[0356] Output: Syntax-checked requirements document and suggested corrections

[0357] Step 12:

[0358] A user edits a document in an online collaborative editing tool

[0359] Users can use online collaborative editing tools to edit requirements documents in real time.

[0360] Input: Grammar-checked requirements document and suggested corrections

[0361] Output: Edited requirements document

[0362] Step 13:

[0363] The server updates changes in real time and manages the history

[0364] The server automatically reflects changes made by the user in real time to the document and manages the change history.

[0365] Input: Edited requirements document

[0366] Output: Updated requirements document and change history

[0367] Step 14:

[0368] The server uses data mining techniques to establish traceability between requirements, implementation, and testing.

[0369] It analyzes and maps the relationship between collected requirements, implementation code, and test cases, making it possible to track in real time how requirements have been implemented and tested.

[0370] Input: Requirement data, implementation code, test cases

[0371] Output: Traceability map

[0372] Step 15:

[0373] The terminal visualizes and displays the traceability results

[0374] The terminal visualizes the traceability map sent from the server and displays it to the user.

[0375] Input: Traceability map

[0376] Output: Traceability visualization results

[0377] Step 16:

[0378] Identify and notify affected server areas

[0379] When changes occur, the server automatically identifies the affected implementations and tests and notifies the user of the necessary modifications.

[0380] Input: Updated requirements data and implementation code

[0381] Output: Notice of affected parts

[0382] (Application example 2)

[0383] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0384] The traditional requirements definition process involves a lot of manual work, which can be inefficient and inaccurate. Furthermore, requirements are collected and analyzed without considering the user's feelings, which can lead to increased user dissatisfaction and stress. Furthermore, product and service proposals can sometimes be made that do not meet the user's tolerance level, resulting in a decrease in customer satisfaction.

[0385] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0386] In this invention, the server includes a means for analyzing requirements data entered by a user using natural language processing, a means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and a means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This makes it possible to recognize the user's emotions in real time during requirements collection and dynamically adjust the interface display content and presentation method. It is also possible to analyze changes in the user's emotions throughout the entire process from requirements collection to implementation and dynamically adjust the priority and risk assessment of requirements. Furthermore, it is possible to make product recommendations based on the user's needs and propose optimal products.

[0387] "Natural language processing" is the technology that enables computers to understand, generate, and manipulate human language.

[0388] "Machine learning" is a technique that refers to a computer system learning from data and improving at its tasks without being explicitly programmed.

[0389] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents and templates based on existing data.

[0390] "Data mining technology" refers to methods and techniques for extracting patterns and knowledge from large amounts of data.

[0391] The "emotion engine" is a technology that recognizes emotions in real time from human facial expressions, tone of voice, etc.

[0392] "Real-time" means that user input and actions are processed immediately.

[0393] A "user interface" refers to the screen or operating environment that allows a user to interact with a system or application.

[0394] "Traceability" refers to the ability to track how requirements are implemented and tested.

[0395] "Changes in user's emotions" refers to changes in the user's emotional state while using the system.

[0396] "Product recommendation" refers to the act of selecting and proposing the most suitable product based on the user's request.

[0397] The present invention is implemented as a smartphone app "Smart Shopping Assistant" to enhance customer experience in brick-and-mortar stores. The system includes the following main components:

[0398] Requirements gathering support

[0399] The server first collects requests entered by the user into the smartphone app. The interface is intuitive and includes a text box for entering specific requests, such as "I want a red dress," as well as a voice input function. Furthermore, the server utilizes an emotion engine to recognize the user's emotions in real time as they are being input. For example, if the emotion engine determines that the user is nervous, the server automatically switches the interface to a more user-friendly design.

[0400] Requirements analysis support

[0401] The server analyzes the request data collected from users using natural language processing (NLP) technology. NLP tokenizes the input text data and extracts important keywords. The server then uses machine learning models to match the request with a database of relevant products and services. Based on the extracted keywords, the server recommends the most suitable products.

[0402] Product recommendation

[0403] Based on the user's request, the server uses TfidfVectorizer to vectorize the request and the product information in the database, and calculates the cosine similarity. This allows the server to suggest products with the highest similarity to the user. For example, if the user's request is a "red dress," the server will present information about the most suitable red dress in stock.

[0404] Traceability and Emotion Regulation

[0405] The server analyzes the user's emotional changes in real time throughout the entire process, from requirements gathering to product recommendations. Based on this information, it dynamically adjusts requirement priorities and risk assessments. If the user is feeling stressed, the system will prioritize and recommend highly accurate products to alleviate the user's anxiety.

[0406] Hardware and Software

[0407] The following specific hardware and software is used in this system:

[0408] Smartphone app: Providing user interface and emotion recognition.

[0409] Server: Data analysis and operation of the recommendation system.

[0410] FER Library: Facial expression analysis for emotion recognition.

[0411] BERT model for transformers: Text analysis for natural language processing.

[0412] TfidfVectorizer: Vectorization and cosine similarity calculation of requirements and products.

[0413] Specific examples

[0414] Below are some specific examples of how this system can be used.

[0415] A user types "I want a red dress" into a smartphone app, and the app sends the request to a server.

[0416] The server uses the BERT model to analyze the text and recommend suitable products.

[0417] The recommended products are presented to the user, and the user's emotions are analyzed by an emotion engine.

[0418] Prompt Sentence Examples

[0419] "Please enter the product you want"

[0420] "The camera takes pictures and detects customer emotions."

[0421] "Recommend products based on customer requests"

[0422] The above describes the embodiments of the present invention, which embody the features of the invention and aim to improve the customer experience in physical stores.

[0423] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0424] Step 1:

[0425] The user inputs their request using a smartphone app. For example, they can enter a specific request such as "I want a red dress." The device then sends this input to the server via the user interface. The input is sent as text data.

[0426] Step 2:

[0427] The server analyzes the received text data using natural language processing (NLP) techniques. First, it tokenizes the input text data and extracts important keywords. In this process, it uses an NLP library (e.g., the BERT model) to perform tokenization and keyword extraction. The output is a list of extracted keywords.

[0428] Step 3:

[0429] The server uses a machine learning model to search for related products based on the extracted keyword list. It uses TfidfVectorizer to vectorize the request and product information in the database, and calculates the cosine similarity to identify the product with the highest similarity. The input is the keyword list and the product database, and the output is a list of recommended products.

[0430] Step 4:

[0431] The server sends a list of recommended products to the terminal, and the terminal presents this information to the user through a user interface. At this point, an emotion engine also operates simultaneously, analyzing the user's facial expressions and voice in real time to grasp the user's emotions. The input is the user's facial expression and voice data, and the output is the detected emotional information.

[0432] Step 5:

[0433] The server dynamically adjusts the content and presentation of the interface based on the detected user emotion information. For example, if it determines that the user is nervous, it changes the interface design to a more friendly one. The input is emotion information, and the output is the adjusted interface design.

[0434] Step 6:

[0435] The server analyzes the user's emotional changes in real time throughout the entire process, from request collection to product recommendation, and dynamically adjusts the priority and risk assessment of requirements. If the user is feeling stressed, it will recommend the most accurate product with the highest priority. The input is information on the user's emotional changes, and the output is the adjusted priority and risk assessment.

[0436] Through each of the above steps, a system is created that improves the customer experience in physical stores by making optimal product suggestions based on the user's needs and adjusting emotions in real time.

[0437] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0438] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0439] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0440] [Second embodiment]

[0441] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0442] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0443] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0444] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0445] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0446] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0447] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0448] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0449] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0450] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0451] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0452] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0453] The present invention describes a specific embodiment of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies to automate and streamline the requirements definition process.

[0454] 1. Requirements gathering support

[0455] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[0456] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[0457] 2. Requirements analysis support

[0458] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[0459] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[0460] 3. Support for requirements documentation

[0461] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and performs grammar checks during the document generation process.

[0462] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[0463] 4. Requirements tracing support

[0464] The server utilizes data mining techniques to establish traceability between collected requirements and implementations and test cases, enabling real-time tracking of how requirements were implemented and tested.

[0465] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[0466] ---

[0467] The advantages of this invention are realized by explaining the specific processing flow and clarifying the specific operations of the server, terminal, and user at each step, which automates the entire requirements definition process and dramatically improves efficiency and accuracy.

[0468] The processing flow will be explained below.

[0469] Step 1:

[0470] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[0471] Step 2:

[0472] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[0473] Step 3:

[0474] The server analyzes the input requirements using natural language processing (NLP) technology. Specifically, it tokenizes the requirement sentence and extracts key keywords. For example, it extracts "customer," "order," "cancellation," and "function."

[0475] Step 4:

[0476] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[0477] Step 5:

[0478] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[0479] Step 6:

[0480] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[0481] Step 7:

[0482] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[0483] Step 8:

[0484] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[0485] Step 9:

[0486] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[0487] Step 10:

[0488] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[0489] Step 11:

[0490] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[0491] Step 12:

[0492] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[0493] Step 13:

[0494] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[0495] Step 14:

[0496] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[0497] Step 15:

[0498] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[0499] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of the present invention are realized, and the requirements definition process is automated and made more efficient.

[0500] Example 1

[0501] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0502] Conventional requirements definition processes require extensive manual operations and complex data analysis, resulting in issues with efficiency and accuracy. Furthermore, requirements collection, analysis, documentation, and traceability are often separated, making it difficult to maintain consistency of information across each process. The present invention aims to solve these issues by providing a system that automates the entire requirements definition process and improves efficiency and accuracy.

[0503] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0504] In this invention, the server includes: means for tokenizing requirements information entered by a user using natural language processing technology and extracting important keywords; means for calculating and classifying features of the requirements information using a machine learning algorithm and generating a graph that visualizes the relevance of the requirements information based on the features; means for automatically creating a requirements document based on the requirements information using template generation artificial intelligence and performing grammar checks using natural language processing technology; and means for establishing traceability between the requirements information, implementation code, and test cases using data mining technology, and automatically identifying and notifying affected parts when changes occur. This enables the automation and efficiency of the entire requirements definition process.

[0505] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[0506] "User" refers to a person who uses the system to input, check, and edit requirements information.

[0507] "Requirements information" is information that describes the functions and characteristics required of a system.

[0508] "Tokenization" is the process of breaking down natural language into its smallest units, such as words and phrases.

[0509] "Important keywords" refer to words or phrases that are considered to be particularly important in the requirements information.

[0510] A "machine learning algorithm" is a computational method for learning patterns and rules based on data and making predictions and classifications.

[0511] "Features" refer to the attributes and variables of data input into a machine learning model.

[0512] "Visualization" is the process of representing data and information in an intuitive and easy-to-understand way using graphs and charts.

[0513] "Template generation artificial intelligence" is an artificial intelligence technology that automatically creates documents and formats based on specified requirements.

[0514] "Grammar checking" is the process of detecting grammatical errors in a sentence and suggesting corrections.

[0515] "Data mining technology" is an analytical technique for extracting useful information from large amounts of data.

[0516] "Traceability" is the ability to trace the relationship from requirements to implementation to testing and identify the impact of any changes.

[0517] "Implementation code" refers to the actual program code written to meet the system requirements.

[0518] A "test case" refers to specific test conditions and procedures for verifying that specific functions or requirements of a system are implemented correctly.

[0519] "Notification" is the act of the system informing the user about a particular event or change.

[0520] MODE FOR CARRYING OUT THE INVENTION

[0521] This invention relates to a system that automates and streamlines the requirements definition process by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. This system aims to integrate and automate the entire process of requirements gathering, analysis, documentation, and traceability.

[0522] Requirements gathering support

[0523] First, the user inputs requirements information using the terminal's interactive collection GUI, which provides an interface that accepts natural language prompt input. For example, the user might input a requirement such as, "I need a feature that allows customers to cancel orders."

[0524] The server then uses natural language processing techniques (e.g., NLTK or spaCy) to tokenize the requirements and extract important keywords. For example, keywords like "customer," "order," and "cancellation" are extracted. Based on these keywords, the server determines the requirement category and matches it with an existing requirements database. This process detects similar, overlapping, or conflicting requirements.

[0525] If necessary, the server generates templates and samples and displays them on the terminal to help the user make decisions. For example, displaying a template for a "cancel function" used in a past project can help clarify requirements.

[0526] Requirements analysis support

[0527] The server analyzes the collected requirements information using machine learning algorithms (e.g., Scikit-Learn or TensorFlow). The collected requirements data is converted into features. For example, a dataset with features such as "customer," "order," and "cancellation" is generated.

[0528] Next, this dataset is fed into a machine learning model to classify requirements and analyze their relationships. As a result, the relationships between basic and derived requirements are identified. Based on the results of this analysis, the server generates a graph to visualize the relationships between requirements and displays it on the terminal. This provides users with requirement priorities and risk assessment information to support decision-making.

[0529] Requirements documentation support

[0530] The template generation AI automatically generates requirements documents based on collected and analyzed requirements information. Based on user input, it suggests appropriate document formats and performs grammar checks on the automatically generated documents.

[0531] Grammar checking is performed using the server's natural language processing technology (e.g., Grammarly API), and suggested corrections are presented to the user. Users can edit the requirements specification document in real time using an online collaborative editing tool (e.g., Google Docs). The server automatically updates the document when changes are made and manages the change history.

[0532] Requirement tracing support

[0533] Finally, the server uses data mining technology to establish traceability between the requirements information, the implementation code, and the test cases. Specifically, it analyzes and maps the relationships between the collected requirements, the implementation code, and the test cases.

[0534] The mapping results are displayed on the terminal, visualizing the relationships, allowing users to directly check the relationship between requirements and implementation. Furthermore, when changes occur, the server automatically identifies the affected implementation and tests, and notifies the user of the necessary modifications.

[0535] Specific examples

[0536] Example prompt sentence:

[0537] "We need the ability for customers to cancel their orders."

[0538] Using this system, the entire requirements definition process described above is automated, dramatically improving efficiency and accuracy.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] The user uses the terminal's collection GUI to input requirement information. For example, they might input "I need a feature that allows customers to cancel orders." The input in this step is text information in natural language, and the output is raw data for the server to analyze.

[0542] Step 2:

[0543] The server analyzes the input requirements information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the requirements sentences and extracts important keywords. For example, tokens such as "customer," "order," and "cancellation" are generated. The input in this step is the raw requirements information, and the output is a tokenized keyword list.

[0544] Step 3:

[0545] The server determines the category of the requirement based on the extracted keywords and compares it with the existing requirements database. A specific operation here is to check whether "cancellation" belongs to "customer management functions." The input in this step is a keyword list, and the output is the category determination result and the database comparison result.

[0546] Step 4:

[0547] The server detects whether there are similar, overlapping, or conflicting requirements, and generates templates or samples as needed, which are then displayed on the device. For example, it displays a template for a "cancel function" used in a past project. The input in this step is the category determination results and matching results, and the output is the presentation of templates or samples.

[0548] Step 5:

[0549] The server analyzes the collected requirements information using a machine learning algorithm (e.g., Scikit-Learn or TensorFlow). The requirements data is converted into features and fed into the machine learning model. For example, features such as "customer," "order," and "cancellation" are calculated. The input in this step is the requirements data, and the output is a list of features and a classification result.

[0550] Step 6:

[0551] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The visualized graph includes requirement priority and risk assessment information. For example, a graph is generated showing that "cancellation function" is related to "order management function." The input in this step is the analysis results, and the output is the visualized graph.

[0552] Step 7:

[0553] The template generation AI automatically generates a requirements document based on requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and grammar checks are also performed during the document generation process. Specifically, it generates a requirement statement such as "We need a function that allows customers to cancel orders." The input in this step is requirements data, and the output is a requirements document.

[0554] Step 8:

[0555] The server checks the generated document for grammar using natural language processing technology (e.g., Grammarly API) and suggests corrections. Users can edit the document in real time using online collaborative editing tools (e.g., Google Docs). The input in this step is the requirements document, and the output is the grammar check results and suggested corrections.

[0556] Step 9:

[0557] The server automatically updates the document when changes are made and maintains the change history. For example, when a user adds or modifies a document, the changes are immediately reflected and recorded in the history. The input in this step is the edited document, and the output is the updated document and the change history.

[0558] Step 10:

[0559] The server uses data mining technology to establish traceability between requirements information, implementation code, and test cases. Specifically, it analyzes and maps the relationships between collected requirements, implementation code, and test cases. The input in this step is requirements information, and the output is the mapping results.

[0560] Step 11:

[0561] When a change occurs, the server automatically identifies the implementation and tests of the affected parts and notifies the user of the necessary modifications. For example, if there is a change to the "cancel function," other affected functions and test cases will be identified and notified. The input to this step is the changed requirements information, and the output is the impact analysis results and notification of the modifications.

[0562] (Application example 1)

[0563] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0564] In modern factories, improved work efficiency is required, as well as accuracy and speed in the requirements definition process. However, manually collecting requirements, analyzing them, documenting them, and establishing traceability is time-consuming and prone to errors. It is also difficult to manage work progress in real time, making it difficult to respond quickly when problems occur. Furthermore, a lack of visualization of work data and provision of related information can delay decision-making by workers and managers.

[0565] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0566] In this invention, the server includes: means for analyzing requirements data entered by a user using natural language processing; means for extracting relevance of the requirements data using machine learning and displaying it as a graph; means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks; means for establishing traceability of requirements, implementation, and testing using data mining technology and evaluating the impact of changes; means for inputting work requirements by voice using a smart device and processing the data in real time; and means for visually presenting work progress and related information in real time and providing necessary corrections. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and enabling real-time work management and rapid response.

[0567] "Natural language processing" is the technology of using computers to understand, analyze, and generate human language.

[0568] "Machine learning" is an algorithm that allows a computer to make decisions by feeding it large amounts of data and automatically learning patterns.

[0569] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates sentences and documents based on a specified format.

[0570] "Data mining" is a technique for discovering useful information and relationships from large amounts of data.

[0571] A "smart device" is an advanced electronic device with internet connectivity and a variety of functions.

[0572] "Voice input" is a technology that inputs voice into a computer or device and converts it into text or commands.

[0573] "Real-time" means that data and information is processed and provided almost immediately.

[0574] "Work progress" is information that indicates how much work has progressed or been completed.

[0575] "Visually presented" means displaying information graphically and making it easy to understand.

[0576] The "requirements definition process" is a procedure for describing the requirements of a system or project in detail and achieving a common understanding.

[0577] This invention provides a system for automating and streamlining the requirements definition process in a factory by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. Specific embodiments are described below.

[0578] System Overview

[0579] The system consists of a smart device (smart glasses or head-mounted display) and a server. The smart device has the function of converting voice input into text data and sending it to the server. The server analyzes the received text data and executes an automated requirements definition process.

[0580] Hardware and Software Used

[0581] Smart Devices: Voice Input and Real-Time Notifications

[0582] Server: Data analysis and processing

[0583] Natural language processing software: SpaCy and NLTK

[0584] Machine learning frameworks: Scikit-learn and TensorFlow

[0585] Template generation AI: GPT-3

[0586] Data mining tools: Weka and RapidMiner

[0587] Details of the process

[0588] 1. Voice input and text conversion

[0589] The user uses the microphone in the smart glasses to input the task requirements by voice, and the smart glasses convert the voice data into text data using the Google Speech-to-Text API or similar.

[0590] The converted text data is sent from the smart device to the server.

[0591] 2. Requirements analysis and relevance assessment

[0592] The server tokenizes the received text data using natural language processing software (e.g., SpaCy or NLTK) and extracts important keywords.

[0593] Based on the extracted keywords, a machine learning framework (e.g., Scikit-learn or TensorFlow) is used to analyze the priority and risks of requirements.

[0594] The analysis results are visualized as a relevance graph and displayed in real time on smart devices.

[0595] 3. Requirements documentation

[0596] Using a template generation AI (e.g., GPT-3), a requirements specification document is automatically generated from the analysis results. Grammar checks are also performed during the document generation process.

[0597] The generated requirements specification document is provided to users and administrators and can be edited in real time through online collaborative editing tools.

[0598] 4. Requirements tracing and real-time notifications

[0599] The server uses data mining tools (e.g., Weka or RapidMiner) to establish traceability between requirements, implementation code, and test cases.

[0600] Work progress and related information are visually displayed on smart devices in real time, and if a problem occurs, you are immediately notified and provided with the necessary corrections.

[0601] Examples of specific examples and prompts

[0602] For example, a worker wearing smart glasses can input "The conveyor belt speed on line C4 needs to be increased by 30%" through voice input. The server receives and analyzes this information, and displays the associated risks and countermeasures on the smart glasses. The generated requirements specification document is provided to the manager, and work progress is updated in real time.

[0603] Example prompts for generative AI models

[0604] "We need to increase the speed of our factory conveyor belts by 30%. Please generate a requirements document for this requirement, including a risk assessment and associated work."

[0605] As a result, the present invention not only dramatically improves the efficiency and accuracy of factory work, but also enables quick response when problems occur.

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] Voice input and text conversion

[0609] The user uses the microphone on the smart device to input the task requirements by voice, and the smart device converts the input voice data into text data using a speech recognition tool such as the Google Speech-to-Text API, which then sends the converted text data from the smart device to the server.

[0610] Input: Voice data from the user

[0611] Output: Text data

[0612] Specific operation: The smart device records voice, and the voice recognition engine analyzes the voice data and converts it into text.

[0613] Step 2:

[0614] Requirements analysis

[0615] The server receives the text data and uses natural language processing (NLP) software (e.g., SpaCy or NLTK) to tokenize the text data and extract important keywords.

[0616] Input: Text data converted from audio

[0617] Output: Keywords and tokenized text

[0618] What happens: The server breaks the text into tokens and performs text analysis to identify keywords.

[0619] Step 3:

[0620] Relevance assessment

[0621] The server uses machine learning algorithms (e.g., Scikit-learn or TensorFlow) based on the extracted keywords to evaluate the priority and risk of requirements. Based on the analysis results, it generates a relevance graph and displays it to the user.

[0622] Input: Extracted keywords

[0623] Output: Requirement priorities, risk assessment, and relationship graphs

[0624] How it works: The server feeds data into a machine learning model, calculates priorities and risks, and generates a visual graph.

[0625] Step 4:

[0626] Requirements documentation

[0627] The server uses template generation AI (e.g., GPT-3) to automatically generate a requirements specification document from the analysis results. It also performs grammar checks during document generation and provides the generated document to users and administrators.

[0628] Input: Parsed requirements data

[0629] Output: Automatically generated requirements specification

[0630] Specific operation: The server provides data to the template generation AI, generates a requirements specification document, and checks the grammar.

[0631] Step 5:

[0632] Requirement Tracing and Notifications

[0633] The server uses data mining tools (e.g., Weka and RapidMiner) to establish traceability between requirements, implementation code, and test cases. It visually displays work progress and related information in real time on smart devices, and immediately notifies users if any problems occur. It also provides necessary fixes.

[0634] Input: Requirements specification, implementation code, test cases

[0635] Output: Traceability map, real-time notifications, remediation guidelines

[0636] Specific operation: The server analyzes the relationship between requirements, implementation, and testing, generates notifications about progress and when problems occur, and sends them to the smart device.

[0637] As a result, the present invention automates and streamlines the requirements definition process in a factory, supporting appropriate work management and rapid response.

[0638] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0639] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[0640] 1. Requirements gathering support

[0641] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[0642] Furthermore, an emotion engine is used to recognize the user's emotions in real time as they input data. For example, if the user appears irritated, the server will change the content and presentation of the collection GUI to provide an environment that makes it easier for the user to input data.

[0643] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[0644] 2. Requirements analysis support

[0645] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[0646] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[0647] Furthermore, the system uses an emotion engine to dynamically adjust the priority and risk assessment of requirements analysis according to changes in the user's emotions. For example, if the user is feeling anxious, the system will review the most important requirements first, thereby reassuring the user.

[0648] 3. Support for requirements documentation

[0649] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to adjust specific expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it will use more gentle expressions and positive vocabulary.

[0650] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[0651] 4. Requirements tracing support

[0652] The server utilizes data mining techniques to establish traceability between collected requirements and implementation code and test cases, enabling real-time tracking of how requirements were implemented and tested.

[0653] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[0654] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of this invention are realized. The entire requirements definition process is automated, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[0655] The processing flow will be explained below.

[0656] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[0657] Step 1:

[0658] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[0659] Step 2:

[0660] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[0661] Step 3:

[0662] The device's built-in emotion engine recognizes the user's emotions in real time from their facial expressions and tone of voice. If the emotion is irritation or anxiety, the device will adjust the content and presentation method.

[0663] Step 4:

[0664] The server analyzes the input requirements using natural language processing (NLP) techniques. It tokenizes the requirement statements and extracts key keywords. For example, it extracts "customer", "order", "cancellation", and "function".

[0665] Step 5:

[0666] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[0667] Step 6:

[0668] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[0669] Step 7:

[0670] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[0671] Step 8:

[0672] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[0673] Step 9:

[0674] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[0675] Step 10:

[0676] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[0677] Step 11:

[0678] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[0679] Step 12:

[0680] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[0681] Step 13:

[0682] The server adjusts certain expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it uses softer expressions and more positive vocabulary.

[0683] Step 14:

[0684] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[0685] Step 15:

[0686] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[0687] Step 16:

[0688] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[0689] Step 17:

[0690] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[0691] By clarifying the specific process flow and the operations at each step, the advantages of this invention are realized, automating the entire requirements definition process, dramatically improving efficiency and accuracy, and taking user emotions into consideration to provide a more user-friendly experience.

[0692] Example 2

[0693] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0694] The traditional requirements definition process had problems such as ambiguity in user input and subjective bias, making it time-consuming and labor-intensive to collect and analyze requirements. It was also unclear how requirements would be tracked and changes managed during the implementation and testing phases, making traceability difficult. Furthermore, inconsistent UI / UX design that did not take user emotions into consideration often resulted in a poor user experience. Effective methods to resolve these issues are needed.

[0695] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0696] In this invention, the server includes means for analyzing requirements data entered by a user using natural language processing, means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[0697] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0698] "Machine learning" is a technique that trains algorithms based on data to make predictions and classifications.

[0699] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents based on a predefined format.

[0700] "Data mining technology" is a technique for extracting useful patterns and knowledge from large amounts of data.

[0701] An "emotion engine" is an algorithm that detects a user's emotions and changes behavior based on them.

[0702] "Traceability" means ensuring traceability of the entire process from requirements to implementation and testing.

[0703] An "interactive collection GUI" is a graphical user interface for collecting requirements data through user interaction.

[0704] An "online collaborative editing tool" is an online tool that allows multiple users to edit and update documents simultaneously.

[0705] This invention relates to a system that automates and streamlines the requirements definition process. The main hardware is a server and a terminal, and the software uses natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining technology, and an emotion engine.

[0706] 1. Requirements Gathering

[0707] First, the user inputs business requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. This interface can also include specific examples such as "We need a function that allows customers to cancel orders." The emotion engine recognizes the user's emotions in real time as they input their requirements. For example, if the user is showing irritation, the server adjusts the content and presentation method of the collection GUI, providing an environment that makes it easier for the user to input.

[0708] 2. Requirements analysis

[0709] The server analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. If necessary, it displays templates or samples on the device to support the user's decision-making.

[0710] 3. Requirements analysis

[0711] The server analyzes the collected requirements using a machine learning algorithm. The collected data is converted into features and input into a machine learning model. This identifies the relationships between basic and derived requirements. The analysis results are generated as graphs to visualize the relationship between requirements and are displayed on the terminal. They also include requirement priority and risk assessment information to support user decision-making. An emotion engine is used to dynamically adjust the analysis results in response to changes in the user's emotions, and requirements with high importance or high risk are displayed first.

[0712] 4. Requirements documentation

[0713] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to reflect the user's emotions, as recognized by the emotion engine, and adjust specific expressions and vocabulary. For example, if the user is nervous, it will use more soft, positive vocabulary. The server uses natural language processing technology to check grammar and suggests corrections. Users can edit requirements specifications in real time using an online collaborative editing tool. The server automatically updates the document when changes are made and manages the change history.

[0714] 5. Requirements Tracing

[0715] The server uses data mining technology to establish traceability between collected requirements and implementation code and test cases. This makes it possible to track how requirements have been implemented and tested in real time. Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. The mapping results are displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected implementation and tests and notifies the user of the necessary modifications.

[0716] Specific examples and prompt sentence examples

[0717] For example, if a user requests "a feature that allows customers to cancel orders," the terminal provides an interactive collection GUI, and if the emotion engine detects frustration with the user's input, the server adjusts the interface and displays a flexible input form. The requirement is checked for overlaps with existing databases and classified as "order management." The following prompt sentence is then input to the generative AI model based on this requirement:

[0718] One requirement input was for the ability for customers to cancel orders. Users were frustrated with some of the input. In this case, we flexed the interface presentation and categorized the requirement under "Order Management." We then checked our existing database for similar requirements to find any overlaps or inconsistencies.

[0719] This system automates the entire requirements definition process, dramatically improving efficiency and accuracy, and also takes user feelings into consideration to provide a more user-friendly environment.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] User enters requirements

[0723] The user inputs business requirements using an interactive collection GUI, including specific requirements such as "We need a function that allows customers to cancel orders." The input requirements data is then sent to the terminal.

[0724] Input: User's business requirements (natural language text)

[0725] Output: Collected requirements data

[0726] Step 2:

[0727] The device uses an emotion engine to recognize the user's emotions in real time.

[0728] The device analyzes the user's facial expressions and tone of voice when inputting, and uses an emotion engine to recognize emotions such as irritation or dissatisfaction in real time. For example, if the user shows irritation, the device will collect emotional data.

[0729] Input: User facial expression, voice tone

[0730] Output: User emotion data

[0731] Step 3:

[0732] The server analyzes the requirements

[0733] The server receives the requirements data sent from the device and analyzes it using natural language processing technology. The requirements sentences are tokenized and important keywords are extracted. For example, keywords such as "order" and "cancel" are extracted.

[0734] Input: Collected requirements data

[0735] Output: Extracted keywords and analysis results

[0736] Step 4:

[0737] The server performs categorization and matching

[0738] The server categorizes the requirements based on the extracted keywords and compares them with existing requirements databases, for example, categorizing them into categories such as "order management" and "cancellation function." It also checks for similar, overlapping, or conflicting requirements.

[0739] Input: Extracted keywords and analysis results

[0740] Output: Categorized requirements data and matching results

[0741] Step 5:

[0742] The device displays templates and examples

[0743] Based on the results of the analysis, the server displays requirement templates and samples on the terminal, allowing the user to determine more specific requirements based on the templates and samples they refer to.

[0744] Input: Categorized requirements data and matching results

[0745] Output: The template or sample to be displayed

[0746] Step 6:

[0747] The server uses machine learning algorithms to analyze requirements

[0748] The collected requirements data is converted into features and analyzed using a machine learning model to identify relationships between base and derived requirements. For example, we analyze how the cancellation function relates to other order management requirements.

[0749] Input: Categorized requirements data

[0750] Output: Requirements association and analysis results

[0751] Step 7:

[0752] The server visualizes the analysis results

[0753] The server visualizes the relationship between requirements based on the analysis results as a graph, including requirement priority and risk assessment information. For example, the importance and risk of the cancel function are visually displayed.

[0754] Input: Requirements associations and analysis results

[0755] Output: Visualized graph

[0756] Step 8:

[0757] The device displays the analysis results.

[0758] The terminal displays visualized graphs sent from the server to the user, clearly presenting requirement priorities and risk assessments.

[0759] Input: Visualized graph

[0760] Output: The analysis results to be displayed

[0761] Step 9:

[0762] The server uses an emotion engine to dynamically adjust the analysis results.

[0763] The server monitors changes in the user's emotions and dynamically adjusts the priority and risk assessment of requirements analysis according to the user's emotions. For example, if the user feels anxious, the server will prioritize reviewing requirements of high importance.

[0764] Input: User sentiment data, requirements analysis results

[0765] Output: Dynamically adjusted analysis results

[0766] Step 10:

[0767] The server automatically generates requirements documents using template generation AI.

[0768] Based on the collected and analyzed requirements data, requirements documents are automatically generated in the appropriate document format, and grammar checks are also performed.

[0769] Input: Requirement analysis results, categorized requirement data

[0770] Output: Auto-generated requirements document

[0771] Step 11:

[0772] The server performs a syntax check

[0773] The server uses natural language processing technology to check the grammar of the generated requirements document and suggests corrections.

[0774] Input: Auto-generated requirements document

[0775] Output: Syntax-checked requirements document and suggested corrections

[0776] Step 12:

[0777] A user edits a document in an online collaborative editing tool

[0778] Users can use online collaborative editing tools to edit requirements documents in real time.

[0779] Input: Grammar-checked requirements document and suggested corrections

[0780] Output: Edited requirements document

[0781] Step 13:

[0782] The server updates changes in real time and manages the history

[0783] The server automatically reflects changes made by the user in real time to the document and manages the change history.

[0784] Input: Edited requirements document

[0785] Output: Updated requirements document and change history

[0786] Step 14:

[0787] The server uses data mining techniques to establish traceability between requirements, implementation, and testing.

[0788] It analyzes and maps the relationship between collected requirements, implementation code, and test cases, making it possible to track in real time how requirements have been implemented and tested.

[0789] Input: Requirement data, implementation code, test cases

[0790] Output: Traceability map

[0791] Step 15:

[0792] The terminal visualizes and displays the traceability results

[0793] The terminal visualizes the traceability map sent from the server and displays it to the user.

[0794] Input: Traceability map

[0795] Output: Traceability visualization results

[0796] Step 16:

[0797] Identify and notify affected server areas

[0798] When changes occur, the server automatically identifies the affected implementations and tests and notifies the user of the necessary modifications.

[0799] Input: Updated requirements data and implementation code

[0800] Output: Notice of affected parts

[0801] (Application example 2)

[0802] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0803] The traditional requirements definition process involves a lot of manual work, which can be inefficient and inaccurate. Furthermore, requirements are collected and analyzed without considering the user's feelings, which can lead to increased user dissatisfaction and stress. Furthermore, product and service proposals can sometimes be made that do not meet the user's tolerance level, resulting in a decrease in customer satisfaction.

[0804] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0805] In this invention, the server includes a means for analyzing requirements data entered by a user using natural language processing, a means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and a means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This makes it possible to recognize the user's emotions in real time during requirements collection and dynamically adjust the interface display content and presentation method. It is also possible to analyze changes in the user's emotions throughout the entire process from requirements collection to implementation and dynamically adjust the priority and risk assessment of requirements. Furthermore, it is possible to make product recommendations based on the user's needs and propose optimal products.

[0806] "Natural language processing" is the technology that enables computers to understand, generate, and manipulate human language.

[0807] "Machine learning" is a technique that refers to a computer system learning from data and improving at its tasks without being explicitly programmed.

[0808] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents and templates based on existing data.

[0809] "Data mining technology" refers to methods and techniques for extracting patterns and knowledge from large amounts of data.

[0810] The "emotion engine" is a technology that recognizes emotions in real time from human facial expressions, tone of voice, etc.

[0811] "Real-time" means that user input and actions are processed immediately.

[0812] A "user interface" refers to the screen or operating environment that allows a user to interact with a system or application.

[0813] "Traceability" refers to the ability to track how requirements are implemented and tested.

[0814] "Changes in user's emotions" refers to changes in the user's emotional state while using the system.

[0815] "Product recommendation" refers to the act of selecting and proposing the most suitable product based on the user's request.

[0816] The present invention is implemented as a smartphone app "Smart Shopping Assistant" to enhance customer experience in brick-and-mortar stores. The system includes the following main components:

[0817] Requirements gathering support

[0818] The server first collects requests entered by the user into the smartphone app. The interface is intuitive and includes a text box for entering specific requests, such as "I want a red dress," as well as a voice input function. Furthermore, the server utilizes an emotion engine to recognize the user's emotions in real time as they are being input. For example, if the emotion engine determines that the user is nervous, the server automatically switches the interface to a more user-friendly design.

[0819] Requirements analysis support

[0820] The server analyzes the request data collected from users using natural language processing (NLP) technology. NLP tokenizes the input text data and extracts important keywords. The server then uses machine learning models to match the request with a database of relevant products and services. Based on the extracted keywords, the server recommends the most suitable products.

[0821] Product recommendation

[0822] Based on the user's request, the server uses TfidfVectorizer to vectorize the request and the product information in the database, and calculates the cosine similarity. This allows the server to suggest products with the highest similarity to the user. For example, if the user's request is a "red dress," the server will present information about the most suitable red dress in stock.

[0823] Traceability and Emotion Regulation

[0824] The server analyzes the user's emotional changes in real time throughout the entire process, from requirements gathering to product recommendations. Based on this information, it dynamically adjusts requirement priorities and risk assessments. If the user is feeling stressed, the system will prioritize and recommend highly accurate products to alleviate the user's anxiety.

[0825] Hardware and Software

[0826] The following specific hardware and software is used in this system:

[0827] Smartphone app: Providing user interface and emotion recognition.

[0828] Server: Data analysis and operation of the recommendation system.

[0829] FER Library: Facial expression analysis for emotion recognition.

[0830] BERT model for transformers: Text analysis for natural language processing.

[0831] TfidfVectorizer: Vectorization and cosine similarity calculation of requirements and products.

[0832] Specific examples

[0833] Below are some specific examples of how this system can be used.

[0834] A user types "I want a red dress" into a smartphone app, and the app sends the request to a server.

[0835] The server uses the BERT model to analyze the text and recommend suitable products.

[0836] The recommended products are presented to the user, and the user's emotions are analyzed by an emotion engine.

[0837] Prompt Sentence Examples

[0838] "Please enter the product you want"

[0839] "The camera takes pictures and detects customer emotions."

[0840] "Recommend products based on customer requests"

[0841] The above describes the embodiments of the present invention, which embody the features of the invention and aim to improve the customer experience in physical stores.

[0842] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] The user inputs their request using a smartphone app. For example, they can enter a specific request such as "I want a red dress." The device then sends this input to the server via the user interface. The input is sent as text data.

[0845] Step 2:

[0846] The server analyzes the received text data using natural language processing (NLP) techniques. First, it tokenizes the input text data and extracts important keywords. In this process, it uses an NLP library (e.g., the BERT model) to perform tokenization and keyword extraction. The output is a list of extracted keywords.

[0847] Step 3:

[0848] The server uses a machine learning model to search for related products based on the extracted keyword list. It uses TfidfVectorizer to vectorize the request and product information in the database, and calculates the cosine similarity to identify the product with the highest similarity. The input is the keyword list and the product database, and the output is a list of recommended products.

[0849] Step 4:

[0850] The server sends a list of recommended products to the terminal, and the terminal presents this information to the user through a user interface. At this point, an emotion engine also operates simultaneously, analyzing the user's facial expressions and voice in real time to grasp the user's emotions. The input is the user's facial expression and voice data, and the output is the detected emotional information.

[0851] Step 5:

[0852] The server dynamically adjusts the content and presentation of the interface based on the detected user emotion information. For example, if it determines that the user is nervous, it changes the interface design to a more friendly one. The input is emotion information, and the output is the adjusted interface design.

[0853] Step 6:

[0854] The server analyzes the user's emotional changes in real time throughout the entire process, from request collection to product recommendation, and dynamically adjusts the priority and risk assessment of requirements. If the user is feeling stressed, it will recommend the most accurate product with the highest priority. The input is information on the user's emotional changes, and the output is the adjusted priority and risk assessment.

[0855] Through each of the above steps, a system is created that improves the customer experience in physical stores by making optimal product suggestions based on the user's needs and adjusting emotions in real time.

[0856] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0857] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0858] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0859] [Third embodiment]

[0860] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0861] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0862] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0863] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0864] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0865] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0866] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0867] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0868] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0869] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0870] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0871] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0872] The present invention describes a specific embodiment of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies to automate and streamline the requirements definition process.

[0873] 1. Requirements gathering support

[0874] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[0875] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[0876] 2. Requirements analysis support

[0877] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[0878] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[0879] 3. Support for requirements documentation

[0880] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and performs grammar checks during the document generation process.

[0881] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[0882] 4. Requirements tracing support

[0883] The server utilizes data mining techniques to establish traceability between collected requirements and implementations and test cases, enabling real-time tracking of how requirements were implemented and tested.

[0884] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[0885] ---

[0886] The advantages of this invention are realized by explaining the specific processing flow and clarifying the specific operations of the server, terminal, and user at each step, which automates the entire requirements definition process and dramatically improves efficiency and accuracy.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[0890] Step 2:

[0891] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[0892] Step 3:

[0893] The server analyzes the input requirements using natural language processing (NLP) technology. Specifically, it tokenizes the requirement sentence and extracts key keywords. For example, it extracts "customer," "order," "cancellation," and "function."

[0894] Step 4:

[0895] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[0896] Step 5:

[0897] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[0898] Step 6:

[0899] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[0900] Step 7:

[0901] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[0902] Step 8:

[0903] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[0904] Step 9:

[0905] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[0906] Step 10:

[0907] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[0908] Step 11:

[0909] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[0910] Step 12:

[0911] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[0912] Step 13:

[0913] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[0914] Step 14:

[0915] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[0916] Step 15:

[0917] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[0918] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of the present invention are realized, and the requirements definition process is automated and made more efficient.

[0919] Example 1

[0920] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] Conventional requirements definition processes require extensive manual operations and complex data analysis, resulting in issues with efficiency and accuracy. Furthermore, requirements collection, analysis, documentation, and traceability are often separated, making it difficult to maintain consistency of information across each process. The present invention aims to solve these issues by providing a system that automates the entire requirements definition process and improves efficiency and accuracy.

[0922] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0923] In this invention, the server includes: means for tokenizing requirements information entered by a user using natural language processing technology and extracting important keywords; means for calculating and classifying features of the requirements information using a machine learning algorithm and generating a graph that visualizes the relevance of the requirements information based on the features; means for automatically creating a requirements document based on the requirements information using template generation artificial intelligence and performing grammar checks using natural language processing technology; and means for establishing traceability between the requirements information, implementation code, and test cases using data mining technology, and automatically identifying and notifying affected parts when changes occur. This enables the automation and efficiency of the entire requirements definition process.

[0924] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[0925] "User" refers to a person who uses the system to input, check, and edit requirements information.

[0926] "Requirements information" is information that describes the functions and characteristics required of a system.

[0927] "Tokenization" is the process of breaking down natural language into its smallest units, such as words and phrases.

[0928] "Important keywords" refer to words or phrases that are considered to be particularly important in the requirements information.

[0929] A "machine learning algorithm" is a computational method for learning patterns and rules based on data and making predictions and classifications.

[0930] "Features" refer to the attributes and variables of data input into a machine learning model.

[0931] "Visualization" is the process of representing data and information in an intuitive and easy-to-understand way using graphs and charts.

[0932] "Template generation artificial intelligence" is an artificial intelligence technology that automatically creates documents and formats based on specified requirements.

[0933] "Grammar checking" is the process of detecting grammatical errors in a sentence and suggesting corrections.

[0934] "Data mining technology" is an analytical technique for extracting useful information from large amounts of data.

[0935] "Traceability" is the ability to trace the relationship from requirements to implementation to testing and identify the impact of any changes.

[0936] "Implementation code" refers to the actual program code written to meet the system requirements.

[0937] A "test case" refers to specific test conditions and procedures for verifying that specific functions or requirements of a system are implemented correctly.

[0938] "Notification" is the act of the system informing the user about a particular event or change.

[0939] MODE FOR CARRYING OUT THE INVENTION

[0940] This invention relates to a system that automates and streamlines the requirements definition process by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. This system aims to integrate and automate the entire process of requirements gathering, analysis, documentation, and traceability.

[0941] Requirements gathering support

[0942] First, the user inputs requirements information using the terminal's interactive collection GUI, which provides an interface that accepts natural language prompt input. For example, the user might input a requirement such as, "I need a feature that allows customers to cancel orders."

[0943] The server then uses natural language processing techniques (e.g., NLTK or spaCy) to tokenize the requirements and extract important keywords. For example, keywords like "customer," "order," and "cancellation" are extracted. Based on these keywords, the server determines the requirement category and matches it with an existing requirements database. This process detects similar, overlapping, or conflicting requirements.

[0944] If necessary, the server generates templates and samples and displays them on the terminal to help the user make decisions. For example, displaying a template for a "cancel function" used in a past project can help clarify requirements.

[0945] Requirements analysis support

[0946] The server analyzes the collected requirements information using machine learning algorithms (e.g., Scikit-Learn or TensorFlow). The collected requirements data is converted into features. For example, a dataset with features such as "customer," "order," and "cancellation" is generated.

[0947] Next, this dataset is fed into a machine learning model to classify requirements and analyze their relationships. As a result, the relationships between basic and derived requirements are identified. Based on the results of this analysis, the server generates a graph to visualize the relationships between requirements and displays it on the terminal. This provides users with requirement priorities and risk assessment information to support decision-making.

[0948] Requirements documentation support

[0949] The template generation AI automatically generates requirements documents based on collected and analyzed requirements information. Based on user input, it suggests appropriate document formats and performs grammar checks on the automatically generated documents.

[0950] Grammar checking is performed using the server's natural language processing technology (e.g., Grammarly API), and suggested corrections are presented to the user. Users can edit the requirements specification document in real time using an online collaborative editing tool (e.g., Google Docs). The server automatically updates the document when changes are made and manages the change history.

[0951] Requirement tracing support

[0952] Finally, the server uses data mining technology to establish traceability between the requirements information, the implementation code, and the test cases. Specifically, it analyzes and maps the relationships between the collected requirements, the implementation code, and the test cases.

[0953] The mapping results are displayed on the terminal, visualizing the relationships, allowing users to directly check the relationship between requirements and implementation. Furthermore, when changes occur, the server automatically identifies the affected implementation and tests, and notifies the user of the necessary modifications.

[0954] Specific examples

[0955] Example prompt sentence:

[0956] "We need the ability for customers to cancel their orders."

[0957] Using this system, the entire requirements definition process described above is automated, dramatically improving efficiency and accuracy.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] The user uses the terminal's collection GUI to input requirement information. For example, they might input "I need a feature that allows customers to cancel orders." The input in this step is text information in natural language, and the output is raw data for the server to analyze.

[0961] Step 2:

[0962] The server analyzes the input requirements information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the requirements sentences and extracts important keywords. For example, tokens such as "customer," "order," and "cancellation" are generated. The input in this step is the raw requirements information, and the output is a tokenized keyword list.

[0963] Step 3:

[0964] The server determines the category of the requirement based on the extracted keywords and compares it with the existing requirements database. A specific operation here is to check whether "cancellation" belongs to "customer management functions." The input in this step is a keyword list, and the output is the category determination result and the database comparison result.

[0965] Step 4:

[0966] The server detects whether there are similar, overlapping, or conflicting requirements, and generates templates or samples as needed, which are then displayed on the device. For example, it displays a template for a "cancel function" used in a past project. The input in this step is the category determination results and matching results, and the output is the presentation of templates or samples.

[0967] Step 5:

[0968] The server analyzes the collected requirements information using a machine learning algorithm (e.g., Scikit-Learn or TensorFlow). The requirements data is converted into features and fed into the machine learning model. For example, features such as "customer," "order," and "cancellation" are calculated. The input in this step is the requirements data, and the output is a list of features and a classification result.

[0969] Step 6:

[0970] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The visualized graph includes requirement priority and risk assessment information. For example, a graph is generated showing that "cancellation function" is related to "order management function." The input in this step is the analysis results, and the output is the visualized graph.

[0971] Step 7:

[0972] The template generation AI automatically generates a requirements document based on requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and grammar checks are also performed during the document generation process. Specifically, it generates a requirement statement such as "We need a function that allows customers to cancel orders." The input in this step is requirements data, and the output is a requirements document.

[0973] Step 8:

[0974] The server checks the generated document for grammar using natural language processing technology (e.g., Grammarly API) and suggests corrections. Users can edit the document in real time using online collaborative editing tools (e.g., Google Docs). The input in this step is the requirements document, and the output is the grammar check results and suggested corrections.

[0975] Step 9:

[0976] The server automatically updates the document when changes are made and maintains the change history. For example, when a user adds or modifies a document, the changes are immediately reflected and recorded in the history. The input in this step is the edited document, and the output is the updated document and the change history.

[0977] Step 10:

[0978] The server uses data mining technology to establish traceability between requirements information, implementation code, and test cases. Specifically, it analyzes and maps the relationships between collected requirements, implementation code, and test cases. The input in this step is requirements information, and the output is the mapping results.

[0979] Step 11:

[0980] When a change occurs, the server automatically identifies the implementation and tests of the affected parts and notifies the user of the necessary modifications. For example, if there is a change to the "cancel function," other affected functions and test cases will be identified and notified. The input to this step is the changed requirements information, and the output is the impact analysis results and notification of the modifications.

[0981] (Application example 1)

[0982] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0983] In modern factories, improved work efficiency is required, as well as accuracy and speed in the requirements definition process. However, manually collecting requirements, analyzing them, documenting them, and establishing traceability is time-consuming and prone to errors. It is also difficult to manage work progress in real time, making it difficult to respond quickly when problems occur. Furthermore, a lack of visualization of work data and provision of related information can delay decision-making by workers and managers.

[0984] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0985] In this invention, the server includes: means for analyzing requirements data entered by a user using natural language processing; means for extracting relevance of the requirements data using machine learning and displaying it as a graph; means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks; means for establishing traceability of requirements, implementation, and testing using data mining technology and evaluating the impact of changes; means for inputting work requirements by voice using a smart device and processing the data in real time; and means for visually presenting work progress and related information in real time and providing necessary corrections. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and enabling real-time work management and rapid response.

[0986] "Natural language processing" is the technology of using computers to understand, analyze, and generate human language.

[0987] "Machine learning" is an algorithm that allows a computer to make decisions by feeding it large amounts of data and automatically learning patterns.

[0988] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates sentences and documents based on a specified format.

[0989] "Data mining" is a technique for discovering useful information and relationships from large amounts of data.

[0990] A "smart device" is an advanced electronic device with internet connectivity and a variety of functions.

[0991] "Voice input" is a technology that inputs voice into a computer or device and converts it into text or commands.

[0992] "Real-time" means that data and information is processed and provided almost immediately.

[0993] "Work progress" is information that indicates how much work has progressed or been completed.

[0994] "Visually presented" means displaying information graphically and making it easy to understand.

[0995] The "requirements definition process" is a procedure for describing the requirements of a system or project in detail and achieving a common understanding.

[0996] This invention provides a system for automating and streamlining the requirements definition process in a factory by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. Specific embodiments are described below.

[0997] System Overview

[0998] The system consists of a smart device (smart glasses or head-mounted display) and a server. The smart device has the function of converting voice input into text data and sending it to the server. The server analyzes the received text data and executes an automated requirements definition process.

[0999] Hardware and Software Used

[1000] Smart Devices: Voice Input and Real-Time Notifications

[1001] Server: Data analysis and processing

[1002] Natural language processing software: SpaCy and NLTK

[1003] Machine learning frameworks: Scikit-learn and TensorFlow

[1004] Template generation AI: GPT-3

[1005] Data mining tools: Weka and RapidMiner

[1006] Details of the process

[1007] 1. Voice input and text conversion

[1008] The user uses the microphone in the smart glasses to input the task requirements by voice, and the smart glasses convert the voice data into text data using the Google Speech-to-Text API or similar.

[1009] The converted text data is sent from the smart device to the server.

[1010] 2. Requirements analysis and relevance assessment

[1011] The server tokenizes the received text data using natural language processing software (e.g., SpaCy or NLTK) and extracts important keywords.

[1012] Based on the extracted keywords, a machine learning framework (e.g., Scikit-learn or TensorFlow) is used to analyze the priority and risks of requirements.

[1013] The analysis results are visualized as a relevance graph and displayed in real time on smart devices.

[1014] 3. Requirements documentation

[1015] Using a template generation AI (e.g., GPT-3), a requirements specification document is automatically generated from the analysis results. Grammar checks are also performed during the document generation process.

[1016] The generated requirements specification document is provided to users and administrators and can be edited in real time through online collaborative editing tools.

[1017] 4. Requirements tracing and real-time notifications

[1018] The server uses data mining tools (e.g., Weka or RapidMiner) to establish traceability between requirements, implementation code, and test cases.

[1019] Work progress and related information are visually displayed on smart devices in real time, and if a problem occurs, you are immediately notified and provided with the necessary corrections.

[1020] Examples of specific examples and prompts

[1021] For example, a worker wearing smart glasses can input "The conveyor belt speed on line C4 needs to be increased by 30%" through voice input. The server receives and analyzes this information, and displays the associated risks and countermeasures on the smart glasses. The generated requirements specification document is provided to the manager, and work progress is updated in real time.

[1022] Example prompts for generative AI models

[1023] "We need to increase the speed of our factory conveyor belts by 30%. Please generate a requirements document for this requirement, including a risk assessment and associated work."

[1024] As a result, the present invention not only dramatically improves the efficiency and accuracy of factory work, but also enables quick response when problems occur.

[1025] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1026] Step 1:

[1027] Voice input and text conversion

[1028] The user uses the microphone on the smart device to input the task requirements by voice, and the smart device converts the input voice data into text data using a speech recognition tool such as the Google Speech-to-Text API, which then sends the converted text data from the smart device to the server.

[1029] Input: Voice data from the user

[1030] Output: Text data

[1031] Specific operation: The smart device records voice, and the voice recognition engine analyzes the voice data and converts it into text.

[1032] Step 2:

[1033] Requirements analysis

[1034] The server receives the text data and uses natural language processing (NLP) software (e.g., SpaCy or NLTK) to tokenize the text data and extract important keywords.

[1035] Input: Text data converted from audio

[1036] Output: Keywords and tokenized text

[1037] What happens: The server breaks the text into tokens and performs text analysis to identify keywords.

[1038] Step 3:

[1039] Relevance assessment

[1040] The server uses machine learning algorithms (e.g., Scikit-learn or TensorFlow) based on the extracted keywords to evaluate the priority and risk of requirements. Based on the analysis results, it generates a relevance graph and displays it to the user.

[1041] Input: Extracted keywords

[1042] Output: Requirement priorities, risk assessment, and relationship graphs

[1043] How it works: The server feeds data into a machine learning model, calculates priorities and risks, and generates a visual graph.

[1044] Step 4:

[1045] Requirements documentation

[1046] The server uses template generation AI (e.g., GPT-3) to automatically generate a requirements specification document from the analysis results. It also performs grammar checks during document generation and provides the generated document to users and administrators.

[1047] Input: Parsed requirements data

[1048] Output: Automatically generated requirements specification

[1049] Specific operation: The server provides data to the template generation AI, generates a requirements specification document, and checks the grammar.

[1050] Step 5:

[1051] Requirement Tracing and Notifications

[1052] The server uses data mining tools (e.g., Weka and RapidMiner) to establish traceability between requirements, implementation code, and test cases. It visually displays work progress and related information in real time on smart devices, and immediately notifies users if any problems occur. It also provides necessary fixes.

[1053] Input: Requirements specification, implementation code, test cases

[1054] Output: Traceability map, real-time notifications, remediation guidelines

[1055] Specific operation: The server analyzes the relationship between requirements, implementation, and testing, generates notifications about progress and when problems occur, and sends them to the smart device.

[1056] As a result, the present invention automates and streamlines the requirements definition process in a factory, supporting appropriate work management and rapid response.

[1057] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1058] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[1059] 1. Requirements gathering support

[1060] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[1061] Furthermore, an emotion engine is used to recognize the user's emotions in real time as they input data. For example, if the user appears irritated, the server will change the content and presentation of the collection GUI to provide an environment that makes it easier for the user to input data.

[1062] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[1063] 2. Requirements analysis support

[1064] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[1065] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[1066] Furthermore, the system uses an emotion engine to dynamically adjust the priority and risk assessment of requirements analysis according to changes in the user's emotions. For example, if the user is feeling anxious, the system will review the most important requirements first, thereby reassuring the user.

[1067] 3. Support for requirements documentation

[1068] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to adjust specific expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it will use more gentle expressions and positive vocabulary.

[1069] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[1070] 4. Requirements tracing support

[1071] The server utilizes data mining techniques to establish traceability between collected requirements and implementation code and test cases, enabling real-time tracking of how requirements were implemented and tested.

[1072] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[1073] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of this invention are realized. The entire requirements definition process is automated, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[1074] The processing flow will be explained below.

[1075] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[1076] Step 1:

[1077] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[1078] Step 2:

[1079] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[1080] Step 3:

[1081] The device's built-in emotion engine recognizes the user's emotions in real time from their facial expressions and tone of voice. If the emotion is irritation or anxiety, the device will adjust the content and presentation method.

[1082] Step 4:

[1083] The server analyzes the input requirements using natural language processing (NLP) techniques. It tokenizes the requirement statements and extracts key keywords. For example, it extracts "customer", "order", "cancellation", and "function".

[1084] Step 5:

[1085] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[1086] Step 6:

[1087] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[1088] Step 7:

[1089] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[1090] Step 8:

[1091] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[1092] Step 9:

[1093] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[1094] Step 10:

[1095] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[1096] Step 11:

[1097] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[1098] Step 12:

[1099] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[1100] Step 13:

[1101] The server adjusts certain expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it uses softer expressions and more positive vocabulary.

[1102] Step 14:

[1103] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[1104] Step 15:

[1105] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[1106] Step 16:

[1107] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[1108] Step 17:

[1109] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[1110] By clarifying the specific process flow and the operations at each step, the advantages of this invention are realized, automating the entire requirements definition process, dramatically improving efficiency and accuracy, and taking user emotions into consideration to provide a more user-friendly experience.

[1111] Example 2

[1112] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1113] The traditional requirements definition process had problems such as ambiguity in user input and subjective bias, making it time-consuming and labor-intensive to collect and analyze requirements. It was also unclear how requirements would be tracked and changes managed during the implementation and testing phases, making traceability difficult. Furthermore, inconsistent UI / UX design that did not take user emotions into consideration often resulted in a poor user experience. Effective methods to resolve these issues are needed.

[1114] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1115] In this invention, the server includes means for analyzing requirements data entered by a user using natural language processing, means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[1116] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1117] "Machine learning" is a technique that trains algorithms based on data to make predictions and classifications.

[1118] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents based on a predefined format.

[1119] "Data mining technology" is a technique for extracting useful patterns and knowledge from large amounts of data.

[1120] An "emotion engine" is an algorithm that detects a user's emotions and changes behavior based on them.

[1121] "Traceability" means ensuring traceability of the entire process from requirements to implementation and testing.

[1122] An "interactive collection GUI" is a graphical user interface for collecting requirements data through user interaction.

[1123] An "online collaborative editing tool" is an online tool that allows multiple users to edit and update documents simultaneously.

[1124] This invention relates to a system that automates and streamlines the requirements definition process. The main hardware is a server and a terminal, and the software uses natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining technology, and an emotion engine.

[1125] 1. Requirements Gathering

[1126] First, the user inputs business requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. This interface can also include specific examples such as "We need a function that allows customers to cancel orders." The emotion engine recognizes the user's emotions in real time as they input their requirements. For example, if the user is showing irritation, the server adjusts the content and presentation method of the collection GUI, providing an environment that makes it easier for the user to input.

[1127] 2. Requirements analysis

[1128] The server analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. If necessary, it displays templates or samples on the device to support the user's decision-making.

[1129] 3. Requirements analysis

[1130] The server analyzes the collected requirements using a machine learning algorithm. The collected data is converted into features and input into a machine learning model. This identifies the relationships between basic and derived requirements. The analysis results are generated as graphs to visualize the relationship between requirements and are displayed on the terminal. They also include requirement priority and risk assessment information to support user decision-making. An emotion engine is used to dynamically adjust the analysis results in response to changes in the user's emotions, and requirements with high importance or high risk are displayed first.

[1131] 4. Requirements documentation

[1132] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to reflect the user's emotions, as recognized by the emotion engine, and adjust specific expressions and vocabulary. For example, if the user is nervous, it will use more soft, positive vocabulary. The server uses natural language processing technology to check grammar and suggests corrections. Users can edit requirements specifications in real time using an online collaborative editing tool. The server automatically updates the document when changes are made and manages the change history.

[1133] 5. Requirements Tracing

[1134] The server uses data mining technology to establish traceability between collected requirements and implementation code and test cases. This makes it possible to track how requirements have been implemented and tested in real time. Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. The mapping results are displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected implementation and tests and notifies the user of the necessary modifications.

[1135] Specific examples and prompt sentence examples

[1136] For example, if a user requests "a feature that allows customers to cancel orders," the terminal provides an interactive collection GUI, and if the emotion engine detects frustration with the user's input, the server adjusts the interface and displays a flexible input form. The requirement is checked for overlaps with existing databases and classified as "order management." The following prompt sentence is then input to the generative AI model based on this requirement:

[1137] One requirement input was for the ability for customers to cancel orders. Users were frustrated with some of the input. In this case, we flexed the interface presentation and categorized the requirement under "Order Management." We then checked our existing database for similar requirements to find any overlaps or inconsistencies.

[1138] This system automates the entire requirements definition process, dramatically improving efficiency and accuracy, and also takes user feelings into consideration to provide a more user-friendly environment.

[1139] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1140] Step 1:

[1141] User enters requirements

[1142] The user inputs business requirements using an interactive collection GUI, including specific requirements such as "We need a function that allows customers to cancel orders." The input requirements data is then sent to the terminal.

[1143] Input: User's business requirements (natural language text)

[1144] Output: Collected requirements data

[1145] Step 2:

[1146] The device uses an emotion engine to recognize the user's emotions in real time.

[1147] The device analyzes the user's facial expressions and tone of voice when inputting, and uses an emotion engine to recognize emotions such as irritation or dissatisfaction in real time. For example, if the user shows irritation, the device will collect emotional data.

[1148] Input: User facial expression, voice tone

[1149] Output: User emotion data

[1150] Step 3:

[1151] The server analyzes the requirements

[1152] The server receives the requirements data sent from the device and analyzes it using natural language processing technology. The requirements sentences are tokenized and important keywords are extracted. For example, keywords such as "order" and "cancel" are extracted.

[1153] Input: Collected requirements data

[1154] Output: Extracted keywords and analysis results

[1155] Step 4:

[1156] The server performs categorization and matching

[1157] The server categorizes the requirements based on the extracted keywords and compares them with existing requirements databases, for example, categorizing them into categories such as "order management" and "cancellation function." It also checks for similar, overlapping, or conflicting requirements.

[1158] Input: Extracted keywords and analysis results

[1159] Output: Categorized requirements data and matching results

[1160] Step 5:

[1161] The device displays templates and examples

[1162] Based on the results of the analysis, the server displays requirement templates and samples on the terminal, allowing the user to determine more specific requirements based on the templates and samples they refer to.

[1163] Input: Categorized requirements data and matching results

[1164] Output: The template or sample to be displayed

[1165] Step 6:

[1166] The server uses machine learning algorithms to analyze requirements

[1167] The collected requirements data is converted into features and analyzed using a machine learning model to identify relationships between base and derived requirements. For example, we analyze how the cancellation function relates to other order management requirements.

[1168] Input: Categorized requirements data

[1169] Output: Requirements association and analysis results

[1170] Step 7:

[1171] The server visualizes the analysis results

[1172] The server visualizes the relationship between requirements based on the analysis results as a graph, including requirement priority and risk assessment information. For example, the importance and risk of the cancel function are visually displayed.

[1173] Input: Requirements associations and analysis results

[1174] Output: Visualized graph

[1175] Step 8:

[1176] The device displays the analysis results.

[1177] The terminal displays visualized graphs sent from the server to the user, clearly presenting requirement priorities and risk assessments.

[1178] Input: Visualized graph

[1179] Output: The analysis results to be displayed

[1180] Step 9:

[1181] The server uses an emotion engine to dynamically adjust the analysis results.

[1182] The server monitors changes in the user's emotions and dynamically adjusts the priority and risk assessment of requirements analysis according to the user's emotions. For example, if the user feels anxious, the server will prioritize reviewing requirements of high importance.

[1183] Input: User sentiment data, requirements analysis results

[1184] Output: Dynamically adjusted analysis results

[1185] Step 10:

[1186] The server automatically generates requirements documents using template generation AI.

[1187] Based on the collected and analyzed requirements data, requirements documents are automatically generated in the appropriate document format, and grammar checks are also performed.

[1188] Input: Requirement analysis results, categorized requirement data

[1189] Output: Auto-generated requirements document

[1190] Step 11:

[1191] The server performs a syntax check

[1192] The server uses natural language processing technology to check the grammar of the generated requirements document and suggests corrections.

[1193] Input: Auto-generated requirements document

[1194] Output: Syntax-checked requirements document and suggested corrections

[1195] Step 12:

[1196] A user edits a document in an online collaborative editing tool

[1197] Users can use online collaborative editing tools to edit requirements documents in real time.

[1198] Input: Grammar-checked requirements document and suggested corrections

[1199] Output: Edited requirements document

[1200] Step 13:

[1201] The server updates changes in real time and manages the history

[1202] The server automatically reflects changes made by the user in real time to the document and manages the change history.

[1203] Input: Edited requirements document

[1204] Output: Updated requirements document and change history

[1205] Step 14:

[1206] The server uses data mining techniques to establish traceability between requirements, implementation, and testing.

[1207] It analyzes and maps the relationship between collected requirements, implementation code, and test cases, making it possible to track in real time how requirements have been implemented and tested.

[1208] Input: Requirement data, implementation code, test cases

[1209] Output: Traceability map

[1210] Step 15:

[1211] The terminal visualizes and displays the traceability results

[1212] The terminal visualizes the traceability map sent from the server and displays it to the user.

[1213] Input: Traceability map

[1214] Output: Traceability visualization results

[1215] Step 16:

[1216] Identify and notify affected server areas

[1217] When changes occur, the server automatically identifies the affected implementations and tests and notifies the user of the necessary modifications.

[1218] Input: Updated requirements data and implementation code

[1219] Output: Notice of affected parts

[1220] (Application example 2)

[1221] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1222] The traditional requirements definition process involves a lot of manual work, which can be inefficient and inaccurate. Furthermore, requirements are collected and analyzed without considering the user's feelings, which can lead to increased user dissatisfaction and stress. Furthermore, product and service proposals can sometimes be made that do not meet the user's tolerance level, resulting in a decrease in customer satisfaction.

[1223] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1224] In this invention, the server includes a means for analyzing requirements data entered by a user using natural language processing, a means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and a means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This makes it possible to recognize the user's emotions in real time during requirements collection and dynamically adjust the interface display content and presentation method. It is also possible to analyze changes in the user's emotions throughout the entire process from requirements collection to implementation and dynamically adjust the priority and risk assessment of requirements. Furthermore, it is possible to make product recommendations based on the user's needs and propose optimal products.

[1225] "Natural language processing" is the technology that enables computers to understand, generate, and manipulate human language.

[1226] "Machine learning" is a technique that refers to a computer system learning from data and improving at its tasks without being explicitly programmed.

[1227] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents and templates based on existing data.

[1228] "Data mining technology" refers to methods and techniques for extracting patterns and knowledge from large amounts of data.

[1229] The "emotion engine" is a technology that recognizes emotions in real time from human facial expressions, tone of voice, etc.

[1230] "Real-time" means that user input and actions are processed immediately.

[1231] A "user interface" refers to the screen or operating environment that allows a user to interact with a system or application.

[1232] "Traceability" refers to the ability to track how requirements are implemented and tested.

[1233] "Changes in user's emotions" refers to changes in the user's emotional state while using the system.

[1234] "Product recommendation" refers to the act of selecting and proposing the most suitable product based on the user's request.

[1235] The present invention is implemented as a smartphone app "Smart Shopping Assistant" to enhance customer experience in brick-and-mortar stores. The system includes the following main components:

[1236] Requirements gathering support

[1237] The server first collects requests entered by the user into the smartphone app. The interface is intuitive and includes a text box for entering specific requests, such as "I want a red dress," as well as a voice input function. Furthermore, the server utilizes an emotion engine to recognize the user's emotions in real time as they are being input. For example, if the emotion engine determines that the user is nervous, the server automatically switches the interface to a more user-friendly design.

[1238] Requirements analysis support

[1239] The server analyzes the request data collected from users using natural language processing (NLP) technology. NLP tokenizes the input text data and extracts important keywords. The server then uses machine learning models to match the request with a database of relevant products and services. Based on the extracted keywords, the server recommends the most suitable products.

[1240] Product recommendation

[1241] Based on the user's request, the server uses TfidfVectorizer to vectorize the request and the product information in the database, and calculates the cosine similarity. This allows the server to suggest products with the highest similarity to the user. For example, if the user's request is a "red dress," the server will present information about the most suitable red dress in stock.

[1242] Traceability and Emotion Regulation

[1243] The server analyzes the user's emotional changes in real time throughout the entire process, from requirements gathering to product recommendations. Based on this information, it dynamically adjusts requirement priorities and risk assessments. If the user is feeling stressed, the system will prioritize and recommend highly accurate products to alleviate the user's anxiety.

[1244] Hardware and Software

[1245] The following specific hardware and software is used in this system:

[1246] Smartphone app: Providing user interface and emotion recognition.

[1247] Server: Data analysis and operation of the recommendation system.

[1248] FER Library: Facial expression analysis for emotion recognition.

[1249] BERT model for transformers: Text analysis for natural language processing.

[1250] TfidfVectorizer: Vectorization and cosine similarity calculation of requirements and products.

[1251] Specific examples

[1252] Below are some specific examples of how this system can be used.

[1253] A user types "I want a red dress" into a smartphone app, and the app sends the request to a server.

[1254] The server uses the BERT model to analyze the text and recommend suitable products.

[1255] The recommended products are presented to the user, and the user's emotions are analyzed by an emotion engine.

[1256] Prompt Sentence Examples

[1257] "Please enter the product you want"

[1258] "The camera takes pictures and detects customer emotions."

[1259] "Recommend products based on customer requests"

[1260] The above describes the embodiments of the present invention, which embody the features of the invention and aim to improve the customer experience in physical stores.

[1261] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1262] Step 1:

[1263] The user inputs their request using a smartphone app. For example, they can enter a specific request such as "I want a red dress." The device then sends this input to the server via the user interface. The input is sent as text data.

[1264] Step 2:

[1265] The server analyzes the received text data using natural language processing (NLP) techniques. First, it tokenizes the input text data and extracts important keywords. In this process, it uses an NLP library (e.g., the BERT model) to perform tokenization and keyword extraction. The output is a list of extracted keywords.

[1266] Step 3:

[1267] The server uses a machine learning model to search for related products based on the extracted keyword list. It uses TfidfVectorizer to vectorize the request and product information in the database, and calculates the cosine similarity to identify the product with the highest similarity. The input is the keyword list and the product database, and the output is a list of recommended products.

[1268] Step 4:

[1269] The server sends a list of recommended products to the terminal, and the terminal presents this information to the user through a user interface. At this point, an emotion engine also operates simultaneously, analyzing the user's facial expressions and voice in real time to grasp the user's emotions. The input is the user's facial expression and voice data, and the output is the detected emotional information.

[1270] Step 5:

[1271] The server dynamically adjusts the content and presentation of the interface based on the detected user emotion information. For example, if it determines that the user is nervous, it changes the interface design to a more friendly one. The input is emotion information, and the output is the adjusted interface design.

[1272] Step 6:

[1273] The server analyzes the user's emotional changes in real time throughout the entire process, from request collection to product recommendation, and dynamically adjusts the priority and risk assessment of requirements. If the user is feeling stressed, it will recommend the most accurate product with the highest priority. The input is information on the user's emotional changes, and the output is the adjusted priority and risk assessment.

[1274] Through each of the above steps, a system is created that improves the customer experience in physical stores by making optimal product suggestions based on the user's needs and adjusting emotions in real time.

[1275] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1276] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1277] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1278] [Fourth embodiment]

[1279] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1280] 7, a 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.

[1281] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1282] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1283] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1284] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1285] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1286] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1287] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1288] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1289] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1290] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1291] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1292] The present invention describes a specific embodiment of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies to automate and streamline the requirements definition process.

[1293] 1. Requirements gathering support

[1294] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[1295] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[1296] 2. Requirements analysis support

[1297] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[1298] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[1299] 3. Support for requirements documentation

[1300] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and performs grammar checks during the document generation process.

[1301] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[1302] 4. Requirements tracing support

[1303] The server utilizes data mining techniques to establish traceability between collected requirements and implementations and test cases, enabling real-time tracking of how requirements were implemented and tested.

[1304] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[1305] ---

[1306] The advantages of this invention are realized by explaining the specific processing flow and clarifying the specific operations of the server, terminal, and user at each step, which automates the entire requirements definition process and dramatically improves efficiency and accuracy.

[1307] The processing flow will be explained below.

[1308] Step 1:

[1309] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[1310] Step 2:

[1311] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[1312] Step 3:

[1313] The server analyzes the input requirements using natural language processing (NLP) technology. Specifically, it tokenizes the requirement sentence and extracts key keywords. For example, it extracts "customer," "order," "cancellation," and "function."

[1314] Step 4:

[1315] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[1316] Step 5:

[1317] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[1318] Step 6:

[1319] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[1320] Step 7:

[1321] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[1322] Step 8:

[1323] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[1324] Step 9:

[1325] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[1326] Step 10:

[1327] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[1328] Step 11:

[1329] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[1330] Step 12:

[1331] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[1332] Step 13:

[1333] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[1334] Step 14:

[1335] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[1336] Step 15:

[1337] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[1338] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of the present invention are realized, and the requirements definition process is automated and made more efficient.

[1339] Example 1

[1340] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1341] Conventional requirements definition processes require extensive manual operations and complex data analysis, resulting in issues with efficiency and accuracy. Furthermore, requirements collection, analysis, documentation, and traceability are often separated, making it difficult to maintain consistency of information across each process. The present invention aims to solve these issues by providing a system that automates the entire requirements definition process and improves efficiency and accuracy.

[1342] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1343] In this invention, the server includes: means for tokenizing requirements information entered by a user using natural language processing technology and extracting important keywords; means for calculating and classifying features of the requirements information using a machine learning algorithm and generating a graph that visualizes the relevance of the requirements information based on the features; means for automatically creating a requirements document based on the requirements information using template generation artificial intelligence and performing grammar checks using natural language processing technology; and means for establishing traceability between the requirements information, implementation code, and test cases using data mining technology, and automatically identifying and notifying affected parts when changes occur. This enables the automation and efficiency of the entire requirements definition process.

[1344] "Natural language processing technology" is a technology that enables computers to understand, interpret, and generate human language.

[1345] "User" refers to a person who uses the system to input, check, and edit requirements information.

[1346] "Requirements information" is information that describes the functions and characteristics required of a system.

[1347] "Tokenization" is the process of breaking down natural language into its smallest units, such as words and phrases.

[1348] "Important keywords" refer to words or phrases that are considered to be particularly important in the requirements information.

[1349] A "machine learning algorithm" is a computational method for learning patterns and rules based on data and making predictions and classifications.

[1350] "Features" refer to the attributes and variables of data input into a machine learning model.

[1351] "Visualization" is the process of representing data and information in an intuitive and easy-to-understand way using graphs and charts.

[1352] "Template generation artificial intelligence" is an artificial intelligence technology that automatically creates documents and formats based on specified requirements.

[1353] "Grammar checking" is the process of detecting grammatical errors in a sentence and suggesting corrections.

[1354] "Data mining technology" is an analytical technique for extracting useful information from large amounts of data.

[1355] "Traceability" is the ability to trace the relationship from requirements to implementation to testing and identify the impact of any changes.

[1356] "Implementation code" refers to the actual program code written to meet the system requirements.

[1357] A "test case" refers to specific test conditions and procedures for verifying that specific functions or requirements of a system are implemented correctly.

[1358] "Notification" is the act of the system informing the user about a particular event or change.

[1359] MODE FOR CARRYING OUT THE INVENTION

[1360] This invention relates to a system that automates and streamlines the requirements definition process by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. This system aims to integrate and automate the entire process of requirements gathering, analysis, documentation, and traceability.

[1361] Requirements gathering support

[1362] First, the user inputs requirements information using the terminal's interactive collection GUI, which provides an interface that accepts natural language prompt input. For example, the user might input a requirement such as, "I need a feature that allows customers to cancel orders."

[1363] The server then uses natural language processing techniques (e.g., NLTK or spaCy) to tokenize the requirements and extract important keywords. For example, keywords like "customer," "order," and "cancellation" are extracted. Based on these keywords, the server determines the requirement category and matches it with an existing requirements database. This process detects similar, overlapping, or conflicting requirements.

[1364] If necessary, the server generates templates and samples and displays them on the terminal to help the user make decisions. For example, displaying a template for a "cancel function" used in a past project can help clarify requirements.

[1365] Requirements analysis support

[1366] The server analyzes the collected requirements information using machine learning algorithms (e.g., Scikit-Learn or TensorFlow). The collected requirements data is converted into features. For example, a dataset with features such as "customer," "order," and "cancellation" is generated.

[1367] Next, this dataset is fed into a machine learning model to classify requirements and analyze their relationships. As a result, the relationships between basic and derived requirements are identified. Based on the results of this analysis, the server generates a graph to visualize the relationships between requirements and displays it on the terminal. This provides users with requirement priorities and risk assessment information to support decision-making.

[1368] Requirements documentation support

[1369] The template generation AI automatically generates requirements documents based on collected and analyzed requirements information. Based on user input, it suggests appropriate document formats and performs grammar checks on the automatically generated documents.

[1370] Grammar checking is performed using the server's natural language processing technology (e.g., Grammarly API), and suggested corrections are presented to the user. Users can edit the requirements specification document in real time using an online collaborative editing tool (e.g., Google Docs). The server automatically updates the document when changes are made and manages the change history.

[1371] Requirement tracing support

[1372] Finally, the server uses data mining technology to establish traceability between the requirements information, the implementation code, and the test cases. Specifically, it analyzes and maps the relationships between the collected requirements, the implementation code, and the test cases.

[1373] The mapping results are displayed on the terminal, visualizing the relationships, allowing users to directly check the relationship between requirements and implementation. Furthermore, when changes occur, the server automatically identifies the affected implementation and tests, and notifies the user of the necessary modifications.

[1374] Specific examples

[1375] Example prompt sentence:

[1376] "We need the ability for customers to cancel their orders."

[1377] Using this system, the entire requirements definition process described above is automated, dramatically improving efficiency and accuracy.

[1378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] The user uses the terminal's collection GUI to input requirement information. For example, they might input "I need a feature that allows customers to cancel orders." The input in this step is text information in natural language, and the output is raw data for the server to analyze.

[1381] Step 2:

[1382] The server analyzes the input requirements information using natural language processing technology (e.g., NLTK or spaCy). Specifically, it tokenizes the requirements sentences and extracts important keywords. For example, tokens such as "customer," "order," and "cancellation" are generated. The input in this step is the raw requirements information, and the output is a tokenized keyword list.

[1383] Step 3:

[1384] The server determines the category of the requirement based on the extracted keywords and compares it with the existing requirements database. A specific operation here is to check whether "cancellation" belongs to "customer management functions." The input in this step is a keyword list, and the output is the category determination result and the database comparison result.

[1385] Step 4:

[1386] The server detects whether there are similar, overlapping, or conflicting requirements, and generates templates or samples as needed, which are then displayed on the device. For example, it displays a template for a "cancel function" used in a past project. The input in this step is the category determination results and matching results, and the output is the presentation of templates or samples.

[1387] Step 5:

[1388] The server analyzes the collected requirements information using a machine learning algorithm (e.g., Scikit-Learn or TensorFlow). The requirements data is converted into features and fed into the machine learning model. For example, features such as "customer," "order," and "cancellation" are calculated. The input in this step is the requirements data, and the output is a list of features and a classification result.

[1389] Step 6:

[1390] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The visualized graph includes requirement priority and risk assessment information. For example, a graph is generated showing that "cancellation function" is related to "order management function." The input in this step is the analysis results, and the output is the visualized graph.

[1391] Step 7:

[1392] The template generation AI automatically generates a requirements document based on requirements data. It suggests an appropriate document format based on the requirements information entered by the user, and grammar checks are also performed during the document generation process. Specifically, it generates a requirement statement such as "We need a function that allows customers to cancel orders." The input in this step is requirements data, and the output is a requirements document.

[1393] Step 8:

[1394] The server checks the generated document for grammar using natural language processing technology (e.g., Grammarly API) and suggests corrections. Users can edit the document in real time using online collaborative editing tools (e.g., Google Docs). The input in this step is the requirements document, and the output is the grammar check results and suggested corrections.

[1395] Step 9:

[1396] The server automatically updates the document when changes are made and maintains the change history. For example, when a user adds or modifies a document, the changes are immediately reflected and recorded in the history. The input in this step is the edited document, and the output is the updated document and the change history.

[1397] Step 10:

[1398] The server uses data mining technology to establish traceability between requirements information, implementation code, and test cases. Specifically, it analyzes and maps the relationships between collected requirements, implementation code, and test cases. The input in this step is requirements information, and the output is the mapping results.

[1399] Step 11:

[1400] When a change occurs, the server automatically identifies the implementation and tests of the affected parts and notifies the user of the necessary modifications. For example, if there is a change to the "cancel function," other affected functions and test cases will be identified and notified. The input to this step is the changed requirements information, and the output is the impact analysis results and notification of the modifications.

[1401] (Application example 1)

[1402] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1403] In modern factories, improved work efficiency is required, as well as accuracy and speed in the requirements definition process. However, manually collecting requirements, analyzing them, documenting them, and establishing traceability is time-consuming and prone to errors. It is also difficult to manage work progress in real time, making it difficult to respond quickly when problems occur. Furthermore, a lack of visualization of work data and provision of related information can delay decision-making by workers and managers.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1405] In this invention, the server includes: means for analyzing requirements data entered by a user using natural language processing; means for extracting relevance of the requirements data using machine learning and displaying it as a graph; means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks; means for establishing traceability of requirements, implementation, and testing using data mining technology and evaluating the impact of changes; means for inputting work requirements by voice using a smart device and processing the data in real time; and means for visually presenting work progress and related information in real time and providing necessary corrections. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and enabling real-time work management and rapid response.

[1406] "Natural language processing" is the technology of using computers to understand, analyze, and generate human language.

[1407] "Machine learning" is an algorithm that allows a computer to make decisions by feeding it large amounts of data and automatically learning patterns.

[1408] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates sentences and documents based on a specified format.

[1409] "Data mining" is a technique for discovering useful information and relationships from large amounts of data.

[1410] A "smart device" is an advanced electronic device with internet connectivity and a variety of functions.

[1411] "Voice input" is a technology that inputs voice into a computer or device and converts it into text or commands.

[1412] "Real-time" means that data and information is processed and provided almost immediately.

[1413] "Work progress" is information that indicates how much work has progressed or been completed.

[1414] "Visually presented" means displaying information graphically and making it easy to understand.

[1415] The "requirements definition process" is a procedure for describing the requirements of a system or project in detail and achieving a common understanding.

[1416] This invention provides a system for automating and streamlining the requirements definition process in a factory by utilizing natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), and data mining technologies. Specific embodiments are described below.

[1417] System Overview

[1418] The system consists of a smart device (smart glasses or head-mounted display) and a server. The smart device has the function of converting voice input into text data and sending it to the server. The server analyzes the received text data and executes an automated requirements definition process.

[1419] Hardware and Software Used

[1420] Smart Devices: Voice Input and Real-Time Notifications

[1421] Server: Data analysis and processing

[1422] Natural language processing software: SpaCy and NLTK

[1423] Machine learning frameworks: Scikit-learn and TensorFlow

[1424] Template generation AI: GPT-3

[1425] Data mining tools: Weka and RapidMiner

[1426] Details of the process

[1427] 1. Voice input and text conversion

[1428] The user uses the microphone in the smart glasses to input the task requirements by voice, and the smart glasses convert the voice data into text data using the Google Speech-to-Text API or similar.

[1429] The converted text data is sent from the smart device to the server.

[1430] 2. Requirements analysis and relevance assessment

[1431] The server tokenizes the received text data using natural language processing software (e.g., SpaCy or NLTK) and extracts important keywords.

[1432] Based on the extracted keywords, a machine learning framework (e.g., Scikit-learn or TensorFlow) is used to analyze the priority and risks of requirements.

[1433] The analysis results are visualized as a relevance graph and displayed in real time on smart devices.

[1434] 3. Requirements documentation

[1435] Using a template generation AI (e.g., GPT-3), a requirements specification document is automatically generated from the analysis results. Grammar checks are also performed during the document generation process.

[1436] The generated requirements specification document is provided to users and administrators and can be edited in real time through online collaborative editing tools.

[1437] 4. Requirements tracing and real-time notifications

[1438] The server uses data mining tools (e.g., Weka or RapidMiner) to establish traceability between requirements, implementation code, and test cases.

[1439] Work progress and related information are visually displayed on smart devices in real time, and if a problem occurs, you are immediately notified and provided with the necessary corrections.

[1440] Examples of specific examples and prompts

[1441] For example, a worker wearing smart glasses can input "The conveyor belt speed on line C4 needs to be increased by 30%" through voice input. The server receives and analyzes this information, and displays the associated risks and countermeasures on the smart glasses. The generated requirements specification document is provided to the manager, and work progress is updated in real time.

[1442] Example prompts for generative AI models

[1443] "We need to increase the speed of our factory conveyor belts by 30%. Please generate a requirements document for this requirement, including a risk assessment and associated work."

[1444] As a result, the present invention not only dramatically improves the efficiency and accuracy of factory work, but also enables quick response when problems occur.

[1445] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1446] Step 1:

[1447] Voice input and text conversion

[1448] The user uses the microphone on the smart device to input the task requirements by voice, and the smart device converts the input voice data into text data using a speech recognition tool such as the Google Speech-to-Text API, which then sends the converted text data from the smart device to the server.

[1449] Input: Voice data from the user

[1450] Output: Text data

[1451] Specific operation: The smart device records voice, and the voice recognition engine analyzes the voice data and converts it into text.

[1452] Step 2:

[1453] Requirements analysis

[1454] The server receives the text data and uses natural language processing (NLP) software (e.g., SpaCy or NLTK) to tokenize the text data and extract important keywords.

[1455] Input: Text data converted from audio

[1456] Output: Keywords and tokenized text

[1457] What happens: The server breaks the text into tokens and performs text analysis to identify keywords.

[1458] Step 3:

[1459] Relevance assessment

[1460] The server uses machine learning algorithms (e.g., Scikit-learn or TensorFlow) based on the extracted keywords to evaluate the priority and risk of requirements. Based on the analysis results, it generates a relevance graph and displays it to the user.

[1461] Input: Extracted keywords

[1462] Output: Requirement priorities, risk assessment, and relationship graphs

[1463] How it works: The server feeds data into a machine learning model, calculates priorities and risks, and generates a visual graph.

[1464] Step 4:

[1465] Requirements documentation

[1466] The server uses template generation AI (e.g., GPT-3) to automatically generate a requirements specification document from the analysis results. It also performs grammar checks during document generation and provides the generated document to users and administrators.

[1467] Input: Parsed requirements data

[1468] Output: Automatically generated requirements specification

[1469] Specific operation: The server provides data to the template generation AI, generates a requirements specification document, and checks the grammar.

[1470] Step 5:

[1471] Requirement Tracing and Notifications

[1472] The server uses data mining tools (e.g., Weka and RapidMiner) to establish traceability between requirements, implementation code, and test cases. It visually displays work progress and related information in real time on smart devices, and immediately notifies users if any problems occur. It also provides necessary fixes.

[1473] Input: Requirements specification, implementation code, test cases

[1474] Output: Traceability map, real-time notifications, remediation guidelines

[1475] Specific operation: The server analyzes the relationship between requirements, implementation, and testing, generates notifications about progress and when problems occur, and sends them to the smart device.

[1476] As a result, the present invention automates and streamlines the requirements definition process in a factory, supporting appropriate work management and rapid response.

[1477] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1478] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[1479] 1. Requirements gathering support

[1480] First, the user inputs requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. For example, the user might input "We need a function that allows customers to cancel orders."

[1481] Furthermore, an emotion engine is used to recognize the user's emotions in real time as they input data. For example, if the user appears irritated, the server will change the content and presentation of the collection GUI to provide an environment that makes it easier for the user to input data.

[1482] The server then analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these extracted keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. Furthermore, it displays templates and samples on the device as needed to support the user's decision-making.

[1483] 2. Requirements analysis support

[1484] The server analyzes the collected requirements using a machine learning algorithm. The collected requirements data is converted into features and fed into a machine learning model, which identifies the relationships between basic requirements and derived requirements.

[1485] The server generates a graph based on the analysis results to visualize the relationship between requirements and displays it on the terminal. The graph also includes requirement priorities and risk assessment information to support user decision-making.

[1486] Furthermore, the system uses an emotion engine to dynamically adjust the priority and risk assessment of requirements analysis according to changes in the user's emotions. For example, if the user is feeling anxious, the system will review the most important requirements first, thereby reassuring the user.

[1487] 3. Support for requirements documentation

[1488] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to adjust specific expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it will use more gentle expressions and positive vocabulary.

[1489] The server uses natural language processing technology to check grammar and suggests corrections. Users can edit the requirements specification document in real time using an online collaborative editing tool. The server also automatically updates the document when changes are made and manages the change history.

[1490] 4. Requirements tracing support

[1491] The server utilizes data mining techniques to establish traceability between collected requirements and implementation code and test cases, enabling real-time tracking of how requirements were implemented and tested.

[1492] Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. This mapping result is displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected parts of the implementation and tests, and notifies the user of the necessary modifications.

[1493] In this way, by clarifying the specific processing flow and the operations at each step, the advantages of this invention are realized. The entire requirements definition process is automated, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[1494] The processing flow will be explained below.

[1495] The present invention describes specific embodiments of a system that utilizes natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining techniques, and an emotion engine to automate and streamline the requirements definition process.

[1496] Step 1:

[1497] The user opens an interactive collection GUI on a terminal, which displays a requirements entry interface.

[1498] Step 2:

[1499] The user enters a business requirement, for example, "I need the ability for customers to cancel their orders."

[1500] Step 3:

[1501] The device's built-in emotion engine recognizes the user's emotions in real time from their facial expressions and tone of voice. If the emotion is irritation or anxiety, the device will adjust the content and presentation method.

[1502] Step 4:

[1503] The server analyzes the input requirements using natural language processing (NLP) techniques. It tokenizes the requirement statements and extracts key keywords. For example, it extracts "customer", "order", "cancellation", and "function".

[1504] Step 5:

[1505] The server determines the category of the requirement based on the extracted keywords. For example, categorize it as "cancel function."

[1506] Step 6:

[1507] The server checks the existing requirements database to find similar, overlapping, or conflicting requirements. For example, check whether a "cancel function" already exists.

[1508] Step 7:

[1509] If necessary, the server displays templates and samples on the terminal, helping the user understand the requirements.

[1510] Step 8:

[1511] The server passes the collected requirements data to a machine learning algorithm for analysis. The requirements data is converted into features and input into the machine learning model.

[1512] Step 9:

[1513] The server identifies the relationship between the basic requirements and derived requirements of a requirement. For example, it identifies the basic requirement "cancellation function" and the derived requirements "notification function" and "reason recording function."

[1514] Step 10:

[1515] The server generates a graph that visualizes the relationships between requirements and displays it on the terminal, including requirement priority and risk assessment information.

[1516] Step 11:

[1517] The server automatically generates requirements documents using template generation AI. Based on the requirements information entered by the user, it proposes an appropriate document format and generates the document.

[1518] Step 12:

[1519] The server performs a grammar check, using natural language processing technology to detect grammatical errors in the requirements document and suggest corrections.

[1520] Step 13:

[1521] The server adjusts certain expressions and vocabulary based on the user's emotions recognized by the emotion engine. For example, if the user is nervous, it uses softer expressions and more positive vocabulary.

[1522] Step 14:

[1523] Users edit the requirements specification document in real time using an online collaborative editing tool, and the server automatically updates the document when changes are made and manages the change history.

[1524] Step 15:

[1525] The server utilizes data mining techniques to establish traceability between the collected requirements and the implementation code and test cases.

[1526] Step 16:

[1527] The server analyzes the relationship between requirements, implementation, and test cases, and creates a traceability map. This is displayed on the terminal, visualizing the relationship.

[1528] Step 17:

[1529] When a change occurs, the server automatically identifies the affected parts of the implementation and tests and notifies the user. Example: When "Customer" is changed to "Registered User" only, the affected parts of the code are identified.

[1530] By clarifying the specific process flow and the operations at each step, the advantages of this invention are realized, automating the entire requirements definition process, dramatically improving efficiency and accuracy, and taking user emotions into consideration to provide a more user-friendly experience.

[1531] Example 2

[1532] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1533] The traditional requirements definition process had problems such as ambiguity in user input and subjective bias, making it time-consuming and labor-intensive to collect and analyze requirements. It was also unclear how requirements would be tracked and changes managed during the implementation and testing phases, making traceability difficult. Furthermore, inconsistent UI / UX design that did not take user emotions into consideration often resulted in a poor user experience. Effective methods to resolve these issues are needed.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1535] In this invention, the server includes means for analyzing requirements data entered by a user using natural language processing, means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This automates the entire requirements definition process, dramatically improving efficiency and accuracy, and by taking user feelings into consideration, it is possible to provide a more user-friendly environment.

[1536] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1537] "Machine learning" is a technique that trains algorithms based on data to make predictions and classifications.

[1538] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents based on a predefined format.

[1539] "Data mining technology" is a technique for extracting useful patterns and knowledge from large amounts of data.

[1540] An "emotion engine" is an algorithm that detects a user's emotions and changes behavior based on them.

[1541] "Traceability" means ensuring traceability of the entire process from requirements to implementation and testing.

[1542] An "interactive collection GUI" is a graphical user interface for collecting requirements data through user interaction.

[1543] An "online collaborative editing tool" is an online tool that allows multiple users to edit and update documents simultaneously.

[1544] This invention relates to a system that automates and streamlines the requirements definition process. The main hardware is a server and a terminal, and the software uses natural language processing (NLP), machine learning (ML), template generation artificial intelligence (AI), data mining technology, and an emotion engine.

[1545] 1. Requirements Gathering

[1546] First, the user inputs business requirements. The terminal provides an interactive collection GUI and displays an interface for inputting business requirements. This interface can also include specific examples such as "We need a function that allows customers to cancel orders." The emotion engine recognizes the user's emotions in real time as they input their requirements. For example, if the user is showing irritation, the server adjusts the content and presentation method of the collection GUI, providing an environment that makes it easier for the user to input.

[1547] 2. Requirements analysis

[1548] The server analyzes the input requirements using natural language processing technology. Specifically, it tokenizes the requirement statements and extracts important keywords. Based on these keywords, it determines the category of the requirements and compares them with an existing requirements database to detect similar, overlapping, or conflicting requirements. If necessary, it displays templates or samples on the device to support the user's decision-making.

[1549] 3. Requirements analysis

[1550] The server analyzes the collected requirements using a machine learning algorithm. The collected data is converted into features and input into a machine learning model. This identifies the relationships between basic and derived requirements. The analysis results are generated as graphs to visualize the relationship between requirements and are displayed on the terminal. They also include requirement priority and risk assessment information to support user decision-making. An emotion engine is used to dynamically adjust the analysis results in response to changes in the user's emotions, and requirements with high importance or high risk are displayed first.

[1551] 4. Requirements documentation

[1552] The template generation AI automatically generates requirements documents using collected and analyzed requirements data. Based on the requirements information entered by the user, it suggests an appropriate document format, and grammar checks are also performed during the document generation process. It is also possible to reflect the user's emotions, as recognized by the emotion engine, and adjust specific expressions and vocabulary. For example, if the user is nervous, it will use more soft, positive vocabulary. The server uses natural language processing technology to check grammar and suggests corrections. Users can edit requirements specifications in real time using an online collaborative editing tool. The server automatically updates the document when changes are made and manages the change history.

[1553] 5. Requirements Tracing

[1554] The server uses data mining technology to establish traceability between collected requirements and implementation code and test cases. This makes it possible to track how requirements have been implemented and tested in real time. Specifically, the server analyzes and maps the relationships between requirements, implementation code, and test cases. The mapping results are displayed on the terminal, visualizing the relationships. When changes occur, the server automatically identifies the affected implementation and tests and notifies the user of the necessary modifications.

[1555] Specific examples and prompt sentence examples

[1556] For example, if a user requests "a feature that allows customers to cancel orders," the terminal provides an interactive collection GUI, and if the emotion engine detects frustration with the user's input, the server adjusts the interface and displays a flexible input form. The requirement is checked for overlaps with existing databases and classified as "order management." The following prompt sentence is then input to the generative AI model based on this requirement:

[1557] One requirement input was for the ability for customers to cancel orders. Users were frustrated with some of the input. In this case, we flexed the interface presentation and categorized the requirement under "Order Management." We then checked our existing database for similar requirements to find any overlaps or inconsistencies.

[1558] This system automates the entire requirements definition process, dramatically improving efficiency and accuracy, and also takes user feelings into consideration to provide a more user-friendly environment.

[1559] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1560] Step 1:

[1561] User enters requirements

[1562] The user inputs business requirements using an interactive collection GUI, including specific requirements such as "We need a function that allows customers to cancel orders." The input requirements data is then sent to the terminal.

[1563] Input: User's business requirements (natural language text)

[1564] Output: Collected requirements data

[1565] Step 2:

[1566] The device uses an emotion engine to recognize the user's emotions in real time.

[1567] The device analyzes the user's facial expressions and tone of voice when inputting, and uses an emotion engine to recognize emotions such as irritation or dissatisfaction in real time. For example, if the user shows irritation, the device will collect emotional data.

[1568] Input: User facial expression, voice tone

[1569] Output: User emotion data

[1570] Step 3:

[1571] The server analyzes the requirements

[1572] The server receives the requirements data sent from the device and analyzes it using natural language processing technology. The requirements sentences are tokenized and important keywords are extracted. For example, keywords such as "order" and "cancel" are extracted.

[1573] Input: Collected requirements data

[1574] Output: Extracted keywords and analysis results

[1575] Step 4:

[1576] The server performs categorization and matching

[1577] The server categorizes the requirements based on the extracted keywords and compares them with existing requirements databases, for example, categorizing them into categories such as "order management" and "cancellation function." It also checks for similar, overlapping, or conflicting requirements.

[1578] Input: Extracted keywords and analysis results

[1579] Output: Categorized requirements data and matching results

[1580] Step 5:

[1581] The device displays templates and examples

[1582] Based on the results of the analysis, the server displays requirement templates and samples on the terminal, allowing the user to determine more specific requirements based on the templates and samples they refer to.

[1583] Input: Categorized requirements data and matching results

[1584] Output: The template or sample to be displayed

[1585] Step 6:

[1586] The server uses machine learning algorithms to analyze requirements

[1587] The collected requirements data is converted into features and analyzed using a machine learning model to identify relationships between base and derived requirements. For example, we analyze how the cancellation function relates to other order management requirements.

[1588] Input: Categorized requirements data

[1589] Output: Requirements association and analysis results

[1590] Step 7:

[1591] The server visualizes the analysis results

[1592] The server visualizes the relationship between requirements based on the analysis results as a graph, including requirement priority and risk assessment information. For example, the importance and risk of the cancel function are visually displayed.

[1593] Input: Requirements associations and analysis results

[1594] Output: Visualized graph

[1595] Step 8:

[1596] The device displays the analysis results.

[1597] The terminal displays visualized graphs sent from the server to the user, clearly presenting requirement priorities and risk assessments.

[1598] Input: Visualized graph

[1599] Output: The analysis results to be displayed

[1600] Step 9:

[1601] The server uses an emotion engine to dynamically adjust the analysis results.

[1602] The server monitors changes in the user's emotions and dynamically adjusts the priority and risk assessment of requirements analysis according to the user's emotions. For example, if the user feels anxious, the server will prioritize reviewing requirements of high importance.

[1603] Input: User sentiment data, requirements analysis results

[1604] Output: Dynamically adjusted analysis results

[1605] Step 10:

[1606] The server automatically generates requirements documents using template generation AI.

[1607] Based on the collected and analyzed requirements data, requirements documents are automatically generated in the appropriate document format, and grammar checks are also performed.

[1608] Input: Requirement analysis results, categorized requirement data

[1609] Output: Auto-generated requirements document

[1610] Step 11:

[1611] The server performs a syntax check

[1612] The server uses natural language processing technology to check the grammar of the generated requirements document and suggests corrections.

[1613] Input: Auto-generated requirements document

[1614] Output: Syntax-checked requirements document and suggested corrections

[1615] Step 12:

[1616] A user edits a document in an online collaborative editing tool

[1617] Users can use online collaborative editing tools to edit requirements documents in real time.

[1618] Input: Grammar-checked requirements document and suggested corrections

[1619] Output: Edited requirements document

[1620] Step 13:

[1621] The server updates changes in real time and manages the history

[1622] The server automatically reflects changes made by the user in real time to the document and manages the change history.

[1623] Input: Edited requirements document

[1624] Output: Updated requirements document and change history

[1625] Step 14:

[1626] The server uses data mining techniques to establish traceability between requirements, implementation, and testing.

[1627] It analyzes and maps the relationship between collected requirements, implementation code, and test cases, making it possible to track in real time how requirements have been implemented and tested.

[1628] Input: Requirement data, implementation code, test cases

[1629] Output: Traceability map

[1630] Step 15:

[1631] The terminal visualizes and displays the traceability results

[1632] The terminal visualizes the traceability map sent from the server and displays it to the user.

[1633] Input: Traceability map

[1634] Output: Traceability visualization results

[1635] Step 16:

[1636] Identify and notify affected server areas

[1637] When changes occur, the server automatically identifies the affected implementations and tests and notifies the user of the necessary modifications.

[1638] Input: Updated requirements data and implementation code

[1639] Output: Notice of affected parts

[1640] (Application example 2)

[1641] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1642] The traditional requirements definition process involves a lot of manual work, which can be inefficient and inaccurate. Furthermore, requirements are collected and analyzed without considering the user's feelings, which can lead to increased user dissatisfaction and stress. Furthermore, product and service proposals can sometimes be made that do not meet the user's tolerance level, resulting in a decrease in customer satisfaction.

[1643] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1644] In this invention, the server includes a means for analyzing requirements data entered by a user using natural language processing, a means for extracting relevance of the requirements data using machine learning and displaying it as a graph, and a means for automatically generating requirements documents using template generation artificial intelligence and performing grammar checks. This makes it possible to recognize the user's emotions in real time during requirements collection and dynamically adjust the interface display content and presentation method. It is also possible to analyze changes in the user's emotions throughout the entire process from requirements collection to implementation and dynamically adjust the priority and risk assessment of requirements. Furthermore, it is possible to make product recommendations based on the user's needs and propose optimal products.

[1645] "Natural language processing" is the technology that enables computers to understand, generate, and manipulate human language.

[1646] "Machine learning" is a technique that refers to a computer system learning from data and improving at its tasks without being explicitly programmed.

[1647] "Template generation artificial intelligence" is an artificial intelligence technology that automatically generates documents and templates based on existing data.

[1648] "Data mining technology" refers to methods and techniques for extracting patterns and knowledge from large amounts of data.

[1649] The "emotion engine" is a technology that recognizes emotions in real time from human facial expressions, tone of voice, etc.

[1650] "Real-time" means that user input and actions are processed immediately.

[1651] A "user interface" refers to the screen or operating environment that allows a user to interact with a system or application.

[1652] "Traceability" refers to the ability to track how requirements are implemented and tested.

[1653] "Changes in user's emotions" refers to changes in the user's emotional state while using the system.

[1654] "Product recommendation" refers to the act of selecting and proposing the most suitable product based on the user's request.

[1655] The present invention is implemented as a smartphone app "Smart Shopping Assistant" to enhance customer experience in brick-and-mortar stores. The system includes the following main components:

[1656] Requirements gathering support

[1657] The server first collects requests entered by the user into the smartphone app. The interface is intuitive and includes a text box for entering specific requests, such as "I want a red dress," as well as a voice input function. Furthermore, the server utilizes an emotion engine to recognize the user's emotions in real time as they are being input. For example, if the emotion engine determines that the user is nervous, the server automatically switches the interface to a more user-friendly design.

[1658] Requirements analysis support

[1659] The server analyzes the request data collected from users using natural language processing (NLP) technology. NLP tokenizes the input text data and extracts important keywords. The server then uses machine learning models to match the request with a database of relevant products and services. Based on the extracted keywords, the server recommends the most suitable products.

[1660] Product recommendation

[1661] Based on the user's request, the server uses TfidfVectorizer to vectorize the request and the product information in the database, and calculates the cosine similarity. This allows the server to suggest products with the highest similarity to the user. For example, if the user's request is a "red dress," the server will present information about the most suitable red dress in stock.

[1662] Traceability and Emotion Regulation

[1663] The server analyzes the user's emotional changes in real time throughout the entire process, from requirements gathering to product recommendations. Based on this information, it dynamically adjusts requirement priorities and risk assessments. If the user is feeling stressed, the system will prioritize and recommend highly accurate products to alleviate the user's anxiety.

[1664] Hardware and Software

[1665] The following specific hardware and software is used in this system:

[1666] Smartphone app: Providing user interface and emotion recognition.

[1667] Server: Data analysis and operation of the recommendation system.

[1668] FER Library: Facial expression analysis for emotion recognition.

[1669] BERT model for transformers: Text analysis for natural language processing.

[1670] TfidfVectorizer: Vectorization and cosine similarity calculation of requirements and products.

[1671] Specific examples

[1672] Below are some specific examples of how this system can be used.

[1673] A user types "I want a red dress" into a smartphone app, and the app sends the request to a server.

[1674] The server uses the BERT model to analyze the text and recommend suitable products.

[1675] The recommended products are presented to the user, and the user's emotions are analyzed by an emotion engine.

[1676] Prompt Sentence Examples

[1677] "Please enter the product you want"

[1678] "The camera takes pictures and detects customer emotions."

[1679] "Recommend products based on customer requests"

[1680] The above describes the embodiments of the present invention, which embody the features of the invention and aim to improve the customer experience in physical stores.

[1681] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1682] Step 1:

[1683] The user inputs their request using a smartphone app. For example, they can enter a specific request such as "I want a red dress." The device then sends this input to the server via the user interface. The input is sent as text data.

[1684] Step 2:

[1685] The server analyzes the received text data using natural language processing (NLP) techniques. First, it tokenizes the input text data and extracts important keywords. In this process, it uses an NLP library (e.g., the BERT model) to perform tokenization and keyword extraction. The output is a list of extracted keywords.

[1686] Step 3:

[1687] The server uses a machine learning model to search for related products based on the extracted keyword list. It uses TfidfVectorizer to vectorize the request and product information in the database, and calculates the cosine similarity to identify the product with the highest similarity. The input is the keyword list and the product database, and the output is a list of recommended products.

[1688] Step 4:

[1689] The server sends a list of recommended products to the terminal, and the terminal presents this information to the user through a user interface. At this point, an emotion engine also operates simultaneously, analyzing the user's facial expressions and voice in real time to grasp the user's emotions. The input is the user's facial expression and voice data, and the output is the detected emotional information.

[1690] Step 5:

[1691] The server dynamically adjusts the content and presentation of the interface based on the detected user emotion information. For example, if it determines that the user is nervous, it changes the interface design to a more friendly one. The input is emotion information, and the output is the adjusted interface design.

[1692] Step 6:

[1693] The server analyzes the user's emotional changes in real time throughout the entire process, from request collection to product recommendation, and dynamically adjusts the priority and risk assessment of requirements. If the user is feeling stressed, it will recommend the most accurate product with the highest priority. The input is information on the user's emotional changes, and the output is the adjusted priority and risk assessment.

[1694] Through each of the above steps, a system is created that improves the customer experience in physical stores by making optimal product suggestions based on the user's needs and adjusting emotions in real time.

[1695] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1696] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1697] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1698] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1699] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1700] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1701] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1702] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1703] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1704] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1705] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1706] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1707] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1708] 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.

[1709] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1710] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1711] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1712] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1713] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1714] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1715] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1716] The following is further disclosed regarding the above embodiment.

[1717] (Claim 1)

[1718] means for analyzing requirement data input by a user using natural language processing;

[1719] A method to extract relationships between requirements data using machine learning and display them as graphs;

[1720] A means for automatically generating a requirements document using template generation artificial intelligence and performing grammar checks;

[1721] A means of establishing traceability of requirements, implementation, and testing using data mining techniques and assessing the impact of changes;

[1722] A system including:

[1723] (Claim 2)

[1724] 10. The system of claim 1, providing a user interface for interactively gathering requirements.

[1725] (Claim 3)

[1726] 10. The system of claim 1, which provides an online collaborative editing tool that enables simultaneous editing of a requirements specification document.

[1727] "Example 1"

[1728] (Claim 1)

[1729] A means for tokenizing requirement information input by a user using natural language processing technology and extracting important keywords;

[1730] a means for calculating and classifying feature quantities of the requirements information using a machine learning algorithm and generating a graph that visualizes the relevance of the requirements information based on the calculated feature quantities;

[1731] A means for automatically creating a requirements document based on requirements information using template generation artificial intelligence and performing grammar checks using natural language processing technology;

[1732] A method for establishing traceability between requirements information, implementation code, and test cases using data mining technology, and automatically identifying and notifying affected parts when changes occur;

[1733] A system including:

[1734] (Claim 2)

[1735] 10. The system of claim 1, providing a user interface for interactively gathering requirements information.

[1736] (Claim 3)

[1737] 10. The system of claim 1, which provides an online collaborative editing tool that enables editing of requirements specifications in real time.

[1738] "Application Example 1"

[1739] (Claim 1)

[1740] means for analyzing requirement data input by a user using natural language processing;

[1741] A method to extract relationships between requirements data using machine learning and display them as graphs;

[1742] A means for automatically generating a requirements document using template generation artificial intelligence and performing grammar checks;

[1743] A means of establishing traceability of requirements, implementation, and testing using data mining techniques and assessing the impact of changes;

[1744] A means to use smart devices to voice input work requirements and process data in real time;

[1745] A means of visually presenting work progress and related information in real time and providing necessary corrections;

[1746] A system including:

[1747] (Claim 2)

[1748] 10. The system of claim 1, providing a user interface for interactively gathering requirements.

[1749] (Claim 3)

[1750] 10. The system of claim 1, which provides an online collaborative editing tool that enables simultaneous editing of a requirements specification document.

[1751] "Example 2: Combining Emotion Engines"

[1752] (Claim 1)

[1753] means for analyzing requirement data input by a user using natural language processing;

[1754] A method to extract relationships between requirements data using machine learning and display them as graphs;

[1755] A means for automatically generating a requirements document using template generation artificial intelligence and performing grammar checks;

[1756] A means of establishing traceability of requirements, implementation, and testing using data mining techniques and assessing the impact of changes;

[1757] a means for recognizing a user's emotion during input using an emotion engine and dynamically adjusting the interface;

[1758] A means to dynamically adjust requirements analysis priorities and risk assessments according to changing sentiment;

[1759] A system including:

[1760] (Claim 2)

[1761] 10. The system of claim 1, which provides a user interface for interactively collecting requirements and recognizes use...

Claims

1. means for analyzing requirement data input by a user using natural language processing; A method to extract relationships between requirements data using machine learning and display them as graphs; A means for automatically generating a requirements document using template generation artificial intelligence and performing grammar checks; A means of establishing traceability of requirements, implementation, and testing using data mining techniques and assessing the impact of changes; A system including:

2. The system of claim 1 , providing a user interface for interactively gathering requirements.

3. The system according to claim 1 , which provides an online collaborative editing tool to enable simultaneous editing of a requirements specification document.

Images