System

Abstract

A system is provided.SOLUTION: A system including means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required time, means for a server to learn the input data and train an AI model, means for the user to input a specification document regarding a new function, means for the server to analyze the new specification document and extract important elements, means for the server to generate an optimal verification item based on the learned data and the analyzed specification document, and means for the server to present the generated verification item list to the user.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] In modern software development, it is important to efficiently and effectively identify the necessary verification items when adding or changing new features. However, traditional methods require a great deal of time and effort to manually create appropriate verification items based on new specifications, and are prone to human error. Furthermore, past failure cases and verification history cannot be fully utilized, resulting in a lack of learning to prevent recurrence and improve quality. In this situation, there is a need to provide an effective and efficient means of generating verification items. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for a server to learn from the input data and train an AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and analyzed specifications; and a means for the server to present the generated list of verification items to the user.

[0006] Specifically, the server performs data cleaning and feature extraction based on the input data, and then performs model learning and validation to generate a highly accurate AI model. Furthermore, it analyzes new specifications using natural language processing technology to extract and structure important elements. This provides efficient and effective verification items when implementing new functions, making it possible to reduce human error.

[0007] A "user" is an entity that uses the system to perform operations such as inputting data and uploading new specifications.

[0008] A "system specification" is a document that contains design information and technical details regarding the operation and configuration of software and hardware.

[0009] "User characteristics" is information that indicates the characteristics of users of the system, such as their age group, behavioral patterns, and needs.

[0010] "Failure cases" are records that show specific instances when a system malfunction, bug, or other problem occurred.

[0011] "Verification items" are specific test contents used to confirm whether each function of a system or software operates according to specifications.

[0012] "Time required" refers to the time required to perform the verification items and other tasks.

[0013] A "server" is a computer that performs primary functions such as processing, storing, and analyzing data.

[0014] "Data learning" is the process of using machine learning and AI techniques to extract specific patterns and relationships from input data.

[0015] An "AI model" is a collection of artificial intelligence algorithms and formulas created based on data learning to perform specific tasks.

[0016] A "specification" is a document that details the design, requirements, and behavior of a new feature or system.

[0017] "Natural language processing" is the technology that allows computers to understand, analyze, and generate human language.

[0018] "Key elements" are key points extracted from specifications and other data that should be given special emphasis in the operation and functionality of the system.

[0019] "Data cleaning" is the process of removing incomplete data and duplicates from input data to improve the quality of the data.

[0020] "Feature extraction" is the process of extracting important patterns or characteristics from data.

[0021] "Model validation" is a verification process to confirm the accuracy and effectiveness of a trained AI model.

[0022] "Analysis" is the process of examining specifications and other data in detail to extract specific information and patterns.

[0023] The "verification item list" is a list of all generated verification items.

[0024] "Presenting" refers to the act of showing information such as the generated verification item list to the user. [Brief explanation of the drawings]

[0025] [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

[0026] 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.

[0027] First, the terms used in the following description will be explained.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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."

[0046] The present embodiment will now be described in natural language with respect to the processing of the system and its programs.

[0047] System Overview

[0048] This invention relates to a system that proposes optimal verification items when implementing new functions, using an AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[0049] Data input and training

[0050] 1. The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and the required time.

[0051] Data entry is done through methods such as file upload and form filling.

[0052] Immediately after the data is uploaded, the server performs data cleaning as a pre-processing of the data.

[0053] 2. The server receives the input data and trains the AI ​​model.

[0054] First, the server performs data cleaning to remove incomplete data and duplicates.

[0055] Next, feature extraction is performed to extract important features of each data.

[0056] The server uses these features to train an AI model and validate the model.

[0057] Entering and parsing new specifications

[0058] 3. The user uploads a specification for a new feature into the system.

[0059] The server performs preprocessing of the text data to ensure a consistent format for the specification.

[0060] 4. The server parses the new specification and extracts the important elements.

[0061] The server analyzes the text using natural language processing (NLP) techniques.

[0062] From the analysis results, important elements (e.g., functional requirements and non-functional requirements) are extracted and structured.

[0063] Generation and presentation of verification items

[0064] 5. The server generates optimal verification items based on the learned data and analyzed specifications.

[0065] The server references past data and automatically generates optimal verification items based on new specifications.

[0066] The generated verification items also include an estimate of the time required for each.

[0067] 6. The server presents the generated list of verification items to the user.

[0068] The results are displayed through the user interface, and the user can create a verification plan based on the list.

[0069] The list can be downloaded in CSV or Excel format, and suggestions for improving items are also accepted via the feedback function.

[0070] Specific examples

[0071] Added new feature "User profile customization function"

[0072] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0073] 2. The server uses this data to train the AI ​​model.

[0074] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0075] 4. The server analyzes the new specifications and extracts important elements such as the ability to change profile pictures and edit self-introductions.

[0076] 5. Based on the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." It also provides an estimate of the time required for each verification item.

[0077] 6. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0078] This reduces the risk of manual creation of verification items and errors, enabling efficient and high-quality software development.

[0079] The processing flow will be explained below.

[0080] Step 1:

[0081] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[0082] Step 2:

[0083] The server preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values.

[0084] Step 3:

[0085] The server then performs feature extraction from the cleaned data. This is the process of extracting important features necessary for training the machine learning model. For example, this includes user characteristics and specific patterns of failure cases.

[0086] Step 4:

[0087] The server uses the feature-extracted data to train the AI ​​model. Deep learning and other machine learning techniques are used to build the model from past data. During this process, the model parameters are optimized.

[0088] Step 5:

[0089] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy and effectiveness, and retrains the model if necessary.

[0090] Step 6:

[0091] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[0092] Step 7:

[0093] The server preprocesses the new specification, using natural language processing (NLP) to parse the text data and standardize the format.

[0094] Step 8:

[0095] The server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract and structure elements from the text. This process leverages techniques such as concrete text classification and named entity recognition (NER).

[0096] Step 9:

[0097] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content, taking into account the verification items and required time of past similar functions.

[0098] Step 10:

[0099] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[0100] As described above, this system involves the processes of sequential data input, analysis, model learning, and verification item generation, making it possible to provide efficient and highly accurate verification items when implementing new functions.

[0101] Example 1

[0102] 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."

[0103] In traditional software development, verification items must be created manually every time a new feature is added, which takes time and effort. Furthermore, creating verification items manually is prone to errors, which can have a negative impact on software quality. Furthermore, it is difficult to generate verification items that fully reflect past failure cases and user characteristics, which can result in a lack of comprehensiveness in verification.

[0104] 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.

[0105] In this invention, the server includes means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times, means for the server to learn the input data and train a machine learning model, means for a user to input specifications for new functions, means for the server to analyze the new specifications and extract important elements, means for the server to generate optimal verification items based on the learned data and the analyzed specifications, means for the server to present the generated list of verification items to the user, and means for the server to save and export the generated list of verification items in a downloadable format, thereby enabling efficient and accurate generation and presentation of verification items.

[0106] plaintext

[0107] "User" refers to an individual or group that operates the system and inputs data such as existing system specifications and specifications for new features.

[0108] "Server" refers to the central computer system that processes, manages, learns, and analyzes data, and generates and presents validation items to the user.

[0109] "Existing system specifications" refers to detailed descriptions of the function, structure, and design of systems currently in operation.

[0110] "User characteristics" refers to information related to users, such as the behavior and attributes of users who use the system.

[0111] "Failure cases" refer to records and details of malfunctions or problems that occurred during system operation.

[0112] "Past verification items" refers to information about the verification content and details of systems and functions that have been previously conducted.

[0113] "Time required" refers to the time required to perform a particular verification item.

[0114] A "machine learning model" is a group of algorithms that are trained to automatically perform specific tasks by studying data.

[0115] "Specification" refers to a document that details new features and improvements.

[0116] "Key elements" refer to functional and non-functional requirements that deserve special attention within the specification.

[0117] "Natural language processing" refers to the technology that allows computers to analyze and understand human language.

[0118] "Verification items" refer to specific verification procedures or checkpoints that are implemented to confirm the accuracy and reliability of a system or function.

[0119] "User interface" refers to the screens, controls, and navigation that allow a user to interact with a system.

[0120] "Export" means to store or provide data or information in another format.

[0121] MODE FOR CARRYING OUT THE INVENTION

[0122] The system and its program processing of this invention are described in detail below. The hardware used includes a server and a user terminal. The software used includes Python, pandas, Scikit-learn, TensorFlow, PyTorch, NLTK, spaCy, etc. This enables efficient and accurate generation and presentation of verification items.

[0123] Overall system flow

[0124] This invention is a system that proposes optimal verification items when implementing new functions, using a generative AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[0125] Data input and training

[0126] 1. User enters existing data

[0127] The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and required time into the system. This operation is performed through the file selection window on the terminal, and uploading of CSV or Excel files is recommended. When the user selects the file and clicks the upload button, the server receives this data.

[0128] 2. The server performs data cleaning and feature extraction

[0129] The server performs data cleaning based on the received data. It uses the Python pandas library to remove invalid values ​​and duplicate data and to fill in missing data. It then uses Scikit-learn to extract features. For example, numerical and categorical features are calculated and used in the next step.

[0130] 3. The server trains the machine learning model

[0131] The server uses the data after cleaning and feature extraction to train a machine learning model using frameworks such as TensorFlow or PyTorch. After training, the accuracy of the model is validated using test data. The results are recorded in a log.

[0132] Entering and parsing new specifications

[0133] 4. User uploads new specification

[0134] The user uploads a specification for a new feature to the system. This is done on the device, and the specification format is recommended as PDF or DOCX. The user selects the file and clicks the upload button, and the server receives the specification.

[0135] 5. The server preprocesses the specification

[0136] The server preprocesses the received specification using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters, converting it into a format suitable for analysis.

[0137] 6. The server analyzes the specification and extracts important elements

[0138] After preprocessing, the server uses NLP techniques to analyze the specifications and extract important elements (e.g., functional and non-functional requirements). The extracted data is structured and used in subsequent steps.

[0139] Generation and presentation of verification items

[0140] 7. The server generates the validation items

[0141] The server uses the trained AI model to generate verification items based on past data and new specifications. For example, for the "profile photo change function," "image format check" and "size restriction check" are automatically generated. Each verification item also includes an estimated time required.

[0142] 8. The server presents a list of verification items

[0143] The generated list of verification items is presented to the user through a user interface. The user can view and download the list, save it in CSV or Excel format, and use the feedback function to add comments to the verification items.

[0144] Specific examples

[0145] Added new feature "User profile customization function"

[0146] 1. The user inputs historical data such as the specifications of the existing system and failure cases into the system.

[0147] 2. The server uses this data to train an AI model. Specifically, it uses Python's pandas to clean the data and extract features. Then, it uses TensorFlow to train and validate the model.

[0148] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0149] 4. The server analyzes the new specifications and extracts important elements such as the ability to change the profile picture and edit the self-introduction. The NLP technology used is spaCy.

[0150] 5. Based on the results of the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" and "checking the character limit for the self-introduction," and estimates the time required for each.

[0151] 6. The server presents the generated list of verification items to the user through the user interface and makes it available for download as a CSV file. The user interface also has a function for sending feedback.

[0152] Prompt Sentence Examples

[0153] Enter specifications for user profile customization features, such as changing your profile picture or editing your bio.

[0154]

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] plaintext

[0157] Step 1:

[0158] The user uploads data on existing system specifications, user characteristics, failure cases, past verification items, and required time from their terminal to the system. Input is done in CSV or Excel format files. Once the file is uploaded, the server receives it and prepares it for data cleaning. Clean data is obtained as output.

[0159] Step 2:

[0160] The server performs data cleaning on the received data, specifically using the Python pandas library to remove invalid values ​​and duplicate data and properly impute missing data. The input is the raw data uploaded in step 1, and the output is a clean data frame.

[0161] Step 3:

[0162] The server extracts features based on the clean data. For this, it uses Scikit-learn to extract numerical and categorical features. For example, age and frequency of use can be extracted as features from user characteristic data. The input is clean data, and features are obtained as output.

[0163] Step 4:

[0164] The server uses the features to train a machine learning model. The frameworks used are TensorFlow and PyTorch. The feature data is used as training data to train the model. The accuracy of the model is validated with test data and the results are recorded. The input is the feature data, and the output is a trained model.

[0165] Step 5:

[0166] The user uploads a specification for a new feature to the system. The input is a PDF or DOCX file, which the user selects from their terminal and clicks the upload button. Once the file is uploaded, the server prepares the specification for preprocessing.

[0167] Step 6:

[0168] The server receives new specifications and preprocesses them using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters. The input is the uploaded specification, and the output is the preprocessed text data.

[0169] Step 7:

[0170] The server analyzes the preprocessed text data and extracts important elements. Important elements refer to functional and non-functional requirements, for example. The input is the preprocessed text data, and the extracted important elements are obtained as the output.

[0171] Step 8:

[0172] The server uses the trained AI model to generate optimal verification items based on new specifications. For example, it automatically generates "image format checks" and "size restriction checks" for the "profile photo change function" from past data and new specifications. Each verification item also has an estimated time required. The input is the extracted important elements, and the output is a list of generated verification items.

[0173] Step 9:

[0174] The server presents the generated list of verification items to the user. The list is displayed through the user interface, and the user can view and download it. The list can be saved in CSV or Excel format, and the user can add comments to the items using the feedback function. The input is the generated list of verification items, and the presented list is provided to the user as the output.

[0175] (Application example 1)

[0176] 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."

[0177] The selection of verification items when implementing new functions in factory robots is usually done manually, which is inefficient and carries a high risk of error. Furthermore, if past failure cases and user characteristics are not sufficiently taken into consideration, the quality of the verification may be affected. There is a need for a method to solve these problems and automate the generation of efficient, high-quality verification items.

[0178] 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.

[0179] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train a generative AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; and a means for the server to present the generated verification item list to the user and display it on a smartphone in real time. This enables efficient automatic generation of high-quality verification items when implementing new functions in factory robots.

[0180] A "user" is an entity that inputs system specifications, failure cases, verification items, etc. into the system and submits specifications for new functions.

[0181] A "system specification" is a collection of technical details and operational requirements for an existing system.

[0182] "User characteristics" refers to information about the attributes and behavioral norms of individual users and user groups who use the system.

[0183] "Failure cases" are specific examples of system problems or errors that have occurred in the past.

[0184] "Verification items" are test items used to verify whether new features or changes to the system work properly.

[0185] "Required time" is the estimated time required to execute each verification item.

[0186] The "server" is a central computer that stores and analyzes input data and trains generative AI models.

[0187] A "generative AI model" is an artificial intelligence model that is trained based on input data and is used to suggest optimal verification items for a system.

[0188] A "specification for new features" is a document that describes the technical details and operational requirements of a newly implemented feature.

[0189] "Natural language processing" is a technology that analyzes text data and extracts important elements.

[0190] "Real-time display" is a function that instantly displays the generated verification item list on the user's device.

[0191] A "smartphone" is a mobile device used to display the generated verification item list.

[0192] The system and its program processing will be described in the embodiment for carrying out the present invention.

[0193] System Overview

[0194] In this system, users input existing system specifications, user characteristics, failure cases, past verification items, and required time, and the server learns from this data to train a generative AI model. Furthermore, specifications for new functions are input, and the system analyzes the specifications to extract important elements and generate optimal verification items. The generated list of verification items is displayed on a smartphone in real time.

[0195] Data input and training

[0196] Users input existing system specifications, failure cases, past verification items, and required time into the system via CSV files or form input. This data is stored on a cloud server (e.g., AWS, Google Cloud).

[0197] The server cleans the input data (removing missing values ​​and duplicates) and extracts features. It then trains a generative AI model using a machine learning library such as scikit-learn. Validation of the model is also performed at the same time.

[0198] Entering and parsing new specifications

[0199] Users upload specifications for new robot functions from their smartphones, and the server analyzes the specifications using natural language processing (NLP) technology to extract key elements.

[0200] Generation and presentation of verification items

[0201] The server estimates the optimal verification items and required time based on the learned data and analyzed specifications, and generates a list of verification items. This list is displayed in real time on the smartphone, and the user can check and download it.

[0202] Specific examples

[0203] For example, when implementing an "obstacle avoidance function" for a new robot, the user uploads past specifications and failure cases in a CSV file. The server uses this information to train the AI ​​model. Next, the user uploads the "specifications for the new obstacle avoidance function," and the server analyzes the specifications. Based on this analysis, verification items such as "verification of the maximum detection distance of the distance sensor" and "verification of operating speed" are automatically generated.

[0204] Example prompt sentence:

[0205] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[0206] "Please upload a specification for the obstacle avoidance function of your new robot."

[0207] This makes it possible to automatically generate efficient, high-quality verification items when implementing new functions in factory robots.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] The user inputs existing system specifications, user characteristics, failure cases, past verification items, and required time into the system via a CSV file or form input.

[0211] Input: Existing system specifications, user characteristics, failure cases, past verification items, required time

[0212] Output: Data stored on the server

[0213] Specific operation: The user selects a CSV file and uploads it to the system. If necessary, the user can also enter data directly into the form. The data is then saved to the cloud server.

[0214] Step 2:

[0215] The server performs data cleaning based on the input data.

[0216] Input: Data saved in step 1

[0217] Output: Cleaned data

[0218] Specific operation: The server uses the pandas library to remove missing values ​​and duplicates from the data and format the data.

[0219] Step 3:

[0220] The server performs feature extraction using the cleaned data.

[0221] Input: Cleaned data

[0222] Output: Feature data

[0223] Specific operation: The server uses scikit-learn's CountVectorizer to digitize the text data and extract features.

[0224] Step 4:

[0225] The server uses the feature data to train a generative AI model.

[0226] Input: Feature data

[0227] Output: Generative AI model

[0228] Specific operation: The server trains and learns the model using algorithms such as scikit-learn's RandomForestClassifier.

[0229] Step 5:

[0230] A user uploads a specification for a new feature to the system from their smartphone.

[0231] Input: Specification for new feature

[0232] Output: The new specification saved on the server.

[0233] Specific operation: The user selects a specification file and uploads it to the system, where it is stored on the cloud server.

[0234] Step 6:

[0235] The server analyzes the new specification using natural language processing to extract important elements.

[0236] Input: New Specification

[0237] Output: Important elements parsed

[0238] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text of the specification and extract important elements such as functional and non-functional requirements.

[0239] Step 7:

[0240] The server generates optimal verification items based on the learned data and analyzed specifications.

[0241] Input: analyzed key elements, generative AI model

[0242] Output: Optimal test list and estimated time required

[0243] Specific operation: The server correlates historical data with the elements of the new specification, generates optimal verification items, and assigns an estimated time for each.

[0244] Step 8:

[0245] The server presents the generated list of verification items to the user and displays it on the smartphone in real time.

[0246] Input: List of optimal verification items, estimated time required

[0247] Output: A list of verification items displayed on the user's smartphone

[0248] Specific operation: The server displays the generated list of verification items on the user's smartphone in real time and also makes it possible to download it if necessary.

[0249] Example prompt sentence:

[0250] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[0251] "Please upload a specification for the obstacle avoidance function of your new robot."

[0252] 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.

[0253] System Overview

[0254] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time, and the server learns the input data to train an AI model. In addition to this system, a user can input specifications for new functions, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications. Furthermore, the present invention combines an emotion engine that recognizes user emotions to achieve more effective and adaptive generation of verification items.

[0255] Data input and training

[0256] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[0257] Next, the server preprocesses the input data. Specifically, it cleans the data. It removes incomplete and duplicate data and standardizes data formats. It also complements outliers and missing values. After this, the server performs feature extraction and extracts important features from each piece of data. These features are used to train an AI model and validate the model.

[0258] Entering and parsing new specifications

[0259] Users upload specifications for new features to the system. The server receives the specifications, stores them in a database, and then performs preprocessing, parsing the text data using natural language processing (NLP) and standardizing the format.

[0260] Next, the server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract elements from the text and structure them. The extracted important elements are organized into a tree data structure or similar.

[0261] Generation and presentation of verification items

[0262] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time for similar functions in the past. The generated verification items also include an estimate of the required time for each item.

[0263] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[0264] Combining Emotion Engines

[0265] To recognize user emotions, an emotion engine is combined. This emotion engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, selected words, frequency of operations, etc.

[0266] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. Specifically, if the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and ensure their resolution is prompt. It also displays support messages as appropriate so that the user can proceed with their work with peace of mind.

[0267] Specific examples

[0268] Example of adding the new feature "User profile customization function"

[0269] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0270] 2. The server uses this data to train and validate the AI ​​model.

[0271] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0272] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[0273] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[0274] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[0275] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0276] In this way, by combining emotion engines, a system can be realized that takes into account the user's emotional state and provides more effective and adaptive verification items.

[0277] The processing flow will be explained below.

[0278] Step 1:

[0279] The user logs in to the system. After logging in, the user enters the existing system specifications, user characteristics, past failure cases, past verification items and the required time into the system. Data entry is done by uploading files or filling in forms. Once the user has completed the data entry, the server receives the data and stores it in storage.

[0280] Step 2:

[0281] The server preprocesses the input data, cleaning it by removing incomplete and duplicate data, filling in missing values, and standardizing the data format.

[0282] Step 3:

[0283] The server extracts features from the cleaned data. Important features are analyzed and used to train the machine learning model. Features include user characteristics, specific patterns of failure cases, and details of past verification items.

[0284] Step 4:

[0285] The server uses the extracted features to train an AI model, applying deep learning and other machine learning techniques to optimize the model parameters.

[0286] Step 5:

[0287] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy, and retrains the AI ​​model if necessary.

[0288] Step 6:

[0289] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[0290] Step 7:

[0291] The server preprocesses the new specification, using natural language processing (NLP) techniques to analyze the text data and standardize the format of the specification.

[0292] Step 8:

[0293] The server analyzes the content of the specification and extracts important elements. Specifically, it uses named entity recognition (NER) to extract important elements such as functional and non-functional requirements from the specification and organizes them into a structure.

[0294] Step 9:

[0295] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content by referring to the verification items and required times of past similar functions.

[0296] Step 10:

[0297] The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. For example, it analyzes the input speed, the content of selected words, click frequency, etc. to determine the user's current emotional state.

[0298] Step 11:

[0299] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user feels nervous or frustrated, it will prioritize verification items with high importance and promptly resolve them. It will also display support messages as needed.

[0300] Step 12:

[0301] The server presents the generated list of verification items to the user through a user interface. The user can create a verification plan based on this list. The list of verification items can also be downloaded in CSV or Excel format, and the user can provide feedback on the results.

[0302] In this way, by combining it with an emotion engine, the system can generate effective and efficient verification items while taking into account the user's emotional state.

[0303] Example 2

[0304] 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."

[0305] Modern software systems are becoming increasingly complex, making verification work extremely important when adding or modifying new features. However, traditional methods often require manually generating verification items, which can lead to human error and effort. Furthermore, user emotions and tension can affect the efficiency of verification, so a flexible system that can accommodate these factors is needed.

[0306] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; means for the server to learn the input data and train the AI ​​model; means for a user to input specifications for new functions; means for the server to analyze the new specifications and extract important elements; means for the server to generate optimal verification items based on the learned data and the analyzed specifications; means for the server to present the generated list of verification items to the user; means for an emotion engine to determine the user's emotional state; and means for the server to adjust the priority of the verification items based on the emotion data. This enables efficient automatic generation of verification items and the presentation of adaptive verification items corresponding to the user's emotions.

[0307] Understood. Below are definitions of important terms contained in the claims:

[0308] An "existing system specification" is a document that details how a currently operational system operates.

[0309] "User characteristics" refers to the characteristics and behavioral patterns of a particular user or user group.

[0310] "Failure cases" refer to cases of trouble or malfunction that have occurred in the system in the past.

[0311] "Past verification items" means evaluation criteria or checklists used in previous verification or testing of the system.

[0312] "Time required" refers to the amount of time required to complete a particular task or process.

[0313] "Means" refers to methods or techniques for achieving a specific purpose.

[0314] A "server" refers to a computer system that processes requests from clients on a network and provides data and services.

[0315] "Learning from input" is the process by which machine learning algorithms learn patterns and trends based on the data you provide them.

[0316] An "AI model" refers to a set of algorithms designed to automate a specific task using artificial intelligence techniques.

[0317] "Training" refers to the process of feeding an AI model data to teach it to recognize patterns and improve its performance.

[0318] A "specification for new functions" is a document that details the functions that will be newly added to the system.

[0319] "Analysis" refers to the process of breaking down specific data or information into more understandable detail.

[0320] "Critical elements" refer to information or components found in the analyzed data that are particularly important to a system or function.

[0321] "Optimal verification items" refer to the most appropriate tests and checkpoints to ensure the quality of a system or function.

[0322] "Emotion engine" refers to an algorithm or program that analyzes and identifies a user's emotional state.

[0323] "Adjusting priorities" refers to changing the order in which tasks or items are performed depending on their importance and the situation.

[0324] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system, and the server learns the input data to train an AI model. Also, specifications for new functions are input, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications.

[0325] System configuration

[0326] The system consists of a user terminal and a server. An interface for users to input data is placed on the user terminal, and the input data is processed by the server. The server has a database and stores and processes the input data. The server also incorporates an AI model that implements machine learning algorithms and natural language processing (NLP) technology.

[0327] Hardware and software used

[0328] Hardware:

[0329] User devices (PCs, tablets, smartphones, etc.)

[0330] A server (with a powerful processor, sufficient memory and storage)

[0331] software:

[0332] Database management systems (e.g., MySQL, PostgreSQL)

[0333] Natural language processing tools (e.g., NLTK, spaCy)

[0334] Machine learning frameworks (e.g. TensorFlow, PyTorch)

[0335] User interface (e.g. web browser, dedicated application)

[0336] Program processing flow

[0337] Data input and training

[0338] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, past verification items and required time. The user provides this data to the system by filling in forms or uploading files. Once the input is complete, the server confirms receipt of the data and saves it in the database.

[0339] The server then preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values. The server then extracts features and trains an AI model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0340] Entering and parsing new specifications

[0341] A user uploads a specification for a new feature to the system. The server receives the uploaded specification, stores it in a database, and then performs preprocessing. NLP techniques are used to parse the specification text and standardize the format.

[0342] The server then analyzes the content of the specification and extracts important elements (functional and non-functional requirements), which are then organized into a tree data structure.

[0343] Generation and presentation of verification items

[0344] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time of past similar functions. Each of these verification items also includes an estimated required time.

[0345] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, allowing the system to continually improve.

[0346] Combining Emotion Engines

[0347] The system is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, the words selected, and the frequency of operations.

[0348] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and aim for a quick resolution. It also displays support messages as appropriate so that the user can proceed with the work with peace of mind.

[0349] Specific examples

[0350] Example of adding the new feature "User profile customization function"

[0351] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0352] 2. The server uses this data to train and validate the AI ​​model.

[0353] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0354] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[0355] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[0356] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[0357] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0358] Example prompts:

[0359] I have uploaded a specification for a new user feature. I would like to add a "user profile customization feature." Please generate optimal verification items based on the current system specifications, past failure cases, verification items, and required time.

[0360] As described above, the present invention efficiently trains an AI model based on data provided by users, analyzes new specifications, and generates optimal verification items. Furthermore, by adjusting the priority of verification items based on user sentiment, more adaptive and effective verification can be achieved.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1:

[0363] The user enters existing data.

[0364] Input: Existing system specifications, user characteristics, past failure cases, past verification items and required time

[0365] How it works: A user logs into the system and enters data via a form or file upload.

[0366] Output: The input data is sent to the server.

[0367] Step 2:

[0368] The server receives and stores the data.

[0369] Input: Existing data entered by the user

[0370] Operation: The server saves the received data in the database and notifies the user with a message asking them to confirm the save.

[0371] Output: Existing data stored in the database

[0372] Step 3:

[0373] The server preprocesses the data.

[0374] Input: Existing data stored in a database

[0375] How it works: The server cleans the data, removes incomplete and duplicate data, standardizes data formats, and imputes outliers and missing values.

[0376] Output: Cleaned and uniformly formatted data

[0377] Step 4:

[0378] The server extracts features.

[0379] Input: Data after cleaning

[0380] How it works: The server uses data analysis tools to extract important features, such as Pandas and Scikit-learn.

[0381] Output: Extracted feature data

[0382] Step 5:

[0383] The server trains the AI ​​model.

[0384] Input: Extracted feature data

[0385] How it works: The server trains an AI model using a machine learning framework (e.g., TensorFlow, PyTorch). It also validates the model to ensure its accuracy.

[0386] Output: A trained AI model

[0387] Step 6:

[0388] A user uploads a new specification.

[0389] Input: Specification for new feature

[0390] How it works: A user uploads a new specification to the system and sends it to the server.

[0391] Output: Uploaded specification data

[0392] Step 7:

[0393] The server receives and stores the specification.

[0394] Input: New specification data uploaded by the user

[0395] Operation: The server saves the specification data to the database and notifies the user that the save is complete.

[0396] Output: New specification data stored in the database

[0397] Step 8:

[0398] The server preprocesses the specification.

[0399] Input: New specification data stored in the database

[0400] How it works: The server uses natural language processing (NLP) techniques to analyze and format text data, specifically removing unnecessary spaces within sentences and converting them into a specific format.

[0401] Output: Preprocessed specification data

[0402] Step 9:

[0403] The server parses the specification and extracts the important elements.

[0404] Input: Preprocessed specification data

[0405] How it works: The server uses NLP technology to analyze the contents of the specification, extract important elements such as functional and non-functional requirements, and organize them into a tree data structure.

[0406] Output: Extracted important element data

[0407] Step 10:

[0408] The server generates the optimal verification items.

[0409] Input: Trained AI model and extracted key element data

[0410] How it works: The server uses a trained AI model to automatically generate optimal verification items based on new specifications, while also referring to the verification items and required time for similar functions in the past.

[0411] Output: Generated verification item list data

[0412] Step 11:

[0413] The server presents the generated list of verification items to the user.

[0414] Input: Generated verification item list data

[0415] How it works: The server presents a list of validation items to the user through a user interface, allowing the user to review and download the list and provide feedback.

[0416] Output: A list of validation items presented to the user

[0417] Step 12:

[0418] An emotion engine recognizes the user's emotional state.

[0419] Input: User input data and operation logs

[0420] Behavior: The emotion engine determines the user's emotional state based on their typing speed, selected words, and frequency of actions.

[0421] Output: User's emotional state data

[0422] Step 13:

[0423] The server adjusts the priority of verification items based on emotional state data.

[0424] Input: User's emotional state data

[0425] How it works: Based on the emotional state data, the server prioritizes the most important verification items and aims to resolve them quickly. It also displays support messages so that the user can proceed with the work with peace of mind.

[0426] Output: Priority adjusted verification item list data

[0427] The above is the flow of specific processing steps of the program of this system.

[0428] (Application example 2)

[0429] 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."

[0430] Conventional systems clean data, extract features, and train AI models, but they have a problem in that they are unable to consider the user's emotional state when generating optimal verification items for new specifications. In particular, when the user is feeling nervous or stressed, they are unable to provide appropriate support, making it difficult to achieve an efficient verification process.

[0431] 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.

[0432] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train an AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; a means for recognizing the emotional state of the user using an emotion engine; a means for the server to adjust the urgency and priority of the verification items based on the emotional state; and a means for the server to present the generated list of verification items to the user. This enables an adaptive and efficient verification process that takes the user's emotional state into consideration.

[0433] "Existing system specifications" are documents and data that explain the technical information, design, and operational details of the current operational system.

[0434] "User characteristics" refers to information including the behavioral patterns and operation tendencies of users who use the system, as well as their past usage history.

[0435] A "trouble case" is a record of details of problems or errors that occurred during system operation and their resolution.

[0436] "Past verification items" refers to information about the contents and results of system tests that have been previously conducted.

[0437] "Time required" is a record of the amount of time required to complete a particular task or verification item.

[0438] An "AI model" is an artificial intelligence algorithm trained through machine learning or deep learning and used to automate or optimize a specific task.

[0439] "Specifications for new functions" refers to documents and data that contain detailed design and operational information regarding newly added functions and changes.

[0440] "Important elements" are information that should be given special importance in verification, such as system requirements and constraints extracted from new specifications.

[0441] An "emotion engine" is a technology that analyzes a user's operation log and input data to recognize and estimate their emotional state.

[0442] "Adjusting the urgency and priority of verification items" means optimizing the importance of items to be verified and the order of processing based on the emotional state of the user.

[0443] This invention is a system that uses a smart verification support robot to generate and implement optimal verification items by making full use of AI and an emotion engine when new machinery is introduced in a factory or an existing line system is updated. This system is composed of the following elements.

[0444] System Configuration

[0445] 1. Data entry method:

[0446] The user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system. The input is done by filling out a form or uploading a file.

[0447] The server stores the input data in storage.

[0448] 2. Data preprocessing:

[0449] The server cleans the input data, removing incomplete and duplicate data and standardizing the data format. It also fills in outliers and missing values.

[0450] 3. Feature extraction and AI model training:

[0451] The server extracts important features from the cleaned data and trains the AI ​​model using machine learning frameworks such as TensorFlow and Keras.

[0452] Validate the AI ​​model and evaluate its accuracy.

[0453] 4. New specification analysis methods:

[0454] A user uploads a specification for a new feature into the system.

[0455] The server uses natural language processing (NLP) to analyze the specifications, extract and structure key elements.

[0456] 5. How to generate verification items:

[0457] The server generates optimal verification items based on the trained AI model and analysis data of the specifications. It also automatically generates specific checklists and test content by referring to the verification items and required time of past similar functions.

[0458] 6. Introducing the Emotion Engine:

[0459] It uses an emotion engine that recognizes the user's emotions. It analyzes input data and operation logs to determine the user's emotional state.

[0460] The server adjusts the urgency and priority of the verification items based on data from the emotion engine. If the user is feeling nervous or stressed, it will prioritize verification items with high importance and display appropriate support messages.

[0461] 7. Method of presenting verification items:

[0462] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, which is used to continuously improve the system.

[0463] Specific processing examples

[0464] For example, if a new robot arm operation control function is introduced in a factory, the user uploads the specifications for the "new robot arm operation control function" to the system. The server extracts important elements such as "operation speed control" and "emergency stop function" from the specifications, and the AI ​​model generates verification items such as "speed control response time test" and "emergency stop signal reaction time test." The emotion engine detects the user's stress level, adjusts priorities, and presents the user with an appropriate list of verification items.

[0465] Prompt Sentence Examples

[0466] "Upload a specification for the user profile customization feature. We then extract key elements based on the specification. Combined with user sentiment data, we generate a list of optimal validation items. The list is then prioritized based on the stress of the user experience."

[0467] The system enables an adaptive and efficient verification process that takes into account the user's emotional state.

[0468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0469] Step 1:

[0470] The user inputs the existing system specifications, user characteristics, past failure cases, past verification items, and required time.

[0471] Input is provided by the user through form entry or file upload from the terminal. The input data is saved in the server's storage. The output is a dataset saved on the server.

[0472] Step 2:

[0473] The server performs pre-processing on the input data.

[0474] Specifically, data cleaning is performed to remove incomplete and duplicate data, standardize data formats, and impute outliers and missing values. The output is a clean and consistent dataset.

[0475] Step 3:

[0476] The server extracts features from the cleaned data.

[0477] Features are important data points used to train AI models. Machine learning frameworks (e.g., TensorFlow or Keras) are used to extract features from data. The output is a set of features.

[0478] Step 4:

[0479] The server uses the extracted features to train an AI model.

[0480] The training step involves splitting the dataset into a training set and a validation set and optimizing the model parameters. Once training is complete, the model is validated to evaluate its accuracy and performance. The output is a trained AI model.

[0481] Step 5:

[0482] A user uploads a specification for a new feature into the system.

[0483] When a user uploads a new specification file from their terminal, it is saved on the server. The output is the new specification data.

[0484] Step 6:

[0485] The server parses the new specification using natural language processing (NLP).

[0486] During the analysis process, the text data is cleaned, tokenized, and parsed. Important elements (e.g., functional requirements and constraints) are extracted and converted into a structured format such as tree data. The output is the data of the analyzed important elements.

[0487] Step 7:

[0488] The server generates optimal verification items based on the trained AI model and analyzed specifications.

[0489] It automatically generates specific checklists and test content by referring to the verification items and required time of similar functions in the past. If necessary, an estimate of the required time is also provided. The output is a list of generated verification items.

[0490] Step 8:

[0491] An emotion engine is introduced to recognize user emotions.

[0492] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and operation log. The input is the user's operation log and input data, and the output is the user's emotional state data.

[0493] Step 9:

[0494] The server adjusts the urgency and priority of verification items based on the recognized emotional state data.

[0495] Specifically, if the user feels nervous or stressed, the system will prioritize the most important verification items and promptly resolve them. It also displays support messages as needed to help the user proceed with their work with peace of mind. The output is a list of adjusted verification items.

[0496] Step 10:

[0497] The server presents the generated list of verification items to the user.

[0498] The list is displayed through a user interface, allowing users to review and download the verification item list and provide feedback, which allows the system to continuously improve. The output is the verification item list and user feedback.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] [Second embodiment]

[0503] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0504] 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.

[0505] 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).

[0506] 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.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] 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."

[0515] The present embodiment will now be described in natural language with respect to the processing of the system and its programs.

[0516] System Overview

[0517] This invention relates to a system that proposes optimal verification items when implementing new functions, using an AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[0518] Data input and training

[0519] 1. The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and the required time.

[0520] Data entry is done through methods such as file upload and form filling.

[0521] Immediately after the data is uploaded, the server performs data cleaning as a pre-processing of the data.

[0522] 2. The server receives the input data and trains the AI ​​model.

[0523] First, the server performs data cleaning to remove incomplete data and duplicates.

[0524] Next, feature extraction is performed to extract important features of each data.

[0525] The server uses these features to train an AI model and validate the model.

[0526] Entering and parsing new specifications

[0527] 3. The user uploads a specification for a new feature into the system.

[0528] The server performs preprocessing of the text data to ensure a consistent format for the specification.

[0529] 4. The server parses the new specification and extracts the important elements.

[0530] The server analyzes the text using natural language processing (NLP) techniques.

[0531] From the analysis results, important elements (e.g., functional requirements and non-functional requirements) are extracted and structured.

[0532] Generation and presentation of verification items

[0533] 5. The server generates optimal verification items based on the learned data and analyzed specifications.

[0534] The server references past data and automatically generates optimal verification items based on new specifications.

[0535] The generated verification items also include an estimate of the time required for each.

[0536] 6. The server presents the generated list of verification items to the user.

[0537] The results are displayed through the user interface, and the user can create a verification plan based on the list.

[0538] The list can be downloaded in CSV or Excel format, and suggestions for improving items are also accepted via the feedback function.

[0539] Specific examples

[0540] Added new feature "User profile customization function"

[0541] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0542] 2. The server uses this data to train the AI ​​model.

[0543] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0544] 4. The server analyzes the new specifications and extracts important elements such as the ability to change profile pictures and edit self-introductions.

[0545] 5. Based on the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." It also provides an estimate of the time required for each verification item.

[0546] 6. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0547] This reduces the risk of manual creation of verification items and errors, enabling efficient and high-quality software development.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[0551] Step 2:

[0552] The server preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values.

[0553] Step 3:

[0554] The server then performs feature extraction from the cleaned data. This is the process of extracting important features necessary for training the machine learning model. For example, this includes user characteristics and specific patterns of failure cases.

[0555] Step 4:

[0556] The server uses the feature-extracted data to train the AI ​​model. Deep learning and other machine learning techniques are used to build the model from past data. During this process, the model parameters are optimized.

[0557] Step 5:

[0558] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy and effectiveness, and retrains the model if necessary.

[0559] Step 6:

[0560] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[0561] Step 7:

[0562] The server preprocesses the new specification, using natural language processing (NLP) to parse the text data and standardize the format.

[0563] Step 8:

[0564] The server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract and structure elements from the text. This process leverages techniques such as concrete text classification and named entity recognition (NER).

[0565] Step 9:

[0566] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content, taking into account the verification items and required time of past similar functions.

[0567] Step 10:

[0568] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[0569] As described above, this system involves the processes of sequential data input, analysis, model learning, and verification item generation, making it possible to provide efficient and highly accurate verification items when implementing new functions.

[0570] Example 1

[0571] 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."

[0572] In traditional software development, verification items must be created manually every time a new feature is added, which takes time and effort. Furthermore, creating verification items manually is prone to errors, which can have a negative impact on software quality. Furthermore, it is difficult to generate verification items that fully reflect past failure cases and user characteristics, which can result in a lack of comprehensiveness in verification.

[0573] 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.

[0574] In this invention, the server includes means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times, means for the server to learn the input data and train a machine learning model, means for a user to input specifications for new functions, means for the server to analyze the new specifications and extract important elements, means for the server to generate optimal verification items based on the learned data and the analyzed specifications, means for the server to present the generated list of verification items to the user, and means for the server to save and export the generated list of verification items in a downloadable format, thereby enabling efficient and accurate generation and presentation of verification items.

[0575] plaintext

[0576] "User" refers to an individual or group that operates the system and inputs data such as existing system specifications and specifications for new features.

[0577] "Server" refers to the central computer system that processes, manages, learns, and analyzes data, and generates and presents validation items to the user.

[0578] "Existing system specifications" refers to detailed descriptions of the function, structure, and design of systems currently in operation.

[0579] "User characteristics" refers to information related to users, such as the behavior and attributes of users who use the system.

[0580] "Failure cases" refer to records and details of malfunctions or problems that occurred during system operation.

[0581] "Past verification items" refers to information about the verification content and details of systems and functions that have been previously conducted.

[0582] "Time required" refers to the time required to perform a particular verification item.

[0583] A "machine learning model" is a group of algorithms that are trained to automatically perform specific tasks by studying data.

[0584] "Specification" refers to a document that details new features and improvements.

[0585] "Key elements" refer to functional and non-functional requirements that deserve special attention within the specification.

[0586] "Natural language processing" refers to the technology that allows computers to analyze and understand human language.

[0587] "Verification items" refer to specific verification procedures or checkpoints that are implemented to confirm the accuracy and reliability of a system or function.

[0588] "User interface" refers to the screens, controls, and navigation that allow a user to interact with a system.

[0589] "Export" means to store or provide data or information in another format.

[0590] MODE FOR CARRYING OUT THE INVENTION

[0591] The system and its program processing of this invention are described in detail below. The hardware used includes a server and a user terminal. The software used includes Python, pandas, Scikit-learn, TensorFlow, PyTorch, NLTK, spaCy, etc. This enables efficient and accurate generation and presentation of verification items.

[0592] Overall system flow

[0593] This invention is a system that proposes optimal verification items when implementing new functions, using a generative AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[0594] Data input and training

[0595] 1. User enters existing data

[0596] The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and required time into the system. This operation is performed through the file selection window on the terminal, and uploading of CSV or Excel files is recommended. When the user selects the file and clicks the upload button, the server receives this data.

[0597] 2. The server performs data cleaning and feature extraction

[0598] The server performs data cleaning based on the received data. It uses the Python pandas library to remove invalid values ​​and duplicate data and to fill in missing data. It then uses Scikit-learn to extract features. For example, numerical and categorical features are calculated and used in the next step.

[0599] 3. The server trains the machine learning model

[0600] The server uses the data after cleaning and feature extraction to train a machine learning model using frameworks such as TensorFlow or PyTorch. After training, the accuracy of the model is validated using test data. The results are recorded in a log.

[0601] Entering and parsing new specifications

[0602] 4. User uploads new specification

[0603] The user uploads a specification for a new feature to the system. This is done on the device, and the specification format is recommended as PDF or DOCX. The user selects the file and clicks the upload button, and the server receives the specification.

[0604] 5. The server preprocesses the specification

[0605] The server preprocesses the received specification using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters, converting it into a format suitable for analysis.

[0606] 6. The server analyzes the specification and extracts important elements

[0607] After preprocessing, the server uses NLP techniques to analyze the specifications and extract important elements (e.g., functional and non-functional requirements). The extracted data is structured and used in subsequent steps.

[0608] Generation and presentation of verification items

[0609] 7. The server generates the validation items

[0610] The server uses the trained AI model to generate verification items based on past data and new specifications. For example, for the "profile photo change function," "image format check" and "size restriction check" are automatically generated. Each verification item also includes an estimated time required.

[0611] 8. The server presents a list of verification items

[0612] The generated list of verification items is presented to the user through a user interface. The user can view and download the list, save it in CSV or Excel format, and use the feedback function to add comments to the verification items.

[0613] Specific examples

[0614] Added new feature "User profile customization function"

[0615] 1. The user inputs historical data such as the specifications of the existing system and failure cases into the system.

[0616] 2. The server uses this data to train an AI model. Specifically, it uses Python's pandas to clean the data and extract features. Then, it uses TensorFlow to train and validate the model.

[0617] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0618] 4. The server analyzes the new specifications and extracts important elements such as the ability to change the profile picture and edit the self-introduction. The NLP technology used is spaCy.

[0619] 5. Based on the results of the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" and "checking the character limit for the self-introduction," and estimates the time required for each.

[0620] 6. The server presents the generated list of verification items to the user through the user interface and makes it available for download as a CSV file. The user interface also has a function for sending feedback.

[0621] Prompt Sentence Examples

[0622] Enter specifications for user profile customization features, such as changing your profile picture or editing your bio.

[0623]

[0624] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0625] plaintext

[0626] Step 1:

[0627] The user uploads data on existing system specifications, user characteristics, failure cases, past verification items, and required time from their terminal to the system. Input is done in CSV or Excel format files. Once the file is uploaded, the server receives it and prepares it for data cleaning. Clean data is obtained as output.

[0628] Step 2:

[0629] The server performs data cleaning on the received data, specifically using the Python pandas library to remove invalid values ​​and duplicate data and properly impute missing data. The input is the raw data uploaded in step 1, and the output is a clean data frame.

[0630] Step 3:

[0631] The server extracts features based on the clean data. For this, it uses Scikit-learn to extract numerical and categorical features. For example, age and frequency of use can be extracted as features from user characteristic data. The input is clean data, and features are obtained as output.

[0632] Step 4:

[0633] The server uses the features to train a machine learning model. The frameworks used are TensorFlow and PyTorch. The feature data is used as training data to train the model. The accuracy of the model is validated with test data and the results are recorded. The input is the feature data, and the output is a trained model.

[0634] Step 5:

[0635] The user uploads a specification for a new feature to the system. The input is a PDF or DOCX file, which the user selects from their terminal and clicks the upload button. Once the file is uploaded, the server prepares the specification for preprocessing.

[0636] Step 6:

[0637] The server receives new specifications and preprocesses them using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters. The input is the uploaded specification, and the output is the preprocessed text data.

[0638] Step 7:

[0639] The server analyzes the preprocessed text data and extracts important elements. Important elements refer to functional and non-functional requirements, for example. The input is the preprocessed text data, and the extracted important elements are obtained as the output.

[0640] Step 8:

[0641] The server uses the trained AI model to generate optimal verification items based on new specifications. For example, it automatically generates "image format checks" and "size restriction checks" for the "profile photo change function" from past data and new specifications. Each verification item also has an estimated time required. The input is the extracted important elements, and the output is a list of generated verification items.

[0642] Step 9:

[0643] The server presents the generated list of verification items to the user. The list is displayed through the user interface, and the user can view and download it. The list can be saved in CSV or Excel format, and the user can add comments to the items using the feedback function. The input is the generated list of verification items, and the presented list is provided to the user as the output.

[0644] (Application example 1)

[0645] 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."

[0646] The selection of verification items when implementing new functions in factory robots is usually done manually, which is inefficient and carries a high risk of error. Furthermore, if past failure cases and user characteristics are not sufficiently taken into consideration, the quality of the verification may be affected. There is a need for a method to solve these problems and automate the generation of efficient, high-quality verification items.

[0647] 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.

[0648] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train a generative AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; and a means for the server to present the generated verification item list to the user and display it on a smartphone in real time. This enables efficient automatic generation of high-quality verification items when implementing new functions in factory robots.

[0649] A "user" is an entity that inputs system specifications, failure cases, verification items, etc. into the system and submits specifications for new functions.

[0650] A "system specification" is a collection of technical details and operational requirements for an existing system.

[0651] "User characteristics" refers to information about the attributes and behavioral norms of individual users and user groups who use the system.

[0652] "Failure cases" are specific examples of system problems or errors that have occurred in the past.

[0653] "Verification items" are test items used to verify whether new features or changes to the system work properly.

[0654] "Required time" is the estimated time required to execute each verification item.

[0655] The "server" is a central computer that stores and analyzes input data and trains generative AI models.

[0656] A "generative AI model" is an artificial intelligence model that is trained based on input data and is used to suggest optimal verification items for a system.

[0657] A "specification for new features" is a document that describes the technical details and operational requirements of a newly implemented feature.

[0658] "Natural language processing" is a technology that analyzes text data and extracts important elements.

[0659] "Real-time display" is a function that instantly displays the generated verification item list on the user's device.

[0660] A "smartphone" is a mobile device used to display the generated verification item list.

[0661] The system and its program processing will be described in the embodiment for carrying out the present invention.

[0662] System Overview

[0663] In this system, users input existing system specifications, user characteristics, failure cases, past verification items, and required time, and the server learns from this data to train a generative AI model. Furthermore, specifications for new functions are input, and the system analyzes the specifications to extract important elements and generate optimal verification items. The generated list of verification items is displayed on a smartphone in real time.

[0664] Data input and training

[0665] Users input existing system specifications, failure cases, past verification items, and required time into the system via CSV files or form input. This data is stored on a cloud server (e.g., AWS, Google Cloud).

[0666] The server cleans the input data (removing missing values ​​and duplicates) and extracts features. It then trains a generative AI model using a machine learning library such as scikit-learn. Validation of the model is also performed at the same time.

[0667] Entering and parsing new specifications

[0668] Users upload specifications for new robot functions from their smartphones, and the server analyzes the specifications using natural language processing (NLP) technology to extract key elements.

[0669] Generation and presentation of verification items

[0670] The server estimates the optimal verification items and required time based on the learned data and analyzed specifications, and generates a list of verification items. This list is displayed in real time on the smartphone, and the user can check and download it.

[0671] Specific examples

[0672] For example, when implementing an "obstacle avoidance function" for a new robot, the user uploads past specifications and failure cases in a CSV file. The server uses this information to train the AI ​​model. Next, the user uploads the "specifications for the new obstacle avoidance function," and the server analyzes the specifications. Based on this analysis, verification items such as "verification of the maximum detection distance of the distance sensor" and "verification of operating speed" are automatically generated.

[0673] Example prompt sentence:

[0674] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[0675] "Please upload a specification for the obstacle avoidance function of your new robot."

[0676] This makes it possible to automatically generate efficient, high-quality verification items when implementing new functions in factory robots.

[0677] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0678] Step 1:

[0679] The user inputs existing system specifications, user characteristics, failure cases, past verification items, and required time into the system via a CSV file or form input.

[0680] Input: Existing system specifications, user characteristics, failure cases, past verification items, required time

[0681] Output: Data stored on the server

[0682] Specific operation: The user selects a CSV file and uploads it to the system. If necessary, the user can also enter data directly into the form. The data is then saved to the cloud server.

[0683] Step 2:

[0684] The server performs data cleaning based on the input data.

[0685] Input: Data saved in step 1

[0686] Output: Cleaned data

[0687] Specific operation: The server uses the pandas library to remove missing values ​​and duplicates from the data and format the data.

[0688] Step 3:

[0689] The server performs feature extraction using the cleaned data.

[0690] Input: Cleaned data

[0691] Output: Feature data

[0692] Specific operation: The server uses scikit-learn's CountVectorizer to digitize the text data and extract features.

[0693] Step 4:

[0694] The server uses the feature data to train a generative AI model.

[0695] Input: Feature data

[0696] Output: Generative AI model

[0697] Specific operation: The server trains and learns the model using algorithms such as scikit-learn's RandomForestClassifier.

[0698] Step 5:

[0699] A user uploads a specification for a new feature to the system from their smartphone.

[0700] Input: Specification for new feature

[0701] Output: The new specification saved on the server.

[0702] Specific operation: The user selects a specification file and uploads it to the system, where it is stored on the cloud server.

[0703] Step 6:

[0704] The server analyzes the new specification using natural language processing to extract important elements.

[0705] Input: New Specification

[0706] Output: Important elements parsed

[0707] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text of the specification and extract important elements such as functional and non-functional requirements.

[0708] Step 7:

[0709] The server generates optimal verification items based on the learned data and analyzed specifications.

[0710] Input: analyzed key elements, generative AI model

[0711] Output: Optimal test list and estimated time required

[0712] Specific operation: The server correlates historical data with the elements of the new specification, generates optimal verification items, and assigns an estimated time for each.

[0713] Step 8:

[0714] The server presents the generated list of verification items to the user and displays it on the smartphone in real time.

[0715] Input: List of optimal verification items, estimated time required

[0716] Output: A list of verification items displayed on the user's smartphone

[0717] Specific operation: The server displays the generated list of verification items on the user's smartphone in real time and also makes it possible to download it if necessary.

[0718] Example prompt sentence:

[0719] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[0720] "Please upload a specification for the obstacle avoidance function of your new robot."

[0721] 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.

[0722] System Overview

[0723] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time, and the server learns the input data to train an AI model. In addition to this system, a user can input specifications for new functions, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications. Furthermore, the present invention combines an emotion engine that recognizes user emotions to achieve more effective and adaptive generation of verification items.

[0724] Data input and training

[0725] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[0726] Next, the server preprocesses the input data. Specifically, it cleans the data. It removes incomplete and duplicate data and standardizes data formats. It also complements outliers and missing values. After this, the server performs feature extraction and extracts important features from each piece of data. These features are used to train an AI model and validate the model.

[0727] Entering and parsing new specifications

[0728] Users upload specifications for new features to the system. The server receives the specifications, stores them in a database, and then performs preprocessing, parsing the text data using natural language processing (NLP) and standardizing the format.

[0729] Next, the server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract elements from the text and structure them. The extracted important elements are organized into a tree data structure or similar.

[0730] Generation and presentation of verification items

[0731] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time for similar functions in the past. The generated verification items also include an estimate of the required time for each item.

[0732] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[0733] Combining Emotion Engines

[0734] To recognize user emotions, an emotion engine is combined. This emotion engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, selected words, frequency of operations, etc.

[0735] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. Specifically, if the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and ensure their resolution is prompt. It also displays support messages as appropriate so that the user can proceed with their work with peace of mind.

[0736] Specific examples

[0737] Example of adding the new feature "User profile customization function"

[0738] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0739] 2. The server uses this data to train and validate the AI ​​model.

[0740] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0741] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[0742] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[0743] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[0744] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0745] In this way, by combining emotion engines, a system can be realized that takes into account the user's emotional state and provides more effective and adaptive verification items.

[0746] The processing flow will be explained below.

[0747] Step 1:

[0748] The user logs in to the system. After logging in, the user enters the existing system specifications, user characteristics, past failure cases, past verification items and the required time into the system. Data entry is done by uploading files or filling in forms. Once the user has completed the data entry, the server receives the data and stores it in storage.

[0749] Step 2:

[0750] The server preprocesses the input data, cleaning it by removing incomplete and duplicate data, filling in missing values, and standardizing the data format.

[0751] Step 3:

[0752] The server extracts features from the cleaned data. Important features are analyzed and used to train the machine learning model. Features include user characteristics, specific patterns of failure cases, and details of past verification items.

[0753] Step 4:

[0754] The server uses the extracted features to train an AI model, applying deep learning and other machine learning techniques to optimize the model parameters.

[0755] Step 5:

[0756] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy, and retrains the AI ​​model if necessary.

[0757] Step 6:

[0758] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[0759] Step 7:

[0760] The server preprocesses the new specification, using natural language processing (NLP) techniques to analyze the text data and standardize the format of the specification.

[0761] Step 8:

[0762] The server analyzes the content of the specification and extracts important elements. Specifically, it uses named entity recognition (NER) to extract important elements such as functional and non-functional requirements from the specification and organizes them into a structure.

[0763] Step 9:

[0764] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content by referring to the verification items and required times of past similar functions.

[0765] Step 10:

[0766] The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. For example, it analyzes the input speed, the content of selected words, click frequency, etc. to determine the user's current emotional state.

[0767] Step 11:

[0768] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user feels nervous or frustrated, it will prioritize verification items with high importance and promptly resolve them. It will also display support messages as needed.

[0769] Step 12:

[0770] The server presents the generated list of verification items to the user through a user interface. The user can create a verification plan based on this list. The list of verification items can also be downloaded in CSV or Excel format, and the user can provide feedback on the results.

[0771] In this way, by combining it with an emotion engine, the system can generate effective and efficient verification items while taking into account the user's emotional state.

[0772] Example 2

[0773] 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."

[0774] Modern software systems are becoming increasingly complex, making verification work extremely important when adding or modifying new features. However, traditional methods often require manually generating verification items, which can lead to human error and effort. Furthermore, user emotions and tension can affect the efficiency of verification, so a flexible system that can accommodate these factors is needed.

[0775] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; means for the server to learn the input data and train the AI ​​model; means for a user to input specifications for new functions; means for the server to analyze the new specifications and extract important elements; means for the server to generate optimal verification items based on the learned data and the analyzed specifications; means for the server to present the generated list of verification items to the user; means for an emotion engine to determine the user's emotional state; and means for the server to adjust the priority of the verification items based on the emotion data. This enables efficient automatic generation of verification items and the presentation of adaptive verification items corresponding to the user's emotions.

[0776] Understood. Below are definitions of important terms contained in the claims:

[0777] An "existing system specification" is a document that details how a currently operational system operates.

[0778] "User characteristics" refers to the characteristics and behavioral patterns of a particular user or user group.

[0779] "Failure cases" refer to cases of trouble or malfunction that have occurred in the system in the past.

[0780] "Past verification items" means evaluation criteria or checklists used in previous verification or testing of the system.

[0781] "Time required" refers to the amount of time required to complete a particular task or process.

[0782] "Means" refers to methods or techniques for achieving a specific purpose.

[0783] A "server" refers to a computer system that processes requests from clients on a network and provides data and services.

[0784] "Learning from input" is the process by which machine learning algorithms learn patterns and trends based on the data you provide them.

[0785] An "AI model" refers to a set of algorithms designed to automate a specific task using artificial intelligence techniques.

[0786] "Training" refers to the process of feeding an AI model data to teach it to recognize patterns and improve its performance.

[0787] A "specification for new functions" is a document that details the functions that will be newly added to the system.

[0788] "Analysis" refers to the process of breaking down specific data or information into more understandable detail.

[0789] "Critical elements" refer to information or components found in the analyzed data that are particularly important to a system or function.

[0790] "Optimal verification items" refer to the most appropriate tests and checkpoints to ensure the quality of a system or function.

[0791] "Emotion engine" refers to an algorithm or program that analyzes and identifies a user's emotional state.

[0792] "Adjusting priorities" refers to changing the order in which tasks or items are performed depending on their importance and the situation.

[0793] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system, and the server learns the input data to train an AI model. Also, specifications for new functions are input, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications.

[0794] System configuration

[0795] The system consists of a user terminal and a server. An interface for users to input data is placed on the user terminal, and the input data is processed by the server. The server has a database and stores and processes the input data. The server also incorporates an AI model that implements machine learning algorithms and natural language processing (NLP) technology.

[0796] Hardware and software used

[0797] Hardware:

[0798] User devices (PCs, tablets, smartphones, etc.)

[0799] A server (with a powerful processor, sufficient memory and storage)

[0800] software:

[0801] Database management systems (e.g., MySQL, PostgreSQL)

[0802] Natural language processing tools (e.g., NLTK, spaCy)

[0803] Machine learning frameworks (e.g. TensorFlow, PyTorch)

[0804] User interface (e.g. web browser, dedicated application)

[0805] Program processing flow

[0806] Data input and training

[0807] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, past verification items and required time. The user provides this data to the system by filling in forms or uploading files. Once the input is complete, the server confirms receipt of the data and saves it in the database.

[0808] The server then preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values. The server then extracts features and trains an AI model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[0809] Entering and parsing new specifications

[0810] A user uploads a specification for a new feature to the system. The server receives the uploaded specification, stores it in a database, and then performs preprocessing. NLP techniques are used to parse the specification text and standardize the format.

[0811] The server then analyzes the content of the specification and extracts important elements (functional and non-functional requirements), which are then organized into a tree data structure.

[0812] Generation and presentation of verification items

[0813] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time of past similar functions. Each of these verification items also includes an estimated required time.

[0814] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, allowing the system to continually improve.

[0815] Combining Emotion Engines

[0816] The system is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, the words selected, and the frequency of operations.

[0817] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and aim for a quick resolution. It also displays support messages as appropriate so that the user can proceed with the work with peace of mind.

[0818] Specific examples

[0819] Example of adding the new feature "User profile customization function"

[0820] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[0821] 2. The server uses this data to train and validate the AI ​​model.

[0822] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[0823] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[0824] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[0825] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[0826] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[0827] Example prompts:

[0828] I have uploaded a specification for a new user feature. I would like to add a "user profile customization feature." Please generate optimal verification items based on the current system specifications, past failure cases, verification items, and required time.

[0829] As described above, the present invention efficiently trains an AI model based on data provided by users, analyzes new specifications, and generates optimal verification items. Furthermore, by adjusting the priority of verification items based on user sentiment, more adaptive and effective verification can be achieved.

[0830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] The user enters existing data.

[0833] Input: Existing system specifications, user characteristics, past failure cases, past verification items and required time

[0834] How it works: A user logs into the system and enters data via a form or file upload.

[0835] Output: The input data is sent to the server.

[0836] Step 2:

[0837] The server receives and stores the data.

[0838] Input: Existing data entered by the user

[0839] Operation: The server saves the received data in the database and notifies the user with a message asking them to confirm the save.

[0840] Output: Existing data stored in the database

[0841] Step 3:

[0842] The server preprocesses the data.

[0843] Input: Existing data stored in a database

[0844] How it works: The server cleans the data, removes incomplete and duplicate data, standardizes data formats, and imputes outliers and missing values.

[0845] Output: Cleaned and uniformly formatted data

[0846] Step 4:

[0847] The server extracts features.

[0848] Input: Data after cleaning

[0849] How it works: The server uses data analysis tools to extract important features, such as Pandas and Scikit-learn.

[0850] Output: Extracted feature data

[0851] Step 5:

[0852] The server trains the AI ​​model.

[0853] Input: Extracted feature data

[0854] How it works: The server trains an AI model using a machine learning framework (e.g., TensorFlow, PyTorch). It also validates the model to ensure its accuracy.

[0855] Output: A trained AI model

[0856] Step 6:

[0857] A user uploads a new specification.

[0858] Input: Specification for new feature

[0859] How it works: A user uploads a new specification to the system and sends it to the server.

[0860] Output: Uploaded specification data

[0861] Step 7:

[0862] The server receives and stores the specification.

[0863] Input: New specification data uploaded by the user

[0864] Operation: The server saves the specification data to the database and notifies the user that the save is complete.

[0865] Output: New specification data stored in the database

[0866] Step 8:

[0867] The server preprocesses the specification.

[0868] Input: New specification data stored in the database

[0869] How it works: The server uses natural language processing (NLP) techniques to analyze and format text data, specifically removing unnecessary spaces within sentences and converting them into a specific format.

[0870] Output: Preprocessed specification data

[0871] Step 9:

[0872] The server parses the specification and extracts the important elements.

[0873] Input: Preprocessed specification data

[0874] How it works: The server uses NLP technology to analyze the contents of the specification, extract important elements such as functional and non-functional requirements, and organize them into a tree data structure.

[0875] Output: Extracted important element data

[0876] Step 10:

[0877] The server generates the optimal verification items.

[0878] Input: Trained AI model and extracted key element data

[0879] How it works: The server uses a trained AI model to automatically generate optimal verification items based on new specifications, while also referring to the verification items and required time for similar functions in the past.

[0880] Output: Generated verification item list data

[0881] Step 11:

[0882] The server presents the generated list of verification items to the user.

[0883] Input: Generated verification item list data

[0884] How it works: The server presents a list of validation items to the user through a user interface, allowing the user to review and download the list and provide feedback.

[0885] Output: A list of validation items presented to the user

[0886] Step 12:

[0887] An emotion engine recognizes the user's emotional state.

[0888] Input: User input data and operation logs

[0889] Behavior: The emotion engine determines the user's emotional state based on their typing speed, selected words, and frequency of actions.

[0890] Output: User's emotional state data

[0891] Step 13:

[0892] The server adjusts the priority of verification items based on emotional state data.

[0893] Input: User's emotional state data

[0894] How it works: Based on the emotional state data, the server prioritizes the most important verification items and aims to resolve them quickly. It also displays support messages so that the user can proceed with the work with peace of mind.

[0895] Output: Priority adjusted verification item list data

[0896] The above is the flow of specific processing steps of the program of this system.

[0897] (Application example 2)

[0898] 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."

[0899] Conventional systems clean data, extract features, and train AI models, but they have a problem in that they are unable to consider the user's emotional state when generating optimal verification items for new specifications. In particular, when the user is feeling nervous or stressed, they are unable to provide appropriate support, making it difficult to achieve an efficient verification process.

[0900] 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.

[0901] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train an AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; a means for recognizing the emotional state of the user using an emotion engine; a means for the server to adjust the urgency and priority of the verification items based on the emotional state; and a means for the server to present the generated list of verification items to the user. This enables an adaptive and efficient verification process that takes the user's emotional state into consideration.

[0902] "Existing system specifications" are documents and data that explain the technical information, design, and operational details of the current operational system.

[0903] "User characteristics" refers to information including the behavioral patterns and operation tendencies of users who use the system, as well as their past usage history.

[0904] A "trouble case" is a record of details of problems or errors that occurred during system operation and their resolution.

[0905] "Past verification items" refers to information about the contents and results of system tests that have been previously conducted.

[0906] "Time required" is a record of the amount of time required to complete a particular task or verification item.

[0907] An "AI model" is an artificial intelligence algorithm trained through machine learning or deep learning and used to automate or optimize a specific task.

[0908] "Specifications for new functions" refers to documents and data that contain detailed design and operational information regarding newly added functions and changes.

[0909] "Important elements" are information that should be given special importance in verification, such as system requirements and constraints extracted from new specifications.

[0910] An "emotion engine" is a technology that analyzes a user's operation log and input data to recognize and estimate their emotional state.

[0911] "Adjusting the urgency and priority of verification items" means optimizing the importance of items to be verified and the order of processing based on the emotional state of the user.

[0912] This invention is a system that uses a smart verification support robot to generate and implement optimal verification items by making full use of AI and an emotion engine when new machinery is introduced in a factory or an existing line system is updated. This system is composed of the following elements.

[0913] System Configuration

[0914] 1. Data entry method:

[0915] The user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system. The input is done by filling out a form or uploading a file.

[0916] The server stores the input data in storage.

[0917] 2. Data preprocessing:

[0918] The server cleans the input data, removing incomplete and duplicate data and standardizing the data format. It also fills in outliers and missing values.

[0919] 3. Feature extraction and AI model training:

[0920] The server extracts important features from the cleaned data and trains the AI ​​model using machine learning frameworks such as TensorFlow and Keras.

[0921] Validate the AI ​​model and evaluate its accuracy.

[0922] 4. New specification analysis methods:

[0923] A user uploads a specification for a new feature into the system.

[0924] The server uses natural language processing (NLP) to analyze the specifications, extract and structure key elements.

[0925] 5. How to generate verification items:

[0926] The server generates optimal verification items based on the trained AI model and analysis data of the specifications. It also automatically generates specific checklists and test content by referring to the verification items and required time of past similar functions.

[0927] 6. Introducing the Emotion Engine:

[0928] It uses an emotion engine that recognizes the user's emotions. It analyzes input data and operation logs to determine the user's emotional state.

[0929] The server adjusts the urgency and priority of the verification items based on data from the emotion engine. If the user is feeling nervous or stressed, it will prioritize verification items with high importance and display appropriate support messages.

[0930] 7. Method of presenting verification items:

[0931] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, which is used to continuously improve the system.

[0932] Specific processing examples

[0933] For example, if a new robot arm operation control function is introduced in a factory, the user uploads the specifications for the "new robot arm operation control function" to the system. The server extracts important elements such as "operation speed control" and "emergency stop function" from the specifications, and the AI ​​model generates verification items such as "speed control response time test" and "emergency stop signal reaction time test." The emotion engine detects the user's stress level, adjusts priorities, and presents the user with an appropriate list of verification items.

[0934] Prompt Sentence Examples

[0935] "Upload a specification for the user profile customization feature. We then extract key elements based on the specification. Combined with user sentiment data, we generate a list of optimal validation items. The list is then prioritized based on the stress of the user experience."

[0936] The system enables an adaptive and efficient verification process that takes into account the user's emotional state.

[0937] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0938] Step 1:

[0939] The user inputs the existing system specifications, user characteristics, past failure cases, past verification items, and required time.

[0940] Input is provided by the user through form entry or file upload from the terminal. The input data is saved in the server's storage. The output is a dataset saved on the server.

[0941] Step 2:

[0942] The server performs pre-processing on the input data.

[0943] Specifically, data cleaning is performed to remove incomplete and duplicate data, standardize data formats, and impute outliers and missing values. The output is a clean and consistent dataset.

[0944] Step 3:

[0945] The server extracts features from the cleaned data.

[0946] Features are important data points used to train AI models. Machine learning frameworks (e.g., TensorFlow or Keras) are used to extract features from data. The output is a set of features.

[0947] Step 4:

[0948] The server uses the extracted features to train an AI model.

[0949] The training step involves splitting the dataset into a training set and a validation set and optimizing the model parameters. Once training is complete, the model is validated to evaluate its accuracy and performance. The output is a trained AI model.

[0950] Step 5:

[0951] A user uploads a specification for a new feature into the system.

[0952] When a user uploads a new specification file from their terminal, it is saved on the server. The output is the new specification data.

[0953] Step 6:

[0954] The server parses the new specification using natural language processing (NLP).

[0955] During the analysis process, the text data is cleaned, tokenized, and parsed. Important elements (e.g., functional requirements and constraints) are extracted and converted into a structured format such as tree data. The output is the data of the analyzed important elements.

[0956] Step 7:

[0957] The server generates optimal verification items based on the trained AI model and analyzed specifications.

[0958] It automatically generates specific checklists and test content by referring to the verification items and required time of similar functions in the past. If necessary, an estimate of the required time is also provided. The output is a list of generated verification items.

[0959] Step 8:

[0960] An emotion engine is introduced to recognize user emotions.

[0961] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and operation log. The input is the user's operation log and input data, and the output is the user's emotional state data.

[0962] Step 9:

[0963] The server adjusts the urgency and priority of verification items based on the recognized emotional state data.

[0964] Specifically, if the user feels nervous or stressed, the system will prioritize the most important verification items and promptly resolve them. It also displays support messages as needed to help the user proceed with their work with peace of mind. The output is a list of adjusted verification items.

[0965] Step 10:

[0966] The server presents the generated list of verification items to the user.

[0967] The list is displayed through a user interface, allowing users to review and download the verification item list and provide feedback, which allows the system to continuously improve. The output is the verification item list and user feedback.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] [Third embodiment]

[0972] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0973] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0974] 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).

[0975] 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.

[0976] 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.

[0977] 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).

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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."

[0984] The present embodiment will now be described in natural language with respect to the processing of the system and its programs.

[0985] System Overview

[0986] This invention relates to a system that proposes optimal verification items when implementing new functions, using an AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[0987] Data input and training

[0988] 1. The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and the required time.

[0989] Data entry is done through methods such as file upload and form filling.

[0990] Immediately after the data is uploaded, the server performs data cleaning as a pre-processing of the data.

[0991] 2. The server receives the input data and trains the AI ​​model.

[0992] First, the server performs data cleaning to remove incomplete data and duplicates.

[0993] Next, feature extraction is performed to extract important features of each data.

[0994] The server uses these features to train an AI model and validate the model.

[0995] Entering and parsing new specifications

[0996] 3. The user uploads a specification for a new feature into the system.

[0997] The server performs preprocessing of the text data to ensure a consistent format for the specification.

[0998] 4. The server parses the new specification and extracts the important elements.

[0999] The server analyzes the text using natural language processing (NLP) techniques.

[1000] From the analysis results, important elements (e.g., functional requirements and non-functional requirements) are extracted and structured.

[1001] Generation and presentation of verification items

[1002] 5. The server generates optimal verification items based on the learned data and analyzed specifications.

[1003] The server references past data and automatically generates optimal verification items based on new specifications.

[1004] The generated verification items also include an estimate of the time required for each.

[1005] 6. The server presents the generated list of verification items to the user.

[1006] The results are displayed through the user interface, and the user can create a verification plan based on the list.

[1007] The list can be downloaded in CSV or Excel format, and suggestions for improving items are also accepted via the feedback function.

[1008] Specific examples

[1009] Added new feature "User profile customization function"

[1010] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1011] 2. The server uses this data to train the AI ​​model.

[1012] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1013] 4. The server analyzes the new specifications and extracts important elements such as the ability to change profile pictures and edit self-introductions.

[1014] 5. Based on the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." It also provides an estimate of the time required for each verification item.

[1015] 6. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1016] This reduces the risk of manual creation of verification items and errors, enabling efficient and high-quality software development.

[1017] The processing flow will be explained below.

[1018] Step 1:

[1019] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[1020] Step 2:

[1021] The server preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values.

[1022] Step 3:

[1023] The server then performs feature extraction from the cleaned data. This is the process of extracting important features necessary for training the machine learning model. For example, this includes user characteristics and specific patterns of failure cases.

[1024] Step 4:

[1025] The server uses the feature-extracted data to train the AI ​​model. Deep learning and other machine learning techniques are used to build the model from past data. During this process, the model parameters are optimized.

[1026] Step 5:

[1027] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy and effectiveness, and retrains the model if necessary.

[1028] Step 6:

[1029] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[1030] Step 7:

[1031] The server preprocesses the new specification, using natural language processing (NLP) to parse the text data and standardize the format.

[1032] Step 8:

[1033] The server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract and structure elements from the text. This process leverages techniques such as concrete text classification and named entity recognition (NER).

[1034] Step 9:

[1035] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content, taking into account the verification items and required time of past similar functions.

[1036] Step 10:

[1037] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[1038] As described above, this system involves the processes of sequential data input, analysis, model learning, and verification item generation, making it possible to provide efficient and highly accurate verification items when implementing new functions.

[1039] Example 1

[1040] 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."

[1041] In traditional software development, verification items must be created manually every time a new feature is added, which takes time and effort. Furthermore, creating verification items manually is prone to errors, which can have a negative impact on software quality. Furthermore, it is difficult to generate verification items that fully reflect past failure cases and user characteristics, which can result in a lack of comprehensiveness in verification.

[1042] 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.

[1043] In this invention, the server includes means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times, means for the server to learn the input data and train a machine learning model, means for a user to input specifications for new functions, means for the server to analyze the new specifications and extract important elements, means for the server to generate optimal verification items based on the learned data and the analyzed specifications, means for the server to present the generated list of verification items to the user, and means for the server to save and export the generated list of verification items in a downloadable format, thereby enabling efficient and accurate generation and presentation of verification items.

[1044] plaintext

[1045] "User" refers to an individual or group that operates the system and inputs data such as existing system specifications and specifications for new features.

[1046] "Server" refers to the central computer system that processes, manages, learns, and analyzes data, and generates and presents validation items to the user.

[1047] "Existing system specifications" refers to detailed descriptions of the function, structure, and design of systems currently in operation.

[1048] "User characteristics" refers to information related to users, such as the behavior and attributes of users who use the system.

[1049] "Failure cases" refer to records and details of malfunctions or problems that occurred during system operation.

[1050] "Past verification items" refers to information about the verification content and details of systems and functions that have been previously conducted.

[1051] "Time required" refers to the time required to perform a particular verification item.

[1052] A "machine learning model" is a group of algorithms that are trained to automatically perform specific tasks by studying data.

[1053] "Specification" refers to a document that details new features and improvements.

[1054] "Key elements" refer to functional and non-functional requirements that deserve special attention within the specification.

[1055] "Natural language processing" refers to the technology that allows computers to analyze and understand human language.

[1056] "Verification items" refer to specific verification procedures or checkpoints that are implemented to confirm the accuracy and reliability of a system or function.

[1057] "User interface" refers to the screens, controls, and navigation that allow a user to interact with a system.

[1058] "Export" means to store or provide data or information in another format.

[1059] MODE FOR CARRYING OUT THE INVENTION

[1060] The system and its program processing of this invention are described in detail below. The hardware used includes a server and a user terminal. The software used includes Python, pandas, Scikit-learn, TensorFlow, PyTorch, NLTK, spaCy, etc. This enables efficient and accurate generation and presentation of verification items.

[1061] Overall system flow

[1062] This invention is a system that proposes optimal verification items when implementing new functions, using a generative AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[1063] Data input and training

[1064] 1. User enters existing data

[1065] The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and required time into the system. This operation is performed through the file selection window on the terminal, and uploading of CSV or Excel files is recommended. When the user selects the file and clicks the upload button, the server receives this data.

[1066] 2. The server performs data cleaning and feature extraction

[1067] The server performs data cleaning based on the received data. It uses the Python pandas library to remove invalid values ​​and duplicate data and to fill in missing data. It then uses Scikit-learn to extract features. For example, numerical and categorical features are calculated and used in the next step.

[1068] 3. The server trains the machine learning model

[1069] The server uses the data after cleaning and feature extraction to train a machine learning model using frameworks such as TensorFlow or PyTorch. After training, the accuracy of the model is validated using test data. The results are recorded in a log.

[1070] Entering and parsing new specifications

[1071] 4. User uploads new specification

[1072] The user uploads a specification for a new feature to the system. This is done on the device, and the specification format is recommended as PDF or DOCX. The user selects the file and clicks the upload button, and the server receives the specification.

[1073] 5. The server preprocesses the specification

[1074] The server preprocesses the received specification using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters, converting it into a format suitable for analysis.

[1075] 6. The server analyzes the specification and extracts important elements

[1076] After preprocessing, the server uses NLP techniques to analyze the specifications and extract important elements (e.g., functional and non-functional requirements). The extracted data is structured and used in subsequent steps.

[1077] Generation and presentation of verification items

[1078] 7. The server generates the validation items

[1079] The server uses the trained AI model to generate verification items based on past data and new specifications. For example, for the "profile photo change function," "image format check" and "size restriction check" are automatically generated. Each verification item also includes an estimated time required.

[1080] 8. The server presents a list of verification items

[1081] The generated list of verification items is presented to the user through a user interface. The user can view and download the list, save it in CSV or Excel format, and use the feedback function to add comments to the verification items.

[1082] Specific examples

[1083] Added new feature "User profile customization function"

[1084] 1. The user inputs historical data such as the specifications of the existing system and failure cases into the system.

[1085] 2. The server uses this data to train an AI model. Specifically, it uses Python's pandas to clean the data and extract features. Then, it uses TensorFlow to train and validate the model.

[1086] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1087] 4. The server analyzes the new specifications and extracts important elements such as the ability to change the profile picture and edit the self-introduction. The NLP technology used is spaCy.

[1088] 5. Based on the results of the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" and "checking the character limit for the self-introduction," and estimates the time required for each.

[1089] 6. The server presents the generated list of verification items to the user through the user interface and makes it available for download as a CSV file. The user interface also has a function for sending feedback.

[1090] Prompt Sentence Examples

[1091] Enter specifications for user profile customization features, such as changing your profile picture or editing your bio.

[1092]

[1093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1094] plaintext

[1095] Step 1:

[1096] The user uploads data on existing system specifications, user characteristics, failure cases, past verification items, and required time from their terminal to the system. Input is done in CSV or Excel format files. Once the file is uploaded, the server receives it and prepares it for data cleaning. Clean data is obtained as output.

[1097] Step 2:

[1098] The server performs data cleaning on the received data, specifically using the Python pandas library to remove invalid values ​​and duplicate data and properly impute missing data. The input is the raw data uploaded in step 1, and the output is a clean data frame.

[1099] Step 3:

[1100] The server extracts features based on the clean data. For this, it uses Scikit-learn to extract numerical and categorical features. For example, age and frequency of use can be extracted as features from user characteristic data. The input is clean data, and features are obtained as output.

[1101] Step 4:

[1102] The server uses the features to train a machine learning model. The frameworks used are TensorFlow and PyTorch. The feature data is used as training data to train the model. The accuracy of the model is validated with test data and the results are recorded. The input is the feature data, and the output is a trained model.

[1103] Step 5:

[1104] The user uploads a specification for a new feature to the system. The input is a PDF or DOCX file, which the user selects from their terminal and clicks the upload button. Once the file is uploaded, the server prepares the specification for preprocessing.

[1105] Step 6:

[1106] The server receives new specifications and preprocesses them using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters. The input is the uploaded specification, and the output is the preprocessed text data.

[1107] Step 7:

[1108] The server analyzes the preprocessed text data and extracts important elements. Important elements refer to functional and non-functional requirements, for example. The input is the preprocessed text data, and the extracted important elements are obtained as the output.

[1109] Step 8:

[1110] The server uses the trained AI model to generate optimal verification items based on new specifications. For example, it automatically generates "image format checks" and "size restriction checks" for the "profile photo change function" from past data and new specifications. Each verification item also has an estimated time required. The input is the extracted important elements, and the output is a list of generated verification items.

[1111] Step 9:

[1112] The server presents the generated list of verification items to the user. The list is displayed through the user interface, and the user can view and download it. The list can be saved in CSV or Excel format, and the user can add comments to the items using the feedback function. The input is the generated list of verification items, and the presented list is provided to the user as the output.

[1113] (Application example 1)

[1114] 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."

[1115] The selection of verification items when implementing new functions in factory robots is usually done manually, which is inefficient and carries a high risk of error. Furthermore, if past failure cases and user characteristics are not sufficiently taken into consideration, the quality of the verification may be affected. There is a need for a method to solve these problems and automate the generation of efficient, high-quality verification items.

[1116] 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.

[1117] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train a generative AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; and a means for the server to present the generated verification item list to the user and display it on a smartphone in real time. This enables efficient automatic generation of high-quality verification items when implementing new functions in factory robots.

[1118] A "user" is an entity that inputs system specifications, failure cases, verification items, etc. into the system and submits specifications for new functions.

[1119] A "system specification" is a collection of technical details and operational requirements for an existing system.

[1120] "User characteristics" refers to information about the attributes and behavioral norms of individual users and user groups who use the system.

[1121] "Failure cases" are specific examples of system problems or errors that have occurred in the past.

[1122] "Verification items" are test items used to verify whether new features or changes to the system work properly.

[1123] "Required time" is the estimated time required to execute each verification item.

[1124] The "server" is a central computer that stores and analyzes input data and trains generative AI models.

[1125] A "generative AI model" is an artificial intelligence model that is trained based on input data and is used to suggest optimal verification items for a system.

[1126] A "specification for new features" is a document that describes the technical details and operational requirements of a newly implemented feature.

[1127] "Natural language processing" is a technology that analyzes text data and extracts important elements.

[1128] "Real-time display" is a function that instantly displays the generated verification item list on the user's device.

[1129] A "smartphone" is a mobile device used to display the generated verification item list.

[1130] The system and its program processing will be described in the embodiment for carrying out the present invention.

[1131] System Overview

[1132] In this system, users input existing system specifications, user characteristics, failure cases, past verification items, and required time, and the server learns from this data to train a generative AI model. Furthermore, specifications for new functions are input, and the system analyzes the specifications to extract important elements and generate optimal verification items. The generated list of verification items is displayed on a smartphone in real time.

[1133] Data input and training

[1134] Users input existing system specifications, failure cases, past verification items, and required time into the system via CSV files or form input. This data is stored on a cloud server (e.g., AWS, Google Cloud).

[1135] The server cleans the input data (removing missing values ​​and duplicates) and extracts features. It then trains a generative AI model using a machine learning library such as scikit-learn. Validation of the model is also performed at the same time.

[1136] Entering and parsing new specifications

[1137] Users upload specifications for new robot functions from their smartphones, and the server analyzes the specifications using natural language processing (NLP) technology to extract key elements.

[1138] Generation and presentation of verification items

[1139] The server estimates the optimal verification items and required time based on the learned data and analyzed specifications, and generates a list of verification items. This list is displayed in real time on the smartphone, and the user can check and download it.

[1140] Specific examples

[1141] For example, when implementing an "obstacle avoidance function" for a new robot, the user uploads past specifications and failure cases in a CSV file. The server uses this information to train the AI ​​model. Next, the user uploads the "specifications for the new obstacle avoidance function," and the server analyzes the specifications. Based on this analysis, verification items such as "verification of the maximum detection distance of the distance sensor" and "verification of operating speed" are automatically generated.

[1142] Example prompt sentence:

[1143] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[1144] "Please upload a specification for the obstacle avoidance function of your new robot."

[1145] This makes it possible to automatically generate efficient, high-quality verification items when implementing new functions in factory robots.

[1146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1147] Step 1:

[1148] The user inputs existing system specifications, user characteristics, failure cases, past verification items, and required time into the system via a CSV file or form input.

[1149] Input: Existing system specifications, user characteristics, failure cases, past verification items, required time

[1150] Output: Data stored on the server

[1151] Specific operation: The user selects a CSV file and uploads it to the system. If necessary, the user can also enter data directly into the form. The data is then saved to the cloud server.

[1152] Step 2:

[1153] The server performs data cleaning based on the input data.

[1154] Input: Data saved in step 1

[1155] Output: Cleaned data

[1156] Specific operation: The server uses the pandas library to remove missing values ​​and duplicates from the data and format the data.

[1157] Step 3:

[1158] The server performs feature extraction using the cleaned data.

[1159] Input: Cleaned data

[1160] Output: Feature data

[1161] Specific operation: The server uses scikit-learn's CountVectorizer to digitize the text data and extract features.

[1162] Step 4:

[1163] The server uses the feature data to train a generative AI model.

[1164] Input: Feature data

[1165] Output: Generative AI model

[1166] Specific operation: The server trains and learns the model using algorithms such as scikit-learn's RandomForestClassifier.

[1167] Step 5:

[1168] A user uploads a specification for a new feature to the system from their smartphone.

[1169] Input: Specification for new feature

[1170] Output: The new specification saved on the server.

[1171] Specific operation: The user selects a specification file and uploads it to the system, where it is stored on the cloud server.

[1172] Step 6:

[1173] The server analyzes the new specification using natural language processing to extract important elements.

[1174] Input: New Specification

[1175] Output: Important elements parsed

[1176] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text of the specification and extract important elements such as functional and non-functional requirements.

[1177] Step 7:

[1178] The server generates optimal verification items based on the learned data and analyzed specifications.

[1179] Input: analyzed key elements, generative AI model

[1180] Output: Optimal test list and estimated time required

[1181] Specific operation: The server correlates historical data with the elements of the new specification, generates optimal verification items, and assigns an estimated time for each.

[1182] Step 8:

[1183] The server presents the generated list of verification items to the user and displays it on the smartphone in real time.

[1184] Input: List of optimal verification items, estimated time required

[1185] Output: A list of verification items displayed on the user's smartphone

[1186] Specific operation: The server displays the generated list of verification items on the user's smartphone in real time and also makes it possible to download it if necessary.

[1187] Example prompt sentence:

[1188] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[1189] "Please upload a specification for the obstacle avoidance function of your new robot."

[1190] 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.

[1191] System Overview

[1192] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time, and the server learns the input data to train an AI model. In addition to this system, a user can input specifications for new functions, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications. Furthermore, the present invention combines an emotion engine that recognizes user emotions to achieve more effective and adaptive generation of verification items.

[1193] Data input and training

[1194] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[1195] Next, the server preprocesses the input data. Specifically, it cleans the data. It removes incomplete and duplicate data and standardizes data formats. It also complements outliers and missing values. After this, the server performs feature extraction and extracts important features from each piece of data. These features are used to train an AI model and validate the model.

[1196] Entering and parsing new specifications

[1197] Users upload specifications for new features to the system. The server receives the specifications, stores them in a database, and then performs preprocessing, parsing the text data using natural language processing (NLP) and standardizing the format.

[1198] Next, the server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract elements from the text and structure them. The extracted important elements are organized into a tree data structure or similar.

[1199] Generation and presentation of verification items

[1200] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time for similar functions in the past. The generated verification items also include an estimate of the required time for each item.

[1201] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[1202] Combining Emotion Engines

[1203] To recognize user emotions, an emotion engine is combined. This emotion engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, selected words, frequency of operations, etc.

[1204] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. Specifically, if the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and ensure their resolution is prompt. It also displays support messages as appropriate so that the user can proceed with their work with peace of mind.

[1205] Specific examples

[1206] Example of adding the new feature "User profile customization function"

[1207] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1208] 2. The server uses this data to train and validate the AI ​​model.

[1209] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1210] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[1211] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[1212] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[1213] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1214] In this way, by combining emotion engines, a system can be realized that takes into account the user's emotional state and provides more effective and adaptive verification items.

[1215] The processing flow will be explained below.

[1216] Step 1:

[1217] The user logs in to the system. After logging in, the user enters the existing system specifications, user characteristics, past failure cases, past verification items and the required time into the system. Data entry is done by uploading files or filling in forms. Once the user has completed the data entry, the server receives the data and stores it in storage.

[1218] Step 2:

[1219] The server preprocesses the input data, cleaning it by removing incomplete and duplicate data, filling in missing values, and standardizing the data format.

[1220] Step 3:

[1221] The server extracts features from the cleaned data. Important features are analyzed and used to train the machine learning model. Features include user characteristics, specific patterns of failure cases, and details of past verification items.

[1222] Step 4:

[1223] The server uses the extracted features to train an AI model, applying deep learning and other machine learning techniques to optimize the model parameters.

[1224] Step 5:

[1225] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy, and retrains the AI ​​model if necessary.

[1226] Step 6:

[1227] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[1228] Step 7:

[1229] The server preprocesses the new specification, using natural language processing (NLP) techniques to analyze the text data and standardize the format of the specification.

[1230] Step 8:

[1231] The server analyzes the content of the specification and extracts important elements. Specifically, it uses named entity recognition (NER) to extract important elements such as functional and non-functional requirements from the specification and organizes them into a structure.

[1232] Step 9:

[1233] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content by referring to the verification items and required times of past similar functions.

[1234] Step 10:

[1235] The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. For example, it analyzes the input speed, the content of selected words, click frequency, etc. to determine the user's current emotional state.

[1236] Step 11:

[1237] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user feels nervous or frustrated, it will prioritize verification items with high importance and promptly resolve them. It will also display support messages as needed.

[1238] Step 12:

[1239] The server presents the generated list of verification items to the user through a user interface. The user can create a verification plan based on this list. The list of verification items can also be downloaded in CSV or Excel format, and the user can provide feedback on the results.

[1240] In this way, by combining it with an emotion engine, the system can generate effective and efficient verification items while taking into account the user's emotional state.

[1241] Example 2

[1242] 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."

[1243] Modern software systems are becoming increasingly complex, making verification work extremely important when adding or modifying new features. However, traditional methods often require manually generating verification items, which can lead to human error and effort. Furthermore, user emotions and tension can affect the efficiency of verification, so a flexible system that can accommodate these factors is needed.

[1244] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; means for the server to learn the input data and train the AI ​​model; means for a user to input specifications for new functions; means for the server to analyze the new specifications and extract important elements; means for the server to generate optimal verification items based on the learned data and the analyzed specifications; means for the server to present the generated list of verification items to the user; means for an emotion engine to determine the user's emotional state; and means for the server to adjust the priority of the verification items based on the emotion data. This enables efficient automatic generation of verification items and the presentation of adaptive verification items corresponding to the user's emotions.

[1245] Understood. Below are definitions of important terms contained in the claims:

[1246] An "existing system specification" is a document that details how a currently operational system operates.

[1247] "User characteristics" refers to the characteristics and behavioral patterns of a particular user or user group.

[1248] "Failure cases" refer to cases of trouble or malfunction that have occurred in the system in the past.

[1249] "Past verification items" means evaluation criteria or checklists used in previous verification or testing of the system.

[1250] "Time required" refers to the amount of time required to complete a particular task or process.

[1251] "Means" refers to methods or techniques for achieving a specific purpose.

[1252] A "server" refers to a computer system that processes requests from clients on a network and provides data and services.

[1253] "Learning from input" is the process by which machine learning algorithms learn patterns and trends based on the data you provide them.

[1254] An "AI model" refers to a set of algorithms designed to automate a specific task using artificial intelligence techniques.

[1255] "Training" refers to the process of feeding an AI model data to teach it to recognize patterns and improve its performance.

[1256] A "specification for new functions" is a document that details the functions that will be newly added to the system.

[1257] "Analysis" refers to the process of breaking down specific data or information into more understandable detail.

[1258] "Critical elements" refer to information or components found in the analyzed data that are particularly important to a system or function.

[1259] "Optimal verification items" refer to the most appropriate tests and checkpoints to ensure the quality of a system or function.

[1260] "Emotion engine" refers to an algorithm or program that analyzes and identifies a user's emotional state.

[1261] "Adjusting priorities" refers to changing the order in which tasks or items are performed depending on their importance and the situation.

[1262] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system, and the server learns the input data to train an AI model. Also, specifications for new functions are input, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications.

[1263] System configuration

[1264] The system consists of a user terminal and a server. An interface for users to input data is placed on the user terminal, and the input data is processed by the server. The server has a database and stores and processes the input data. The server also incorporates an AI model that implements machine learning algorithms and natural language processing (NLP) technology.

[1265] Hardware and software used

[1266] Hardware:

[1267] User devices (PCs, tablets, smartphones, etc.)

[1268] A server (with a powerful processor, sufficient memory and storage)

[1269] software:

[1270] Database management systems (e.g., MySQL, PostgreSQL)

[1271] Natural language processing tools (e.g., NLTK, spaCy)

[1272] Machine learning frameworks (e.g. TensorFlow, PyTorch)

[1273] User interface (e.g. web browser, dedicated application)

[1274] Program processing flow

[1275] Data input and training

[1276] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, past verification items and required time. The user provides this data to the system by filling in forms or uploading files. Once the input is complete, the server confirms receipt of the data and saves it in the database.

[1277] The server then preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values. The server then extracts features and trains an AI model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[1278] Entering and parsing new specifications

[1279] A user uploads a specification for a new feature to the system. The server receives the uploaded specification, stores it in a database, and then performs preprocessing. NLP techniques are used to parse the specification text and standardize the format.

[1280] The server then analyzes the content of the specification and extracts important elements (functional and non-functional requirements), which are then organized into a tree data structure.

[1281] Generation and presentation of verification items

[1282] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time of past similar functions. Each of these verification items also includes an estimated required time.

[1283] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, allowing the system to continually improve.

[1284] Combining Emotion Engines

[1285] The system is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, the words selected, and the frequency of operations.

[1286] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and aim for a quick resolution. It also displays support messages as appropriate so that the user can proceed with the work with peace of mind.

[1287] Specific examples

[1288] Example of adding the new feature "User profile customization function"

[1289] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1290] 2. The server uses this data to train and validate the AI ​​model.

[1291] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1292] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[1293] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[1294] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[1295] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1296] Example prompts:

[1297] I have uploaded a specification for a new user feature. I would like to add a "user profile customization feature." Please generate optimal verification items based on the current system specifications, past failure cases, verification items, and required time.

[1298] As described above, the present invention efficiently trains an AI model based on data provided by users, analyzes new specifications, and generates optimal verification items. Furthermore, by adjusting the priority of verification items based on user sentiment, more adaptive and effective verification can be achieved.

[1299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1300] Step 1:

[1301] The user enters existing data.

[1302] Input: Existing system specifications, user characteristics, past failure cases, past verification items and required time

[1303] How it works: A user logs into the system and enters data via a form or file upload.

[1304] Output: The input data is sent to the server.

[1305] Step 2:

[1306] The server receives and stores the data.

[1307] Input: Existing data entered by the user

[1308] Operation: The server saves the received data in the database and notifies the user with a message asking them to confirm the save.

[1309] Output: Existing data stored in the database

[1310] Step 3:

[1311] The server preprocesses the data.

[1312] Input: Existing data stored in a database

[1313] How it works: The server cleans the data, removes incomplete and duplicate data, standardizes data formats, and imputes outliers and missing values.

[1314] Output: Cleaned and uniformly formatted data

[1315] Step 4:

[1316] The server extracts features.

[1317] Input: Data after cleaning

[1318] How it works: The server uses data analysis tools to extract important features, such as Pandas and Scikit-learn.

[1319] Output: Extracted feature data

[1320] Step 5:

[1321] The server trains the AI ​​model.

[1322] Input: Extracted feature data

[1323] How it works: The server trains an AI model using a machine learning framework (e.g., TensorFlow, PyTorch). It also validates the model to ensure its accuracy.

[1324] Output: A trained AI model

[1325] Step 6:

[1326] A user uploads a new specification.

[1327] Input: Specification for new feature

[1328] How it works: A user uploads a new specification to the system and sends it to the server.

[1329] Output: Uploaded specification data

[1330] Step 7:

[1331] The server receives and stores the specification.

[1332] Input: New specification data uploaded by the user

[1333] Operation: The server saves the specification data to the database and notifies the user that the save is complete.

[1334] Output: New specification data stored in the database

[1335] Step 8:

[1336] The server preprocesses the specification.

[1337] Input: New specification data stored in the database

[1338] How it works: The server uses natural language processing (NLP) techniques to analyze and format text data, specifically removing unnecessary spaces within sentences and converting them into a specific format.

[1339] Output: Preprocessed specification data

[1340] Step 9:

[1341] The server parses the specification and extracts the important elements.

[1342] Input: Preprocessed specification data

[1343] How it works: The server uses NLP technology to analyze the contents of the specification, extract important elements such as functional and non-functional requirements, and organize them into a tree data structure.

[1344] Output: Extracted important element data

[1345] Step 10:

[1346] The server generates the optimal verification items.

[1347] Input: Trained AI model and extracted key element data

[1348] How it works: The server uses a trained AI model to automatically generate optimal verification items based on new specifications, while also referring to the verification items and required time for similar functions in the past.

[1349] Output: Generated verification item list data

[1350] Step 11:

[1351] The server presents the generated list of verification items to the user.

[1352] Input: Generated verification item list data

[1353] How it works: The server presents a list of validation items to the user through a user interface, allowing the user to review and download the list and provide feedback.

[1354] Output: A list of validation items presented to the user

[1355] Step 12:

[1356] An emotion engine recognizes the user's emotional state.

[1357] Input: User input data and operation logs

[1358] Behavior: The emotion engine determines the user's emotional state based on their typing speed, selected words, and frequency of actions.

[1359] Output: User's emotional state data

[1360] Step 13:

[1361] The server adjusts the priority of verification items based on emotional state data.

[1362] Input: User's emotional state data

[1363] How it works: Based on the emotional state data, the server prioritizes the most important verification items and aims to resolve them quickly. It also displays support messages so that the user can proceed with the work with peace of mind.

[1364] Output: Priority adjusted verification item list data

[1365] The above is the flow of specific processing steps of the program of this system.

[1366] (Application example 2)

[1367] 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."

[1368] Conventional systems clean data, extract features, and train AI models, but they have a problem in that they are unable to consider the user's emotional state when generating optimal verification items for new specifications. In particular, when the user is feeling nervous or stressed, they are unable to provide appropriate support, making it difficult to achieve an efficient verification process.

[1369] 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.

[1370] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train an AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; a means for recognizing the emotional state of the user using an emotion engine; a means for the server to adjust the urgency and priority of the verification items based on the emotional state; and a means for the server to present the generated list of verification items to the user. This enables an adaptive and efficient verification process that takes the user's emotional state into consideration.

[1371] "Existing system specifications" are documents and data that explain the technical information, design, and operational details of the current operational system.

[1372] "User characteristics" refers to information including the behavioral patterns and operation tendencies of users who use the system, as well as their past usage history.

[1373] A "trouble case" is a record of details of problems or errors that occurred during system operation and their resolution.

[1374] "Past verification items" refers to information about the contents and results of system tests that have been previously conducted.

[1375] "Time required" is a record of the amount of time required to complete a particular task or verification item.

[1376] An "AI model" is an artificial intelligence algorithm trained through machine learning or deep learning and used to automate or optimize a specific task.

[1377] "Specifications for new functions" refers to documents and data that contain detailed design and operational information regarding newly added functions and changes.

[1378] "Important elements" are information that should be given special importance in verification, such as system requirements and constraints extracted from new specifications.

[1379] An "emotion engine" is a technology that analyzes a user's operation log and input data to recognize and estimate their emotional state.

[1380] "Adjusting the urgency and priority of verification items" means optimizing the importance of items to be verified and the order of processing based on the emotional state of the user.

[1381] This invention is a system that uses a smart verification support robot to generate and implement optimal verification items by making full use of AI and an emotion engine when new machinery is introduced in a factory or an existing line system is updated. This system is composed of the following elements.

[1382] System Configuration

[1383] 1. Data entry method:

[1384] The user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system. The input is done by filling out a form or uploading a file.

[1385] The server stores the input data in storage.

[1386] 2. Data preprocessing:

[1387] The server cleans the input data, removing incomplete and duplicate data and standardizing the data format. It also fills in outliers and missing values.

[1388] 3. Feature extraction and AI model training:

[1389] The server extracts important features from the cleaned data and trains the AI ​​model using machine learning frameworks such as TensorFlow and Keras.

[1390] Validate the AI ​​model and evaluate its accuracy.

[1391] 4. New specification analysis methods:

[1392] A user uploads a specification for a new feature into the system.

[1393] The server uses natural language processing (NLP) to analyze the specifications, extract and structure key elements.

[1394] 5. How to generate verification items:

[1395] The server generates optimal verification items based on the trained AI model and analysis data of the specifications. It also automatically generates specific checklists and test content by referring to the verification items and required time of past similar functions.

[1396] 6. Introducing the Emotion Engine:

[1397] It uses an emotion engine that recognizes the user's emotions. It analyzes input data and operation logs to determine the user's emotional state.

[1398] The server adjusts the urgency and priority of the verification items based on data from the emotion engine. If the user is feeling nervous or stressed, it will prioritize verification items with high importance and display appropriate support messages.

[1399] 7. Method of presenting verification items:

[1400] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, which is used to continuously improve the system.

[1401] Specific processing examples

[1402] For example, if a new robot arm operation control function is introduced in a factory, the user uploads the specifications for the "new robot arm operation control function" to the system. The server extracts important elements such as "operation speed control" and "emergency stop function" from the specifications, and the AI ​​model generates verification items such as "speed control response time test" and "emergency stop signal reaction time test." The emotion engine detects the user's stress level, adjusts priorities, and presents the user with an appropriate list of verification items.

[1403] Prompt Sentence Examples

[1404] "Upload a specification for the user profile customization feature. We then extract key elements based on the specification. Combined with user sentiment data, we generate a list of optimal validation items. The list is then prioritized based on the stress of the user experience."

[1405] The system enables an adaptive and efficient verification process that takes into account the user's emotional state.

[1406] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1407] Step 1:

[1408] The user inputs the existing system specifications, user characteristics, past failure cases, past verification items, and required time.

[1409] Input is provided by the user through form entry or file upload from the terminal. The input data is saved in the server's storage. The output is a dataset saved on the server.

[1410] Step 2:

[1411] The server performs pre-processing on the input data.

[1412] Specifically, data cleaning is performed to remove incomplete and duplicate data, standardize data formats, and impute outliers and missing values. The output is a clean and consistent dataset.

[1413] Step 3:

[1414] The server extracts features from the cleaned data.

[1415] Features are important data points used to train AI models. Machine learning frameworks (e.g., TensorFlow or Keras) are used to extract features from data. The output is a set of features.

[1416] Step 4:

[1417] The server uses the extracted features to train an AI model.

[1418] The training step involves splitting the dataset into a training set and a validation set and optimizing the model parameters. Once training is complete, the model is validated to evaluate its accuracy and performance. The output is a trained AI model.

[1419] Step 5:

[1420] A user uploads a specification for a new feature into the system.

[1421] When a user uploads a new specification file from their terminal, it is saved on the server. The output is the new specification data.

[1422] Step 6:

[1423] The server parses the new specification using natural language processing (NLP).

[1424] During the analysis process, the text data is cleaned, tokenized, and parsed. Important elements (e.g., functional requirements and constraints) are extracted and converted into a structured format such as tree data. The output is the data of the analyzed important elements.

[1425] Step 7:

[1426] The server generates optimal verification items based on the trained AI model and analyzed specifications.

[1427] It automatically generates specific checklists and test content by referring to the verification items and required time of similar functions in the past. If necessary, an estimate of the required time is also provided. The output is a list of generated verification items.

[1428] Step 8:

[1429] An emotion engine is introduced to recognize user emotions.

[1430] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and operation log. The input is the user's operation log and input data, and the output is the user's emotional state data.

[1431] Step 9:

[1432] The server adjusts the urgency and priority of verification items based on the recognized emotional state data.

[1433] Specifically, if the user feels nervous or stressed, the system will prioritize the most important verification items and promptly resolve them. It also displays support messages as needed to help the user proceed with their work with peace of mind. The output is a list of adjusted verification items.

[1434] Step 10:

[1435] The server presents the generated list of verification items to the user.

[1436] The list is displayed through a user interface, allowing users to review and download the verification item list and provide feedback, which allows the system to continuously improve. The output is the verification item list and user feedback.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] [Fourth embodiment]

[1441] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1442] 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.

[1443] 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).

[1444] 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.

[1445] 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.

[1446] 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).

[1447] 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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."

[1454] The present embodiment will now be described in natural language with respect to the processing of the system and its programs.

[1455] System Overview

[1456] This invention relates to a system that proposes optimal verification items when implementing new functions, using an AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[1457] Data input and training

[1458] 1. The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and the required time.

[1459] Data entry is done through methods such as file upload and form filling.

[1460] Immediately after the data is uploaded, the server performs data cleaning as a pre-processing of the data.

[1461] 2. The server receives the input data and trains the AI ​​model.

[1462] First, the server performs data cleaning to remove incomplete data and duplicates.

[1463] Next, feature extraction is performed to extract important features of each data.

[1464] The server uses these features to train an AI model and validate the model.

[1465] Entering and parsing new specifications

[1466] 3. The user uploads a specification for a new feature into the system.

[1467] The server performs preprocessing of the text data to ensure a consistent format for the specification.

[1468] 4. The server parses the new specification and extracts the important elements.

[1469] The server analyzes the text using natural language processing (NLP) techniques.

[1470] From the analysis results, important elements (e.g., functional requirements and non-functional requirements) are extracted and structured.

[1471] Generation and presentation of verification items

[1472] 5. The server generates optimal verification items based on the learned data and analyzed specifications.

[1473] The server references past data and automatically generates optimal verification items based on new specifications.

[1474] The generated verification items also include an estimate of the time required for each.

[1475] 6. The server presents the generated list of verification items to the user.

[1476] The results are displayed through the user interface, and the user can create a verification plan based on the list.

[1477] The list can be downloaded in CSV or Excel format, and suggestions for improving items are also accepted via the feedback function.

[1478] Specific examples

[1479] Added new feature "User profile customization function"

[1480] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1481] 2. The server uses this data to train the AI ​​model.

[1482] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1483] 4. The server analyzes the new specifications and extracts important elements such as the ability to change profile pictures and edit self-introductions.

[1484] 5. Based on the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." It also provides an estimate of the time required for each verification item.

[1485] 6. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1486] This reduces the risk of manual creation of verification items and errors, enabling efficient and high-quality software development.

[1487] The processing flow will be explained below.

[1488] Step 1:

[1489] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[1490] Step 2:

[1491] The server preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values.

[1492] Step 3:

[1493] The server then performs feature extraction from the cleaned data. This is the process of extracting important features necessary for training the machine learning model. For example, this includes user characteristics and specific patterns of failure cases.

[1494] Step 4:

[1495] The server uses the feature-extracted data to train the AI ​​model. Deep learning and other machine learning techniques are used to build the model from past data. During this process, the model parameters are optimized.

[1496] Step 5:

[1497] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy and effectiveness, and retrains the model if necessary.

[1498] Step 6:

[1499] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[1500] Step 7:

[1501] The server preprocesses the new specification, using natural language processing (NLP) to parse the text data and standardize the format.

[1502] Step 8:

[1503] The server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract and structure elements from the text. This process leverages techniques such as concrete text classification and named entity recognition (NER).

[1504] Step 9:

[1505] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content, taking into account the verification items and required time of past similar functions.

[1506] Step 10:

[1507] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[1508] As described above, this system involves the processes of sequential data input, analysis, model learning, and verification item generation, making it possible to provide efficient and highly accurate verification items when implementing new functions.

[1509] Example 1

[1510] 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."

[1511] In traditional software development, verification items must be created manually every time a new feature is added, which takes time and effort. Furthermore, creating verification items manually is prone to errors, which can have a negative impact on software quality. Furthermore, it is difficult to generate verification items that fully reflect past failure cases and user characteristics, which can result in a lack of comprehensiveness in verification.

[1512] 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.

[1513] In this invention, the server includes means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times, means for the server to learn the input data and train a machine learning model, means for a user to input specifications for new functions, means for the server to analyze the new specifications and extract important elements, means for the server to generate optimal verification items based on the learned data and the analyzed specifications, means for the server to present the generated list of verification items to the user, and means for the server to save and export the generated list of verification items in a downloadable format, thereby enabling efficient and accurate generation and presentation of verification items.

[1514] plaintext

[1515] "User" refers to an individual or group that operates the system and inputs data such as existing system specifications and specifications for new features.

[1516] "Server" refers to the central computer system that processes, manages, learns, and analyzes data, and generates and presents validation items to the user.

[1517] "Existing system specifications" refers to detailed descriptions of the function, structure, and design of systems currently in operation.

[1518] "User characteristics" refers to information related to users, such as the behavior and attributes of users who use the system.

[1519] "Failure cases" refer to records and details of malfunctions or problems that occurred during system operation.

[1520] "Past verification items" refers to information about the verification content and details of systems and functions that have been previously conducted.

[1521] "Time required" refers to the time required to perform a particular verification item.

[1522] A "machine learning model" is a group of algorithms that are trained to automatically perform specific tasks by studying data.

[1523] "Specification" refers to a document that details new features and improvements.

[1524] "Key elements" refer to functional and non-functional requirements that deserve special attention within the specification.

[1525] "Natural language processing" refers to the technology that allows computers to analyze and understand human language.

[1526] "Verification items" refer to specific verification procedures or checkpoints that are implemented to confirm the accuracy and reliability of a system or function.

[1527] "User interface" refers to the screens, controls, and navigation that allow a user to interact with a system.

[1528] "Export" means to store or provide data or information in another format.

[1529] MODE FOR CARRYING OUT THE INVENTION

[1530] The system and its program processing of this invention are described in detail below. The hardware used includes a server and a user terminal. The software used includes Python, pandas, Scikit-learn, TensorFlow, PyTorch, NLTK, spaCy, etc. This enables efficient and accurate generation and presentation of verification items.

[1531] Overall system flow

[1532] This invention is a system that proposes optimal verification items when implementing new functions, using a generative AI model that has learned the overall service specifications, user characteristics, past failure cases, past verification items, and required times.

[1533] Data input and training

[1534] 1. User enters existing data

[1535] The user inputs the existing system specifications, user characteristics, failure cases, past verification items, and required time into the system. This operation is performed through the file selection window on the terminal, and uploading of CSV or Excel files is recommended. When the user selects the file and clicks the upload button, the server receives this data.

[1536] 2. The server performs data cleaning and feature extraction

[1537] The server performs data cleaning based on the received data. It uses the Python pandas library to remove invalid values ​​and duplicate data and to fill in missing data. It then uses Scikit-learn to extract features. For example, numerical and categorical features are calculated and used in the next step.

[1538] 3. The server trains the machine learning model

[1539] The server uses the data after cleaning and feature extraction to train a machine learning model using frameworks such as TensorFlow or PyTorch. After training, the accuracy of the model is validated using test data. The results are recorded in a log.

[1540] Entering and parsing new specifications

[1541] 4. User uploads new specification

[1542] The user uploads a specification for a new feature to the system. This is done on the device, and the specification format is recommended as PDF or DOCX. The user selects the file and clicks the upload button, and the server receives the specification.

[1543] 5. The server preprocesses the specification

[1544] The server preprocesses the received specification using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters, converting it into a format suitable for analysis.

[1545] 6. The server analyzes the specification and extracts important elements

[1546] After preprocessing, the server uses NLP techniques to analyze the specifications and extract important elements (e.g., functional and non-functional requirements). The extracted data is structured and used in subsequent steps.

[1547] Generation and presentation of verification items

[1548] 7. The server generates the validation items

[1549] The server uses the trained AI model to generate verification items based on past data and new specifications. For example, for the "profile photo change function," "image format check" and "size restriction check" are automatically generated. Each verification item also includes an estimated time required.

[1550] 8. The server presents a list of verification items

[1551] The generated list of verification items is presented to the user through a user interface. The user can view and download the list, save it in CSV or Excel format, and use the feedback function to add comments to the verification items.

[1552] Specific examples

[1553] Added new feature "User profile customization function"

[1554] 1. The user inputs historical data such as the specifications of the existing system and failure cases into the system.

[1555] 2. The server uses this data to train an AI model. Specifically, it uses Python's pandas to clean the data and extract features. Then, it uses TensorFlow to train and validate the model.

[1556] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1557] 4. The server analyzes the new specifications and extracts important elements such as the ability to change the profile picture and edit the self-introduction. The NLP technology used is spaCy.

[1558] 5. Based on the results of the analysis of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" and "checking the character limit for the self-introduction," and estimates the time required for each.

[1559] 6. The server presents the generated list of verification items to the user through the user interface and makes it available for download as a CSV file. The user interface also has a function for sending feedback.

[1560] Prompt Sentence Examples

[1561] Enter specifications for user profile customization features, such as changing your profile picture or editing your bio.

[1562]

[1563] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1564] plaintext

[1565] Step 1:

[1566] The user uploads data on existing system specifications, user characteristics, failure cases, past verification items, and required time from their terminal to the system. Input is done in CSV or Excel format files. Once the file is uploaded, the server receives it and prepares it for data cleaning. Clean data is obtained as output.

[1567] Step 2:

[1568] The server performs data cleaning on the received data, specifically using the Python pandas library to remove invalid values ​​and duplicate data and properly impute missing data. The input is the raw data uploaded in step 1, and the output is a clean data frame.

[1569] Step 3:

[1570] The server extracts features based on the clean data. For this, it uses Scikit-learn to extract numerical and categorical features. For example, age and frequency of use can be extracted as features from user characteristic data. The input is clean data, and features are obtained as output.

[1571] Step 4:

[1572] The server uses the features to train a machine learning model. The frameworks used are TensorFlow and PyTorch. The feature data is used as training data to train the model. The accuracy of the model is validated with test data and the results are recorded. The input is the feature data, and the output is a trained model.

[1573] Step 5:

[1574] The user uploads a specification for a new feature to the system. The input is a PDF or DOCX file, which the user selects from their terminal and clicks the upload button. Once the file is uploaded, the server prepares the specification for preprocessing.

[1575] Step 6:

[1576] The server receives new specifications and preprocesses them using natural language processing (NLP) techniques, such as NLTK and spaCy, to tokenize and normalize the text and remove extra whitespace and special characters. The input is the uploaded specification, and the output is the preprocessed text data.

[1577] Step 7:

[1578] The server analyzes the preprocessed text data and extracts important elements. Important elements refer to functional and non-functional requirements, for example. The input is the preprocessed text data, and the extracted important elements are obtained as the output.

[1579] Step 8:

[1580] The server uses the trained AI model to generate optimal verification items based on new specifications. For example, it automatically generates "image format checks" and "size restriction checks" for the "profile photo change function" from past data and new specifications. Each verification item also has an estimated time required. The input is the extracted important elements, and the output is a list of generated verification items.

[1581] Step 9:

[1582] The server presents the generated list of verification items to the user. The list is displayed through the user interface, and the user can view and download it. The list can be saved in CSV or Excel format, and the user can add comments to the items using the feedback function. The input is the generated list of verification items, and the presented list is provided to the user as the output.

[1583] (Application example 1)

[1584] 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."

[1585] The selection of verification items when implementing new functions in factory robots is usually done manually, which is inefficient and carries a high risk of error. Furthermore, if past failure cases and user characteristics are not sufficiently taken into consideration, the quality of the verification may be affected. There is a need for a method to solve these problems and automate the generation of efficient, high-quality verification items.

[1586] 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.

[1587] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train a generative AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; and a means for the server to present the generated verification item list to the user and display it on a smartphone in real time. This enables efficient automatic generation of high-quality verification items when implementing new functions in factory robots.

[1588] A "user" is an entity that inputs system specifications, failure cases, verification items, etc. into the system and submits specifications for new functions.

[1589] A "system specification" is a collection of technical details and operational requirements for an existing system.

[1590] "User characteristics" refers to information about the attributes and behavioral norms of individual users and user groups who use the system.

[1591] "Failure cases" are specific examples of system problems or errors that have occurred in the past.

[1592] "Verification items" are test items used to verify whether new features or changes to the system work properly.

[1593] "Required time" is the estimated time required to execute each verification item.

[1594] The "server" is a central computer that stores and analyzes input data and trains generative AI models.

[1595] A "generative AI model" is an artificial intelligence model that is trained based on input data and is used to suggest optimal verification items for a system.

[1596] A "specification for new features" is a document that describes the technical details and operational requirements of a newly implemented feature.

[1597] "Natural language processing" is a technology that analyzes text data and extracts important elements.

[1598] "Real-time display" is a function that instantly displays the generated verification item list on the user's device.

[1599] A "smartphone" is a mobile device used to display the generated verification item list.

[1600] The system and its program processing will be described in the embodiment for carrying out the present invention.

[1601] System Overview

[1602] In this system, users input existing system specifications, user characteristics, failure cases, past verification items, and required time, and the server learns from this data to train a generative AI model. Furthermore, specifications for new functions are input, and the system analyzes the specifications to extract important elements and generate optimal verification items. The generated list of verification items is displayed on a smartphone in real time.

[1603] Data input and training

[1604] Users input existing system specifications, failure cases, past verification items, and required time into the system via CSV files or form input. This data is stored on a cloud server (e.g., AWS, Google Cloud).

[1605] The server cleans the input data (removing missing values ​​and duplicates) and extracts features. It then trains a generative AI model using a machine learning library such as scikit-learn. Validation of the model is also performed at the same time.

[1606] Entering and parsing new specifications

[1607] Users upload specifications for new robot functions from their smartphones, and the server analyzes the specifications using natural language processing (NLP) technology to extract key elements.

[1608] Generation and presentation of verification items

[1609] The server estimates the optimal verification items and required time based on the learned data and analyzed specifications, and generates a list of verification items. This list is displayed in real time on the smartphone, and the user can check and download it.

[1610] Specific examples

[1611] For example, when implementing an "obstacle avoidance function" for a new robot, the user uploads past specifications and failure cases in a CSV file. The server uses this information to train the AI ​​model. Next, the user uploads the "specifications for the new obstacle avoidance function," and the server analyzes the specifications. Based on this analysis, verification items such as "verification of the maximum detection distance of the distance sensor" and "verification of operating speed" are automatically generated.

[1612] Example prompt sentence:

[1613] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[1614] "Please upload a specification for the obstacle avoidance function of your new robot."

[1615] This makes it possible to automatically generate efficient, high-quality verification items when implementing new functions in factory robots.

[1616] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1617] Step 1:

[1618] The user inputs existing system specifications, user characteristics, failure cases, past verification items, and required time into the system via a CSV file or form input.

[1619] Input: Existing system specifications, user characteristics, failure cases, past verification items, required time

[1620] Output: Data stored on the server

[1621] Specific operation: The user selects a CSV file and uploads it to the system. If necessary, the user can also enter data directly into the form. The data is then saved to the cloud server.

[1622] Step 2:

[1623] The server performs data cleaning based on the input data.

[1624] Input: Data saved in step 1

[1625] Output: Cleaned data

[1626] Specific operation: The server uses the pandas library to remove missing values ​​and duplicates from the data and format the data.

[1627] Step 3:

[1628] The server performs feature extraction using the cleaned data.

[1629] Input: Cleaned data

[1630] Output: Feature data

[1631] Specific operation: The server uses scikit-learn's CountVectorizer to digitize the text data and extract features.

[1632] Step 4:

[1633] The server uses the feature data to train a generative AI model.

[1634] Input: Feature data

[1635] Output: Generative AI model

[1636] Specific operation: The server trains and learns the model using algorithms such as scikit-learn's RandomForestClassifier.

[1637] Step 5:

[1638] A user uploads a specification for a new feature to the system from their smartphone.

[1639] Input: Specification for new feature

[1640] Output: The new specification saved on the server.

[1641] Specific operation: The user selects a specification file and uploads it to the system, where it is stored on the cloud server.

[1642] Step 6:

[1643] The server analyzes the new specification using natural language processing to extract important elements.

[1644] Input: New Specification

[1645] Output: Important elements parsed

[1646] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text of the specification and extract important elements such as functional and non-functional requirements.

[1647] Step 7:

[1648] The server generates optimal verification items based on the learned data and analyzed specifications.

[1649] Input: analyzed key elements, generative AI model

[1650] Output: Optimal test list and estimated time required

[1651] Specific operation: The server correlates historical data with the elements of the new specification, generates optimal verification items, and assigns an estimated time for each.

[1652] Step 8:

[1653] The server presents the generated list of verification items to the user and displays it on the smartphone in real time.

[1654] Input: List of optimal verification items, estimated time required

[1655] Output: A list of verification items displayed on the user's smartphone

[1656] Specific operation: The server displays the generated list of verification items on the user's smartphone in real time and also makes it possible to download it if necessary.

[1657] Example prompt sentence:

[1658] "Please upload past validation data (numerical and textual) for the robot's obstacle detection system."

[1659] "Please upload a specification for the obstacle avoidance function of your new robot."

[1660] 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.

[1661] System Overview

[1662] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time, and the server learns the input data to train an AI model. In addition to this system, a user can input specifications for new functions, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications. Furthermore, the present invention combines an emotion engine that recognizes user emotions to achieve more effective and adaptive generation of verification items.

[1663] Data input and training

[1664] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, and past verification items and required time. The user provides this data by filling out a form or uploading a file. Once the input is complete, the server confirms receipt of the data and saves it in the data storage.

[1665] Next, the server preprocesses the input data. Specifically, it cleans the data. It removes incomplete and duplicate data and standardizes data formats. It also complements outliers and missing values. After this, the server performs feature extraction and extracts important features from each piece of data. These features are used to train an AI model and validate the model.

[1666] Entering and parsing new specifications

[1667] Users upload specifications for new features to the system. The server receives the specifications, stores them in a database, and then performs preprocessing, parsing the text data using natural language processing (NLP) and standardizing the format.

[1668] Next, the server analyzes the content of the specification and extracts important elements (e.g., functional and non-functional requirements). NLP techniques are used to extract elements from the text and structure them. The extracted important elements are organized into a tree data structure or similar.

[1669] Generation and presentation of verification items

[1670] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time for similar functions in the past. The generated verification items also include an estimate of the required time for each item.

[1671] The server presents the generated list of validation items to the user through a user interface, which the user can review and download, and can provide feedback based on which the system can be continuously improved.

[1672] Combining Emotion Engines

[1673] To recognize user emotions, an emotion engine is combined. This emotion engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, selected words, frequency of operations, etc.

[1674] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. Specifically, if the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and ensure their resolution is prompt. It also displays support messages as appropriate so that the user can proceed with their work with peace of mind.

[1675] Specific examples

[1676] Example of adding the new feature "User profile customization function"

[1677] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1678] 2. The server uses this data to train and validate the AI ​​model.

[1679] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1680] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[1681] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[1682] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[1683] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1684] In this way, by combining emotion engines, a system can be realized that takes into account the user's emotional state and provides more effective and adaptive verification items.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] The user logs in to the system. After logging in, the user enters the existing system specifications, user characteristics, past failure cases, past verification items and the required time into the system. Data entry is done by uploading files or filling in forms. Once the user has completed the data entry, the server receives the data and stores it in storage.

[1688] Step 2:

[1689] The server preprocesses the input data, cleaning it by removing incomplete and duplicate data, filling in missing values, and standardizing the data format.

[1690] Step 3:

[1691] The server extracts features from the cleaned data. Important features are analyzed and used to train the machine learning model. Features include user characteristics, specific patterns of failure cases, and details of past verification items.

[1692] Step 4:

[1693] The server uses the extracted features to train an AI model, applying deep learning and other machine learning techniques to optimize the model parameters.

[1694] Step 5:

[1695] The server validates the trained AI model, compares it with past validation results to evaluate the model's accuracy, and retrains the AI ​​model if necessary.

[1696] Step 6:

[1697] A user uploads a specification for a new feature to the system. The server receives the specification and stores it in a database.

[1698] Step 7:

[1699] The server preprocesses the new specification, using natural language processing (NLP) techniques to analyze the text data and standardize the format of the specification.

[1700] Step 8:

[1701] The server analyzes the content of the specification and extracts important elements. Specifically, it uses named entity recognition (NER) to extract important elements such as functional and non-functional requirements from the specification and organizes them into a structure.

[1702] Step 9:

[1703] The server generates optimal verification items based on the trained AI model and analyzed specification data. It automatically generates specific checklists and test content by referring to the verification items and required times of past similar functions.

[1704] Step 10:

[1705] The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. For example, it analyzes the input speed, the content of selected words, click frequency, etc. to determine the user's current emotional state.

[1706] Step 11:

[1707] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user feels nervous or frustrated, it will prioritize verification items with high importance and promptly resolve them. It will also display support messages as needed.

[1708] Step 12:

[1709] The server presents the generated list of verification items to the user through a user interface. The user can create a verification plan based on this list. The list of verification items can also be downloaded in CSV or Excel format, and the user can provide feedback on the results.

[1710] In this way, by combining it with an emotion engine, the system can generate effective and efficient verification items while taking into account the user's emotional state.

[1711] Example 2

[1712] 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."

[1713] Modern software systems are becoming increasingly complex, making verification work extremely important when adding or modifying new features. However, traditional methods often require manually generating verification items, which can lead to human error and effort. Furthermore, user emotions and tension can affect the efficiency of verification, so a flexible system that can accommodate these factors is needed.

[1714] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; means for the server to learn the input data and train the AI ​​model; means for a user to input specifications for new functions; means for the server to analyze the new specifications and extract important elements; means for the server to generate optimal verification items based on the learned data and the analyzed specifications; means for the server to present the generated list of verification items to the user; means for an emotion engine to determine the user's emotional state; and means for the server to adjust the priority of the verification items based on the emotion data. This enables efficient automatic generation of verification items and the presentation of adaptive verification items corresponding to the user's emotions.

[1715] Understood. Below are definitions of important terms contained in the claims:

[1716] An "existing system specification" is a document that details how a currently operational system operates.

[1717] "User characteristics" refers to the characteristics and behavioral patterns of a particular user or user group.

[1718] "Failure cases" refer to cases of trouble or malfunction that have occurred in the system in the past.

[1719] "Past verification items" means evaluation criteria or checklists used in previous verification or testing of the system.

[1720] "Time required" refers to the amount of time required to complete a particular task or process.

[1721] "Means" refers to methods or techniques for achieving a specific purpose.

[1722] A "server" refers to a computer system that processes requests from clients on a network and provides data and services.

[1723] "Learning from input" is the process by which machine learning algorithms learn patterns and trends based on the data you provide them.

[1724] An "AI model" refers to a set of algorithms designed to automate a specific task using artificial intelligence techniques.

[1725] "Training" refers to the process of feeding an AI model data to teach it to recognize patterns and improve its performance.

[1726] A "specification for new functions" is a document that details the functions that will be newly added to the system.

[1727] "Analysis" refers to the process of breaking down specific data or information into more understandable detail.

[1728] "Critical elements" refer to information or components found in the analyzed data that are particularly important to a system or function.

[1729] "Optimal verification items" refer to the most appropriate tests and checkpoints to ensure the quality of a system or function.

[1730] "Emotion engine" refers to an algorithm or program that analyzes and identifies a user's emotional state.

[1731] "Adjusting priorities" refers to changing the order in which tasks or items are performed depending on their importance and the situation.

[1732] The present invention is a system in which a user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system, and the server learns the input data to train an AI model. Also, specifications for new functions are input, and the server analyzes the specifications to extract important elements and generates optimal verification items based on the learned data and analyzed specifications.

[1733] System configuration

[1734] The system consists of a user terminal and a server. An interface for users to input data is placed on the user terminal, and the input data is processed by the server. The server has a database and stores and processes the input data. The server also incorporates an AI model that implements machine learning algorithms and natural language processing (NLP) technology.

[1735] Hardware and software used

[1736] Hardware:

[1737] User devices (PCs, tablets, smartphones, etc.)

[1738] A server (with a powerful processor, sufficient memory and storage)

[1739] software:

[1740] Database management systems (e.g., MySQL, PostgreSQL)

[1741] Natural language processing tools (e.g., NLTK, spaCy)

[1742] Machine learning frameworks (e.g. TensorFlow, PyTorch)

[1743] User interface (e.g. web browser, dedicated application)

[1744] Program processing flow

[1745] Data input and training

[1746] The user logs in to the system and enters the existing system specifications, user characteristics, past failure cases, past verification items and required time. The user provides this data to the system by filling in forms or uploading files. Once the input is complete, the server confirms receipt of the data and saves it in the database.

[1747] The server then preprocesses the input data. Specifically, it cleans the data, removes incomplete and duplicate data, standardizes data formats, and fills in outliers and missing values. The server then extracts features and trains an AI model. Deep learning frameworks such as TensorFlow and PyTorch are used for training.

[1748] Entering and parsing new specifications

[1749] A user uploads a specification for a new feature to the system. The server receives the uploaded specification, stores it in a database, and then performs preprocessing. NLP techniques are used to parse the specification text and standardize the format.

[1750] The server then analyzes the content of the specification and extracts important elements (functional and non-functional requirements), which are then organized into a tree data structure.

[1751] Generation and presentation of verification items

[1752] The server generates optimal verification items based on the trained AI model and analyzed specification data. Specific checklists and test content are automatically generated, taking into account the verification items and required time of past similar functions. Each of these verification items also includes an estimated required time.

[1753] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, allowing the system to continually improve.

[1754] Combining Emotion Engines

[1755] The system is equipped with an emotion engine that recognizes the user's emotions. This engine analyzes the user's input data and operation logs to determine the user's emotional state. For example, emotions are recognized from the speed of text input, the words selected, and the frequency of operations.

[1756] The server adjusts the urgency and priority of verification items based on emotional state data from the emotion engine. If the user is in a state of tension or dissatisfaction, it will prioritize verification items with high importance and aim for a quick resolution. It also displays support messages as appropriate so that the user can proceed with the work with peace of mind.

[1757] Specific examples

[1758] Example of adding the new feature "User profile customization function"

[1759] 1. The user inputs existing system specifications and historical data such as failure cases into the system.

[1760] 2. The server uses this data to train and validate the AI ​​model.

[1761] 3. The user uploads the new specification for the "User Profile Customization Function" to the system.

[1762] 4. The server analyzes the specifications and extracts and structures important elements such as the "function to change profile picture" and the "function to edit self-introduction."

[1763] 5. Based on the analysis results of the learning data and specifications, the server generates verification items such as "checking the image format when changing the profile picture" or "checking the character limit for the self-introduction." Each verification item is also assigned an estimated time required.

[1764] 6. The emotion engine analyzes the user's input data and operation logs to recognize the user's emotional state. The server uses this emotional data to adjust the priority of verification items as needed.

[1765] 7. The server presents the generated list of verification items to the user through the user interface, and the user can use this as a basis to create a verification plan.

[1766] Example prompts:

[1767] I have uploaded a specification for a new user feature. I would like to add a "user profile customization feature." Please generate optimal verification items based on the current system specifications, past failure cases, verification items, and required time.

[1768] As described above, the present invention efficiently trains an AI model based on data provided by users, analyzes new specifications, and generates optimal verification items. Furthermore, by adjusting the priority of verification items based on user sentiment, more adaptive and effective verification can be achieved.

[1769] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1770] Step 1:

[1771] The user enters existing data.

[1772] Input: Existing system specifications, user characteristics, past failure cases, past verification items and required time

[1773] How it works: A user logs into the system and enters data via a form or file upload.

[1774] Output: The input data is sent to the server.

[1775] Step 2:

[1776] The server receives and stores the data.

[1777] Input: Existing data entered by the user

[1778] Operation: The server saves the received data in the database and notifies the user with a message asking them to confirm the save.

[1779] Output: Existing data stored in the database

[1780] Step 3:

[1781] The server preprocesses the data.

[1782] Input: Existing data stored in a database

[1783] How it works: The server cleans the data, removes incomplete and duplicate data, standardizes data formats, and imputes outliers and missing values.

[1784] Output: Cleaned and uniformly formatted data

[1785] Step 4:

[1786] The server extracts features.

[1787] Input: Data after cleaning

[1788] How it works: The server uses data analysis tools to extract important features, such as Pandas and Scikit-learn.

[1789] Output: Extracted feature data

[1790] Step 5:

[1791] The server trains the AI ​​model.

[1792] Input: Extracted feature data

[1793] How it works: The server trains an AI model using a machine learning framework (e.g., TensorFlow, PyTorch). It also validates the model to ensure its accuracy.

[1794] Output: A trained AI model

[1795] Step 6:

[1796] A user uploads a new specification.

[1797] Input: Specification for new feature

[1798] How it works: A user uploads a new specification to the system and sends it to the server.

[1799] Output: Uploaded specification data

[1800] Step 7:

[1801] The server receives and stores the specification.

[1802] Input: New specification data uploaded by the user

[1803] Operation: The server saves the specification data to the database and notifies the user that the save is complete.

[1804] Output: New specification data stored in the database

[1805] Step 8:

[1806] The server preprocesses the specification.

[1807] Input: New specification data stored in the database

[1808] How it works: The server uses natural language processing (NLP) techniques to analyze and format text data, specifically removing unnecessary spaces within sentences and converting them into a specific format.

[1809] Output: Preprocessed specification data

[1810] Step 9:

[1811] The server parses the specification and extracts the important elements.

[1812] Input: Preprocessed specification data

[1813] How it works: The server uses NLP technology to analyze the contents of the specification, extract important elements such as functional and non-functional requirements, and organize them into a tree data structure.

[1814] Output: Extracted important element data

[1815] Step 10:

[1816] The server generates the optimal verification items.

[1817] Input: Trained AI model and extracted key element data

[1818] How it works: The server uses a trained AI model to automatically generate optimal verification items based on new specifications, while also referring to the verification items and required time for similar functions in the past.

[1819] Output: Generated verification item list data

[1820] Step 11:

[1821] The server presents the generated list of verification items to the user.

[1822] Input: Generated verification item list data

[1823] How it works: The server presents a list of validation items to the user through a user interface, allowing the user to review and download the list and provide feedback.

[1824] Output: A list of validation items presented to the user

[1825] Step 12:

[1826] An emotion engine recognizes the user's emotional state.

[1827] Input: User input data and operation logs

[1828] Behavior: The emotion engine determines the user's emotional state based on their typing speed, selected words, and frequency of actions.

[1829] Output: User's emotional state data

[1830] Step 13:

[1831] The server adjusts the priority of verification items based on emotional state data.

[1832] Input: User's emotional state data

[1833] How it works: Based on the emotional state data, the server prioritizes the most important verification items and aims to resolve them quickly. It also displays support messages so that the user can proceed with the work with peace of mind.

[1834] Output: Priority adjusted verification item list data

[1835] The above is the flow of specific processing steps of the program of this system.

[1836] (Application example 2)

[1837] 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."

[1838] Conventional systems clean data, extract features, and train AI models, but they have a problem in that they are unable to consider the user's emotional state when generating optimal verification items for new specifications. In particular, when the user is feeling nervous or stressed, they are unable to provide appropriate support, making it difficult to achieve an efficient verification process.

[1839] 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.

[1840] In this invention, the server includes: a means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required times; a means for the server to learn the input data and train an AI model; a means for a user to input specifications for new functions; a means for the server to analyze the new specifications and extract important elements; a means for the server to generate optimal verification items based on the learned data and the analyzed specifications; a means for recognizing the emotional state of the user using an emotion engine; a means for the server to adjust the urgency and priority of the verification items based on the emotional state; and a means for the server to present the generated list of verification items to the user. This enables an adaptive and efficient verification process that takes the user's emotional state into consideration.

[1841] "Existing system specifications" are documents and data that explain the technical information, design, and operational details of the current operational system.

[1842] "User characteristics" refers to information including the behavioral patterns and operation tendencies of users who use the system, as well as their past usage history.

[1843] A "trouble case" is a record of details of problems or errors that occurred during system operation and their resolution.

[1844] "Past verification items" refers to information about the contents and results of system tests that have been previously conducted.

[1845] "Time required" is a record of the amount of time required to complete a particular task or verification item.

[1846] An "AI model" is an artificial intelligence algorithm trained through machine learning or deep learning and used to automate or optimize a specific task.

[1847] "Specifications for new functions" refers to documents and data that contain detailed design and operational information regarding newly added functions and changes.

[1848] "Important elements" are information that should be given special importance in verification, such as system requirements and constraints extracted from new specifications.

[1849] An "emotion engine" is a technology that analyzes a user's operation log and input data to recognize and estimate their emotional state.

[1850] "Adjusting the urgency and priority of verification items" means optimizing the importance of items to be verified and the order of processing based on the emotional state of the user.

[1851] This invention is a system that uses a smart verification support robot to generate and implement optimal verification items by making full use of AI and an emotion engine when new machinery is introduced in a factory or an existing line system is updated. This system is composed of the following elements.

[1852] System Configuration

[1853] 1. Data entry method:

[1854] The user inputs existing system specifications, user characteristics, past failure cases, past verification items, and required time into the system. The input is done by filling out a form or uploading a file.

[1855] The server stores the input data in storage.

[1856] 2. Data preprocessing:

[1857] The server cleans the input data, removing incomplete and duplicate data and standardizing the data format. It also fills in outliers and missing values.

[1858] 3. Feature extraction and AI model training:

[1859] The server extracts important features from the cleaned data and trains the AI ​​model using machine learning frameworks such as TensorFlow and Keras.

[1860] Validate the AI ​​model and evaluate its accuracy.

[1861] 4. New specification analysis methods:

[1862] A user uploads a specification for a new feature into the system.

[1863] The server uses natural language processing (NLP) to analyze the specifications, extract and structure key elements.

[1864] 5. How to generate verification items:

[1865] The server generates optimal verification items based on the trained AI model and analysis data of the specifications. It also automatically generates specific checklists and test content by referring to the verification items and required time of past similar functions.

[1866] 6. Introducing the Emotion Engine:

[1867] It uses an emotion engine that recognizes the user's emotions. It analyzes input data and operation logs to determine the user's emotional state.

[1868] The server adjusts the urgency and priority of the verification items based on data from the emotion engine. If the user is feeling nervous or stressed, it will prioritize verification items with high importance and display appropriate support messages.

[1869] 7. Method of presenting verification items:

[1870] The server presents the generated list of verification items to the user through a user interface, where the user can review and download the list and provide feedback, which is used to continuously improve the system.

[1871] Specific processing examples

[1872] For example, if a new robot arm operation control function is introduced in a factory, the user uploads the specifications for the "new robot arm operation control function" to the system. The server extracts important elements such as "operation speed control" and "emergency stop function" from the specifications, and the AI ​​model generates verification items such as "speed control response time test" and "emergency stop signal reaction time test." The emotion engine detects the user's stress level, adjusts priorities, and presents the user with an appropriate list of verification items.

[1873] Prompt Sentence Examples

[1874] "Upload a specification for the user profile customization feature. We then extract key elements based on the specification. Combined with user sentiment data, we generate a list of optimal validation items. The list is then prioritized based on the stress of the user experience."

[1875] The system enables an adaptive and efficient verification process that takes into account the user's emotional state.

[1876] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1877] Step 1:

[1878] The user inputs the existing system specifications, user characteristics, past failure cases, past verification items, and required time.

[1879] Input is provided by the user through form entry or file upload from the terminal. The input data is saved in the server's storage. The output is a dataset saved on the server.

[1880] Step 2:

[1881] The server performs pre-processing on the input data.

[1882] Specifically, data cleaning is performed to remove incomplete and duplicate data, standardize data formats, and impute outliers and missing values. The output is a clean and consistent dataset.

[1883] Step 3:

[1884] The server extracts features from the cleaned data.

[1885] Features are important data points used to train AI models. Machine learning frameworks (e.g., TensorFlow or Keras) are used to extract features from data. The output is a set of features.

[1886] Step 4:

[1887] The server uses the extracted features to train an AI model.

[1888] The training step involves splitting the dataset into a training set and a validation set and optimizing the model parameters. Once training is complete, the model is validated to evaluate its accuracy and performance. The output is a trained AI model.

[1889] Step 5:

[1890] A user uploads a specification for a new feature into the system.

[1891] When a user uploads a new specification file from their terminal, it is saved on the server. The output is the new specification data.

[1892] Step 6:

[1893] The server parses the new specification using natural language processing (NLP).

[1894] During the analysis process, the text data is cleaned, tokenized, and parsed. Important elements (e.g., functional requirements and constraints) are extracted and converted into a structured format such as tree data. The output is the data of the analyzed important elements.

[1895] Step 7:

[1896] The server generates optimal verification items based on the trained AI model and analyzed specifications.

[1897] It automatically generates specific checklists and test content by referring to the verification items and required time of similar functions in the past. If necessary, an estimate of the required time is also provided. The output is a list of generated verification items.

[1898] Step 8:

[1899] An emotion engine is introduced to recognize user emotions.

[1900] The server uses an emotion engine to recognize the user's emotional state based on the user's input data and operation log. The input is the user's operation log and input data, and the output is the user's emotional state data.

[1901] Step 9:

[1902] The server adjusts the urgency and priority of verification items based on the recognized emotional state data.

[1903] Specifically, if the user feels nervous or stressed, the system will prioritize the most important verification items and promptly resolve them. It also displays support messages as needed to help the user proceed with their work with peace of mind. The output is a list of adjusted verification items.

[1904] Step 10:

[1905] The server presents the generated list of verification items to the user.

[1906] The list is displayed through a user interface, allowing users to review and download the verification item list and provide feedback, which allows the system to continuously improve. The output is the verification item list and user feedback.

[1907] 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.

[1908] 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.

[1909] 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.

[1910] 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.

[1911] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion 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.

[1912] 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.

[1913] 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).

[1914] 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.

[1915] 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."

[1916] 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.

[1917] 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).

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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.

[1922] 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.

[1923] 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.

[1924] 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.

[1925] 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.

[1926] 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.

[1927] 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.

[1928] The following is further disclosed regarding the above embodiment.

[1929] (Claim 1)

[1930] A means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required time;

[1931] A means for the server to learn from the input data and train the AI ​​model;

[1932] a means for a user to input specifications for new functionality;

[1933] a means for the server to parse the new specification and extract important elements;

[1934] A means for the server to generate optimal verification items based on the learn...

Claims

1. A means for a user to input existing system specifications, user characteristics, failure cases, past verification items, and required time; A means for the server to learn from the input data and train the AI ​​model; a means for a user to input specifications for new functionality; a means for the server to parse the new specification and extract important elements; A means for the server to generate optimal verification items based on the learned data and the analyzed specifications; The server provides a means for presenting the generated verification item list to the user. Including system.

2. 2. The system according to claim 1, wherein the server comprises means for performing data cleaning based on input data, means for performing feature extraction, and means for performing model learning and model validation.

3. 2. The system according to claim 1, wherein the server includes means for analyzing the new specification using natural language processing and means for extracting and structuring important elements.

Images