system

Abstract

We provide the system. [Solution] A means for inputting the details of the case, A means for pre-processing the summary of the entered case, A means for extracting keywords from preprocessed data, A means of generating preconditions based on extracted keywords, A means for outputting the generated preconditions, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional SE business, the creation of quotation prerequisite conditions has been manually performed each time, which requires a lot of time and labor. Also, it has been difficult to appropriately utilize past prerequisite conditions, and there have been cases where consistency and efficiency are lacking. As long as this problem is not solved, it is difficult to improve the efficiency of the entire business. Furthermore, there has been a problem that quality variations are likely to occur because each SE creates prerequisite conditions individually.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system that includes means for inputting a case overview, means for preprocessing the input case overview, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, and means for outputting the generated preconditions. This system tunes the generation model by utilizing a past precondition database and automatically generates appropriate preconditions in a short time when a case overview is input. This eliminates the need for manual creation work, reducing man-hours and improving operational efficiency. It also enables the provision of consistent, high-quality preconditions.

[0006] A "project overview" is information that concisely describes the project's objectives, scope, requirements, etc.

[0007] "Preprocessing" refers to the process of performing necessary cleaning and formatting on input data before analyzing it.

[0008] Keyword extraction is the process of identifying and extracting important words and phrases from text data.

[0009] "Prerequisites" are conditions or assumptions that are set in advance for the progress of a project or task.

[0010] A "generative model" is an algorithm that uses machine learning and artificial intelligence technologies to generate new information or predictions from data.

[0011] "Means" refer to the methods or tools used to accomplish a specific function.

[0012] "Output" refers to displaying, printing, or sending processing results to another system.

[0013] A "system" is a series of devices or software composed of multiple elements that are interconnected. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system for automatically generating estimation preconditions in SE (Systems Engineering) work. The configuration for implementing this system will be described below.

[0036] System Configuration

[0037] This system consists of a terminal where the user inputs the project overview, a server that performs preprocessing and generates preconditions, and a terminal that displays the generated preconditions. Each element works in conjunction to efficiently generate estimation preconditions.

[0038] Program Processing Overview

[0039] User input

[0040] Terminal input:

[0041] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[0042] Processing on the server

[0043] Data reception:

[0044] The server receives the case summary sent from the terminal.

[0045] Text cleaning:

[0046] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[0047] Keyword extraction:

[0048] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[0049] Generating preconditions

[0050] Input to and generation of the model:

[0051] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions, and this is used to generate the preconditions.

[0052] Formatting of prerequisites:

[0053] The server formats the generated preconditions and converts them into a readable format.

[0054] Output to the user

[0055] Submit prerequisites:

[0056] The server returns the formatted prerequisites to the terminal.

[0057] Review and correction:

[0058] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[0059] Specific example

[0060] If the project description is "Support for the implementation of a large-scale ERP system," using this system will automatically generate the following prerequisites.

[0061] The duration of this project will be six months.

[0062] The system to be implemented is version X of a certain company's ERP system.

[0063] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0064] The required resources will be one project manager, five developers, and three testers.

[0065] Based on these prerequisites, users can efficiently proceed with their project planning.

[0066] The above describes the embodiment for carrying out the invention. This system can significantly reduce the time and effort required to prepare estimation preconditions.

[0067] The following describes the processing flow.

[0068] Step 1:

[0069] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[0070] Step 2:

[0071] The user clicks the submit button to send the entered case summary to the server.

[0072] Step 3:

[0073] The server receives the project summary from the terminal.

[0074] Step 4:

[0075] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[0076] Step 5:

[0077] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[0078] Step 6:

[0079] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[0080] Step 7:

[0081] The generative model generates preconditions based on the input keywords.

[0082] Step 8:

[0083] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0084] Step 9:

[0085] The server returns the formatted prerequisites to the terminal.

[0086] Step 10:

[0087] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[0088] Step 11:

[0089] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[0090] Step 12:

[0091] Confirm the user's modified preconditions and save them as the final preconditions.

[0092] This series of processes efficiently generates estimation assumptions, allowing users to quickly and easily obtain the necessary assumptions.

[0093] (Example 1)

[0094] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In conventional system engineering work, the manual creation of estimation assumptions often required a great deal of time and effort. Furthermore, manual creation was prone to human error, resulting in the risk of inaccurate project plans. This invention aims to solve these problems by automating the creation of estimation assumptions.

[0096] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0097] In this invention, the server includes means for inputting a case overview, means for preprocessing the input case overview, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, means for receiving data from the means for inputting the case overview, means for cleaning the text of the received data, and means for formatting the preconditions. This enables the rapid and accurate generation of estimation preconditions.

[0098] "Means for inputting project details" refers to a device or software that provides an interface for users to input basic project information and requirements into the system.

[0099] "Means for pre-processing the input case summary" refers to a device or software that organizes the received case summary data and performs processing to remove unnecessary elements in order to improve consistency and quality.

[0100] "Means for extracting keywords from preprocessed data" refers to algorithms or software for automatically identifying and extracting important terms and phrases from preprocessed text.

[0101] "Means for generating preconditions based on extracted keywords" refers to a device or software that includes a generative model or algorithm for automatically creating estimation preconditions using extracted keywords.

[0102] "Means for outputting generated preconditions" refers to a device or software for displaying or providing the generated preconditions in a format that can be reviewed by the user.

[0103] "Means for receiving data from means for inputting the case overview" refers to a device or software that enables the transfer of case overview data entered by the user to a server via communication.

[0104] "Means for cleaning the text of received data" refers to a device or software that performs processing to improve data consistency and quality by removing unnecessary spaces, symbols, HTML tags, etc., from received text data.

[0105] "Means for formatting preconditions" refers to a device or software that formats the generated preconditions into a readable format and displays them appropriately for the user.

[0106] This invention relates to a system for automatically generating estimation preconditions in system engineering work. The system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and precondition generation, and a terminal that displays the generated preconditions. Specific embodiments for carrying out this invention are described below.

[0107] System hardware and software

[0108] First, let's describe specific examples of the hardware and software that make up this system. This system uses the following hardware and software.

[0109] hardware

[0110] Terminal: A device used to input project details and display the generated prerequisites. Examples include personal computers (PCs) and tablets.

[0111] Server: A device used for executing data processing and generative AI models. Examples include cloud servers and on-premises servers.

[0112] software

[0113] Web browser: Software used by users to input project details on their devices. Examples include Google Chrome (registered trademark) and Mozilla Firefox.

[0114] Data cleaning library: Software for cleaning the text of received data. The Python `re` module is used as an example.

[0115] Natural Language Processing (NLP) libraries: Software used to extract keywords from pre-processed data. Examples include NLTK and Spacy.

[0116] Generative AI model: A model used to generate preconditions based on extracted keywords. Examples include GPT-3 (registered trademark).

[0117] Text formatting library: Software used to format generated preconditions. The Python `textwrap` module is used as an example.

[0118] Program processing and specific examples

[0119] In this system, the user enters a summary of the case into an input form on their terminal and sends it to the server. The specific process and examples are shown below.

[0120] 1. User input

[0121] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal. Once the input is complete, the user clicks the "Submit" button to send the data to the server. This operation is performed via a web browser.

[0122] 2. Data reception and preprocessing

[0123] The server receives the case summary sent from the terminal via an HTTP request. The received data is first processed using a data cleaning library to remove unnecessary spaces and symbols.

[0124] 3. Keyword Extraction

[0125] Key keywords are extracted from the pre-processed data using an NLP library. For example, keywords such as "ERP" and "implementation support" are extracted.

[0126] 4. Input to the model and generation

[0127] The extracted keywords are input to the AI ​​model as prompts. The following types of prompts are used:

[0128] Please generate the prerequisites for the estimate regarding "Support for the implementation of a large-scale ERP system."

[0129] The generative AI model generates estimation assumptions based on this.

[0130] 5. Formatting and displaying prerequisites

[0131] The generated preconditions are formatted on the server using a text formatting library. The formatted data is then sent back to the terminal via an HTTP response. The user reviews this data on the terminal screen and makes corrections as needed.

[0132] The above describes the embodiments for carrying out the present invention. This system enables the rapid and accurate automatic generation of estimation preconditions.

[0133] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0134] Step 1:

[0135] The user enters a project overview. They enter a project overview, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and click the submit button to send the data to the server. The input at this stage involves the user entering project details as text. The output is the entered text data.

[0136] Step 2:

[0137] The server receives a case summary sent from the terminal via an HTTP request. The input is the case summary data sent from the terminal, and the output is the received text data. This text data is temporarily stored in memory.

[0138] Step 3:

[0139] The server preprocesses the received text data using a data cleaning library (for example, Python's re module). Specifically, it removes unnecessary spaces, symbols, HTML tags, etc. The input is the received text data, and the output is the cleaned text data.

[0140] Step 4:

[0141] The server extracts keywords from preprocessed text data using natural language processing (NLP) libraries (e.g., NLTK or Spacy). Specifically, it performs text analysis to identify nouns and important phrases. The input is cleaned text data, and the output is a list of extracted keywords.

[0142] Step 5:

[0143] The server generates a prompt based on the extracted keywords. This prompt is then input to the generation AI model (e.g., GPT-3). An example of a specific prompt is as follows:

[0144] "Please generate the prerequisites for the estimate regarding support for the implementation of a large-scale ERP system."

[0145] The input is a list of keywords, and the output is the generated prompt statement.

[0146] Step 6:

[0147] The server inputs the generated prompt sentences into the generation AI model and generates estimation preconditions. The model generates preconditions based on historical data. The input is the prompt sentences, and the output is the generated estimation preconditions.

[0148] Step 7:

[0149] The server formats the generated estimation assumptions. It uses a text formatting library (e.g., Python's textwrap module) to convert them into a readable format. The input is the generated estimation assumptions text, and the output is the formatted text.

[0150] Step 8:

[0151] The server returns the formatted estimation preconditions to the terminal via an HTTP response. The input is formatted text, and the output is data in a format that can be displayed on the terminal.

[0152] Step 9:

[0153] The terminal displays the returned estimate preconditions on the user interface. The user reviews the displayed preconditions and edits them as needed. Specifically, the user can change "3 testers" to "4 testers." The input is the data returned from the server, and the output is the preconditions reviewed and edited by the user.

[0154] The above describes the processing steps of the program for this system.

[0155] (Application Example 1)

[0156] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0157] In conventional SE (Systems Engineer) work, creating estimation preconditions is a time-consuming and laborious process due to its manual nature, resulting in inefficiency. Similarly, in the automated generation of factory production plans, detailed planning requires numerous condition settings, making the process complex and cumbersome, thus demanding rapid response. This invention aims to solve these problems and streamline the automated generation of preconditions and production plans.

[0158] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0159] In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, and means for automatically generating a production plan based on the preconditions. This enables the automatic generation of estimation preconditions and the efficient creation of a production plan.

[0160] "Means for inputting project details" refers to an interface that allows users to input specific project details and requirements into the system in text format.

[0161] "Means for pre-processing the summary of the entered case" refers to a device or software that provides a function including a process to clean up the data by removing unnecessary spaces and symbols from the text data entered by the user.

[0162] "Means for extracting keywords from preprocessed data" refers to a process or algorithm for identifying and extracting important words and phrases from preprocessed text data.

[0163] "Methods for generating preconditions based on extracted keywords" refers to methods for automatically generating preconditions and requirements for specific tasks or projects using extracted keywords.

[0164] "Means for outputting generated preconditions" refers to a device or interface that has the function of displaying automatically generated preconditions to the user.

[0165] "Means for automatically generating production plans based on preconditions" refers to a device or software that has the function of automatically creating detailed production plans for factories and production lines based on the generated preconditions.

[0166] This invention relates to an automated production plan generation system for a factory. The system consists of a terminal for inputting the outline of a project and a server for processing that data.

[0167] System Configuration

[0168] The overall flow of this system is as follows: the user inputs a project overview via a terminal, the server preprocesses the data, extracts keywords, generates preconditions, and automatically generates a production plan. The generated production plan is then provided back to the terminal for the user to review and make any necessary corrections.

[0169] Program Processing Overview

[0170] User input

[0171] The user enters an outline of the production plan into the input form on the terminal. For example, they might enter "Design a production line for new automotive parts." After entering the information, the user clicks the submit button to send the project outline to the server.

[0172] Processing on the server

[0173] Data reception:

[0174] The server receives the case summary sent from the terminal.

[0175] Text cleaning:

[0176] The server removes unnecessary spaces and symbols from the received case summaries. It uses the Python `re` library for this purpose, thus pre-processing the data.

[0177] Keyword extraction:

[0178] The server extracts important keywords from the pre-processed text. This process uses text analysis algorithms, for example, to extract keywords based on word length and frequency.

[0179] Generating prerequisites and production plans

[0180] Input to and generation of the model:

[0181] The server generates prompt sentences based on the extracted keywords and inputs them into the Hugging Face GPT-2 model. The generation model is tuned based on historical data and generates appropriate preconditions.

[0182] Formatting of prerequisites:

[0183] The server formats the generated preconditions and converts them into a readable format.

[0184] Automatic generation of production plans:

[0185] Based on the preconditions, the server automatically generates a production plan and sends that plan back to the terminal.

[0186] Output to the user

[0187] Submission of prerequisites and production plan:

[0188] The server returns the formatted prerequisites and automatically generated production plan to the terminal.

[0189] Review and correction:

[0190] The user reviews the generated assumptions and production plan on the terminal and makes corrections as needed. For example, if the generated assumption is "design phase is 4 months," the user can change it to "design phase is 3 months."

[0191] Specific example

[0192] Examples of prompts that the user will enter are as follows:

[0193] We will be designing a new automotive parts production line. Please tell us the prerequisites required for the process from design to production, testing, and implementation.

[0194] The server uses the Generative AI Model (GPT-2) to automatically generate the following preconditions and production plan:

[0195] The duration of this project will be 12 months.

[0196] The design phase will take 4 months, the prototype phase 3 months, the testing phase 3 months, and the implementation phase 2 months.

[0197] The required resources will be one project manager, three mechanical designers, two test engineers, and five manufacturing personnel.

[0198] This system can significantly reduce the time and effort required to create production plans.

[0199] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0200] Step 1:

[0201] The user enters a project overview into an input form on their device and submits it. Specifically, the user enters an overview in text format, such as "Design a new automotive parts production line," and clicks the submit button. This includes sending the input (project overview) to the server.

[0202] Step 2:

[0203] The server receives the submitted case summary. It receives the input (case summary) and passes it on to the next process. Here, the received raw text data is handled.

[0204] Step 3:

[0205] The server cleans the received case summary text. This process uses the Python re library to remove unnecessary spaces and symbols. It includes converting the input (case summary) into clean text data.

[0206] Step 4:

[0207] The server extracts keywords from clean text data. Using a text analysis algorithm, it identifies important words and phrases and generates a list of extracted keywords. This process involves analyzing input (clean text) and obtaining output (keyword list).

[0208] Step 5:

[0209] The server generates preconditions using the extracted keywords. It generates prompt sentences and inputs them into the Hugging Face GPT-2 model to automatically generate preconditions. Specifically, it uses a generation AI model to convert the input (keywords) into prompt sentences and generates preconditions based on the results.

[0210] Step 6:

[0211] The server formats the generated preconditions and converts them into a readable format. This process involves formatting the generated text data. It includes formatting the input (preconditions) and obtaining the output (formatted preconditions).

[0212] Step 7:

[0213] The server automatically generates a production plan based on formatted preconditions. An algorithm is then applied to create a detailed production plan using the generated preconditions as input. This process involves analyzing the input (formatted preconditions) and obtaining the output (production plan).

[0214] Step 8:

[0215] The server sends the generated production plan back to the terminal. It then sends the production plan to the user for viewing, confirmation, and modification. This process involves acquiring input (production plan) and outputting it (sending it to the user terminal).

[0216] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0217] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineering) work with an emotion engine that recognizes user emotions. The configuration for implementing this system will be described below.

[0218] System Configuration

[0219] This system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and generates preconditions, a terminal that displays the generated preconditions, and an emotion engine that recognizes the user's emotions. Each element works in conjunction to efficiently generate estimation preconditions and adjust them while taking the user's emotions into consideration.

[0220] Program Processing Overview

[0221] User input

[0222] Terminal input:

[0223] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[0224] Processing on the server

[0225] Data reception:

[0226] The server receives the case summary sent from the terminal.

[0227] Text cleaning:

[0228] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[0229] Keyword extraction:

[0230] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[0231] Generating preconditions

[0232] Input to and generation of the model:

[0233] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of historical preconditions.

[0234] Formatting of prerequisites:

[0235] The server formats the generated preconditions and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0236] Use of an emotion engine

[0237] User emotion recognition:

[0238] The emotion engine built into the device recognizes the user's emotions. For example, it uses facial recognition technology and voice analysis technology to determine the user's emotions from their facial expressions and tone of voice.

[0239] Emotion-based adjustment:

[0240] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[0241] Output to the user

[0242] Submit prerequisites:

[0243] The server returns the formatted and adjusted prerequisites to the terminal.

[0244] Review and correction:

[0245] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[0246] Specific example

[0247] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[0248] The duration of this project will be six months.

[0249] The system to be implemented is version X of a certain company's ERP system.

[0250] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0251] The required resources will be one project manager, five developers, and three testers.

[0252] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[0253] Based on these prerequisites, users can efficiently advance their project plans. Furthermore, adjustments made by the emotion engine provide prerequisites tailored to the user's needs and circumstances.

[0254] The above describes the embodiment for carrying out the invention. This system significantly reduces the time and effort required to create estimation preconditions and enables the provision of services that take user emotions into consideration.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[0258] Step 2:

[0259] The user clicks the submit button to send the entered case summary to the server.

[0260] Step 3:

[0261] The server receives the project summary from the terminal.

[0262] Step 4:

[0263] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[0264] Step 5:

[0265] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[0266] Step 6:

[0267] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[0268] Step 7:

[0269] The generative model generates preconditions based on the input keywords.

[0270] Step 8:

[0271] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0272] Step 9:

[0273] The emotion engine recognizes the user's emotion. The emotion engine installed on the terminal uses face recognition and voice analysis of the user to judge the emotion.

[0274] Step 10:

[0275] The server receives the emotion data passed from the emotion engine and adjusts the preconditions. For example, if the user is feeling stressed, adjustments such as adding more detailed explanations are made.

[0276] Step 11:

[0277] The server returns the adjusted preconditions to the terminal.

[0278] Step 12:

[0279] The user checks the preconditions generated on the terminal. Read the displayed preconditions and check the content.

[0280] Step 13:

[0281] The user modifies the preconditions as needed. For example, "3 testers" can be changed to "4 testers".

[0282] Step 14:

[0283] The user finalizes the modified preconditions and saves them as the final preconditions.

[0284] Through this series of processes, the generation and adjustment of the quotation preconditions are efficiently carried out, and high-quality preconditions reflecting the user's emotion are provided.

[0285] (Example 2)

[0286] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0287] Although a conventional estimate prerequisite condition generation system generates prerequisite conditions based on user input, it does not consider the user's emotional state. Therefore, when the user feels stressed or is distracted, the generated prerequisite conditions may not be appropriate. In addition, there are problems in that the efficiency of preprocessing and keyword extraction is low, and practical estimate prerequisite conditions cannot be provided quickly.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0289] In this invention, the server includes means for inputting an outline of a case, means for preprocessing the input case outline, means for extracting keywords from the preprocessed data, means for generating prerequisite conditions based on the extracted keywords, means for shaping the generated prerequisite conditions, means for recognizing the user's emotion, means for adjusting the prerequisite conditions based on the recognized emotion, and means for outputting the generated and adjusted prerequisite conditions. Thereby, it becomes possible to quickly generate and provide appropriate prerequisite conditions considering the user's emotional state.

[0290] The "means for inputting an outline of a case" is a device or software that provides an interface for the user to input detailed information of a case.

[0291] The "means for preprocessing the input case outline" is a device or software that analyzes the received case outline data and deletes unnecessary information.

[0292] The "means for extracting keywords from the preprocessed data" is an algorithm or device for selecting important keywords from the preprocessed text data.

[0293] "Means for generating preconditions based on extracted keywords" refers to devices or software used to create estimation preconditions based on selected keywords.

[0294] "Means for formatting generated preconditions" refers to devices or software that organize and format generated preconditions in a way that makes them easy to read.

[0295] "Means of recognizing user emotions" refer to devices or software that determine emotions from a user's facial expressions, tone of voice, etc.

[0296] "Means for adjusting preconditions based on recognized emotions" refers to devices or software for modifying and adjusting preconditions generated according to the user's emotional state.

[0297] "Means for outputting generated and adjusted preconditions" refers to devices or software for ultimately displaying or transmitting the generated preconditions to the user.

[0298] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineer) work with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[0299] System Configuration

[0300] This system consists of a terminal for inputting project details, a server for pre-processing data and generating preconditions, a terminal for displaying the generated preconditions, and an emotion engine that recognizes the user's emotions.

[0301] Program processing

[0302] User input

[0303] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system" and click the submit button. This data is then sent from the terminal to the server.

[0304] Data reception and preprocessing

[0305] The server receives the case summary data sent from the terminal. Then, as preprocessing, it deletes unnecessary spaces and symbols.

[0306] Keyword extraction

[0307] From the preprocessed data, the server extracts important keywords. For example, from the case summary "Support for the introduction of a large-scale ERP system", keywords such as "large-scale", "ERP system", and "introduction support" are extracted.

[0308] Generation of prerequisite conditions

[0309] Based on the extracted keywords, the server uses a generation AI model to generate prerequisite conditions. This generation AI model is tuned based on the past prerequisite condition database. For example, prerequisite conditions such as "project period", "required resources", and "period of each phase" are generated based on the keywords.

[0310] Formatting of prerequisite conditions

[0311] The server formats the generated prerequisite conditions into a more readable format. Specifically, each item is organized in a numbered list.

[0312] Use of the emotion engine

[0313] The emotion engine installed on the terminal recognizes the user's emotion. Using face recognition technology and voice analysis technology, the emotion is judged from the user's expression and voice tone.

[0314] Adjustment based on emotion

[0315] Based on the emotion data obtained from the emotion engine, the server adjusts the generated prerequisite conditions. For example, when the user is feeling stressed, corresponding actions such as making the explanation of the prerequisite conditions more detailed are taken.

[0316] Output of prerequisites

[0317] The formatted and adjusted prerequisites are sent from the server to the terminal and displayed to the user. The user can review these prerequisites and modify them as needed.

[0318] Specific example

[0319] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[0320] The duration of this project will be six months.

[0321] The system to be implemented is version X of a certain company's ERP system.

[0322] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0323] The required resources will be one project manager, five developers, and three testers.

[0324] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[0325] Example of a prompt

[0326] If the project description is "Support for the implementation of a large-scale ERP system" and the users are experiencing high levels of stress, please generate appropriate estimation assumptions.

[0327] This invention significantly reduces the time and effort required to create estimation assumptions and makes it possible to provide assumptions that take user sentiment into consideration.

[0328] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0329] Step 1:

[0330] User input

[0331] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and clicks the submit button.

[0332] Input: Project summary text (e.g., "Support for the implementation of a large-scale ERP system")

[0333] Operation: The terminal sends the entered text to the server.

[0334] Output: A summary text of the case is sent to the server.

[0335] Step 2:

[0336] Data reception

[0337] The server receives the case summary text sent from the terminal.

[0338] Input: Case summary text sent from the terminal

[0339] Operation: The server stores the received data in memory.

[0340] Output: Saved case summary text

[0341] Step 3:

[0342] Text cleaning

[0343] The server removes unnecessary spaces and symbols from the received case summary text.

[0344] Input: Received case summary text

[0345] Operation: The server uses regular expressions and string manipulation functions to remove unnecessary spaces and symbols (e.g., changing "Support for implementing large-scale ERP systems!!" to "Support for implementing large-scale ERP systems").

[0346] Output: Cleaned text data

[0347] Step 4:

[0348] Keyword Extraction

[0349] The server extracts important keywords from the cleaned text.

[0350] Input: Cleaned text data

[0351] Operation: The server uses natural language processing (NLP) algorithms to extract keywords (e.g., "large scale," "ERP system," "implementation support").

[0352] Output: List of extracted keywords

[0353] Step 5:

[0354] Generating preconditions

[0355] The server generates preconditions based on keywords extracted using a generative AI model.

[0356] Input: List of extracted keywords

[0357] Operation: The server inputs keywords into the generated AI model, and the model generates preconditions based on the learned database.

[0358] Output: Generated prerequisite data

[0359] Step 6:

[0360] Formatting of prerequisites

[0361] The server formats the generated preconditions into a readable format.

[0362] Input: Generated prerequisite data

[0363] Operation: The server formats the prerequisite data into bullet points or tables to make it easier to understand visually.

[0364] Output: Formatted prerequisites document

[0365] Step 7:

[0366] User emotion recognition

[0367] The emotion engine built into the device recognizes the user's emotions.

[0368] Input: User's facial expressions and voice data

[0369] Operation: The device uses facial recognition and voice analysis technologies to determine the user's emotions (e.g., if it recognizes that the user is feeling stressed).

[0370] Output: Recognized emotion data

[0371] Step 8:

[0372] Emotion-based adjustment

[0373] The server adjusts the preconditions based on the emotional data obtained from the emotion engine.

[0374] Input: Formatted prerequisite document, recognized sentiment data

[0375] Operation: Depending on the user's emotional state (e.g., stress), the explanation of prerequisites may be elaborated or specific items may be highlighted.

[0376] Output: Adjusted prerequisites document

[0377] Step 9:

[0378] Submitting prerequisites

[0379] The server sends the adjusted prerequisites to the terminal.

[0380] Input: Adjusted prerequisites document

[0381] Operation: The server sends prerequisite documents to the terminal.

[0382] Output: Prerequisites displayed on the terminal

[0383] Step 10:

[0384] Check and correct prerequisites

[0385] The user reviews the generated prerequisites and makes corrections as needed.

[0386] Input: Prerequisites displayed on the terminal

[0387] Operation: The user checks the prerequisites and makes corrections through the terminal interface (e.g., changing the prerequisite from "3 testers" to "4 testers").

[0388] Output: Modified final prerequisites

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0391] Traditional automated systems for generating estimation assumptions in system engineering (SE) work have been unable to consider user emotions, limiting their ability to provide assumptions that reflect user stress and emotional states. Furthermore, assumptions that do not consider emotions may present users with unclear explanations or inappropriate conditions, potentially hindering project progress. A system is needed to address this issue and provide optimal assumptions that reflect user emotions.

[0392] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for recognizing the user's emotions, means for adjusting the preconditions generated based on the emotions, and means for outputting the adjusted preconditions. This makes it possible to automatically generate estimation preconditions that take the user's emotions into consideration, and to provide the user with preconditions that are easy to understand and appropriate.

[0393] A "project overview" is a comprehensive description of a specific task or project, outlining key information, objectives, and scope.

[0394] "Preprocessing" refers to processes such as cleaning, formatting, and noise reduction to convert the input data into a more user-friendly format.

[0395] "Keywords" are words or phrases that have been extracted from text data as being particularly important.

[0396] "Prerequisites" refer to items that define the necessary elements, requirements, and constraints before the design and planning of a project or system.

[0397] "Means of recognizing user emotions" refers to technologies that detect and identify user emotions through the analysis of text, facial expressions, voice, etc.

[0398] "Means for adjusting preconditions generated based on emotions" refers to a mechanism that appropriately modifies the content and expression of generated preconditions in accordance with the detected emotions of the user.

[0399] This invention is a system for improving the user's shopping experience on e-commerce websites. When a user searches for and purchases products, the system recognizes the user's emotions and recommends the most suitable products and services. Furthermore, it provides a mechanism for automatically adjusting customer support based on the user's emotions. The embodiments of this system will be described in detail below.

[0400] System Configuration

[0401] This system consists of the following main components:

[0402] 1. User's device: A mobile device such as a smartphone or tablet.

[0403] 2. Server: Performs data reception, preprocessing, keyword extraction, precondition generation, sentiment recognition, precondition adjustment, and output.

[0404] 3. Emotion Engine: Uses facial recognition and voice analysis technologies to determine the user's emotions.

[0405] Program Processing Overview

[0406] 1. User input

[0407] The user enters a search query, for example, "new smartphone," into the search bar on the smartphone app.

[0408] 2. Data reception and preprocessing

[0409] The server receives the entered search query and processes it to remove unnecessary spaces and symbols. Specifically, it performs cleaning using a text processing library (e.g., NLTK or SpaCy).

[0410] 3. Keyword Extraction

[0411] The server extracts keywords from the pre-processed text data. This identifies important words such as "smartphone."

[0412] 4. Product Recommendation Generation

[0413] Based on past purchase data and user browsing history, a recommendation engine (e.g., TENSORFLOW® Recommenders) is used to generate a list of suitable products.

[0414] 5. Emotion recognition

[0415] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft® Azure® Face API or Amazon Rekognition) is used to acquire emotion data from the user's facial expressions and voice tone.

[0416] 6. Emotion-based adjustment

[0417] The server adjusts the generated product list and descriptions based on the emotional data obtained from the emotion engine. For example, if a user is feeling stressed, it provides a concise product description and a permanent purchase link in friendly language.

[0418] 7. Output to the user

[0419] We provide users with a streamlined product list and descriptions on their devices, ensuring a smooth shopping experience.

[0420] Specific example

[0421] The following are examples of prompts to input into the generative AI model.

[0422] Prompt example:

[0423] The user searched for "new smartphone," and the emotion engine detected stress. In this case, to make the shopping experience smoother, display a concise product description and a permanent purchase link using friendly language.

[0424] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0425] Step 1:

[0426] User input

[0427] The user enters "new smartphone" into the search bar on the smartphone app. Once the user finishes typing and clicks the search button, this search query is sent to the server. The input data is sent to the server in text format.

[0428] Step 2:

[0429] Data reception and preprocessing

[0430] The server receives the search query sent from the user's terminal. The server uses a text processing library (e.g., NLTK or SpaCy) to clean this text data, removing unnecessary spaces and symbols. This results in a formatted search query.

[0431] Step 3:

[0432] Keyword Extraction

[0433] The server extracts important keywords from the pre-processed text data. It uses a keyword extraction algorithm to identify key words such as "smartphone." The extracted keywords are stored as data for use in subsequent processing.

[0434] Step 4:

[0435] Generate product recommendations

[0436] Based on the extracted keywords, the server uses a recommendation engine (e.g., TensorFlow Recommenders) to generate a list of appropriate products by referencing past purchase data and user browsing history. This results in a list of relevant products.

[0437] Step 5:

[0438] emotion recognition

[0439] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) analyzes the user's facial expressions and voice tone to obtain emotional data. This emotional data is categorized into states such as stress, excitement, and indifference, and then sent to the server.

[0440] Step 6:

[0441] Emotion-based adjustment

[0442] The server adjusts the product list and descriptions generated based on the emotional data obtained from the emotion engine. For example, if the server determines that the user is stressed, it automatically generates a concise product description in friendly language and provides a fixed purchase link. This adjusted data is then generated.

[0443] Step 7:

[0444] Output to the user

[0445] The server sends the adjusted product list and descriptions to the user's device. The user's device receives this and displays it on the screen. This allows the user to proceed with the purchase process smoothly based on the adjusted information.

[0446] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0447] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0448] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0449] [Second Embodiment]

[0450] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0451] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0452] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0453] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0454] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0455] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0456] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0457] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0458] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0459] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0460] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0461] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0462] This invention is a system for automatically generating estimation preconditions in SE (Systems Engineering) work. The configuration for implementing this system will be described below.

[0463] System Configuration

[0464] This system consists of a terminal where the user inputs the project overview, a server that performs preprocessing and generates preconditions, and a terminal that displays the generated preconditions. Each element works in conjunction to efficiently generate estimation preconditions.

[0465] Program Processing Overview

[0466] User input

[0467] Terminal input:

[0468] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[0469] Processing on the server

[0470] Data reception:

[0471] The server receives the case summary sent from the terminal.

[0472] Text cleaning:

[0473] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[0474] Keyword extraction:

[0475] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[0476] Generating preconditions

[0477] Input to and generation of the model:

[0478] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions, and this is used to generate the preconditions.

[0479] Formatting of prerequisites:

[0480] The server formats the generated preconditions and converts them into a readable format.

[0481] Output to the user

[0482] Submit prerequisites:

[0483] The server returns the formatted prerequisites to the terminal.

[0484] Review and correction:

[0485] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[0486] Specific example

[0487] If the project description is "Support for the implementation of a large-scale ERP system," using this system will automatically generate the following prerequisites.

[0488] The duration of this project will be six months.

[0489] The system to be implemented is version X of a certain company's ERP system.

[0490] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0491] The required resources will be one project manager, five developers, and three testers.

[0492] Based on these prerequisites, users can efficiently proceed with their project planning.

[0493] The above describes the embodiment for carrying out the invention. This system can significantly reduce the time and effort required to prepare estimation preconditions.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[0497] Step 2:

[0498] The user clicks the submit button to send the entered case summary to the server.

[0499] Step 3:

[0500] The server receives the project summary from the terminal.

[0501] Step 4:

[0502] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[0503] Step 5:

[0504] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[0505] Step 6:

[0506] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[0507] Step 7:

[0508] The generative model generates preconditions based on the input keywords.

[0509] Step 8:

[0510] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0511] Step 9:

[0512] The server returns the formatted prerequisites to the terminal.

[0513] Step 10:

[0514] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[0515] Step 11:

[0516] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[0517] Step 12:

[0518] Confirm the user's modified preconditions and save them as the final preconditions.

[0519] This series of processes efficiently generates estimation assumptions, allowing users to quickly and easily obtain the necessary assumptions.

[0520] (Example 1)

[0521] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0522] In conventional system engineering work, the manual creation of estimation assumptions often required a great deal of time and effort. Furthermore, manual creation was prone to human error, resulting in the risk of inaccurate project plans. This invention aims to solve these problems by automating the creation of estimation assumptions.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0524] In this invention, the server includes means for inputting a case overview, means for preprocessing the input case overview, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, means for receiving data from the means for inputting the case overview, means for cleaning the text of the received data, and means for formatting the preconditions. This enables the rapid and accurate generation of estimation preconditions.

[0525] "Means for inputting project details" refers to a device or software that provides an interface for users to input basic project information and requirements into the system.

[0526] "Means for pre-processing the input case summary" refers to a device or software that organizes the received case summary data and performs processing to remove unnecessary elements in order to improve consistency and quality.

[0527] "Means for extracting keywords from preprocessed data" refers to algorithms or software for automatically identifying and extracting important terms and phrases from preprocessed text.

[0528] "Means for generating preconditions based on extracted keywords" refers to a device or software that includes a generative model or algorithm for automatically creating estimation preconditions using extracted keywords.

[0529] "Means for outputting generated preconditions" refers to a device or software for displaying or providing the generated preconditions in a format that can be reviewed by the user.

[0530] "Means for receiving data from means for inputting the case overview" refers to a device or software that enables the transfer of case overview data entered by the user to a server via communication.

[0531] "Means for cleaning the text of received data" refers to a device or software that performs processing to improve data consistency and quality by removing unnecessary spaces, symbols, HTML tags, etc., from received text data.

[0532] "Means for formatting preconditions" refers to a device or software that formats the generated preconditions into a readable format and displays them appropriately for the user.

[0533] This invention relates to a system for automatically generating estimation preconditions in system engineering work. The system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and precondition generation, and a terminal that displays the generated preconditions. Specific embodiments for carrying out this invention are described below.

[0534] System hardware and software

[0535] First, let's describe specific examples of the hardware and software that make up this system. This system uses the following hardware and software.

[0536] hardware

[0537] Terminal: A device used to input project details and display the generated prerequisites. Examples include personal computers (PCs) and tablets.

[0538] Server: A device used for executing data processing and generative AI models. Examples include cloud servers and on-premises servers.

[0539] software

[0540] Web browser: Software used by users to input project details on their devices. Examples include Google Chrome and Mozilla Firefox.

[0541] Data cleaning library: Software for cleaning the text of received data. The Python `re` module is used as an example.

[0542] Natural Language Processing (NLP) libraries: Software used to extract keywords from pre-processed data. Examples include NLTK and Spacy.

[0543] Generative AI model: A model used to generate preconditions based on extracted keywords. Examples include GPT-3.

[0544] Text formatting library: Software used to format generated preconditions. The Python `textwrap` module is used as an example.

[0545] Program processing and specific examples

[0546] In this system, the user enters a summary of the case into an input form on their terminal and sends it to the server. The specific process and examples are shown below.

[0547] 1. User input

[0548] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal. Once the input is complete, the user clicks the "Submit" button to send the data to the server. This operation is performed via a web browser.

[0549] 2. Data reception and preprocessing

[0550] The server receives the case summary sent from the terminal via an HTTP request. The received data is first processed using a data cleaning library to remove unnecessary spaces and symbols.

[0551] 3. Keyword Extraction

[0552] Key keywords are extracted from the pre-processed data using an NLP library. For example, keywords such as "ERP" and "implementation support" are extracted.

[0553] 4. Input to the model and generation

[0554] The extracted keywords are input to the AI ​​model as prompts. The following types of prompts are used:

[0555] Please generate the prerequisites for the estimate regarding "Support for the implementation of a large-scale ERP system."

[0556] The generative AI model generates estimation assumptions based on this.

[0557] 5. Formatting and displaying prerequisites

[0558] The generated preconditions are formatted on the server using a text formatting library. The formatted data is then sent back to the terminal via an HTTP response. The user reviews this data on the terminal screen and makes corrections as needed.

[0559] The above describes the embodiments for carrying out the present invention. This system enables the rapid and accurate automatic generation of estimation preconditions.

[0560] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0561] Step 1:

[0562] The user enters a project overview. They enter a project overview, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and click the submit button to send the data to the server. The input at this stage involves the user entering project details as text. The output is the entered text data.

[0563] Step 2:

[0564] The server receives a case summary sent from the terminal via an HTTP request. The input is the case summary data sent from the terminal, and the output is the received text data. This text data is temporarily stored in memory.

[0565] Step 3:

[0566] The server preprocesses the received text data using a data cleaning library (for example, Python's re module). Specifically, it removes unnecessary spaces, symbols, HTML tags, etc. The input is the received text data, and the output is the cleaned text data.

[0567] Step 4:

[0568] The server extracts keywords from preprocessed text data using natural language processing (NLP) libraries (e.g., NLTK or Spacy). Specifically, it performs text analysis to identify nouns and important phrases. The input is cleaned text data, and the output is a list of extracted keywords.

[0569] Step 5:

[0570] The server generates a prompt based on the extracted keywords. This prompt is then input to the generation AI model (e.g., GPT-3). An example of a specific prompt is as follows:

[0571] "Please generate the prerequisites for the estimate regarding support for the implementation of a large-scale ERP system."

[0572] The input is a list of keywords, and the output is the generated prompt statement.

[0573] Step 6:

[0574] The server inputs the generated prompt sentences into the generation AI model and generates estimation preconditions. The model generates preconditions based on historical data. The input is the prompt sentences, and the output is the generated estimation preconditions.

[0575] Step 7:

[0576] The server formats the generated estimation assumptions. It uses a text formatting library (e.g., Python's textwrap module) to convert them into a readable format. The input is the generated estimation assumptions text, and the output is the formatted text.

[0577] Step 8:

[0578] The server returns the formatted estimation preconditions to the terminal via an HTTP response. The input is formatted text, and the output is data in a format that can be displayed on the terminal.

[0579] Step 9:

[0580] The terminal displays the returned estimate preconditions on the user interface. The user reviews the displayed preconditions and edits them as needed. Specifically, the user can change "3 testers" to "4 testers." The input is the data returned from the server, and the output is the preconditions reviewed and edited by the user.

[0581] The above describes the processing steps of the program for this system.

[0582] (Application Example 1)

[0583] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0584] In conventional SE (Systems Engineer) work, creating estimation preconditions is a time-consuming and laborious process due to its manual nature, resulting in inefficiency. Similarly, in the automated generation of factory production plans, detailed planning requires numerous condition settings, making the process complex and cumbersome, thus demanding rapid response. This invention aims to solve these problems and streamline the automated generation of preconditions and production plans.

[0585] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0586] In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, and means for automatically generating a production plan based on the preconditions. This enables the automatic generation of estimation preconditions and the efficient creation of a production plan.

[0587] "Means for inputting project details" refers to an interface that allows users to input specific project details and requirements into the system in text format.

[0588] "Means for pre-processing the summary of the entered case" refers to a device or software that provides a function including a process to clean up the data by removing unnecessary spaces and symbols from the text data entered by the user.

[0589] "Means for extracting keywords from preprocessed data" refers to a process or algorithm for identifying and extracting important words and phrases from preprocessed text data.

[0590] "Methods for generating preconditions based on extracted keywords" refers to methods for automatically generating preconditions and requirements for specific tasks or projects using extracted keywords.

[0591] "Means for outputting generated preconditions" refers to a device or interface that has the function of displaying automatically generated preconditions to the user.

[0592] "Means for automatically generating production plans based on preconditions" refers to a device or software that has the function of automatically creating detailed production plans for factories and production lines based on the generated preconditions.

[0593] This invention relates to an automated production plan generation system for a factory. The system consists of a terminal for inputting the outline of a project and a server for processing that data.

[0594] System Configuration

[0595] The overall flow of this system is as follows: the user inputs a project overview via a terminal, the server preprocesses the data, extracts keywords, generates preconditions, and automatically generates a production plan. The generated production plan is then provided back to the terminal for the user to review and make any necessary corrections.

[0596] Program Processing Overview

[0597] User input

[0598] The user enters an outline of the production plan into the input form on the terminal. For example, they might enter "Design a production line for new automotive parts." After entering the information, the user clicks the submit button to send the project outline to the server.

[0599] Processing on the server

[0600] Data reception:

[0601] The server receives the case summary sent from the terminal.

[0602] Text cleaning:

[0603] The server removes unnecessary spaces and symbols from the received case summaries. It uses the Python `re` library for this purpose, thus pre-processing the data.

[0604] Keyword extraction:

[0605] The server extracts important keywords from the pre-processed text. This process uses text analysis algorithms, for example, to extract keywords based on word length and frequency.

[0606] Generating prerequisites and production plans

[0607] Input to and generation of the model:

[0608] The server generates prompt sentences based on the extracted keywords and inputs them into the Hugging Face GPT-2 model. The generation model is tuned based on historical data and generates appropriate preconditions.

[0609] Formatting of prerequisites:

[0610] The server formats the generated preconditions and converts them into a readable format.

[0611] Automatic generation of production plans:

[0612] Based on the preconditions, the server automatically generates a production plan and sends that plan back to the terminal.

[0613] Output to the user

[0614] Submission of prerequisites and production plan:

[0615] The server returns the formatted prerequisites and automatically generated production plan to the terminal.

[0616] Review and correction:

[0617] The user reviews the generated assumptions and production plan on the terminal and makes corrections as needed. For example, if the generated assumption is "design phase is 4 months," the user can change it to "design phase is 3 months."

[0618] Specific example

[0619] Examples of prompts that the user will enter are as follows:

[0620] We will be designing a new automotive parts production line. Please tell us the prerequisites required for the process from design to production, testing, and implementation.

[0621] The server uses the Generative AI Model (GPT-2) to automatically generate the following preconditions and production plan:

[0622] The duration of this project will be 12 months.

[0623] The design phase will take 4 months, the prototype phase 3 months, the testing phase 3 months, and the implementation phase 2 months.

[0624] The required resources will be one project manager, three mechanical designers, two test engineers, and five manufacturing personnel.

[0625] This system can significantly reduce the time and effort required to create production plans.

[0626] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0627] Step 1:

[0628] The user enters a project overview into an input form on their device and submits it. Specifically, the user enters an overview in text format, such as "Design a new automotive parts production line," and clicks the submit button. This includes sending the input (project overview) to the server.

[0629] Step 2:

[0630] The server receives the submitted case summary. It receives the input (case summary) and passes it on to the next process. Here, the received raw text data is handled.

[0631] Step 3:

[0632] The server cleans the received case summary text. This process uses the Python re library to remove unnecessary spaces and symbols. It includes converting the input (case summary) into clean text data.

[0633] Step 4:

[0634] The server extracts keywords from clean text data. Using a text analysis algorithm, it identifies important words and phrases and generates a list of extracted keywords. This process involves analyzing input (clean text) and obtaining output (keyword list).

[0635] Step 5:

[0636] The server generates preconditions using the extracted keywords. It generates prompt sentences and inputs them into the Hugging Face GPT-2 model to automatically generate preconditions. Specifically, it uses a generation AI model to convert the input (keywords) into prompt sentences and generates preconditions based on the results.

[0637] Step 6:

[0638] The server formats the generated preconditions and converts them into a readable format. This process involves formatting the generated text data. It includes formatting the input (preconditions) and obtaining the output (formatted preconditions).

[0639] Step 7:

[0640] The server automatically generates a production plan based on formatted preconditions. An algorithm is then applied to create a detailed production plan using the generated preconditions as input. This process involves analyzing the input (formatted preconditions) and obtaining the output (production plan).

[0641] Step 8:

[0642] The server sends the generated production plan back to the terminal. It then sends the production plan to the user for viewing, confirmation, and modification. This process involves acquiring input (production plan) and outputting it (sending it to the user terminal).

[0643] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0644] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineering) work with an emotion engine that recognizes user emotions. The configuration for implementing this system will be described below.

[0645] System Configuration

[0646] This system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and generates preconditions, a terminal that displays the generated preconditions, and an emotion engine that recognizes the user's emotions. Each element works in conjunction to efficiently generate estimation preconditions and adjust them while taking the user's emotions into consideration.

[0647] Program Processing Overview

[0648] User input

[0649] Terminal input:

[0650] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[0651] Processing on the server

[0652] Data reception:

[0653] The server receives the case summary sent from the terminal.

[0654] Text cleaning:

[0655] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[0656] Keyword extraction:

[0657] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[0658] Generating preconditions

[0659] Input to and generation of the model:

[0660] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of historical preconditions.

[0661] Formatting of prerequisites:

[0662] The server formats the generated preconditions and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0663] Use of an emotion engine

[0664] User emotion recognition:

[0665] The emotion engine built into the device recognizes the user's emotions. For example, it uses facial recognition technology and voice analysis technology to determine the user's emotions from their facial expressions and tone of voice.

[0666] Emotion-based adjustment:

[0667] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[0668] Output to the user

[0669] Submit prerequisites:

[0670] The server returns the formatted and adjusted prerequisites to the terminal.

[0671] Review and correction:

[0672] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[0673] Specific example

[0674] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[0675] The duration of this project will be six months.

[0676] The system to be implemented is version X of a certain company's ERP system.

[0677] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0678] The required resources will be one project manager, five developers, and three testers.

[0679] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[0680] Based on these prerequisites, users can efficiently advance their project plans. Furthermore, adjustments made by the emotion engine provide prerequisites tailored to the user's needs and circumstances.

[0681] The above describes the embodiment for carrying out the invention. This system significantly reduces the time and effort required to create estimation preconditions and enables the provision of services that take user emotions into consideration.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[0685] Step 2:

[0686] The user clicks the submit button to send the entered case summary to the server.

[0687] Step 3:

[0688] The server receives the project summary from the terminal.

[0689] Step 4:

[0690] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[0691] Step 5:

[0692] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[0693] Step 6:

[0694] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[0695] Step 7:

[0696] The generative model generates preconditions based on the input keywords.

[0697] Step 8:

[0698] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0699] Step 9:

[0700] The emotion engine recognizes the user's emotions. The emotion engine installed in the device uses facial recognition and voice analysis to determine the user's emotions.

[0701] Step 10:

[0702] The server receives emotion data from the emotion engine and adjusts the underlying assumptions. For example, if the user is feeling stressed, it might add more detailed explanations.

[0703] Step 11:

[0704] The server returns the adjusted prerequisites to the terminal.

[0705] Step 12:

[0706] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[0707] Step 13:

[0708] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[0709] Step 14:

[0710] Confirm the user's modified preconditions and save them as the final preconditions.

[0711] This series of processes efficiently generates and adjusts estimation assumptions, providing high-quality assumptions that reflect user preferences.

[0712] (Example 2)

[0713] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0714] Conventional estimation precondition generation systems generate preconditions based on user input, but they do not take into account the user's emotional state. Therefore, if the user is stressed or distracted, the generated preconditions may be inappropriate. Furthermore, they have the problem of low efficiency in preprocessing and keyword extraction, making it difficult to quickly provide practical estimation preconditions.

[0715] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0716] In this invention, the server includes means for inputting a case summary, means for preprocessing the input case summary, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for formatting the generated preconditions, means for recognizing the user's emotions, means for adjusting the preconditions based on the recognized emotions, and means for outputting the generated and adjusted preconditions. This makes it possible to quickly generate and provide appropriate preconditions that take into account the user's emotional state.

[0717] "Means for inputting project overviews" refers to devices or software that provide an interface for users to input detailed project information.

[0718] "Means for pre-processing the input case summary" refers to devices or software that analyze the received case summary data and delete unnecessary information.

[0719] "Means for extracting keywords from pre-processed data" refers to algorithms or devices for selecting important keywords from pre-processed text data.

[0720] "Means for generating preconditions based on extracted keywords" refers to devices or software used to create estimation preconditions based on selected keywords.

[0721] "Means for formatting generated preconditions" refers to devices or software that organize and format generated preconditions in a way that makes them easy to read.

[0722] "Means of recognizing user emotions" refer to devices or software that determine emotions from a user's facial expressions, tone of voice, etc.

[0723] "Means for adjusting preconditions based on recognized emotions" refers to devices or software for modifying and adjusting preconditions generated according to the user's emotional state.

[0724] "Means for outputting generated and adjusted preconditions" refers to devices or software for ultimately displaying or transmitting the generated preconditions to the user.

[0725] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineer) work with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[0726] System Configuration

[0727] This system consists of a terminal for inputting project details, a server for pre-processing data and generating preconditions, a terminal for displaying the generated preconditions, and an emotion engine that recognizes the user's emotions.

[0728] Program processing

[0729] User input

[0730] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system" and click the submit button. This data is then sent from the terminal to the server.

[0731] Data reception and preprocessing

[0732] The server receives the case summary data sent from the terminal. Then, as a preprocessing step, it removes unnecessary spaces and symbols.

[0733] Keyword Extraction

[0734] From the pre-processed data, the server extracts key keywords. For example, from the project summary "Support for the implementation of a large-scale ERP system," keywords such as "large-scale," "ERP system," and "implementation support" are extracted.

[0735] Generating preconditions

[0736] The server uses a generative AI model to generate preconditions based on the extracted keywords. This generative AI model is tuned based on a database of past preconditions. For example, preconditions such as "project duration," "required resources," and "duration of each phase" are generated based on the keywords.

[0737] Formatting of prerequisites

[0738] The server formats the generated preconditions into a readable format. Specifically, it organizes each item into a bulleted list.

[0739] Using an Emotion Engine

[0740] The emotion engine built into the device recognizes the user's emotions. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice.

[0741] Emotion-based adjustment

[0742] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[0743] Output of prerequisites

[0744] The formatted and adjusted prerequisites are sent from the server to the terminal and displayed to the user. The user can review these prerequisites and modify them as needed.

[0745] Specific example

[0746] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[0747] The duration of this project will be six months.

[0748] The system to be implemented is version X of a certain company's ERP system.

[0749] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0750] The required resources will be one project manager, five developers, and three testers.

[0751] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[0752] Example of a prompt

[0753] If the project description is "Support for the implementation of a large-scale ERP system" and the users are experiencing high levels of stress, please generate appropriate estimation assumptions.

[0754] This invention significantly reduces the time and effort required to create estimation assumptions and makes it possible to provide assumptions that take user sentiment into consideration.

[0755] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0756] Step 1:

[0757] User input

[0758] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and clicks the submit button.

[0759] Input: Project summary text (e.g., "Support for the implementation of a large-scale ERP system")

[0760] Operation: The terminal sends the entered text to the server.

[0761] Output: A summary text of the case is sent to the server.

[0762] Step 2:

[0763] Data reception

[0764] The server receives the case summary text sent from the terminal.

[0765] Input: Case summary text sent from the terminal

[0766] Operation: The server stores the received data in memory.

[0767] Output: Saved case summary text

[0768] Step 3:

[0769] Text cleaning

[0770] The server removes unnecessary spaces and symbols from the received case summary text.

[0771] Input: Received case summary text

[0772] Operation: The server uses regular expressions and string manipulation functions to remove unnecessary spaces and symbols (e.g., changing "Support for implementing large-scale ERP systems!!" to "Support for implementing large-scale ERP systems").

[0773] Output: Cleaned text data

[0774] Step 4:

[0775] Keyword Extraction

[0776] The server extracts important keywords from the cleaned text.

[0777] Input: Cleaned text data

[0778] Operation: The server uses natural language processing (NLP) algorithms to extract keywords (e.g., "large scale," "ERP system," "implementation support").

[0779] Output: List of extracted keywords

[0780] Step 5:

[0781] Generating preconditions

[0782] The server generates preconditions based on keywords extracted using a generative AI model.

[0783] Input: List of extracted keywords

[0784] Operation: The server inputs keywords into the generated AI model, and the model generates preconditions based on the learned database.

[0785] Output: Generated prerequisite data

[0786] Step 6:

[0787] Formatting of prerequisites

[0788] The server formats the generated preconditions into a readable format.

[0789] Input: Generated prerequisite data

[0790] Operation: The server formats the prerequisite data into bullet points or tables to make it easier to understand visually.

[0791] Output: Formatted prerequisites document

[0792] Step 7:

[0793] User emotion recognition

[0794] The emotion engine built into the device recognizes the user's emotions.

[0795] Input: User's facial expressions and voice data

[0796] Operation: The device uses facial recognition and voice analysis technologies to determine the user's emotions (e.g., if it recognizes that the user is feeling stressed).

[0797] Output: Recognized emotion data

[0798] Step 8:

[0799] Emotion-based adjustment

[0800] The server adjusts the preconditions based on the emotional data obtained from the emotion engine.

[0801] Input: Formatted prerequisite document, recognized sentiment data

[0802] Operation: Depending on the user's emotional state (e.g., stress), the explanation of prerequisites may be elaborated or specific items may be highlighted.

[0803] Output: Adjusted prerequisites document

[0804] Step 9:

[0805] Submitting prerequisites

[0806] The server sends the adjusted prerequisites to the terminal.

[0807] Input: Adjusted prerequisites document

[0808] Operation: The server sends prerequisite documents to the terminal.

[0809] Output: Prerequisites displayed on the terminal

[0810] Step 10:

[0811] Check and correct prerequisites

[0812] The user reviews the generated prerequisites and makes corrections as needed.

[0813] Input: Prerequisites displayed on the terminal

[0814] Operation: The user checks the prerequisites and makes corrections through the terminal interface (e.g., changing the prerequisite from "3 testers" to "4 testers").

[0815] Output: Modified final prerequisites

[0816] (Application Example 2)

[0817] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0818] Traditional automated systems for generating estimation assumptions in system engineering (SE) work have been unable to consider user emotions, limiting their ability to provide assumptions that reflect user stress and emotional states. Furthermore, assumptions that do not consider emotions may present users with unclear explanations or inappropriate conditions, potentially hindering project progress. A system is needed to address this issue and provide optimal assumptions that reflect user emotions.

[0819] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for recognizing the user's emotions, means for adjusting the preconditions generated based on the emotions, and means for outputting the adjusted preconditions. This makes it possible to automatically generate estimation preconditions that take the user's emotions into consideration, and to provide the user with preconditions that are easy to understand and appropriate.

[0820] A "project overview" is a comprehensive description of a specific task or project, outlining key information, objectives, and scope.

[0821] "Preprocessing" refers to processes such as cleaning, formatting, and noise reduction to convert the input data into a more user-friendly format.

[0822] "Keywords" are words or phrases that have been extracted from text data as being particularly important.

[0823] "Prerequisites" refer to items that define the necessary elements, requirements, and constraints before the design and planning of a project or system.

[0824] "Means of recognizing user emotions" refers to technologies that detect and identify user emotions through the analysis of text, facial expressions, voice, etc.

[0825] "Means for adjusting preconditions generated based on emotions" refers to a mechanism that appropriately modifies the content and expression of generated preconditions in accordance with the detected emotions of the user.

[0826] This invention is a system for improving the user's shopping experience on e-commerce websites. When a user searches for and purchases products, the system recognizes the user's emotions and recommends the most suitable products and services. Furthermore, it provides a mechanism for automatically adjusting customer support based on the user's emotions. The embodiments of this system will be described in detail below.

[0827] System Configuration

[0828] This system consists of the following main components:

[0829] 1. User's device: A mobile device such as a smartphone or tablet.

[0830] 2. Server: Performs data reception, preprocessing, keyword extraction, precondition generation, sentiment recognition, precondition adjustment, and output.

[0831] 3. Emotion Engine: Uses facial recognition and voice analysis technologies to determine the user's emotions.

[0832] Program Processing Overview

[0833] 1. User input

[0834] The user enters a search query, for example, "new smartphone," into the search bar on the smartphone app.

[0835] 2. Data reception and preprocessing

[0836] The server receives the entered search query and processes it to remove unnecessary spaces and symbols. Specifically, it performs cleaning using a text processing library (e.g., NLTK or SpaCy).

[0837] 3. Keyword Extraction

[0838] The server extracts keywords from the pre-processed text data. This identifies important words such as "smartphone."

[0839] 4. Product Recommendation Generation

[0840] Based on past purchase data and user browsing history, a recommendation engine (e.g., TensorFlow Recommenders) is used to generate a list of appropriate products.

[0841] 5. Emotion recognition

[0842] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) is used to acquire emotional data from the user's facial expressions and voice tone.

[0843] 6. Emotion-based adjustment

[0844] The server adjusts the generated product list and descriptions based on the emotional data obtained from the emotion engine. For example, if a user is feeling stressed, it provides a concise product description and a permanent purchase link in friendly language.

[0845] 7. Output to the user

[0846] We provide users with a streamlined product list and descriptions on their devices, ensuring a smooth shopping experience.

[0847] Specific example

[0848] The following are examples of prompts to input into the generative AI model.

[0849] Prompt example:

[0850] The user searched for "new smartphone," and the emotion engine detected stress. In this case, to make the shopping experience smoother, display a concise product description and a permanent purchase link using friendly language.

[0851] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0852] Step 1:

[0853] User input

[0854] The user enters "new smartphone" into the search bar on the smartphone app. Once the user finishes typing and clicks the search button, this search query is sent to the server. The input data is sent to the server in text format.

[0855] Step 2:

[0856] Data reception and preprocessing

[0857] The server receives the search query sent from the user's terminal. The server uses a text processing library (e.g., NLTK or SpaCy) to clean this text data, removing unnecessary spaces and symbols. This results in a formatted search query.

[0858] Step 3:

[0859] Keyword Extraction

[0860] The server extracts important keywords from the pre-processed text data. It uses a keyword extraction algorithm to identify key words such as "smartphone." The extracted keywords are stored as data for use in subsequent processing.

[0861] Step 4:

[0862] Generate product recommendations

[0863] Based on the extracted keywords, the server uses a recommendation engine (e.g., TensorFlow Recommenders) to generate a list of appropriate products by referencing past purchase data and user browsing history. This results in a list of relevant products.

[0864] Step 5:

[0865] emotion recognition

[0866] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) analyzes the user's facial expressions and voice tone to obtain emotional data. This emotional data is categorized into states such as stress, excitement, and indifference, and then sent to the server.

[0867] Step 6:

[0868] Emotion-based adjustment

[0869] The server adjusts the product list and descriptions generated based on the emotional data obtained from the emotion engine. For example, if the server determines that the user is stressed, it automatically generates a concise product description in friendly language and provides a fixed purchase link. This adjusted data is then generated.

[0870] Step 7:

[0871] Output to the user

[0872] The server sends the adjusted product list and descriptions to the user's device. The user's device receives this and displays it on the screen. This allows the user to proceed with the purchase process smoothly based on the adjusted information.

[0873] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0874] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0875] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0876] [Third Embodiment]

[0877] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0878] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0879] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0880] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0881] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0882] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0883] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0884] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0885] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0886] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0887] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0888] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0889] This invention is a system for automatically generating estimation preconditions in SE (Systems Engineering) work. The configuration for implementing this system will be described below.

[0890] System Configuration

[0891] This system consists of a terminal where the user inputs the project overview, a server that performs preprocessing and generates preconditions, and a terminal that displays the generated preconditions. Each element works in conjunction to efficiently generate estimation preconditions.

[0892] Program Processing Overview

[0893] User input

[0894] Terminal input:

[0895] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[0896] Processing on the server

[0897] Data reception:

[0898] The server receives the case summary sent from the terminal.

[0899] Text cleaning:

[0900] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[0901] Keyword extraction:

[0902] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[0903] Generating preconditions

[0904] Input to and generation of the model:

[0905] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions, and this is used to generate the preconditions.

[0906] Formatting of prerequisites:

[0907] The server formats the generated preconditions and converts them into a readable format.

[0908] Output to the user

[0909] Submit prerequisites:

[0910] The server returns the formatted prerequisites to the terminal.

[0911] Review and correction:

[0912] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[0913] Specific example

[0914] If the project description is "Support for the implementation of a large-scale ERP system," using this system will automatically generate the following prerequisites.

[0915] The duration of this project will be six months.

[0916] The system to be implemented is version X of a certain company's ERP system.

[0917] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[0918] The required resources will be one project manager, five developers, and three testers.

[0919] Based on these prerequisites, users can efficiently proceed with their project planning.

[0920] The above describes the embodiment for carrying out the invention. This system can significantly reduce the time and effort required to prepare estimation preconditions.

[0921] The following describes the processing flow.

[0922] Step 1:

[0923] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[0924] Step 2:

[0925] The user clicks the submit button to send the entered case summary to the server.

[0926] Step 3:

[0927] The server receives the project summary from the terminal.

[0928] Step 4:

[0929] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[0930] Step 5:

[0931] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[0932] Step 6:

[0933] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[0934] Step 7:

[0935] The generative model generates preconditions based on the input keywords.

[0936] Step 8:

[0937] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[0938] Step 9:

[0939] The server returns the formatted prerequisites to the terminal.

[0940] Step 10:

[0941] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[0942] Step 11:

[0943] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[0944] Step 12:

[0945] Confirm the user's modified preconditions and save them as the final preconditions.

[0946] This series of processes efficiently generates estimation assumptions, allowing users to quickly and easily obtain the necessary assumptions.

[0947] (Example 1)

[0948] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0949] In conventional system engineering work, the manual creation of estimation assumptions often required a great deal of time and effort. Furthermore, manual creation was prone to human error, resulting in the risk of inaccurate project plans. This invention aims to solve these problems by automating the creation of estimation assumptions.

[0950] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0951] In this invention, the server includes means for inputting a case overview, means for preprocessing the input case overview, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, means for receiving data from the means for inputting the case overview, means for cleaning the text of the received data, and means for formatting the preconditions. This enables the rapid and accurate generation of estimation preconditions.

[0952] "Means for inputting project details" refers to a device or software that provides an interface for users to input basic project information and requirements into the system.

[0953] "Means for pre-processing the input case summary" refers to a device or software that organizes the received case summary data and performs processing to remove unnecessary elements in order to improve consistency and quality.

[0954] "Means for extracting keywords from preprocessed data" refers to algorithms or software for automatically identifying and extracting important terms and phrases from preprocessed text.

[0955] "Means for generating preconditions based on extracted keywords" refers to a device or software that includes a generative model or algorithm for automatically creating estimation preconditions using extracted keywords.

[0956] "Means for outputting generated preconditions" refers to a device or software for displaying or providing the generated preconditions in a format that can be reviewed by the user.

[0957] "Means for receiving data from means for inputting the case overview" refers to a device or software that enables the transfer of case overview data entered by the user to a server via communication.

[0958] "Means for cleaning the text of received data" refers to a device or software that performs processing to improve data consistency and quality by removing unnecessary spaces, symbols, HTML tags, etc., from received text data.

[0959] "Means for formatting preconditions" refers to a device or software that formats the generated preconditions into a readable format and displays them appropriately for the user.

[0960] This invention relates to a system for automatically generating estimation preconditions in system engineering work. The system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and precondition generation, and a terminal that displays the generated preconditions. Specific embodiments for carrying out this invention are described below.

[0961] System hardware and software

[0962] First, let's describe specific examples of the hardware and software that make up this system. This system uses the following hardware and software.

[0963] hardware

[0964] Terminal: A device used to input project details and display the generated prerequisites. Examples include personal computers (PCs) and tablets.

[0965] Server: A device used for executing data processing and generative AI models. Examples include cloud servers and on-premises servers.

[0966] software

[0967] Web browser: Software used by users to input project details on their devices. Examples include Google Chrome and Mozilla Firefox.

[0968] Data cleaning library: Software for cleaning the text of received data. The Python `re` module is used as an example.

[0969] Natural Language Processing (NLP) libraries: Software used to extract keywords from pre-processed data. Examples include NLTK and Spacy.

[0970] Generative AI model: A model used to generate preconditions based on extracted keywords. Examples include GPT-3.

[0971] Text formatting library: Software used to format generated preconditions. The Python `textwrap` module is used as an example.

[0972] Program processing and specific examples

[0973] In this system, the user enters a summary of the case into an input form on their terminal and sends it to the server. The specific process and examples are shown below.

[0974] 1. User input

[0975] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal. Once the input is complete, the user clicks the "Submit" button to send the data to the server. This operation is performed via a web browser.

[0976] 2. Data reception and preprocessing

[0977] The server receives the case summary sent from the terminal via an HTTP request. The received data is first processed using a data cleaning library to remove unnecessary spaces and symbols.

[0978] 3. Keyword Extraction

[0979] Key keywords are extracted from the pre-processed data using an NLP library. For example, keywords such as "ERP" and "implementation support" are extracted.

[0980] 4. Input to the model and generation

[0981] The extracted keywords are input to the AI ​​model as prompts. The following types of prompts are used:

[0982] Please generate the prerequisites for the estimate regarding "Support for the implementation of a large-scale ERP system."

[0983] The generative AI model generates estimation assumptions based on this.

[0984] 5. Formatting and displaying prerequisites

[0985] The generated preconditions are formatted on the server using a text formatting library. The formatted data is then sent back to the terminal via an HTTP response. The user reviews this data on the terminal screen and makes corrections as needed.

[0986] The above describes the embodiments for carrying out the present invention. This system enables the rapid and accurate automatic generation of estimation preconditions.

[0987] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0988] Step 1:

[0989] The user enters a project overview. They enter a project overview, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and click the submit button to send the data to the server. The input at this stage involves the user entering project details as text. The output is the entered text data.

[0990] Step 2:

[0991] The server receives a case summary sent from the terminal via an HTTP request. The input is the case summary data sent from the terminal, and the output is the received text data. This text data is temporarily stored in memory.

[0992] Step 3:

[0993] The server preprocesses the received text data using a data cleaning library (for example, Python's re module). Specifically, it removes unnecessary spaces, symbols, HTML tags, etc. The input is the received text data, and the output is the cleaned text data.

[0994] Step 4:

[0995] The server extracts keywords from preprocessed text data using natural language processing (NLP) libraries (e.g., NLTK or Spacy). Specifically, it performs text analysis to identify nouns and important phrases. The input is cleaned text data, and the output is a list of extracted keywords.

[0996] Step 5:

[0997] The server generates a prompt based on the extracted keywords. This prompt is then input to the generation AI model (e.g., GPT-3). An example of a specific prompt is as follows:

[0998] "Please generate the prerequisites for the estimate regarding support for the implementation of a large-scale ERP system."

[0999] The input is a list of keywords, and the output is the generated prompt statement.

[1000] Step 6:

[1001] The server inputs the generated prompt sentences into the generation AI model and generates estimation preconditions. The model generates preconditions based on historical data. The input is the prompt sentences, and the output is the generated estimation preconditions.

[1002] Step 7:

[1003] The server formats the generated estimation assumptions. It uses a text formatting library (e.g., Python's textwrap module) to convert them into a readable format. The input is the generated estimation assumptions text, and the output is the formatted text.

[1004] Step 8:

[1005] The server returns the formatted estimation preconditions to the terminal via an HTTP response. The input is formatted text, and the output is data in a format that can be displayed on the terminal.

[1006] Step 9:

[1007] The terminal displays the returned estimate preconditions on the user interface. The user reviews the displayed preconditions and edits them as needed. Specifically, the user can change "3 testers" to "4 testers." The input is the data returned from the server, and the output is the preconditions reviewed and edited by the user.

[1008] The above describes the processing steps of the program for this system.

[1009] (Application Example 1)

[1010] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1011] In conventional SE (Systems Engineer) work, creating estimation preconditions is a time-consuming and laborious process due to its manual nature, resulting in inefficiency. Similarly, in the automated generation of factory production plans, detailed planning requires numerous condition settings, making the process complex and cumbersome, thus demanding rapid response. This invention aims to solve these problems and streamline the automated generation of preconditions and production plans.

[1012] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1013] In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, and means for automatically generating a production plan based on the preconditions. This enables the automatic generation of estimation preconditions and the efficient creation of a production plan.

[1014] "Means for inputting project details" refers to an interface that allows users to input specific project details and requirements into the system in text format.

[1015] "Means for pre-processing the summary of the entered case" refers to a device or software that provides a function including a process to clean up the data by removing unnecessary spaces and symbols from the text data entered by the user.

[1016] "Means for extracting keywords from preprocessed data" refers to a process or algorithm for identifying and extracting important words and phrases from preprocessed text data.

[1017] "Methods for generating preconditions based on extracted keywords" refers to methods for automatically generating preconditions and requirements for specific tasks or projects using extracted keywords.

[1018] "Means for outputting generated preconditions" refers to a device or interface that has the function of displaying automatically generated preconditions to the user.

[1019] "Means for automatically generating production plans based on preconditions" refers to a device or software that has the function of automatically creating detailed production plans for factories and production lines based on the generated preconditions.

[1020] This invention relates to an automated production plan generation system for a factory. The system consists of a terminal for inputting the outline of a project and a server for processing that data.

[1021] System Configuration

[1022] The overall flow of this system is as follows: the user inputs a project overview via a terminal, the server preprocesses the data, extracts keywords, generates preconditions, and automatically generates a production plan. The generated production plan is then provided back to the terminal for the user to review and make any necessary corrections.

[1023] Program Processing Overview

[1024] User input

[1025] The user enters an outline of the production plan into the input form on the terminal. For example, they might enter "Design a production line for new automotive parts." After entering the information, the user clicks the submit button to send the project outline to the server.

[1026] Processing on the server

[1027] Data reception:

[1028] The server receives the case summary sent from the terminal.

[1029] Text cleaning:

[1030] The server removes unnecessary spaces and symbols from the received case summaries. It uses the Python `re` library for this purpose, thus pre-processing the data.

[1031] Keyword extraction:

[1032] The server extracts important keywords from the pre-processed text. This process uses text analysis algorithms, for example, to extract keywords based on word length and frequency.

[1033] Generating prerequisites and production plans

[1034] Input to and generation of the model:

[1035] The server generates prompt sentences based on the extracted keywords and inputs them into the Hugging Face GPT-2 model. The generation model is tuned based on historical data and generates appropriate preconditions.

[1036] Formatting of prerequisites:

[1037] The server formats the generated preconditions and converts them into a readable format.

[1038] Automatic generation of production plans:

[1039] Based on the preconditions, the server automatically generates a production plan and sends that plan back to the terminal.

[1040] Output to the user

[1041] Submission of prerequisites and production plan:

[1042] The server returns the formatted prerequisites and automatically generated production plan to the terminal.

[1043] Review and correction:

[1044] The user reviews the generated assumptions and production plan on the terminal and makes corrections as needed. For example, if the generated assumption is "design phase is 4 months," the user can change it to "design phase is 3 months."

[1045] Specific example

[1046] Examples of prompts that the user will enter are as follows:

[1047] We will be designing a new automotive parts production line. Please tell us the prerequisites required for the process from design to production, testing, and implementation.

[1048] The server uses the Generative AI Model (GPT-2) to automatically generate the following preconditions and production plan:

[1049] The duration of this project will be 12 months.

[1050] The design phase will take 4 months, the prototype phase 3 months, the testing phase 3 months, and the implementation phase 2 months.

[1051] The required resources will be one project manager, three mechanical designers, two test engineers, and five manufacturing personnel.

[1052] This system can significantly reduce the time and effort required to create production plans.

[1053] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1054] Step 1:

[1055] The user enters a project overview into an input form on their device and submits it. Specifically, the user enters an overview in text format, such as "Design a new automotive parts production line," and clicks the submit button. This includes sending the input (project overview) to the server.

[1056] Step 2:

[1057] The server receives the submitted case summary. It receives the input (case summary) and passes it on to the next process. Here, the received raw text data is handled.

[1058] Step 3:

[1059] The server cleans the received case summary text. This process uses the Python re library to remove unnecessary spaces and symbols. It includes converting the input (case summary) into clean text data.

[1060] Step 4:

[1061] The server extracts keywords from clean text data. Using a text analysis algorithm, it identifies important words and phrases and generates a list of extracted keywords. This process involves analyzing input (clean text) and obtaining output (keyword list).

[1062] Step 5:

[1063] The server generates preconditions using the extracted keywords. It generates prompt sentences and inputs them into the Hugging Face GPT-2 model to automatically generate preconditions. Specifically, it uses a generation AI model to convert the input (keywords) into prompt sentences and generates preconditions based on the results.

[1064] Step 6:

[1065] The server formats the generated preconditions and converts them into a readable format. This process involves formatting the generated text data. It includes formatting the input (preconditions) and obtaining the output (formatted preconditions).

[1066] Step 7:

[1067] The server automatically generates a production plan based on formatted preconditions. An algorithm is then applied to create a detailed production plan using the generated preconditions as input. This process involves analyzing the input (formatted preconditions) and obtaining the output (production plan).

[1068] Step 8:

[1069] The server sends the generated production plan back to the terminal. It then sends the production plan to the user for viewing, confirmation, and modification. This process involves acquiring input (production plan) and outputting it (sending it to the user terminal).

[1070] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1071] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineering) work with an emotion engine that recognizes user emotions. The configuration for implementing this system will be described below.

[1072] System Configuration

[1073] This system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and generates preconditions, a terminal that displays the generated preconditions, and an emotion engine that recognizes the user's emotions. Each element works in conjunction to efficiently generate estimation preconditions and adjust them while taking the user's emotions into consideration.

[1074] Program Processing Overview

[1075] User input

[1076] Terminal input:

[1077] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[1078] Processing on the server

[1079] Data reception:

[1080] The server receives the case summary sent from the terminal.

[1081] Text cleaning:

[1082] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[1083] Keyword extraction:

[1084] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[1085] Generating preconditions

[1086] Input to and generation of the model:

[1087] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of historical preconditions.

[1088] Formatting of prerequisites:

[1089] The server formats the generated preconditions and converts them into a readable format. For example, it organizes each item into a bulleted list.

[1090] Use of an emotion engine

[1091] User emotion recognition:

[1092] The emotion engine built into the device recognizes the user's emotions. For example, it uses facial recognition technology and voice analysis technology to determine the user's emotions from their facial expressions and tone of voice.

[1093] Emotion-based adjustment:

[1094] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[1095] Output to the user

[1096] Submit prerequisites:

[1097] The server returns the formatted and adjusted prerequisites to the terminal.

[1098] Review and correction:

[1099] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[1100] Specific example

[1101] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[1102] The duration of this project will be six months.

[1103] The system to be implemented is version X of a certain company's ERP system.

[1104] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[1105] The required resources will be one project manager, five developers, and three testers.

[1106] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[1107] Based on these prerequisites, users can efficiently advance their project plans. Furthermore, adjustments made by the emotion engine provide prerequisites tailored to the user's needs and circumstances.

[1108] The above describes the embodiment for carrying out the invention. This system significantly reduces the time and effort required to create estimation preconditions and enables the provision of services that take user emotions into consideration.

[1109] The following describes the processing flow.

[1110] Step 1:

[1111] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[1112] Step 2:

[1113] The user clicks the submit button to send the entered case summary to the server.

[1114] Step 3:

[1115] The server receives the project summary from the terminal.

[1116] Step 4:

[1117] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[1118] Step 5:

[1119] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[1120] Step 6:

[1121] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[1122] Step 7:

[1123] The generative model generates preconditions based on the input keywords.

[1124] Step 8:

[1125] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[1126] Step 9:

[1127] The emotion engine recognizes the user's emotions. The emotion engine installed in the device uses facial recognition and voice analysis to determine the user's emotions.

[1128] Step 10:

[1129] The server receives emotion data from the emotion engine and adjusts the underlying assumptions. For example, if the user is feeling stressed, it might add more detailed explanations.

[1130] Step 11:

[1131] The server returns the adjusted prerequisites to the terminal.

[1132] Step 12:

[1133] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[1134] Step 13:

[1135] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[1136] Step 14:

[1137] Confirm the user's modified preconditions and save them as the final preconditions.

[1138] This series of processes efficiently generates and adjusts estimation assumptions, providing high-quality assumptions that reflect user preferences.

[1139] (Example 2)

[1140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1141] Conventional estimation precondition generation systems generate preconditions based on user input, but they do not take into account the user's emotional state. Therefore, if the user is stressed or distracted, the generated preconditions may be inappropriate. Furthermore, they have the problem of low efficiency in preprocessing and keyword extraction, making it difficult to quickly provide practical estimation preconditions.

[1142] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1143] In this invention, the server includes means for inputting a case summary, means for preprocessing the input case summary, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for formatting the generated preconditions, means for recognizing the user's emotions, means for adjusting the preconditions based on the recognized emotions, and means for outputting the generated and adjusted preconditions. This makes it possible to quickly generate and provide appropriate preconditions that take into account the user's emotional state.

[1144] "Means for inputting project overviews" refers to devices or software that provide an interface for users to input detailed project information.

[1145] "Means for pre-processing the input case summary" refers to devices or software that analyze the received case summary data and delete unnecessary information.

[1146] "Means for extracting keywords from pre-processed data" refers to algorithms or devices for selecting important keywords from pre-processed text data.

[1147] "Means for generating preconditions based on extracted keywords" refers to devices or software used to create estimation preconditions based on selected keywords.

[1148] "Means for formatting generated preconditions" refers to devices or software that organize and format generated preconditions in a way that makes them easy to read.

[1149] "Means of recognizing user emotions" refer to devices or software that determine emotions from a user's facial expressions, tone of voice, etc.

[1150] "Means for adjusting preconditions based on recognized emotions" refers to devices or software for modifying and adjusting preconditions generated according to the user's emotional state.

[1151] "Means for outputting generated and adjusted preconditions" refers to devices or software for ultimately displaying or transmitting the generated preconditions to the user.

[1152] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineer) work with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[1153] System Configuration

[1154] This system consists of a terminal for inputting project details, a server for pre-processing data and generating preconditions, a terminal for displaying the generated preconditions, and an emotion engine that recognizes the user's emotions.

[1155] Program processing

[1156] User input

[1157] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system" and click the submit button. This data is then sent from the terminal to the server.

[1158] Data reception and preprocessing

[1159] The server receives the case summary data sent from the terminal. Then, as a preprocessing step, it removes unnecessary spaces and symbols.

[1160] Keyword Extraction

[1161] From the pre-processed data, the server extracts key keywords. For example, from the project summary "Support for the implementation of a large-scale ERP system," keywords such as "large-scale," "ERP system," and "implementation support" are extracted.

[1162] Generating preconditions

[1163] The server uses a generative AI model to generate preconditions based on the extracted keywords. This generative AI model is tuned based on a database of past preconditions. For example, preconditions such as "project duration," "required resources," and "duration of each phase" are generated based on the keywords.

[1164] Formatting of prerequisites

[1165] The server formats the generated preconditions into a readable format. Specifically, it organizes each item into a bulleted list.

[1166] Using an Emotion Engine

[1167] The emotion engine built into the device recognizes the user's emotions. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice.

[1168] Emotion-based adjustment

[1169] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[1170] Output of prerequisites

[1171] The formatted and adjusted prerequisites are sent from the server to the terminal and displayed to the user. The user can review these prerequisites and modify them as needed.

[1172] Specific example

[1173] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[1174] The duration of this project will be six months.

[1175] The system to be implemented is version X of a certain company's ERP system.

[1176] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[1177] The required resources will be one project manager, five developers, and three testers.

[1178] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[1179] Example of a prompt

[1180] If the project description is "Support for the implementation of a large-scale ERP system" and the users are experiencing high levels of stress, please generate appropriate estimation assumptions.

[1181] This invention significantly reduces the time and effort required to create estimation assumptions and makes it possible to provide assumptions that take user sentiment into consideration.

[1182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1183] Step 1:

[1184] User input

[1185] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and clicks the submit button.

[1186] Input: Project summary text (e.g., "Support for the implementation of a large-scale ERP system")

[1187] Operation: The terminal sends the entered text to the server.

[1188] Output: A summary text of the case is sent to the server.

[1189] Step 2:

[1190] Data reception

[1191] The server receives the case summary text sent from the terminal.

[1192] Input: Case summary text sent from the terminal

[1193] Operation: The server stores the received data in memory.

[1194] Output: Saved case summary text

[1195] Step 3:

[1196] Text cleaning

[1197] The server removes unnecessary spaces and symbols from the received case summary text.

[1198] Input: Received case summary text

[1199] Operation: The server uses regular expressions and string manipulation functions to remove unnecessary spaces and symbols (e.g., changing "Support for implementing large-scale ERP systems!!" to "Support for implementing large-scale ERP systems").

[1200] Output: Cleaned text data

[1201] Step 4:

[1202] Keyword Extraction

[1203] The server extracts important keywords from the cleaned text.

[1204] Input: Cleaned text data

[1205] Operation: The server uses natural language processing (NLP) algorithms to extract keywords (e.g., "large scale," "ERP system," "implementation support").

[1206] Output: List of extracted keywords

[1207] Step 5:

[1208] Generating preconditions

[1209] The server generates preconditions based on keywords extracted using a generative AI model.

[1210] Input: List of extracted keywords

[1211] Operation: The server inputs keywords into the generated AI model, and the model generates preconditions based on the learned database.

[1212] Output: Generated prerequisite data

[1213] Step 6:

[1214] Formatting of prerequisites

[1215] The server formats the generated preconditions into a readable format.

[1216] Input: Generated prerequisite data

[1217] Operation: The server formats the prerequisite data into bullet points or tables to make it easier to understand visually.

[1218] Output: Formatted prerequisites document

[1219] Step 7:

[1220] User emotion recognition

[1221] The emotion engine built into the device recognizes the user's emotions.

[1222] Input: User's facial expressions and voice data

[1223] Operation: The device uses facial recognition and voice analysis technologies to determine the user's emotions (e.g., if it recognizes that the user is feeling stressed).

[1224] Output: Recognized emotion data

[1225] Step 8:

[1226] Emotion-based adjustment

[1227] The server adjusts the preconditions based on the emotional data obtained from the emotion engine.

[1228] Input: Formatted prerequisite document, recognized sentiment data

[1229] Operation: Depending on the user's emotional state (e.g., stress), the explanation of prerequisites may be elaborated or specific items may be highlighted.

[1230] Output: Adjusted prerequisites document

[1231] Step 9:

[1232] Submitting prerequisites

[1233] The server sends the adjusted prerequisites to the terminal.

[1234] Input: Adjusted prerequisites document

[1235] Operation: The server sends prerequisite documents to the terminal.

[1236] Output: Prerequisites displayed on the terminal

[1237] Step 10:

[1238] Check and correct prerequisites

[1239] The user reviews the generated prerequisites and makes corrections as needed.

[1240] Input: Prerequisites displayed on the terminal

[1241] Operation: The user checks the prerequisites and makes corrections through the terminal interface (e.g., changing the prerequisite from "3 testers" to "4 testers").

[1242] Output: Modified final prerequisites

[1243] (Application Example 2)

[1244] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1245] Traditional automated systems for generating estimation assumptions in system engineering (SE) work have been unable to consider user emotions, limiting their ability to provide assumptions that reflect user stress and emotional states. Furthermore, assumptions that do not consider emotions may present users with unclear explanations or inappropriate conditions, potentially hindering project progress. A system is needed to address this issue and provide optimal assumptions that reflect user emotions.

[1246] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for recognizing the user's emotions, means for adjusting the preconditions generated based on the emotions, and means for outputting the adjusted preconditions. This makes it possible to automatically generate estimation preconditions that take the user's emotions into consideration, and to provide the user with preconditions that are easy to understand and appropriate.

[1247] A "project overview" is a comprehensive description of a specific task or project, outlining key information, objectives, and scope.

[1248] "Preprocessing" refers to processes such as cleaning, formatting, and noise reduction to convert the input data into a more user-friendly format.

[1249] "Keywords" are words or phrases that have been extracted from text data as being particularly important.

[1250] "Prerequisites" refer to items that define the necessary elements, requirements, and constraints before the design and planning of a project or system.

[1251] "Means of recognizing user emotions" refers to technologies that detect and identify user emotions through the analysis of text, facial expressions, voice, etc.

[1252] "Means for adjusting preconditions generated based on emotions" refers to a mechanism that appropriately modifies the content and expression of generated preconditions in accordance with the detected emotions of the user.

[1253] This invention is a system for improving the user's shopping experience on e-commerce websites. When a user searches for and purchases products, the system recognizes the user's emotions and recommends the most suitable products and services. Furthermore, it provides a mechanism for automatically adjusting customer support based on the user's emotions. The embodiments of this system will be described in detail below.

[1254] System Configuration

[1255] This system consists of the following main components:

[1256] 1. User's device: A mobile device such as a smartphone or tablet.

[1257] 2. Server: Performs data reception, preprocessing, keyword extraction, precondition generation, sentiment recognition, precondition adjustment, and output.

[1258] 3. Emotion Engine: Uses facial recognition and voice analysis technologies to determine the user's emotions.

[1259] Program Processing Overview

[1260] 1. User input

[1261] The user enters a search query, for example, "new smartphone," into the search bar on the smartphone app.

[1262] 2. Data reception and preprocessing

[1263] The server receives the entered search query and processes it to remove unnecessary spaces and symbols. Specifically, it performs cleaning using a text processing library (e.g., NLTK or SpaCy).

[1264] 3. Keyword Extraction

[1265] The server extracts keywords from the pre-processed text data. This identifies important words such as "smartphone."

[1266] 4. Product Recommendation Generation

[1267] Based on past purchase data and user browsing history, a recommendation engine (e.g., TensorFlow Recommenders) is used to generate a list of appropriate products.

[1268] 5. Emotion recognition

[1269] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) is used to acquire emotional data from the user's facial expressions and voice tone.

[1270] 6. Emotion-based adjustment

[1271] The server adjusts the generated product list and descriptions based on the emotional data obtained from the emotion engine. For example, if a user is feeling stressed, it provides a concise product description and a permanent purchase link in friendly language.

[1272] 7. Output to the user

[1273] We provide users with a streamlined product list and descriptions on their devices, ensuring a smooth shopping experience.

[1274] Specific example

[1275] The following are examples of prompts to input into the generative AI model.

[1276] Prompt example:

[1277] The user searched for "new smartphone," and the emotion engine detected stress. In this case, to make the shopping experience smoother, display a concise product description and a permanent purchase link using friendly language.

[1278] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1279] Step 1:

[1280] User input

[1281] The user enters "new smartphone" into the search bar on the smartphone app. Once the user finishes typing and clicks the search button, this search query is sent to the server. The input data is sent to the server in text format.

[1282] Step 2:

[1283] Data reception and preprocessing

[1284] The server receives the search query sent from the user's terminal. The server uses a text processing library (e.g., NLTK or SpaCy) to clean this text data, removing unnecessary spaces and symbols. This results in a formatted search query.

[1285] Step 3:

[1286] Keyword Extraction

[1287] The server extracts important keywords from the pre-processed text data. It uses a keyword extraction algorithm to identify key words such as "smartphone." The extracted keywords are stored as data for use in subsequent processing.

[1288] Step 4:

[1289] Generate product recommendations

[1290] Based on the extracted keywords, the server uses a recommendation engine (e.g., TensorFlow Recommenders) to generate a list of appropriate products by referencing past purchase data and user browsing history. This results in a list of relevant products.

[1291] Step 5:

[1292] emotion recognition

[1293] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) analyzes the user's facial expressions and voice tone to obtain emotional data. This emotional data is categorized into states such as stress, excitement, and indifference, and then sent to the server.

[1294] Step 6:

[1295] Emotion-based adjustment

[1296] The server adjusts the product list and descriptions generated based on the emotional data obtained from the emotion engine. For example, if the server determines that the user is stressed, it automatically generates a concise product description in friendly language and provides a fixed purchase link. This adjusted data is then generated.

[1297] Step 7:

[1298] Output to the user

[1299] The server sends the adjusted product list and descriptions to the user's device. The user's device receives this and displays it on the screen. This allows the user to proceed with the purchase process smoothly based on the adjusted information.

[1300] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1301] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1302] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1303] [Fourth Embodiment]

[1304] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1305] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1306] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1307] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1308] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1309] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1310] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1311] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1312] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1313] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1314] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1315] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1316] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1317] This invention is a system for automatically generating estimation preconditions in SE (Systems Engineering) work. The configuration for implementing this system will be described below.

[1318] System Configuration

[1319] This system consists of a terminal where the user inputs the project overview, a server that performs preprocessing and generates preconditions, and a terminal that displays the generated preconditions. Each element works in conjunction to efficiently generate estimation preconditions.

[1320] Program Processing Overview

[1321] User input

[1322] Terminal input:

[1323] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[1324] Processing on the server

[1325] Data reception:

[1326] The server receives the case summary sent from the terminal.

[1327] Text cleaning:

[1328] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[1329] Keyword extraction:

[1330] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[1331] Generating preconditions

[1332] Input to and generation of the model:

[1333] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions, and this is used to generate the preconditions.

[1334] Formatting of prerequisites:

[1335] The server formats the generated preconditions and converts them into a readable format.

[1336] Output to the user

[1337] Submit prerequisites:

[1338] The server returns the formatted prerequisites to the terminal.

[1339] Review and correction:

[1340] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[1341] Specific example

[1342] If the project description is "Support for the implementation of a large-scale ERP system," using this system will automatically generate the following prerequisites.

[1343] The duration of this project will be six months.

[1344] The system to be implemented is version X of a certain company's ERP system.

[1345] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[1346] The required resources will be one project manager, five developers, and three testers.

[1347] Based on these prerequisites, users can efficiently proceed with their project planning.

[1348] The above describes the embodiment for carrying out the invention. This system can significantly reduce the time and effort required to prepare estimation preconditions.

[1349] The following describes the processing flow.

[1350] Step 1:

[1351] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[1352] Step 2:

[1353] The user clicks the submit button to send the entered case summary to the server.

[1354] Step 3:

[1355] The server receives the project summary from the terminal.

[1356] Step 4:

[1357] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[1358] Step 5:

[1359] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[1360] Step 6:

[1361] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[1362] Step 7:

[1363] The generative model generates preconditions based on the input keywords.

[1364] Step 8:

[1365] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[1366] Step 9:

[1367] The server returns the formatted prerequisites to the terminal.

[1368] Step 10:

[1369] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[1370] Step 11:

[1371] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[1372] Step 12:

[1373] Confirm the user's modified preconditions and save them as the final preconditions.

[1374] This series of processes efficiently generates estimation assumptions, allowing users to quickly and easily obtain the necessary assumptions.

[1375] (Example 1)

[1376] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1377] In conventional system engineering work, the manual creation of estimation assumptions often required a great deal of time and effort. Furthermore, manual creation was prone to human error, resulting in the risk of inaccurate project plans. This invention aims to solve these problems by automating the creation of estimation assumptions.

[1378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1379] In this invention, the server includes means for inputting a case overview, means for preprocessing the input case overview, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, means for receiving data from the means for inputting the case overview, means for cleaning the text of the received data, and means for formatting the preconditions. This enables the rapid and accurate generation of estimation preconditions.

[1380] "Means for inputting project details" refers to a device or software that provides an interface for users to input basic project information and requirements into the system.

[1381] "Means for pre-processing the input case summary" refers to a device or software that organizes the received case summary data and performs processing to remove unnecessary elements in order to improve consistency and quality.

[1382] "Means for extracting keywords from preprocessed data" refers to algorithms or software for automatically identifying and extracting important terms and phrases from preprocessed text.

[1383] "Means for generating preconditions based on extracted keywords" refers to a device or software that includes a generative model or algorithm for automatically creating estimation preconditions using extracted keywords.

[1384] "Means for outputting generated preconditions" refers to a device or software for displaying or providing the generated preconditions in a format that can be reviewed by the user.

[1385] "Means for receiving data from means for inputting the case overview" refers to a device or software that enables the transfer of case overview data entered by the user to a server via communication.

[1386] "Means for cleaning the text of received data" refers to a device or software that performs processing to improve data consistency and quality by removing unnecessary spaces, symbols, HTML tags, etc., from received text data.

[1387] "Means for formatting preconditions" refers to a device or software that formats the generated preconditions into a readable format and displays them appropriately for the user.

[1388] This invention relates to a system for automatically generating estimation preconditions in system engineering work. The system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and precondition generation, and a terminal that displays the generated preconditions. Specific embodiments for carrying out this invention are described below.

[1389] System hardware and software

[1390] First, let's describe specific examples of the hardware and software that make up this system. This system uses the following hardware and software.

[1391] hardware

[1392] Terminal: A device used to input project details and display the generated prerequisites. Examples include personal computers (PCs) and tablets.

[1393] Server: A device used for executing data processing and generative AI models. Examples include cloud servers and on-premises servers.

[1394] software

[1395] Web browser: Software used by users to input project details on their devices. Examples include Google Chrome and Mozilla Firefox.

[1396] Data cleaning library: Software for cleaning the text of received data. The Python `re` module is used as an example.

[1397] Natural Language Processing (NLP) libraries: Software used to extract keywords from pre-processed data. Examples include NLTK and Spacy.

[1398] Generative AI model: A model used to generate preconditions based on extracted keywords. Examples include GPT-3.

[1399] Text formatting library: Software used to format generated preconditions. The Python `textwrap` module is used as an example.

[1400] Program processing and specific examples

[1401] In this system, the user enters a summary of the case into an input form on their terminal and sends it to the server. The specific process and examples are shown below.

[1402] 1. User input

[1403] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal. Once the input is complete, the user clicks the "Submit" button to send the data to the server. This operation is performed via a web browser.

[1404] 2. Data reception and preprocessing

[1405] The server receives the case summary sent from the terminal via an HTTP request. The received data is first processed using a data cleaning library to remove unnecessary spaces and symbols.

[1406] 3. Keyword Extraction

[1407] Key keywords are extracted from the pre-processed data using an NLP library. For example, keywords such as "ERP" and "implementation support" are extracted.

[1408] 4. Input to the model and generation

[1409] The extracted keywords are input to the AI ​​model as prompts. The following types of prompts are used:

[1410] Please generate the prerequisites for the estimate regarding "Support for the implementation of a large-scale ERP system."

[1411] The generative AI model generates estimation assumptions based on this.

[1412] 5. Formatting and displaying prerequisites

[1413] The generated preconditions are formatted on the server using a text formatting library. The formatted data is then sent back to the terminal via an HTTP response. The user reviews this data on the terminal screen and makes corrections as needed.

[1414] The above describes the embodiments for carrying out the present invention. This system enables the rapid and accurate automatic generation of estimation preconditions.

[1415] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1416] Step 1:

[1417] The user enters a project overview. They enter a project overview, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and click the submit button to send the data to the server. The input at this stage involves the user entering project details as text. The output is the entered text data.

[1418] Step 2:

[1419] The server receives a case summary sent from the terminal via an HTTP request. The input is the case summary data sent from the terminal, and the output is the received text data. This text data is temporarily stored in memory.

[1420] Step 3:

[1421] The server preprocesses the received text data using a data cleaning library (for example, Python's re module). Specifically, it removes unnecessary spaces, symbols, HTML tags, etc. The input is the received text data, and the output is the cleaned text data.

[1422] Step 4:

[1423] The server extracts keywords from preprocessed text data using natural language processing (NLP) libraries (e.g., NLTK or Spacy). Specifically, it performs text analysis to identify nouns and important phrases. The input is cleaned text data, and the output is a list of extracted keywords.

[1424] Step 5:

[1425] The server generates a prompt based on the extracted keywords. This prompt is then input to the generation AI model (e.g., GPT-3). An example of a specific prompt is as follows:

[1426] "Please generate the prerequisites for the estimate regarding support for the implementation of a large-scale ERP system."

[1427] The input is a list of keywords, and the output is the generated prompt statement.

[1428] Step 6:

[1429] The server inputs the generated prompt sentences into the generation AI model and generates estimation preconditions. The model generates preconditions based on historical data. The input is the prompt sentences, and the output is the generated estimation preconditions.

[1430] Step 7:

[1431] The server formats the generated estimation assumptions. It uses a text formatting library (e.g., Python's textwrap module) to convert them into a readable format. The input is the generated estimation assumptions text, and the output is the formatted text.

[1432] Step 8:

[1433] The server returns the formatted estimation preconditions to the terminal via an HTTP response. The input is formatted text, and the output is data in a format that can be displayed on the terminal.

[1434] Step 9:

[1435] The terminal displays the returned estimate preconditions on the user interface. The user reviews the displayed preconditions and edits them as needed. Specifically, the user can change "3 testers" to "4 testers." The input is the data returned from the server, and the output is the preconditions reviewed and edited by the user.

[1436] The above describes the processing steps of the program for this system.

[1437] (Application Example 1)

[1438] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1439] In conventional SE (Systems Engineer) work, creating estimation preconditions is a time-consuming and laborious process due to its manual nature, resulting in inefficiency. Similarly, in the automated generation of factory production plans, detailed planning requires numerous condition settings, making the process complex and cumbersome, thus demanding rapid response. This invention aims to solve these problems and streamline the automated generation of preconditions and production plans.

[1440] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1441] In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for generating preconditions based on the extracted keywords, means for outputting the generated preconditions, and means for automatically generating a production plan based on the preconditions. This enables the automatic generation of estimation preconditions and the efficient creation of a production plan.

[1442] "Means for inputting project details" refers to an interface that allows users to input specific project details and requirements into the system in text format.

[1443] "Means for pre-processing the summary of the entered case" refers to a device or software that provides a function including a process to clean up the data by removing unnecessary spaces and symbols from the text data entered by the user.

[1444] "Means for extracting keywords from preprocessed data" refers to a process or algorithm for identifying and extracting important words and phrases from preprocessed text data.

[1445] "Methods for generating preconditions based on extracted keywords" refers to methods for automatically generating preconditions and requirements for specific tasks or projects using extracted keywords.

[1446] "Means for outputting generated preconditions" refers to a device or interface that has the function of displaying automatically generated preconditions to the user.

[1447] "Means for automatically generating production plans based on preconditions" refers to a device or software that has the function of automatically creating detailed production plans for factories and production lines based on the generated preconditions.

[1448] This invention relates to an automated production plan generation system for a factory. The system consists of a terminal for inputting the outline of a project and a server for processing that data.

[1449] System Configuration

[1450] The overall flow of this system is as follows: the user inputs a project overview via a terminal, the server preprocesses the data, extracts keywords, generates preconditions, and automatically generates a production plan. The generated production plan is then provided back to the terminal for the user to review and make any necessary corrections.

[1451] Program Processing Overview

[1452] User input

[1453] The user enters an outline of the production plan into the input form on the terminal. For example, they might enter "Design a production line for new automotive parts." After entering the information, the user clicks the submit button to send the project outline to the server.

[1454] Processing on the server

[1455] Data reception:

[1456] The server receives the case summary sent from the terminal.

[1457] Text cleaning:

[1458] The server removes unnecessary spaces and symbols from the received case summaries. It uses the Python `re` library for this purpose, thus pre-processing the data.

[1459] Keyword extraction:

[1460] The server extracts important keywords from the pre-processed text. This process uses text analysis algorithms, for example, to extract keywords based on word length and frequency.

[1461] Generating prerequisites and production plans

[1462] Input to and generation of the model:

[1463] The server generates prompt sentences based on the extracted keywords and inputs them into the Hugging Face GPT-2 model. The generation model is tuned based on historical data and generates appropriate preconditions.

[1464] Formatting of prerequisites:

[1465] The server formats the generated preconditions and converts them into a readable format.

[1466] Automatic generation of production plans:

[1467] Based on the preconditions, the server automatically generates a production plan and sends that plan back to the terminal.

[1468] Output to the user

[1469] Submission of prerequisites and production plan:

[1470] The server returns the formatted prerequisites and automatically generated production plan to the terminal.

[1471] Review and correction:

[1472] The user reviews the generated assumptions and production plan on the terminal and makes corrections as needed. For example, if the generated assumption is "design phase is 4 months," the user can change it to "design phase is 3 months."

[1473] Specific example

[1474] Examples of prompts that the user will enter are as follows:

[1475] We will be designing a new automotive parts production line. Please tell us the prerequisites required for the process from design to production, testing, and implementation.

[1476] The server uses the Generative AI Model (GPT-2) to automatically generate the following preconditions and production plan:

[1477] The duration of this project will be 12 months.

[1478] The design phase will take 4 months, the prototype phase 3 months, the testing phase 3 months, and the implementation phase 2 months.

[1479] The required resources will be one project manager, three mechanical designers, two test engineers, and five manufacturing personnel.

[1480] This system can significantly reduce the time and effort required to create production plans.

[1481] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1482] Step 1:

[1483] The user enters a project overview into an input form on their device and submits it. Specifically, the user enters an overview in text format, such as "Design a new automotive parts production line," and clicks the submit button. This includes sending the input (project overview) to the server.

[1484] Step 2:

[1485] The server receives the submitted case summary. It receives the input (case summary) and passes it on to the next process. Here, the received raw text data is handled.

[1486] Step 3:

[1487] The server cleans the received case summary text. This process uses the Python re library to remove unnecessary spaces and symbols. It includes converting the input (case summary) into clean text data.

[1488] Step 4:

[1489] The server extracts keywords from clean text data. Using a text analysis algorithm, it identifies important words and phrases and generates a list of extracted keywords. This process involves analyzing input (clean text) and obtaining output (keyword list).

[1490] Step 5:

[1491] The server generates preconditions using the extracted keywords. It generates prompt sentences and inputs them into the Hugging Face GPT-2 model to automatically generate preconditions. Specifically, it uses a generation AI model to convert the input (keywords) into prompt sentences and generates preconditions based on the results.

[1492] Step 6:

[1493] The server formats the generated preconditions and converts them into a readable format. This process involves formatting the generated text data. It includes formatting the input (preconditions) and obtaining the output (formatted preconditions).

[1494] Step 7:

[1495] The server automatically generates a production plan based on formatted preconditions. An algorithm is then applied to create a detailed production plan using the generated preconditions as input. This process involves analyzing the input (formatted preconditions) and obtaining the output (production plan).

[1496] Step 8:

[1497] The server sends the generated production plan back to the terminal. It then sends the production plan to the user for viewing, confirmation, and modification. This process involves acquiring input (production plan) and outputting it (sending it to the user terminal).

[1498] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1499] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineering) work with an emotion engine that recognizes user emotions. The configuration for implementing this system will be described below.

[1500] System Configuration

[1501] This system consists of a terminal where the user inputs a project overview, a server that performs preprocessing and generates preconditions, a terminal that displays the generated preconditions, and an emotion engine that recognizes the user's emotions. Each element works in conjunction to efficiently generate estimation preconditions and adjust them while taking the user's emotions into consideration.

[1502] Program Processing Overview

[1503] User input

[1504] Terminal input:

[1505] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system." After entering the information, the user clicks the submit button to send the project summary to the server.

[1506] Processing on the server

[1507] Data reception:

[1508] The server receives the case summary sent from the terminal.

[1509] Text cleaning:

[1510] The server removes unnecessary spaces and symbols from the received case summary. This process pre-processes the data.

[1511] Keyword extraction:

[1512] The server extracts key keywords from the pre-processed text. This keyword extraction clarifies the essential points of the project overview.

[1513] Generating preconditions

[1514] Input to and generation of the model:

[1515] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of historical preconditions.

[1516] Formatting of prerequisites:

[1517] The server formats the generated preconditions and converts them into a readable format. For example, it organizes each item into a bulleted list.

[1518] Use of an emotion engine

[1519] User emotion recognition:

[1520] The emotion engine built into the device recognizes the user's emotions. For example, it uses facial recognition technology and voice analysis technology to determine the user's emotions from their facial expressions and tone of voice.

[1521] Emotion-based adjustment:

[1522] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[1523] Output to the user

[1524] Submit prerequisites:

[1525] The server returns the formatted and adjusted prerequisites to the terminal.

[1526] Review and correction:

[1527] The user reviews the prerequisites generated on the device and corrects them as needed. For example, if the generated prerequisite is "3 testers," the user can correct it to "4 testers."

[1528] Specific example

[1529] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[1530] The duration of this project will be six months.

[1531] The system to be implemented is version X of a certain company's ERP system.

[1532] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[1533] The required resources will be one project manager, five developers, and three testers.

[1534] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[1535] Based on these prerequisites, users can efficiently advance their project plans. Furthermore, adjustments made by the emotion engine provide prerequisites tailored to the user's needs and circumstances.

[1536] The above describes the embodiment for carrying out the invention. This system significantly reduces the time and effort required to create estimation preconditions and enables the provision of services that take user emotions into consideration.

[1537] The following describes the processing flow.

[1538] Step 1:

[1539] The user enters a summary of the project into the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system."

[1540] Step 2:

[1541] The user clicks the submit button to send the entered case summary to the server.

[1542] Step 3:

[1543] The server receives the project summary from the terminal.

[1544] Step 4:

[1545] The server performs text cleaning on the case summaries it receives. Specifically, it removes unnecessary spaces and symbols.

[1546] Step 5:

[1547] The server extracts keywords from the cleaned text. At this stage, important words and phrases related to the case are identified.

[1548] Step 6:

[1549] The server inputs the extracted keywords into the generative model. The generative model is tuned based on a database of past preconditions.

[1550] Step 7:

[1551] The generative model generates preconditions based on the input keywords.

[1552] Step 8:

[1553] The server formats the generated prerequisites and converts them into a readable format. For example, it organizes each item into a bulleted list.

[1554] Step 9:

[1555] The emotion engine recognizes the user's emotions. The emotion engine installed in the device uses facial recognition and voice analysis to determine the user's emotions.

[1556] Step 10:

[1557] The server receives emotion data from the emotion engine and adjusts the underlying assumptions. For example, if the user is feeling stressed, it might add more detailed explanations.

[1558] Step 11:

[1559] The server returns the adjusted prerequisites to the terminal.

[1560] Step 12:

[1561] The user checks the prerequisites generated on their device. They read the displayed prerequisites and check their contents.

[1562] Step 13:

[1563] Users can modify the prerequisites as needed. For example, they can change "3 testers" to "4 testers."

[1564] Step 14:

[1565] Confirm the user's modified preconditions and save them as the final preconditions.

[1566] This series of processes efficiently generates and adjusts estimation assumptions, providing high-quality assumptions that reflect user preferences.

[1567] (Example 2)

[1568] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1569] Conventional estimation precondition generation systems generate preconditions based on user input, but they do not take into account the user's emotional state. Therefore, if the user is stressed or distracted, the generated preconditions may be inappropriate. Furthermore, they have the problem of low efficiency in preprocessing and keyword extraction, making it difficult to quickly provide practical estimation preconditions.

[1570] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1571] In this invention, the server includes means for inputting a case summary, means for preprocessing the input case summary, means for extracting keywords from the preprocessed data, means for generating preconditions based on the extracted keywords, means for formatting the generated preconditions, means for recognizing the user's emotions, means for adjusting the preconditions based on the recognized emotions, and means for outputting the generated and adjusted preconditions. This makes it possible to quickly generate and provide appropriate preconditions that take into account the user's emotional state.

[1572] "Means for inputting project overviews" refers to devices or software that provide an interface for users to input detailed project information.

[1573] "Means for pre-processing the input case summary" refers to devices or software that analyze the received case summary data and delete unnecessary information.

[1574] "Means for extracting keywords from pre-processed data" refers to algorithms or devices for selecting important keywords from pre-processed text data.

[1575] "Means for generating preconditions based on extracted keywords" refers to devices or software used to create estimation preconditions based on selected keywords.

[1576] "Means for formatting generated preconditions" refers to devices or software that organize and format generated preconditions in a way that makes them easy to read.

[1577] "Means of recognizing user emotions" refer to devices or software that determine emotions from a user's facial expressions, tone of voice, etc.

[1578] "Means for adjusting preconditions based on recognized emotions" refers to devices or software for modifying and adjusting preconditions generated according to the user's emotional state.

[1579] "Means for outputting generated and adjusted preconditions" refers to devices or software for ultimately displaying or transmitting the generated preconditions to the user.

[1580] This invention combines a system for automatically generating estimation preconditions in SE (Systems Engineer) work with an emotion engine that recognizes user emotions. Specific embodiments are described below.

[1581] System Configuration

[1582] This system consists of a terminal for inputting project details, a server for pre-processing data and generating preconditions, a terminal for displaying the generated preconditions, and an emotion engine that recognizes the user's emotions.

[1583] Program processing

[1584] User input

[1585] The user enters a summary of the project into the input form on the terminal. For example, they might enter "Support for the implementation of a large-scale ERP system" and click the submit button. This data is then sent from the terminal to the server.

[1586] Data reception and preprocessing

[1587] The server receives the case summary data sent from the terminal. Then, as a preprocessing step, it removes unnecessary spaces and symbols.

[1588] Keyword Extraction

[1589] From the pre-processed data, the server extracts key keywords. For example, from the project summary "Support for the implementation of a large-scale ERP system," keywords such as "large-scale," "ERP system," and "implementation support" are extracted.

[1590] Generating preconditions

[1591] The server uses a generative AI model to generate preconditions based on the extracted keywords. This generative AI model is tuned based on a database of past preconditions. For example, preconditions such as "project duration," "required resources," and "duration of each phase" are generated based on the keywords.

[1592] Formatting of prerequisites

[1593] The server formats the generated preconditions into a readable format. Specifically, it organizes each item into a bulleted list.

[1594] Using an Emotion Engine

[1595] The emotion engine built into the device recognizes the user's emotions. It uses facial recognition and voice analysis technologies to determine emotions from the user's facial expressions and tone of voice.

[1596] Emotion-based adjustment

[1597] The server adjusts the generated assumptions based on the emotional data obtained from the emotion engine. For example, if the user is experiencing stress, it may make the explanation of the assumptions more detailed.

[1598] Output of prerequisites

[1599] The formatted and adjusted prerequisites are sent from the server to the terminal and displayed to the user. The user can review these prerequisites and modify them as needed.

[1600] Specific example

[1601] The project description is "Support for the implementation of a large-scale ERP system," and if the emotion engine recognizes the user's stress when they input data, the following preconditions will be automatically generated and adjusted when using this system.

[1602] The duration of this project will be six months.

[1603] The system to be implemented is version X of a certain company's ERP system.

[1604] The design phase will take 3 months, the testing phase 2 months, and the transition phase 1 month.

[1605] The required resources will be one project manager, five developers, and three testers.

[1606] Since users are experiencing stress, we will supplement the explanation with more detailed information for each phase.

[1607] Example of a prompt

[1608] If the project description is "Support for the implementation of a large-scale ERP system" and the users are experiencing high levels of stress, please generate appropriate estimation assumptions.

[1609] This invention significantly reduces the time and effort required to create estimation assumptions and makes it possible to provide assumptions that take user sentiment into consideration.

[1610] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1611] Step 1:

[1612] User input

[1613] The user enters a summary of the project, such as "Support for the implementation of a large-scale ERP system," into the input form on the terminal and clicks the submit button.

[1614] Input: Project summary text (e.g., "Support for the implementation of a large-scale ERP system")

[1615] Operation: The terminal sends the entered text to the server.

[1616] Output: A summary text of the case is sent to the server.

[1617] Step 2:

[1618] Data reception

[1619] The server receives the case summary text sent from the terminal.

[1620] Input: Case summary text sent from the terminal

[1621] Operation: The server stores the received data in memory.

[1622] Output: Saved case summary text

[1623] Step 3:

[1624] Text cleaning

[1625] The server removes unnecessary spaces and symbols from the received case summary text.

[1626] Input: Received case summary text

[1627] Operation: The server uses regular expressions and string manipulation functions to remove unnecessary spaces and symbols (e.g., changing "Support for implementing large-scale ERP systems!!" to "Support for implementing large-scale ERP systems").

[1628] Output: Cleaned text data

[1629] Step 4:

[1630] Keyword Extraction

[1631] The server extracts important keywords from the cleaned text.

[1632] Input: Cleaned text data

[1633] Operation: The server uses natural language processing (NLP) algorithms to extract keywords (e.g., "large scale," "ERP system," "implementation support").

[1634] Output: List of extracted keywords

[1635] Step 5:

[1636] Generating preconditions

[1637] The server generates preconditions based on keywords extracted using a generative AI model.

[1638] Input: List of extracted keywords

[1639] Operation: The server inputs keywords into the generated AI model, and the model generates preconditions based on the learned database.

[1640] Output: Generated prerequisite data

[1641] Step 6:

[1642] Formatting of prerequisites

[1643] The server formats the generated preconditions into a readable format.

[1644] Input: Generated prerequisite data

[1645] Operation: The server formats the prerequisite data into bullet points or tables to make it easier to understand visually.

[1646] Output: Formatted prerequisites document

[1647] Step 7:

[1648] User emotion recognition

[1649] The emotion engine built into the device recognizes the user's emotions.

[1650] Input: User's facial expressions and voice data

[1651] Operation: The device uses facial recognition and voice analysis technologies to determine the user's emotions (e.g., if it recognizes that the user is feeling stressed).

[1652] Output: Recognized emotion data

[1653] Step 8:

[1654] Emotion-based adjustment

[1655] The server adjusts the preconditions based on the emotional data obtained from the emotion engine.

[1656] Input: Formatted prerequisite document, recognized sentiment data

[1657] Operation: Depending on the user's emotional state (e.g., stress), the explanation of prerequisites may be elaborated or specific items may be highlighted.

[1658] Output: Adjusted prerequisites document

[1659] Step 9:

[1660] Submitting prerequisites

[1661] The server sends the adjusted prerequisites to the terminal.

[1662] Input: Adjusted prerequisites document

[1663] Operation: The server sends prerequisite documents to the terminal.

[1664] Output: Prerequisites displayed on the terminal

[1665] Step 10:

[1666] Check and correct prerequisites

[1667] The user reviews the generated prerequisites and makes corrections as needed.

[1668] Input: Prerequisites displayed on the terminal

[1669] Operation: The user checks the prerequisites and makes corrections through the terminal interface (e.g., changing the prerequisite from "3 testers" to "4 testers").

[1670] Output: Modified final prerequisites

[1671] (Application Example 2)

[1672] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1673] Traditional automated systems for generating estimation assumptions in system engineering (SE) work have been unable to consider user emotions, limiting their ability to provide assumptions that reflect user stress and emotional states. Furthermore, assumptions that do not consider emotions may present users with unclear explanations or inappropriate conditions, potentially hindering project progress. A system is needed to address this issue and provide optimal assumptions that reflect user emotions.

[1674] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting a case overview, means for pre-processing the input case overview, means for extracting keywords from the pre-processed data, means for recognizing the user's emotions, means for adjusting the preconditions generated based on the emotions, and means for outputting the adjusted preconditions. This makes it possible to automatically generate estimation preconditions that take the user's emotions into consideration, and to provide the user with preconditions that are easy to understand and appropriate.

[1675] A "project overview" is a comprehensive description of a specific task or project, outlining key information, objectives, and scope.

[1676] "Preprocessing" refers to processes such as cleaning, formatting, and noise reduction to convert the input data into a more user-friendly format.

[1677] "Keywords" are words or phrases that have been extracted from text data as being particularly important.

[1678] "Prerequisites" refer to items that define the necessary elements, requirements, and constraints before the design and planning of a project or system.

[1679] "Means of recognizing user emotions" refers to technologies that detect and identify user emotions through the analysis of text, facial expressions, voice, etc.

[1680] "Means for adjusting preconditions generated based on emotions" refers to a mechanism that appropriately modifies the content and expression of generated preconditions in accordance with the detected emotions of the user.

[1681] This invention is a system for improving the user's shopping experience on e-commerce websites. When a user searches for and purchases products, the system recognizes the user's emotions and recommends the most suitable products and services. Furthermore, it provides a mechanism for automatically adjusting customer support based on the user's emotions. The embodiments of this system will be described in detail below.

[1682] System Configuration

[1683] This system consists of the following main components:

[1684] 1. User's device: A mobile device such as a smartphone or tablet.

[1685] 2. Server: Performs data reception, preprocessing, keyword extraction, precondition generation, sentiment recognition, precondition adjustment, and output.

[1686] 3. Emotion Engine: Uses facial recognition and voice analysis technologies to determine the user's emotions.

[1687] Program Processing Overview

[1688] 1. User input

[1689] The user enters a search query, for example, "new smartphone," into the search bar on the smartphone app.

[1690] 2. Data reception and preprocessing

[1691] The server receives the entered search query and processes it to remove unnecessary spaces and symbols. Specifically, it performs cleaning using a text processing library (e.g., NLTK or SpaCy).

[1692] 3. Keyword Extraction

[1693] The server extracts keywords from the pre-processed text data. This identifies important words such as "smartphone."

[1694] 4. Product Recommendation Generation

[1695] Based on past purchase data and user browsing history, a recommendation engine (e.g., TensorFlow Recommenders) is used to generate a list of appropriate products.

[1696] 5. Emotion recognition

[1697] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) is used to acquire emotional data from the user's facial expressions and voice tone.

[1698] 6. Emotion-based adjustment

[1699] The server adjusts the generated product list and descriptions based on the emotional data obtained from the emotion engine. For example, if a user is feeling stressed, it provides a concise product description and a permanent purchase link in friendly language.

[1700] 7. Output to the user

[1701] We provide users with a streamlined product list and descriptions on their devices, ensuring a smooth shopping experience.

[1702] Specific example

[1703] The following are examples of prompts to input into the generative AI model.

[1704] Prompt example:

[1705] The user searched for "new smartphone," and the emotion engine detected stress. In this case, to make the shopping experience smoother, display a concise product description and a permanent purchase link using friendly language.

[1706] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1707] Step 1:

[1708] User input

[1709] The user enters "new smartphone" into the search bar on the smartphone app. Once the user finishes typing and clicks the search button, this search query is sent to the server. The input data is sent to the server in text format.

[1710] Step 2:

[1711] Data reception and preprocessing

[1712] The server receives the search query sent from the user's terminal. The server uses a text processing library (e.g., NLTK or SpaCy) to clean this text data, removing unnecessary spaces and symbols. This results in a formatted search query.

[1713] Step 3:

[1714] Keyword Extraction

[1715] The server extracts important keywords from the pre-processed text data. It uses a keyword extraction algorithm to identify key words such as "smartphone." The extracted keywords are stored as data for use in subsequent processing.

[1716] Step 4:

[1717] Generate product recommendations

[1718] Based on the extracted keywords, the server uses a recommendation engine (e.g., TensorFlow Recommenders) to generate a list of appropriate products by referencing past purchase data and user browsing history. This results in a list of relevant products.

[1719] Step 5:

[1720] emotion recognition

[1721] Using the camera and microphone on the user's device, an emotion engine (e.g., Microsoft Azure Face API or Amazon Rekognition) analyzes the user's facial expressions and voice tone to obtain emotional data. This emotional data is categorized into states such as stress, excitement, and indifference, and then sent to the server.

[1722] Step 6:

[1723] Emotion-based adjustment

[1724] The server adjusts the product list and descriptions generated based on the emotional data obtained from the emotion engine. For example, if the server determines that the user is stressed, it automatically generates a concise product description in friendly language and provides a fixed purchase link. This adjusted data is then generated.

[1725] Step 7:

[1726] Output to the user

[1727] The server sends the adjusted product list and descriptions to the user's device. The user's device receives this and displays it on the screen. This allows the user to proceed with the purchase process smoothly based on the adjusted information.

[1728] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1729] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1730] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1731] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1732] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1733] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1734] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1735] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1736] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1737] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1738] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1739] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1740] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1741] 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.

[1742] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1743] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1744] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1745] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1746] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1747] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1748] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1749] The following is further disclosed regarding the embodiments described above.

[1750] (Claim 1)

[1751] A means of entering the project details,

[1752] A means for pre-processing the summary of the entered case,

[1753] A means for extracting keywords from preprocessed data,

[1754] A means of generating preconditions based on extracted keywords,

[1755] A means for outputting the generated preconditions,

[1756] A system that includes this.

[1757] (Claim 2)

[1758] The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

[1759] (Claim 3)

[1760] The system according to claim 1, comprising means for generating preconditions using a generative model.

[1761] "Example 1"

[1762] (Claim 1)

[1763] A means of entering the project details,

[1764] A means for pre-processing the summary of the entered case,

[1765] A means for extracting keywords from preprocessed data,

[1766] A means of generating preconditions based on extracted keywords,

[1767] A means for outputting the generated preconditions,

[1768] From a means of inputting the project overview to a means of receiving data,

[1769] A means of cleaning the text of the received data,

[1770] Means for refining the preconditions,

[1771] A system that includes this.

[1772] (Claim 2)

[1773] The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

[1774] (Claim 3)

[1775] The system according to claim 1, comprising means for generating preconditions using a generative model.

[1776] "Application Example 1"

[1777] (Claim 1)

[1778] A means of entering the project details,

[1779] A means for pre-processing the summary of the entered case,

[1780] A means for extracting keywords from preprocessed data,

[1781] A means of generating preconditions based on extracted keywords,

[1782] A means for outputting the generated preconditions,

[1783] A means of automatically generating a production plan based on preconditions,

[1784] A system that includes this.

[1785] (Claim 2)

[1786] The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

[1787] (Claim 3)

[1788] The system according to claim 1, comprising means for generating preconditions using a generative model.

[1789] "Example 2 of combining an emotion engine"

[1790] (Claim 1)

[1791] A means of entering the project details,

[1792] A means for pre-processing the summary of the entered case,

[1793] A means for extracting keywords from preprocessed data,

[1794] A means of generating preconditions based on extracted keywords,

[1795] A means of formatting the generated preconditions,

[1796] Means of recognizing user emotions,

[1797] Means for adjusting preconditions based on recognized emotions,

[1798] Means for outputting generated and adjusted preconditions,

[1799] A system that includes this.

[1800] (Claim 2)

[1801] The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

[1802] (Claim 3)

[1803] The system according to claim 1, comprising means for generating preconditions using a generative model.

[1804] "Application example 2 when combining with an emotional engine"

[1805] (Claim 1)

[1806] A means of entering the project details,

[1807] A means for pre-processing the summary of the entered case,

[1808] A means for extracting keywords from preprocessed data,

[1809] A means of generating preconditions based on extracted keywords,

[1810] Means of recognizing user emotions,

[1811] Means for adjusting the preconditions generated based on emotions,

[1812] A means for outputting the adjusted preconditions,

[1813] A system that includes this.

[1814] (Claim 2)

[1815] The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

[1816] (Claim 3)

[1817] The system according to claim 1, comprising means for generating preconditions using a generative AI model. [Explanation of Symbols]

[1818] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of entering the project details, A means for pre-processing the summary of the entered case, A means for extracting keywords from preprocessed data, A means of generating preconditions based on extracted keywords, A means for outputting the generated preconditions, A system that includes this.

2. The system according to claim 1, further comprising means for removing unnecessary spaces and symbols from preprocessed data.

3. The system according to claim 1, comprising means for generating preconditions using a generative model.

Images