system

Abstract

Provide a system. 【Solution means】 Terminal means for inputting information, Server means for receiving information from the terminal means, Server means for extracting similar data from a past database, Server means for selecting an optimal member using a generation model, Server means for generating and outputting a selected member list, Server means for transmitting the member list to the terminal means, Server means for receiving feedback from the user and training the generation model, ··· A system including the above.

Description

【Technical Field】 , , , , , , 【0004】 , , , , 【0005】 , , , , , 【0003】 , , , 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 that responds to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Unexamined Patent Application Publication No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 <00000၂5>In base station construction work, the selection work of various members required for each frequency depends on the skills and know-how of skilled workers, so it is personnel-dependent, and there is a problem that resource allocation to new projects and construction efficiency are hindered. Therefore, it is necessary to standardize and improve the efficiency of member selection to secure resources for new challenges. 【Means for Solving the Problems】 【0005】 This invention provides a system in which a server receives construction information entered via a terminal and extracts similar data from a past database. It then uses a generative model to select the optimal components and generates and outputs a list of selected components. Furthermore, by receiving user feedback and training the generative model, the accuracy of component selection is improved. This aims to standardize and streamline the construction process and reduce tasks that rely on individual expertise. 【0006】 A "terminal device" is a device used by users to input information related to construction work and transmit it to a server device. 【0007】 A "server device" is a central device that analyzes past data based on information received from terminal devices and performs generational model execution and component selection list generation. 【0008】 A "database" is an information repository that stores data related to past construction projects and enables the extraction of similar data. 【0009】 A "generative model" is an algorithm that uses past data and know-how to select the optimal materials according to construction conditions. 【0010】 A "parts list" is a summary of the types and quantities of necessary parts selected by the generation model. 【0011】 "Feedback" refers to confirmations and corrections made by the user regarding the contents of the component selection list, and is sent to the server. [Brief explanation of the drawing] 【0012】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and 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. 【Embodiments for Carrying Out the Invention】 【0013】 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. 【0014】 First, the language used in the following description will be explained. 【0015】 In the following embodiments, the labeled 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. 【0016】 In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0017】 In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and 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. 【0018】 In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0019】 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." 【0020】 [First Embodiment] 【0021】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0022】 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. 【0023】 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). 【0024】 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. 【0025】 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. 【0026】 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. 【0027】 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. 【0028】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0029】 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. 【0030】 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. 【0031】 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. 【0032】 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". 【0033】 The component selection system according to the present invention automates the selection of necessary components in base station construction work using AI technology, thereby achieving standardization and efficiency. This system operates according to the following flow. 【0034】 First, the user uses a terminal to enter detailed information about the construction project. This includes data such as the location of the construction, the type of base station to be built, and the frequency band to be used. The entered data is sent to the server in real time, and processing begins. 【0035】 Upon receiving this information, the server searches its internal database for similar past construction records. These search results are used as the basis for selecting the necessary components. The server then performs an analysis using a generative model to select the optimal components. This generative model analyzes past construction data and incorporates an algorithm to select the type and quantity of components based on the results. 【0036】 The component list generated by the server is sent to the user's terminal. This list includes information such as the specific names of the selected components, the required quantities, and recommended suppliers, which the user can use to procure components at the construction site. The user who receives the list can also review its contents and provide feedback as needed. 【0037】 User feedback is sent back to the server from the device, and the server incorporates it into the generative model as training data. This allows for improved accuracy in future analyses and the accumulation of know-how. 【0038】 As a concrete example, considering base station construction within a high-rise building, the user inputs the building's height, wall materials, and operating frequency. The server then references similar past cases to select the optimal antenna type and cable type. As a result, the user is immediately provided with an optimized list of materials, allowing them to smoothly proceed with construction preparations based on this list. In this way, the system provides a form that achieves highly efficient construction without relying on individual skills. 【0039】 The following describes the processing flow. 【0040】 Step 1: 【0041】 The user uses a terminal to input detailed information about the construction project. This includes the construction location, the planned base station type, the frequency used, and the terrain conditions. The terminal organizes the entered information and prepares it for transmission to the server. 【0042】 Step 2: 【0043】 The terminal sends the entered construction information to the server. The transmitted data is processed in real time and received within the server. 【0044】 Step 3: 【0045】 Based on the received construction information, the server searches the database for data on similar past construction projects. The server efficiently extracts past cases that have attributes that match or are similar to the received information. 【0046】 Step 4: 【0047】 The server inputs the extracted data into a generative model to select the optimal materials for the construction conditions. The generative model utilizes accumulated know-how to perform analysis to determine the types and quantities of materials required. 【0048】 Step 5: 【0049】 The server creates an optimal list of components based on the analysis results of the generative model. The component list includes the names of the selected components, the required quantities, and recommended suppliers. 【0050】 Step 6: 【0051】 The server sends the materials list it has created to the user's terminal. The user can then review the received list and proceed smoothly with construction preparations. 【0052】 Step 7: 【0053】 The user enters feedback on the received parts list via their device. This feedback includes the accuracy of the list and any additional requests. 【0054】 Step 8: 【0055】 The device sends user feedback to the server. The server receives the feedback and uses it as training data to incorporate it into the generative model. 【0056】 Step 9: 【0057】 The server stores the feedback in the model's data and trains the model to use it for subsequent analyses. This process improves the accuracy of component selection. 【0058】 (Example 1) 【0059】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0060】 The process of selecting materials for telecommunications base station construction has traditionally relied on the knowledge and experience of specialists, and there is a need for efficiency and standardization. Furthermore, data analysis for optimal material selection is time-consuming and a source of inefficiency. In addition, it has been difficult to make improvements based on real-time user feedback, and there have been challenges in accumulating know-how. 【0061】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0062】 In this invention, the server includes an information processing device for receiving and storing information, an information processing device for extracting similar information from past records, and an information processing device for selecting the optimal components using a generative model. This enables efficient and standardized component selection. 【0063】 An "input device means" is a device that provides an interface for the user to input detailed information about the construction work and transmits that information to a server. 【0064】 An "information processing device" is a device that stores information received from an input device, extracts similar information from a past database, and selects the optimal components using a generative model. 【0065】 A "generative model" is a machine learning model that learns from information about past operations and is equipped with an algorithm to optimize component selection. 【0066】 "Components" refers to the types and quantities of materials used in base station construction. 【0067】 A "response mechanism" is a means of receiving feedback from the operator and incorporating it into the learning process of the generative model. 【0068】 "Operator" refers to the user who inputs detailed construction information through an input device and checks the results. 【0069】 This invention is a system for streamlining and standardizing the selection of components in telecommunications base station construction. Specific embodiments for carrying out the invention are described below. 【0070】 The user uses a terminal to input detailed information about the construction work. This information includes, for example, the location and type of base station to be installed, and the frequency band to be used. The terminal transmits this input information to the server in real time. 【0071】 The server receives the input information and stores it in the database. The information processing device installed on the server searches the database for records of similar past construction projects and extracts the necessary information. Based on this data, the generative AI model is activated and begins the process of selecting the optimal components. The generative AI model utilizes various machine learning algorithms to output the optimal antenna and cable types based on the construction conditions. 【0072】 The generated list of components is sent from the server to the user's terminal. The user can then use this list to prepare for construction. Furthermore, the user can review the list and provide feedback on its contents. This feedback is sent back to the server and used as training data for the generated AI model, which will be used to improve the accuracy of future selections. 【0073】 A concrete example is the installation of a base station inside a high-rise building. When the user inputs information such as the building's height, wall materials, and the frequency to be used, the server refers to similar past cases and selects the optimal antenna type and cable type. In this process, a generative AI model functions effectively, quickly providing an optimized list of components. 【0074】 An example of a prompt message is: "What are the optimal antenna and cable types for base station installation in a high-rise building? The building is 200m tall, the walls are made of concrete, and the operating frequency is 3.5GHz." 【0075】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0076】 Step 1: 【0077】 The user operates the terminal to input detailed information about the construction work. Specifically, they enter the location, type, and frequency band of the base station, and write the data in the input form on the terminal. This data is sent to the server when the send button is clicked. 【0078】 Step 2: 【0079】 The server securely receives information from the terminal and stores it in the database. The server then parses and indexes the received data to prepare it for efficient data retrieval. In this scenario, the input is construction information sent by the user, and the output is the parsed data stored in the database. 【0080】 Step 3: 【0081】 The server searches the database based on the stored data and extracts records of similar past construction projects. Specifically, it uses SQL queries to extract relevant data and uses it as basic data for selecting materials. This process uses filtering based on similarity to obtain highly accurate data. The output is relevant past construction data. 【0082】 Step 4: 【0083】 The server launches the generative model, analyzes the extracted historical data, and selects the optimal components. The input is the historical construction data obtained in step 3, and the generative AI model analyzes this data to determine the optimal components. Specifically, the algorithm uses advanced machine learning techniques to scrutinize the data and outputs a list of components that best meet the requirements. 【0084】 Step 5: 【0085】 The server sends the generated parts list to the user's terminal. The output includes details such as the specific names, quantities, and recommended suppliers for each part. This list is delivered to the user via email or in-app message. 【0086】 Step 6: 【0087】 The user reviews the received parts list using a terminal and provides feedback. Specifically, the user evaluates the list and fills in suggested changes or additional information as needed. The resulting feedback data is then sent from the terminal to the server as input. 【0088】 Step 7: 【0089】 The server receives feedback from users and updates the generative AI model. The input is user feedback data, which is added to the generative AI model's training dataset. Specifically, the model's training algorithm takes the feedback into account, aiming to enhance its know-how and improve future analytical accuracy. The output is the updated generative AI model. 【0090】 (Application Example 1) 【0091】 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." 【0092】 Material selection at construction sites is inefficient because it relies on subjective judgment based on experience. Furthermore, inappropriate material selection can lead to delays in the overall construction plan. Solving this problem is essential. 【0093】 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. 【0094】 In this invention, the server includes a mobile information terminal equipped with information processing means, a calculation means for extracting similar records from past work records, and a calculation means for selecting the optimal materials using a generative model. This enables efficient and highly accurate material selection at construction sites. 【0095】 An "information processing device" is a device installed in a mobile information terminal for analyzing and processing input information. 【0096】 A "mobile information terminal" is a portable electronic device used for on-site information input and communication. 【0097】 "Computation means" refers to a device or system for processing data and performing specific computational operations. 【0098】 A "generative model" is an algorithm or mathematical model used to make optimal selections based on historical data. 【0099】 A "materials list" is a collection of data that summarizes the specific names and quantities of selected construction materials. 【0100】 "Information means" refers to a device or method for receiving input information from a user and performing a specific function. 【0101】 A "worker" is a person who performs tasks such as selecting materials and entering information at a construction site. 【0102】 This invention is a system designed to streamline material selection at construction sites. The system consists of a server that receives and processes information, and a mobile information terminal that inputs and receives information. 【0103】 Users input information related to construction projects using mobile information terminals such as smartphones and tablets. This information includes the location of the construction site, building structure information, and required materials. The terminals are equipped with information processing means to transmit data to a server. 【0104】 Upon receiving information, the server uses computational tools to compare it with past construction records in the database and extract similar records. During this process, an AI algorithm called a generative model is used to select the optimal type and quantity of materials. Because the generative model optimizes materials based on historical data, it can address the diverse needs of each construction site. 【0105】 The selected materials are output as a materials list, and the server sends this list back to the terminal. The user can review this list through the information system and modify it as needed. 【0106】 As a concrete example, consider the case of a high-rise building construction project in central Tokyo. For instance, by entering a request into the terminal such as, "Tell me what antenna installation materials are needed for the construction of a 50-story building in Shinjuku Ward," the server can refer to similar past cases to select the most suitable antenna type and accessories, and immediately return a list to the user. 【0107】 An example of a prompt message is as follows: "Project: Base station installation in a high-rise building in Shinjuku Ward, Floors: 50th floor, Frequency used: 2.5 GHz, Wall material: Concrete, Result: 'List of optimal antennas and cables'". 【0108】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0109】 Step 1: 【0110】 The terminal receives information about construction projects entered by the user. This information includes the construction site, building structure information, and technical specifications to be used. The terminal packages this information as digital data and sends it to the server. The input is text data, and the output is packaged digital data. 【0111】 Step 2: 【0112】 The server analyzes the received digital data and extracts similar records from the past construction database. This process involves performing database query operations to filter data that matches specific criteria. The input is digital data received from the terminal, and the output is the extracted similar record data. 【0113】 Step 3: 【0114】 The server uses a generative AI model to analyze extracted similar records and generate an optimal material list. At this stage, the AI ​​algorithm selects materials and determines the optimal type and quantity. The input is similar record data, and the output is the generated material list. 【0115】 Step 4: 【0116】 The server sends the generated material list as digital data to the terminal. The terminal then displays this information in a user-friendly format. The input here is the digital material list, and the output is digital data formatted for display. 【0117】 Step 5: 【0118】 Users can view the material list through their terminal and add or modify information as needed. This process generates user feedback data. The input is the displayed material list, and the output is the modified feedback data. 【0119】 Step 6: 【0120】 The device sends user feedback data to the server. The server receives this data and uses it as training data to improve the accuracy of the generative AI model. The input is the user feedback data, and the output is the updated generative AI model. 【0121】 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. 【0122】 The system according to the present invention streamlines and standardizes the selection of materials in base station construction work, and further provides a more advanced feedback system by taking into account the user's emotional state. In addition to its basic function of processing user input in real time and generating an optimal list of materials using past data and generative models, the system incorporates an emotion engine to understand the user's satisfaction and dissatisfaction. 【0123】 First, the user uses a terminal to input detailed information about the construction project. This information includes the location of the construction, the type of base station to be used, and the frequency to be used. The terminal organizes the information before sending it to the server. Based on the received information, the server searches its database for appropriate past cases and selects materials using a generative model. This process generates a list of selected materials. 【0124】 The emotion engine analyzes data entered by the user on the device and the content of the feedback. This engine utilizes natural language processing technology to evaluate potential satisfaction and dissatisfaction from the user's language, and dynamically adjusts the generative model's learning algorithm based on the results. This is expected to bring future analysis and component selection results closer to the user's expectations. 【0125】 When users review the generated parts list, their emotions are displayed in the interface, allowing them to receive appropriate support. This interface can provide operational guidance and information recommendations tailored to the user's emotional response. For example, if a user feels anxious while reviewing the parts list, the system, sensing this emotion, will immediately provide supplementary information to aid understanding. 【0126】 By introducing this system, it will be possible to move away from traditional, person-dependent methods in the component selection process while improving the user experience and streamlining project management. 【0127】 The following describes the processing flow. 【0128】 Step 1: 【0129】 The user uses a terminal to input details about the construction project. This information includes details about the construction location, base station type, frequency used, and construction environment. The terminal organizes the entered information and prepares it for transmission to the server. 【0130】 Step 2: 【0131】 The terminal sends the input information to the server. The server receives this information in real time and proceeds to the next processing step. 【0132】 Step 3: 【0133】 Based on the received construction information, the server searches the database for similar past construction cases. The server quickly extracts the search results and aggregates data on similar cases. 【0134】 Step 4: 【0135】 The server applies a generative model based on similar cases to select the optimal components for the construction conditions. The generative model uses the accumulated data to create an optimal component list. 【0136】 Step 5: 【0137】 The server generates a list of components and sends it to the user's terminal. The user can then review the received list on their terminal and use it as needed. 【0138】 Step 6: 【0139】 Users input feedback through their devices. Users review the contents of the parts list and provide feedback, including their satisfaction level and any points of dissatisfaction. 【0140】 Step 7: 【0141】 The device sends user feedback to the server. The server receives this feedback and analyzes it using an emotion engine. 【0142】 Step 8: 【0143】 The server's emotion engine analyzes the feedback content and evaluates the user's emotional state. Natural language processing is used to analyze the user's language use and understand their level of satisfaction or dissatisfaction. 【0144】 Step 9: 【0145】 The server adjusts the generative model's learning process based on the results obtained from the emotion engine. This information is fed back into the algorithm and used to improve the accuracy of subsequent analyses and component selections. 【0146】 (Example 2) 【0147】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0148】 This invention aims to move away from conventional, subjective methods in the selection process of elements in construction work, and to standardize and improve efficiency. Furthermore, it seeks to solve the problem of achieving more sophisticated element selection and improved user experience based on feedback that takes user emotions into consideration. 【0149】 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. 【0150】 In this invention, the server includes a computing device for receiving information, a computing device for extracting similar information from past information sets, and a computing device for selecting the optimal elements using a generative model. This enables efficient element selection that takes user emotions into consideration. 【0151】 "Device" refers to hardware or software means for a user to input or receive information. 【0152】 A "processing unit" is a central processing unit or a means of a computer used to process, analyze, or output information. 【0153】 An "information collection" is a database or data repository that stores past cases and related data. 【0154】 A "generative model" is an algorithm or program that uses machine learning or artificial intelligence techniques to generate the optimal output from target data. 【0155】 An "element" refers to a component, material, or other constituent element that should be selected in a construction or project. 【0156】 "Opinions" refer to feedback and comments provided by users to the system, and are data that helps improve the system. 【0157】 An "operation screen" is an interface used by a user to input information into a system or to view output from the system. 【0158】 The system of this invention achieves efficient element selection in construction through information input, analysis, element selection, and dynamic adjustment based on feedback. This system mainly consists of terminals and a server. 【0159】 First, the user inputs detailed information about the construction project through a terminal. This information includes the construction location, the type of base station to be used, and the frequency to be used. The terminal organizes the input information and sends it to the server. Based on this information, the server searches for similar information from past data sets. This makes it possible to support selection based on experience. 【0160】 The server uses a generative AI model in the selection process. This model is trained using machine learning techniques to suggest the most suitable elements for the input information. For example, if the construction site is in an urban area, the model will prioritize selecting elements with superior durability. This selection generates a list of appropriate elements, which are then sent back to the terminal. 【0161】 User feedback is sent to the server and evaluated by the sentiment engine. This allows the system to dynamically adjust the generative model's algorithm, enabling selections that are more in line with the user's emotions. 【0162】 For example, if a user has concerns about a construction element, the system detects this concern and provides supplementary information to help the user understand. Furthermore, the user interface displays an information guide that allows the user to confidently review the selection results. 【0163】 An example of a prompt message might be, "The construction site is in Minato Ward, Tokyo, and the base station to be installed is a small base station. The operating frequency is the 2.5GHz band. What materials are recommended?" Based on this, the system selects the necessary components. 【0164】 In this way, the system achieves efficient and highly accurate element selection while taking user emotions into consideration. 【0165】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0166】 Step 1: 【0167】 The user uses a terminal to input information about the construction work. Specifically, they input data such as the location of the construction, the type of base station to be built, and the frequency to be used. This information is formatted into the appropriate format within the terminal. Input is in text format, and a formatted JSON object is generated as output. 【0168】 Step 2: 【0169】 The terminal sends formatted information to the server. HTTPS is used as the communication protocol, ensuring that the information is transmitted securely. The input is formatted data, and output is produced when the information correctly reaches the server. The terminal then sends a "POST" request to the server endpoint. 【0170】 Step 3: 【0171】 The server analyzes the received information and extracts similar information from past data sets. It executes SQL queries against the database to retrieve data that matches the criteria. The input is the construction information received by the server, and the output is a data list containing similar information. Specifically, it searches for data that matches past project data. 【0172】 Step 4: 【0173】 The server uses a generative AI model to select the optimal elements based on construction information and similar data. A model algorithm trained through machine learning is used to create a list of elements as selection candidates. The input is extracted similar data, and the output is a list of elements based on the model's predictions. The server then feeds the data into the generative AI model, and the element selection process is executed. 【0174】 Step 5: 【0175】 The server sends a list of selected elements to the terminal. The generated list of elements is sent again using the HTTPS protocol, ensuring secure transmission. The input is the list of elements, and the output is the list displayed on the user's terminal. The server returns data to the terminal using a "GET" request. 【0176】 Step 6: 【0177】 Users can view a list of elements received on their device and provide feedback. This user feedback is transmitted as input to the emotion engine, analyzed, and used to refine future AI model generation. A feedback form is displayed on the device, and the specific action of submitting the feedback is performed. 【0178】 Step 7: 【0179】 The server utilizes user feedback to dynamically adjust the algorithms of the generated AI model. Natural language processing techniques are used for sentiment analysis, and this data is incorporated to improve the model's prediction accuracy. The input is user feedback, and the output is the updating of the model's parameters. The sentiment analysis engine then performs the specific operation of analyzing the feedback. 【0180】 (Application Example 2) 【0181】 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". 【0182】 Traditional base station construction methods for selecting materials tend to be experience-dependent and subjective, limiting efficiency and standardization. Furthermore, the lack of mechanisms to adequately consider user emotions and feedback made it difficult to improve user satisfaction. To address these challenges, a system for efficient material selection that also considers user emotions is needed. 【0183】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0184】 In this invention, the server includes a computing device means for inputting information, a computer means for receiving information from the computing device means, and a computer means for evaluating the user's emotional state using emotion analysis means and providing support information based on the results. This makes it possible to improve efficiency and standardization in the component selection process, and to improve user satisfaction by providing support information that takes the user's emotions into consideration. 【0185】 "Information input device means" refers to a device system for users to input detailed information and feedback on construction work. 【0186】 "Computing means" refers to a server system that processes information received from a computing device and performs necessary calculations. 【0187】 A "data repository" is a database where past cases and data are stored, and it is an information source that computer systems refer to. 【0188】 A "generative model" is an algorithm that generates the optimal list of components based on past data. 【0189】 The "component list" is a list of materials required for base station construction, output by a computer using a generative model. 【0190】 A "computer means for receiving opinions" refers to a server system that receives feedback from users and utilizes it to train generative models. 【0191】 An "emotion analysis tool" is a program or algorithm that evaluates a user's emotional state from their voice, facial expressions, etc., and generates support information based on that evaluation. 【0192】 "Computer means for providing support information" refers to a server system for providing support information generated by emotion analysis means to users. 【0193】 The "display function" is a screen display system that allows users to view and confirm component lists and related information. 【0194】 This invention supports the realization of a system that enables efficient and emotionally conscious selection of components at construction sites. Users can input necessary information and select components via a smart device. The computing means extracts similar past data from a database based on the input information and generates an optimal component list using a generative model. Artificial intelligence technologies such as TENSORFLOW® and PyTorch are applied to this generative model. 【0195】 The server also analyzes the user's voice and facial expressions using sentiment analysis tools to understand the user's emotions. This utilizes Google® Cloud Natural Language API and Azure® Text Analytics. Based on the analysis results, the computing tools provide the user with the most appropriate support information and advice. The goal is to enhance the user's sense of security and satisfaction through the presentation of support information. 【0196】 As a concrete example, when construction workers select components in real time, their feelings of anxiety are analyzed, and information such as "This component complies with the latest building standards" is immediately presented as supporting information. In this way, computing means can provide information that contributes to the success of a project based on the user's emotions. 【0197】 An example prompt might be: "Generate a list of the best materials for this construction project. The target location is an urban area, and we plan to build a 3G LTE base station. The workers seem unsure about material selection." This allows the server to provide appropriate feedback. 【0198】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0199】 Step 1: 【0200】 Users input detailed information about the construction site using a smart device. This information includes the construction location, base station type, and operating frequency. This information is temporarily stored on the device. 【0201】 Step 2: 【0202】 The terminal organizes the entered information and sends it to the server. The server receives this information and searches its database for similar past project data. This search result is temporarily stored for use in the next step. 【0203】 Step 3: 【0204】 The server applies a generative model to generate the optimal component list based on the searched similar data. The generation process uses input construction information and data retrieved from the database. The generative model leverages algorithms from TensorFlow and PyTorch. The resulting component list is stored in the database. 【0205】 Step 4: 【0206】 Users submit feedback via their smart devices. This feedback includes comments and questions about the user's component list. This information is received and temporarily stored by the server. 【0207】 Step 5: 【0208】 The server uses sentiment analysis tools to evaluate the user's emotional state from their feedback and voice. Google Cloud Natural Language API and Azure Text Analytics are used for this analysis. The emotional information obtained from this analysis is then used in the next step. 【0209】 Step 6: 【0210】 Based on the sentiment analysis results, the server generates supportive information for the user. This information includes advice and recommendations designed to enhance the user's sense of security. The server then sends this information to the user's smart device. 【0211】 Step 7: 【0212】 The user receives and reviews the support information provided through their smart device. Specific instructions are displayed to help the user understand the information in more detail. 【0213】 Step 8: 【0214】 The server updates its generative model based on user feedback and sentiment analysis results. This improvement enhances the accuracy of component selection in subsequent uses. 【0215】 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. 【0216】 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. 【0217】 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. 【0218】 [Second Embodiment] 【0219】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0220】 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. 【0221】 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). 【0222】 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. 【0223】 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. 【0224】 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). 【0225】 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. 【0226】 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. 【0227】 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. 【0228】 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. 【0229】 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. 【0230】 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". 【0231】 The component selection system according to the present invention automates the selection of necessary components in base station construction work using AI technology, thereby achieving standardization and efficiency. This system operates according to the following flow. 【0232】 First, the user uses a terminal to enter detailed information about the construction project. This includes data such as the location of the construction, the type of base station to be built, and the frequency band to be used. The entered data is sent to the server in real time, and processing begins. 【0233】 Upon receiving this information, the server searches its internal database for similar past construction records. These search results are used as the basis for selecting the necessary components. The server then performs an analysis using a generative model to select the optimal components. This generative model analyzes past construction data and incorporates an algorithm to select the type and quantity of components based on the results. 【0234】 The component list generated by the server is sent to the user's terminal. This list includes information such as the specific names of the selected components, the required quantities, and recommended suppliers, which the user can use to procure components at the construction site. The user who receives the list can also review its contents and provide feedback as needed. 【0235】 User feedback is sent back to the server from the device, and the server incorporates it into the generative model as training data. This allows for improved accuracy in future analyses and the accumulation of know-how. 【0236】 As a concrete example, considering base station construction within a high-rise building, the user inputs the building's height, wall materials, and operating frequency. The server then references similar past cases to select the optimal antenna type and cable type. As a result, the user is immediately provided with an optimized list of materials, allowing them to smoothly proceed with construction preparations based on this list. In this way, the system provides a form that achieves highly efficient construction without relying on individual skills. 【0237】 The following describes the processing flow. 【0238】 Step 1: 【0239】 The user uses a terminal to input detailed information about the construction project. This includes the construction location, the planned base station type, the frequency used, and the terrain conditions. The terminal organizes the entered information and prepares it for transmission to the server. 【0240】 Step 2: 【0241】 The terminal sends the entered construction information to the server. The transmitted data is processed in real time and received within the server. 【0242】 Step 3: 【0243】 Based on the received construction information, the server searches the database for data on similar past construction projects. The server efficiently extracts past cases that have attributes that match or are similar to the received information. 【0244】 Step 4: 【0245】 The server inputs the extracted data into a generative model to select the optimal materials for the construction conditions. The generative model utilizes accumulated know-how to perform analysis to determine the types and quantities of materials required. 【0246】 Step 5: 【0247】 The server creates an optimal list of components based on the analysis results of the generative model. The component list includes the names of the selected components, the required quantities, and recommended suppliers. 【0248】 Step 6: 【0249】 The server sends the materials list it has created to the user's terminal. The user can then review the received list and proceed smoothly with construction preparations. 【0250】 Step 7: 【0251】 The user enters feedback on the received parts list via their device. This feedback includes the accuracy of the list and any additional requests. 【0252】 Step 8: 【0253】 The device sends user feedback to the server. The server receives the feedback and uses it as training data to incorporate it into the generative model. 【0254】 Step 9: 【0255】 The server stores the feedback in the model's data and trains the model to use it for subsequent analyses. This process improves the accuracy of component selection. 【0256】 (Example 1) 【0257】 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." 【0258】 The process of selecting materials for telecommunications base station construction has traditionally relied on the knowledge and experience of specialists, and there is a need for efficiency and standardization. Furthermore, data analysis for optimal material selection is time-consuming and a source of inefficiency. In addition, it has been difficult to make improvements based on real-time user feedback, and there have been challenges in accumulating know-how. 【0259】 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. 【0260】 In this invention, the server includes an information processing device for receiving and storing information, an information processing device for extracting similar information from past records, and an information processing device for selecting the optimal components using a generative model. This enables efficient and standardized component selection. 【0261】 An "input device means" is a device that provides an interface for the user to input detailed information about the construction work and transmits that information to a server. 【0262】 An "information processing device" is a device that stores information received from an input device, extracts similar information from a past database, and selects the optimal components using a generative model. 【0263】 A "generative model" is a machine learning model that learns from information about past operations and is equipped with an algorithm to optimize component selection. 【0264】 "Components" refers to the types and quantities of materials used in base station construction. 【0265】 A "response mechanism" is a means of receiving feedback from the operator and incorporating it into the learning process of the generative model. 【0266】 "Operator" refers to the user who inputs detailed construction information through an input device and checks the results. 【0267】 This invention is a system for streamlining and standardizing the selection of components in telecommunications base station construction. Specific embodiments for carrying out the invention are described below. 【0268】 The user uses a terminal to input detailed information about the construction work. This information includes, for example, the location and type of base station to be installed, and the frequency band to be used. The terminal transmits this input information to the server in real time. 【0269】 The server receives the input information and stores it in the database. The information processing device installed on the server searches the database for records of similar past construction projects and extracts the necessary information. Based on this data, the generative AI model is activated and begins the process of selecting the optimal components. The generative AI model utilizes various machine learning algorithms to output the optimal antenna and cable types based on the construction conditions. 【0270】 The generated list of components is sent from the server to the user's terminal. The user can then use this list to prepare for construction. Furthermore, the user can review the list and provide feedback on its contents. This feedback is sent back to the server and used as training data for the generated AI model, which will be used to improve the accuracy of future selections. 【0271】 A concrete example is the installation of a base station inside a high-rise building. When the user inputs information such as the building's height, wall materials, and the frequency to be used, the server refers to similar past cases and selects the optimal antenna type and cable type. In this process, a generative AI model functions effectively, quickly providing an optimized list of components. 【0272】 An example of a prompt message is: "What are the optimal antenna and cable types for base station installation in a high-rise building? The building is 200m tall, the walls are made of concrete, and the operating frequency is 3.5GHz." 【0273】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0274】 Step 1: 【0275】 The user operates the terminal to input detailed information about the construction work. Specifically, they enter the location, type, and frequency band of the base station, and write the data in the input form on the terminal. This data is sent to the server when the send button is clicked. 【0276】 Step 2: 【0277】 The server securely receives information from the terminal and stores it in the database. The server then parses and indexes the received data to prepare it for efficient data retrieval. In this scenario, the input is construction information sent by the user, and the output is the parsed data stored in the database. 【0278】 Step 3: 【0279】 The server searches the database based on the stored data and extracts records of past similar projects. Specifically, SQL queries are used to extract relevant data, which is utilized as the basic data for component selection. In this process, filtering based on similarity is employed to obtain highly accurate data. As output, relevant past project data is obtained. 【0280】 Step 4: 【0281】 The server activates the generation model to analyze the extracted past data and selects the optimal components. The input is the past project data obtained in Step 3, and the generative AI model analyzes this to determine the optimal components. As a specific operation, an algorithm scrutinizes the data using advanced machine learning techniques and outputs a list of components that best meet the requirements. 【0282】 Step 5: 【0283】 The server sends the generated component list to the user's terminal. The output includes details such as the specific names, quantities, and recommended suppliers of the components. This list is delivered to the user as an email or an in-application message. 【0284】 Step 6: 【0285】 The user uses the terminal to check the received component list and provides feedback. As a specific operation, the user evaluates the list and fills in change proposals or additional information as needed. The feedback data obtained thereby is sent from the terminal to the server as input. 【0286】 Step 7: 【0287】 The server receives feedback from users and updates the generative AI model. The input is user feedback data, which is added to the generative AI model's training dataset. Specifically, the model's training algorithm takes the feedback into account, aiming to enhance its know-how and improve future analytical accuracy. The output is the updated generative AI model. 【0288】 (Application Example 1) 【0289】 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." 【0290】 Material selection at construction sites is inefficient because it relies on subjective judgment based on experience. Furthermore, inappropriate material selection can lead to delays in the overall construction plan. Solving this problem is essential. 【0291】 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. 【0292】 In this invention, the server includes a mobile information terminal equipped with information processing means, a calculation means for extracting similar records from past work records, and a calculation means for selecting the optimal materials using a generative model. This enables efficient and highly accurate material selection at construction sites. 【0293】 An "information processing device" is a device installed in a mobile information terminal for analyzing and processing input information. 【0294】 A "mobile information terminal" is a portable electronic device used for on-site information input and communication. 【0295】 "Computation means" refers to a device or system for processing data and performing specific computational operations. 【0296】 A "generative model" is an algorithm or mathematical model used to make optimal selections based on historical data. 【0297】 A "materials list" is a collection of data that summarizes the specific names and quantities of selected construction materials. 【0298】 "Information means" refers to a device or method for receiving input information from a user and performing a specific function. 【0299】 A "worker" is a person who performs tasks such as selecting materials and entering information at a construction site. 【0300】 This invention is a system designed to streamline material selection at construction sites. The system consists of a server that receives and processes information, and a mobile information terminal that inputs and receives information. 【0301】 Users input information related to construction projects using mobile information terminals such as smartphones and tablets. This information includes the location of the construction site, building structure information, and required materials. The terminals are equipped with information processing means to transmit data to a server. 【0302】 Upon receiving information, the server uses computational tools to compare it with past construction records in the database and extract similar records. During this process, an AI algorithm called a generative model is used to select the optimal type and quantity of materials. Because the generative model optimizes materials based on historical data, it can address the diverse needs of each construction site. 【0303】 The selected materials are output as a materials list, and the server sends this list back to the terminal. The user can review this list through the information system and modify it as needed. 【0304】 As a specific example, consider the case where a high-rise building construction project is carried out in the center of Tokyo. For example, by inputting into the terminal "Tell me the components for installing an antenna required for the construction of a 50-story building in Shinjuku Ward", the server can select the optimal antenna type and accessories while referring to past similar cases and immediately return a list to the user. 【0305】 Examples of prompt sentences are as follows. "Project: Installation of a base station in a high-rise building in Shinjuku Ward, Number of floors: 50 floors, Operating frequency: 2.5 GHz, Wall material: Concrete, Generation result: 'List of optimal antennas and cables'". 【0306】 The flow of the specific process in Application Example 1 will be described using FIG. 12. 【0307】 Step 1: 【0308】 The terminal receives information about the construction project input by the user. This information includes the location of the construction, the structural information of the building, and the technical specifications used. The terminal packages this information as digital data and transmits it to the server. The input is text data, and the output is the packaged digital data. 【0309】 Step 2: 【0310】 The server analyzes the received digital data and extracts similar records from the past construction database. In this process, database query operations are performed to filter the data that meets the conditions. The input is the digital data received from the terminal, and the output is the extracted similar record data. 【0311】 Step 3: 【0312】 The server uses the generation AI model to analyze the extracted similar records and generate an optimal material list. At this stage, the AI algorithm selects the materials and determines the optimal type and quantity. The input is the similar record data, and the output is the generated material list. 【0313】 Step 4: 【0314】 The server sends the generated material list as digital data to the terminal. The terminal then displays this information in a user-friendly format. The input here is the digital material list, and the output is digital data formatted for display. 【0315】 Step 5: 【0316】 Users can view the material list through their terminal and add or modify information as needed. This process generates user feedback data. The input is the displayed material list, and the output is the modified feedback data. 【0317】 Step 6: 【0318】 The device sends user feedback data to the server. The server receives this data and uses it as training data to improve the accuracy of the generative AI model. The input is the user feedback data, and the output is the updated generative AI model. 【0319】 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. 【0320】 The system according to the present invention streamlines and standardizes the selection of materials in base station construction work, and further provides a more advanced feedback system by taking into account the user's emotional state. In addition to its basic function of processing user input in real time and generating an optimal list of materials using past data and generative models, the system incorporates an emotion engine to understand the user's satisfaction and dissatisfaction. 【0321】 First, the user uses a terminal to input detailed information about the construction project. This information includes the location of the construction, the type of base station to be used, and the frequency to be used. The terminal organizes the information before sending it to the server. Based on the received information, the server searches its database for appropriate past cases and selects materials using a generative model. This process generates a list of selected materials. 【0322】 The emotion engine analyzes data entered by the user on the device and the content of the feedback. This engine utilizes natural language processing technology to evaluate potential satisfaction and dissatisfaction from the user's language, and dynamically adjusts the generative model's learning algorithm based on the results. This is expected to bring future analysis and component selection results closer to the user's expectations. 【0323】 When users review the generated parts list, their emotions are displayed in the interface, allowing them to receive appropriate support. This interface can provide operational guidance and information recommendations tailored to the user's emotional response. For example, if a user feels anxious while reviewing the parts list, the system, sensing this emotion, will immediately provide supplementary information to aid understanding. 【0324】 By introducing this system, it will be possible to move away from traditional, person-dependent methods in the component selection process while improving the user experience and streamlining project management. 【0325】 The following describes the processing flow. 【0326】 Step 1: 【0327】 The user uses a terminal to input details about the construction project. This information includes details about the construction location, base station type, frequency used, and construction environment. The terminal organizes the entered information and prepares it for transmission to the server. 【0328】 Step 2: 【0329】 The terminal sends the input information to the server. The server receives this information in real time and proceeds to the next processing step. 【0330】 Step 3: 【0331】 Based on the received construction information, the server searches the database for similar past construction cases. The server quickly extracts the search results and aggregates data on similar cases. 【0332】 Step 4: 【0333】 The server applies a generative model based on similar cases to select the optimal components for the construction conditions. The generative model uses the accumulated data to create an optimal component list. 【0334】 Step 5: 【0335】 The server generates a list of components and sends it to the user's terminal. The user can then review the received list on their terminal and use it as needed. 【0336】 Step 6: 【0337】 Users input feedback through their devices. Users review the contents of the parts list and provide feedback, including their satisfaction level and any points of dissatisfaction. 【0338】 Step 7: 【0339】 The device sends user feedback to the server. The server receives this feedback and analyzes it using an emotion engine. 【0340】 Step 8: 【0341】 The server's emotion engine analyzes the feedback content and evaluates the user's emotional state. Natural language processing is used to analyze the user's language use and understand their level of satisfaction or dissatisfaction. 【0342】 Step 9: 【0343】 The server adjusts the generative model's learning process based on the results obtained from the emotion engine. This information is fed back into the algorithm and used to improve the accuracy of subsequent analyses and component selections. 【0344】 (Example 2) 【0345】 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". 【0346】 This invention aims to move away from conventional, subjective methods in the selection process of elements in construction work, and to standardize and improve efficiency. Furthermore, it seeks to solve the problem of achieving more sophisticated element selection and improved user experience based on feedback that takes user emotions into consideration. 【0347】 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. 【0348】 In this invention, the server includes a computing device for receiving information, a computing device for extracting similar information from past information sets, and a computing device for selecting the optimal elements using a generative model. This enables efficient element selection that takes user emotions into consideration. 【0349】 "Device" refers to hardware or software means for a user to input or receive information. 【0350】 A "processing unit" is a central processing unit or a means of a computer used to process, analyze, or output information. 【0351】 An "information collection" is a database or data repository that stores past cases and related data. 【0352】 A "generative model" is an algorithm or program that uses machine learning or artificial intelligence techniques to generate the optimal output from target data. 【0353】 An "element" refers to a component, material, or other constituent element that should be selected in a construction or project. 【0354】 "Opinions" refer to feedback and comments provided by users to the system, and are data that helps improve the system. 【0355】 An "operation screen" is an interface used by a user to input information into a system or to view output from the system. 【0356】 The system of this invention achieves efficient element selection in construction through information input, analysis, element selection, and dynamic adjustment based on feedback. This system mainly consists of terminals and a server. 【0357】 First, the user inputs detailed information about the construction project through a terminal. This information includes the construction location, the type of base station to be used, and the frequency to be used. The terminal organizes the input information and sends it to the server. Based on this information, the server searches for similar information from past data sets. This makes it possible to support selection based on experience. 【0358】 The server uses a generative AI model in the selection process. This model is trained using machine learning techniques to suggest the most suitable elements for the input information. For example, if the construction site is in an urban area, the model will prioritize selecting elements with superior durability. This selection generates a list of appropriate elements, which are then sent back to the terminal. 【0359】 User feedback is sent to the server and evaluated by the sentiment engine. This allows the system to dynamically adjust the generative model's algorithm, enabling selections that are more in line with the user's emotions. 【0360】 For example, if a user has concerns about a construction element, the system detects this concern and provides supplementary information to help the user understand. Furthermore, the user interface displays an information guide that allows the user to confidently review the selection results. 【0361】 An example of a prompt message might be, "The construction site is in Minato Ward, Tokyo, and the base station to be installed is a small base station. The operating frequency is the 2.5GHz band. What materials are recommended?" Based on this, the system selects the necessary components. 【0362】 In this way, the system achieves efficient and highly accurate element selection while taking user emotions into consideration. 【0363】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0364】 Step 1: 【0365】 The user uses a terminal to input information about the construction work. Specifically, they input data such as the location of the construction, the type of base station to be built, and the frequency to be used. This information is formatted into the appropriate format within the terminal. Input is in text format, and a formatted JSON object is generated as output. 【0366】 Step 2: 【0367】 The terminal sends formatted information to the server. HTTPS is used as the communication protocol, ensuring that the information is transmitted securely. The input is formatted data, and output is produced when the information correctly reaches the server. The terminal then sends a "POST" request to the server endpoint. 【0368】 Step 3: 【0369】 The server analyzes the received information and extracts similar information from past data sets. It executes SQL queries against the database to retrieve data that matches the criteria. The input is the construction information received by the server, and the output is a data list containing similar information. Specifically, it searches for data that matches past project data. 【0370】 Step 4: 【0371】 The server uses a generative AI model to select the optimal elements based on construction information and similar data. A model algorithm trained through machine learning is used to create a list of elements as selection candidates. The input is extracted similar data, and the output is a list of elements based on the model's predictions. The server then feeds the data into the generative AI model, and the element selection process is executed. 【0372】 Step 5: 【0373】 The server sends a list of selected elements to the terminal. The generated list of elements is sent again using the HTTPS protocol, ensuring secure transmission. The input is the list of elements, and the output is the list displayed on the user's terminal. The server returns data to the terminal using a "GET" request. 【0374】 Step 6: 【0375】 Users can view a list of elements received on their device and provide feedback. This user feedback is transmitted as input to the emotion engine, analyzed, and used to refine future AI model generation. A feedback form is displayed on the device, and the specific action of submitting the feedback is performed. 【0376】 Step 7: 【0377】 The server utilizes user feedback to dynamically adjust the algorithms of the generated AI model. Natural language processing techniques are used for sentiment analysis, and this data is incorporated to improve the model's prediction accuracy. The input is user feedback, and the output is the updating of the model's parameters. The sentiment analysis engine then performs the specific operation of analyzing the feedback. 【0378】 (Application Example 2) 【0379】 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." 【0380】 Traditional base station construction methods for selecting materials tend to be experience-dependent and subjective, limiting efficiency and standardization. Furthermore, the lack of mechanisms to adequately consider user emotions and feedback made it difficult to improve user satisfaction. To address these challenges, a system for efficient material selection that also considers user emotions is needed. 【0381】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0382】 In this invention, the server includes a computing device means for inputting information, a computer means for receiving information from the computing device means, and a computer means for evaluating the user's emotional state using emotion analysis means and providing support information based on the results. This makes it possible to improve efficiency and standardization in the component selection process, and to improve user satisfaction by providing support information that takes the user's emotions into consideration. 【0383】 "Information input device means" refers to a device system for users to input detailed information and feedback on construction work. 【0384】 "Computing means" refers to a server system that processes information received from a computing device and performs necessary calculations. 【0385】 A "data repository" is a database where past cases and data are stored, and it is an information source that computer systems refer to. 【0386】 A "generative model" is an algorithm that generates the optimal list of components based on past data. 【0387】 The "component list" is a list of materials required for base station construction, output by a computer using a generative model. 【0388】 A "computer means for receiving opinions" refers to a server system that receives feedback from users and utilizes it to train generative models. 【0389】 An "emotion analysis tool" is a program or algorithm that evaluates a user's emotional state from their voice, facial expressions, etc., and generates support information based on that evaluation. 【0390】 "Computer means for providing support information" refers to a server system for providing support information generated by emotion analysis means to users. 【0391】 The "display function" is a screen display system that allows users to view and confirm component lists and related information. 【0392】 This invention supports the realization of a system that enables efficient and emotionally conscious selection of components at construction sites. Users can input necessary information via a smart device and select components. The computing means extracts similar past data from a database based on the input information and generates an optimal component list using a generative model. Artificial intelligence technologies such as TensorFlow and PyTorch are applied to this generative model. 【0393】 The server also uses emotion analysis tools to analyze the user's voice and facial expressions to understand their emotions. This utilizes Google Cloud Natural Language API and Azure Text Analytics. Based on the analysis results, the computing tools provide the user with the most appropriate support information and advice. The goal is to enhance the user's sense of security and satisfaction through the presentation of this support information. 【0394】 As a concrete example, when construction workers select components in real time, their feelings of anxiety are analyzed, and information such as "This component complies with the latest building standards" is immediately presented as supporting information. In this way, computing means can provide information that contributes to the success of a project based on the user's emotions. 【0395】 An example prompt might be: "Generate a list of the best materials for this construction project. The target location is an urban area, and we plan to build a 3G LTE base station. The workers seem unsure about material selection." This allows the server to provide appropriate feedback. 【0396】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0397】 Step 1: 【0398】 Users input detailed information about the construction site using a smart device. This information includes the construction location, base station type, and operating frequency. This information is temporarily stored on the device. 【0399】 Step 2: 【0400】 The terminal organizes the entered information and sends it to the server. The server receives this information and searches its database for similar past project data. This search result is temporarily stored for use in the next step. 【0401】 Step 3: 【0402】 The server applies a generative model to generate the optimal component list based on the searched similar data. The generation process uses input construction information and data retrieved from the database. The generative model leverages algorithms from TensorFlow and PyTorch. The resulting component list is stored in the database. 【0403】 Step 4: 【0404】 Users submit feedback via their smart devices. This feedback includes comments and questions about the user's component list. This information is received and temporarily stored by the server. 【0405】 Step 5: 【0406】 The server uses sentiment analysis tools to evaluate the user's emotional state from their feedback and voice. Google Cloud Natural Language API and Azure Text Analytics are used for this analysis. The emotional information obtained from this analysis is then used in the next step. 【0407】 Step 6: 【0408】 Based on the sentiment analysis results, the server generates supportive information for the user. This information includes advice and recommendations designed to enhance the user's sense of security. The server then sends this information to the user's smart device. 【0409】 Step 7: 【0410】 The user receives and reviews the support information provided through their smart device. Specific instructions are displayed to help the user understand the information in more detail. 【0411】 Step 8: 【0412】 The server updates its generative model based on user feedback and sentiment analysis results. This improvement enhances the accuracy of component selection in subsequent uses. 【0413】 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. 【0414】 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. 【0415】 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. 【0416】 [Third Embodiment] 【0417】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0418】 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. 【0419】 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). 【0420】 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. 【0421】 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. 【0422】 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). 【0423】 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. 【0424】 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. 【0425】 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. 【0426】 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. 【0427】 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. 【0428】 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". 【0429】 The component selection system according to the present invention automates the selection of necessary components in base station construction work using AI technology, thereby achieving standardization and efficiency. This system operates according to the following flow. 【0430】 First, the user uses a terminal to enter detailed information about the construction project. This includes data such as the location of the construction, the type of base station to be built, and the frequency band to be used. The entered data is sent to the server in real time, and processing begins. 【0431】 Upon receiving this information, the server searches its internal database for similar past construction records. These search results are used as the basis for selecting the necessary components. The server then performs an analysis using a generative model to select the optimal components. This generative model analyzes past construction data and incorporates an algorithm to select the type and quantity of components based on the results. 【0432】 The component list generated by the server is sent to the user's terminal. This list includes information such as the specific names of the selected components, the required quantities, and recommended suppliers, which the user can use to procure components at the construction site. The user who receives the list can also review its contents and provide feedback as needed. 【0433】 User feedback is sent back to the server from the device, and the server incorporates it into the generative model as training data. This allows for improved accuracy in future analyses and the accumulation of know-how. 【0434】 As a concrete example, considering base station construction within a high-rise building, the user inputs the building's height, wall materials, and operating frequency. The server then references similar past cases to select the optimal antenna type and cable type. As a result, the user is immediately provided with an optimized list of materials, allowing them to smoothly proceed with construction preparations based on this list. In this way, the system provides a form that achieves highly efficient construction without relying on individual skills. 【0435】 The following describes the processing flow. 【0436】 Step 1: 【0437】 The user uses a terminal to input detailed information about the construction project. This includes the construction location, the planned base station type, the frequency used, and the terrain conditions. The terminal organizes the entered information and prepares it for transmission to the server. 【0438】 Step 2: 【0439】 The terminal sends the entered construction information to the server. The transmitted data is processed in real time and received within the server. 【0440】 Step 3: 【0441】 Based on the received construction information, the server searches the database for data on similar past construction projects. The server efficiently extracts past cases that have attributes that match or are similar to the received information. 【0442】 Step 4: 【0443】 The server inputs the extracted data into a generative model to select the optimal materials for the construction conditions. The generative model utilizes accumulated know-how to perform analysis to determine the types and quantities of materials required. 【0444】 Step 5: 【0445】 The server creates an optimal list of components based on the analysis results of the generative model. The component list includes the names of the selected components, the required quantities, and recommended suppliers. 【0446】 Step 6: 【0447】 The server sends the materials list it has created to the user's terminal. The user can then review the received list and proceed smoothly with construction preparations. 【0448】 Step 7: 【0449】 The user enters feedback on the received parts list via their device. This feedback includes the accuracy of the list and any additional requests. 【0450】 Step 8: 【0451】 The device sends user feedback to the server. The server receives the feedback and uses it as training data to incorporate it into the generative model. 【0452】 Step 9: 【0453】 The server stores the feedback in the model's data and trains the model to use it for subsequent analyses. This process improves the accuracy of component selection. 【0454】 (Example 1) 【0455】 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." 【0456】 The process of selecting materials for telecommunications base station construction has traditionally relied on the knowledge and experience of specialists, and there is a need for efficiency and standardization. Furthermore, data analysis for optimal material selection is time-consuming and a source of inefficiency. In addition, it has been difficult to make improvements based on real-time user feedback, and there have been challenges in accumulating know-how. 【0457】 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. 【0458】 In this invention, the server includes an information processing device for receiving and storing information, an information processing device for extracting similar information from past records, and an information processing device for selecting the optimal components using a generative model. This enables efficient and standardized component selection. 【0459】 An "input device means" is a device that provides an interface for the user to input detailed information about the construction work and transmits that information to a server. 【0460】 An "information processing device" is a device that stores information received from an input device, extracts similar information from a past database, and selects the optimal components using a generative model. 【0461】 A "generative model" is a machine learning model that learns from information about past operations and is equipped with an algorithm to optimize component selection. 【0462】 "Components" refers to the types and quantities of materials used in base station construction. 【0463】 A "response mechanism" is a means of receiving feedback from the operator and incorporating it into the learning process of the generative model. 【0464】 "Operator" refers to the user who inputs detailed construction information through an input device and checks the results. 【0465】 This invention is a system for streamlining and standardizing the selection of components in telecommunications base station construction. Specific embodiments for carrying out the invention are described below. 【0466】 The user uses a terminal to input detailed information about the construction work. This information includes, for example, the location and type of base station to be installed, and the frequency band to be used. The terminal transmits this input information to the server in real time. 【0467】 The server receives the input information and stores it in the database. The information processing device installed on the server searches the database for records of similar past construction projects and extracts the necessary information. Based on this data, the generative AI model is activated and begins the process of selecting the optimal components. The generative AI model utilizes various machine learning algorithms to output the optimal antenna and cable types based on the construction conditions. 【0468】 The generated list of components is sent from the server to the user's terminal. The user can then use this list to prepare for construction. Furthermore, the user can review the list and provide feedback on its contents. This feedback is sent back to the server and used as training data for the generated AI model, which will be used to improve the accuracy of future selections. 【0469】 A concrete example is the installation of a base station inside a high-rise building. When the user inputs information such as the building's height, wall materials, and the frequency to be used, the server refers to similar past cases and selects the optimal antenna type and cable type. In this process, a generative AI model functions effectively, quickly providing an optimized list of components. 【0470】 An example of a prompt message is: "What are the optimal antenna and cable types for base station installation in a high-rise building? The building is 200m tall, the walls are made of concrete, and the operating frequency is 3.5GHz." 【0471】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0472】 Step 1: 【0473】 The user operates the terminal to input detailed information about the construction work. Specifically, they enter the location, type, and frequency band of the base station, and write the data in the input form on the terminal. This data is sent to the server when the send button is clicked. 【0474】 Step 2: 【0475】 The server securely receives information from the terminal and stores it in the database. The server then parses and indexes the received data to prepare it for efficient data retrieval. In this scenario, the input is construction information sent by the user, and the output is the parsed data stored in the database. 【0476】 Step 3: 【0477】 The server searches the database based on the stored data and extracts records of similar past construction projects. Specifically, it uses SQL queries to extract relevant data and uses it as basic data for selecting materials. This process uses filtering based on similarity to obtain highly accurate data. The output is relevant past construction data. 【0478】 Step 4: 【0479】 The server launches the generative model, analyzes the extracted historical data, and selects the optimal components. The input is the historical construction data obtained in step 3, and the generative AI model analyzes this data to determine the optimal components. Specifically, the algorithm uses advanced machine learning techniques to scrutinize the data and outputs a list of components that best meet the requirements. 【0480】 Step 5: 【0481】 The server sends the generated parts list to the user's terminal. The output includes details such as the specific names, quantities, and recommended suppliers for each part. This list is delivered to the user via email or in-app message. 【0482】 Step 6: 【0483】 The user reviews the received parts list using a terminal and provides feedback. Specifically, the user evaluates the list and fills in suggested changes or additional information as needed. The resulting feedback data is then sent from the terminal to the server as input. 【0484】 Step 7: 【0485】 The server receives feedback from users and updates the generative AI model. The input is user feedback data, which is added to the generative AI model's training dataset. Specifically, the model's training algorithm takes the feedback into account, aiming to enhance its know-how and improve future analytical accuracy. The output is the updated generative AI model. 【0486】 (Application Example 1) 【0487】 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." 【0488】 Material selection at construction sites is inefficient because it relies on subjective judgment based on experience. Furthermore, inappropriate material selection can lead to delays in the overall construction plan. Solving this problem is essential. 【0489】 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. 【0490】 In this invention, the server includes a mobile information terminal equipped with information processing means, a calculation means for extracting similar records from past work records, and a calculation means for selecting the optimal materials using a generative model. This enables efficient and highly accurate material selection at construction sites. 【0491】 An "information processing device" is a device installed in a mobile information terminal for analyzing and processing input information. 【0492】 A "mobile information terminal" is a portable electronic device used for on-site information input and communication. 【0493】 "Computation means" refers to a device or system for processing data and performing specific computational operations. 【0494】 A "generative model" is an algorithm or mathematical model used to make optimal selections based on historical data. 【0495】 A "materials list" is a collection of data that summarizes the specific names and quantities of selected construction materials. 【0496】 "Information means" refers to a device or method for receiving input information from a user and performing a specific function. 【0497】 A "worker" is a person who performs tasks such as selecting materials and entering information at a construction site. 【0498】 This invention is a system designed to streamline material selection at construction sites. The system consists of a server that receives and processes information, and a mobile information terminal that inputs and receives information. 【0499】 Users input information related to construction projects using mobile information terminals such as smartphones and tablets. This information includes the location of the construction site, building structure information, and required materials. The terminals are equipped with information processing means to transmit data to a server. 【0500】 Upon receiving information, the server uses computational tools to compare it with past construction records in the database and extract similar records. During this process, an AI algorithm called a generative model is used to select the optimal type and quantity of materials. Because the generative model optimizes materials based on historical data, it can address the diverse needs of each construction site. 【0501】 The selected materials are output as a materials list, and the server sends this list back to the terminal. The user can review this list through the information system and modify it as needed. 【0502】 As a concrete example, consider the case of a high-rise building construction project in central Tokyo. For instance, by entering a request into the terminal such as, "Tell me what antenna installation materials are needed for the construction of a 50-story building in Shinjuku Ward," the server can refer to similar past cases to select the most suitable antenna type and accessories, and immediately return a list to the user. 【0503】 An example of a prompt message is as follows: "Project: Base station installation in a high-rise building in Shinjuku Ward, Floors: 50th floor, Frequency used: 2.5 GHz, Wall material: Concrete, Result: 'List of optimal antennas and cables'". 【0504】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0505】 Step 1: 【0506】 The terminal receives information about construction projects entered by the user. This information includes the construction site, building structure information, and technical specifications to be used. The terminal packages this information as digital data and sends it to the server. The input is text data, and the output is packaged digital data. 【0507】 Step 2: 【0508】 The server analyzes the received digital data and extracts similar records from the past construction database. This process involves performing database query operations to filter data that matches specific criteria. The input is digital data received from the terminal, and the output is the extracted similar record data. 【0509】 Step 3: 【0510】 The server uses a generative AI model to analyze extracted similar records and generate an optimal material list. At this stage, the AI ​​algorithm selects materials and determines the optimal type and quantity. The input is similar record data, and the output is the generated material list. 【0511】 Step 4: 【0512】 The server sends the generated material list as digital data to the terminal. The terminal then displays this information in a user-friendly format. The input here is the digital material list, and the output is digital data formatted for display. 【0513】 Step 5: 【0514】 Users can view the material list through their terminal and add or modify information as needed. This process generates user feedback data. The input is the displayed material list, and the output is the modified feedback data. 【0515】 Step 6: 【0516】 The device sends user feedback data to the server. The server receives this data and uses it as training data to improve the accuracy of the generative AI model. The input is the user feedback data, and the output is the updated generative AI model. 【0517】 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. 【0518】 The system according to the present invention streamlines and standardizes the selection of materials in base station construction work, and further provides a more advanced feedback system by taking into account the user's emotional state. In addition to its basic function of processing user input in real time and generating an optimal list of materials using past data and generative models, the system incorporates an emotion engine to understand the user's satisfaction and dissatisfaction. 【0519】 First, the user uses a terminal to input detailed information about the construction project. This information includes the location of the construction, the type of base station to be used, and the frequency to be used. The terminal organizes the information before sending it to the server. Based on the received information, the server searches its database for appropriate past cases and selects materials using a generative model. This process generates a list of selected materials. 【0520】 The emotion engine analyzes data entered by the user on the device and the content of the feedback. This engine utilizes natural language processing technology to evaluate potential satisfaction and dissatisfaction from the user's language, and dynamically adjusts the generative model's learning algorithm based on the results. This is expected to bring future analysis and component selection results closer to the user's expectations. 【0521】 When users review the generated parts list, their emotions are displayed in the interface, allowing them to receive appropriate support. This interface can provide operational guidance and information recommendations tailored to the user's emotional response. For example, if a user feels anxious while reviewing the parts list, the system, sensing this emotion, will immediately provide supplementary information to aid understanding. 【0522】 By introducing this system, it will be possible to move away from traditional, person-dependent methods in the component selection process while improving the user experience and streamlining project management. 【0523】 The following describes the processing flow. 【0524】 Step 1: 【0525】 The user uses a terminal to input details about the construction project. This information includes details about the construction location, base station type, frequency used, and construction environment. The terminal organizes the entered information and prepares it for transmission to the server. 【0526】 Step 2: 【0527】 The terminal sends the input information to the server. The server receives this information in real time and proceeds to the next processing step. 【0528】 Step 3: 【0529】 Based on the received construction information, the server searches the database for similar past construction cases. The server quickly extracts the search results and aggregates data on similar cases. 【0530】 Step 4: 【0531】 The server applies a generative model based on similar cases to select the optimal components for the construction conditions. The generative model uses the accumulated data to create an optimal component list. 【0532】 Step 5: 【0533】 The server generates a list of components and sends it to the user's terminal. The user can then review the received list on their terminal and use it as needed. 【0534】 Step 6: 【0535】 Users input feedback through their devices. Users review the contents of the parts list and provide feedback, including their satisfaction level and any points of dissatisfaction. 【0536】 Step 7: 【0537】 The device sends user feedback to the server. The server receives this feedback and analyzes it using an emotion engine. 【0538】 Step 8: 【0539】 The server's emotion engine analyzes the feedback content and evaluates the user's emotional state. Natural language processing is used to analyze the user's language use and understand their level of satisfaction or dissatisfaction. 【0540】 Step 9: 【0541】 The server adjusts the generative model's learning process based on the results obtained from the emotion engine. This information is fed back into the algorithm and used to improve the accuracy of subsequent analyses and component selections. 【0542】 (Example 2) 【0543】 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." 【0544】 This invention aims to move away from conventional, subjective methods in the selection process of elements in construction work, and to standardize and improve efficiency. Furthermore, it seeks to solve the problem of achieving more sophisticated element selection and improved user experience based on feedback that takes user emotions into consideration. 【0545】 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. 【0546】 In this invention, the server includes a computing device for receiving information, a computing device for extracting similar information from past information sets, and a computing device for selecting the optimal elements using a generative model. This enables efficient element selection that takes user emotions into consideration. 【0547】 "Device" refers to hardware or software means for a user to input or receive information. 【0548】 A "processing unit" is a central processing unit or a means of a computer used to process, analyze, or output information. 【0549】 An "information collection" is a database or data repository that stores past cases and related data. 【0550】 A "generative model" is an algorithm or program that uses machine learning or artificial intelligence techniques to generate the optimal output from target data. 【0551】 An "element" refers to a component, material, or other constituent element that should be selected in a construction or project. 【0552】 "Opinions" refer to feedback and comments provided by users to the system, and are data that helps improve the system. 【0553】 An "operation screen" is an interface used by a user to input information into a system or to view output from the system. 【0554】 The system of this invention achieves efficient element selection in construction through information input, analysis, element selection, and dynamic adjustment based on feedback. This system mainly consists of terminals and a server. 【0555】 First, the user inputs detailed information about the construction project through a terminal. This information includes the construction location, the type of base station to be used, and the frequency to be used. The terminal organizes the input information and sends it to the server. Based on this information, the server searches for similar information from past data sets. This makes it possible to support selection based on experience. 【0556】 The server uses a generative AI model in the selection process. This model is trained using machine learning techniques to suggest the most suitable elements for the input information. For example, if the construction site is in an urban area, the model will prioritize selecting elements with superior durability. This selection generates a list of appropriate elements, which are then sent back to the terminal. 【0557】 User feedback is sent to the server and evaluated by the sentiment engine. This allows the system to dynamically adjust the generative model's algorithm, enabling selections that are more in line with the user's emotions. 【0558】 For example, if a user has concerns about a construction element, the system detects this concern and provides supplementary information to help the user understand. Furthermore, the user interface displays an information guide that allows the user to confidently review the selection results. 【0559】 An example of a prompt message might be, "The construction site is in Minato Ward, Tokyo, and the base station to be installed is a small base station. The operating frequency is the 2.5GHz band. What materials are recommended?" Based on this, the system selects the necessary components. 【0560】 In this way, the system achieves efficient and highly accurate element selection while taking user emotions into consideration. 【0561】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0562】 Step 1: 【0563】 The user uses a terminal to input information about the construction work. Specifically, they input data such as the location of the construction, the type of base station to be built, and the frequency to be used. This information is formatted into the appropriate format within the terminal. Input is in text format, and a formatted JSON object is generated as output. 【0564】 Step 2: 【0565】 The terminal sends formatted information to the server. HTTPS is used as the communication protocol, ensuring that the information is transmitted securely. The input is formatted data, and output is produced when the information correctly reaches the server. The terminal then sends a "POST" request to the server endpoint. 【0566】 Step 3: 【0567】 The server analyzes the received information and extracts similar information from past data sets. It executes SQL queries against the database to retrieve data that matches the criteria. The input is the construction information received by the server, and the output is a data list containing similar information. Specifically, it searches for data that matches past project data. 【0568】 Step 4: 【0569】 The server uses a generative AI model to select the optimal elements based on construction information and similar data. A model algorithm trained through machine learning is used to create a list of elements as selection candidates. The input is extracted similar data, and the output is a list of elements based on the model's predictions. The server then feeds the data into the generative AI model, and the element selection process is executed. 【0570】 Step 5: 【0571】 The server sends a list of selected elements to the terminal. The generated list of elements is sent again using the HTTPS protocol, ensuring secure transmission. The input is the list of elements, and the output is the list displayed on the user's terminal. The server returns data to the terminal using a "GET" request. 【0572】 Step 6: 【0573】 Users can view a list of elements received on their device and provide feedback. This user feedback is transmitted as input to the emotion engine, analyzed, and used to refine future AI model generation. A feedback form is displayed on the device, and the specific action of submitting the feedback is performed. 【0574】 Step 7: 【0575】 The server utilizes user feedback to dynamically adjust the algorithms of the generated AI model. Natural language processing techniques are used for sentiment analysis, and this data is incorporated to improve the model's prediction accuracy. The input is user feedback, and the output is the updating of the model's parameters. The sentiment analysis engine then performs the specific operation of analyzing the feedback. 【0576】 (Application Example 2) 【0577】 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." 【0578】 Traditional base station construction methods for selecting materials tend to be experience-dependent and subjective, limiting efficiency and standardization. Furthermore, the lack of mechanisms to adequately consider user emotions and feedback made it difficult to improve user satisfaction. To address these challenges, a system for efficient material selection that also considers user emotions is needed. 【0579】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0580】 In this invention, the server includes a computing device means for inputting information, a computer means for receiving information from the computing device means, and a computer means for evaluating the user's emotional state using emotion analysis means and providing support information based on the results. This makes it possible to improve efficiency and standardization in the component selection process, and to improve user satisfaction by providing support information that takes the user's emotions into consideration. 【0581】 "Information input device means" refers to a device system for users to input detailed information and feedback on construction work. 【0582】 "Computing means" refers to a server system that processes information received from a computing device and performs necessary calculations. 【0583】 A "data repository" is a database where past cases and data are stored, and it is an information source that computer systems refer to. 【0584】 A "generative model" is an algorithm that generates the optimal list of components based on past data. 【0585】 The "component list" is a list of materials required for base station construction, output by a computer using a generative model. 【0586】 A "computer means for receiving opinions" refers to a server system that receives feedback from users and utilizes it to train generative models. 【0587】 An "emotion analysis tool" is a program or algorithm that evaluates a user's emotional state from their voice, facial expressions, etc., and generates support information based on that evaluation. 【0588】 "Computer means for providing support information" refers to a server system for providing support information generated by emotion analysis means to users. 【0589】 The "display function" is a screen display system that allows users to view and confirm component lists and related information. 【0590】 This invention supports the realization of a system that enables efficient and emotionally conscious selection of components at construction sites. Users can input necessary information via a smart device and select components. The computing means extracts similar past data from a database based on the input information and generates an optimal component list using a generative model. Artificial intelligence technologies such as TensorFlow and PyTorch are applied to this generative model. 【0591】 The server also uses emotion analysis tools to analyze the user's voice and facial expressions to understand their emotions. This utilizes Google Cloud Natural Language API and Azure Text Analytics. Based on the analysis results, the computing tools provide the user with the most appropriate support information and advice. The goal is to enhance the user's sense of security and satisfaction through the presentation of this support information. 【0592】 As a concrete example, when construction workers select components in real time, their feelings of anxiety are analyzed, and information such as "This component complies with the latest building standards" is immediately presented as supporting information. In this way, computing means can provide information that contributes to the success of a project based on the user's emotions. 【0593】 An example prompt might be: "Generate a list of the best materials for this construction project. The target location is an urban area, and we plan to build a 3G LTE base station. The workers seem unsure about material selection." This allows the server to provide appropriate feedback. 【0594】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0595】 Step 1: 【0596】 Users input detailed information about the construction site using a smart device. This information includes the construction location, base station type, and operating frequency. This information is temporarily stored on the device. 【0597】 Step 2: 【0598】 The terminal organizes the entered information and sends it to the server. The server receives this information and searches its database for similar past project data. This search result is temporarily stored for use in the next step. 【0599】 Step 3: 【0600】 The server applies a generative model to generate the optimal component list based on the searched similar data. The generation process uses input construction information and data retrieved from the database. The generative model leverages algorithms from TensorFlow and PyTorch. The resulting component list is stored in the database. 【0601】 Step 4: 【0602】 Users submit feedback via their smart devices. This feedback includes comments and questions about the user's component list. This information is received and temporarily stored by the server. 【0603】 Step 5: 【0604】 The server uses sentiment analysis tools to evaluate the user's emotional state from their feedback and voice. Google Cloud Natural Language API and Azure Text Analytics are used for this analysis. The emotional information obtained from this analysis is then used in the next step. 【0605】 Step 6: 【0606】 Based on the sentiment analysis results, the server generates supportive information for the user. This information includes advice and recommendations designed to enhance the user's sense of security. The server then sends this information to the user's smart device. 【0607】 Step 7: 【0608】 The user receives and reviews the support information provided through their smart device. Specific instructions are displayed to help the user understand the information in more detail. 【0609】 Step 8: 【0610】 The server updates its generative model based on user feedback and sentiment analysis results. This improvement enhances the accuracy of component selection in subsequent uses. 【0611】 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. 【0612】 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. 【0613】 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. 【0614】 [Fourth Embodiment] 【0615】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0616】 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. 【0617】 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). 【0618】 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. 【0619】 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. 【0620】 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). 【0621】 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. 【0622】 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. 【0623】 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. 【0624】 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. 【0625】 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. 【0626】 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. 【0627】 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". 【0628】 The component selection system according to the present invention automates the selection of necessary components in base station construction work using AI technology, thereby achieving standardization and efficiency. This system operates according to the following flow. 【0629】 First, the user uses a terminal to enter detailed information about the construction project. This includes data such as the location of the construction, the type of base station to be built, and the frequency band to be used. The entered data is sent to the server in real time, and processing begins. 【0630】 Upon receiving this information, the server searches its internal database for similar past construction records. These search results are used as the basis for selecting the necessary components. The server then performs an analysis using a generative model to select the optimal components. This generative model analyzes past construction data and incorporates an algorithm to select the type and quantity of components based on the results. 【0631】 The component list generated by the server is sent to the user's terminal. This list includes information such as the specific names of the selected components, the required quantities, and recommended suppliers, which the user can use to procure components at the construction site. The user who receives the list can also review its contents and provide feedback as needed. 【0632】 User feedback is sent back to the server from the device, and the server incorporates it into the generative model as training data. This allows for improved accuracy in future analyses and the accumulation of know-how. 【0633】 As a concrete example, considering base station construction within a high-rise building, the user inputs the building's height, wall materials, and operating frequency. The server then references similar past cases to select the optimal antenna type and cable type. As a result, the user is immediately provided with an optimized list of materials, allowing them to smoothly proceed with construction preparations based on this list. In this way, the system provides a form that achieves highly efficient construction without relying on individual skills. 【0634】 The following describes the processing flow. 【0635】 Step 1: 【0636】 The user uses a terminal to input detailed information about the construction project. This includes the construction location, the planned base station type, the frequency used, and the terrain conditions. The terminal organizes the entered information and prepares it for transmission to the server. 【0637】 Step 2: 【0638】 The terminal sends the entered construction information to the server. The transmitted data is processed in real time and received within the server. 【0639】 Step 3: 【0640】 Based on the received construction information, the server searches the database for data on similar past construction projects. The server efficiently extracts past cases that have attributes that match or are similar to the received information. 【0641】 Step 4: 【0642】 The server inputs the extracted data into a generative model to select the optimal materials for the construction conditions. The generative model utilizes accumulated know-how to perform analysis to determine the types and quantities of materials required. 【0643】 Step 5: 【0644】 The server creates an optimal list of components based on the analysis results of the generative model. The component list includes the names of the selected components, the required quantities, and recommended suppliers. 【0645】 Step 6: 【0646】 The server sends the materials list it has created to the user's terminal. The user can then review the received list and proceed smoothly with construction preparations. 【0647】 Step 7: 【0648】 The user enters feedback on the received parts list via their device. This feedback includes the accuracy of the list and any additional requests. 【0649】 Step 8: 【0650】 The device sends user feedback to the server. The server receives the feedback and uses it as training data to incorporate it into the generative model. 【0651】 Step 9: 【0652】 The server stores the feedback in the model's data and trains the model to use it for subsequent analyses. This process improves the accuracy of component selection. 【0653】 (Example 1) 【0654】 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". 【0655】 The process of selecting materials for telecommunications base station construction has traditionally relied on the knowledge and experience of specialists, and there is a need for efficiency and standardization. Furthermore, data analysis for optimal material selection is time-consuming and a source of inefficiency. In addition, it has been difficult to make improvements based on real-time user feedback, and there have been challenges in accumulating know-how. 【0656】 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. 【0657】 In this invention, the server includes an information processing device for receiving and storing information, an information processing device for extracting similar information from past records, and an information processing device for selecting the optimal components using a generative model. This enables efficient and standardized component selection. 【0658】 An "input device means" is a device that provides an interface for the user to input detailed information about the construction work and transmits that information to a server. 【0659】 An "information processing device" is a device that stores information received from an input device, extracts similar information from a past database, and selects the optimal components using a generative model. 【0660】 A "generative model" is a machine learning model that learns from information about past operations and is equipped with an algorithm to optimize component selection. 【0661】 "Components" refers to the types and quantities of materials used in base station construction. 【0662】 A "response mechanism" is a means of receiving feedback from the operator and incorporating it into the learning process of the generative model. 【0663】 "Operator" refers to the user who inputs detailed construction information through an input device and checks the results. 【0664】 This invention is a system for streamlining and standardizing the selection of components in telecommunications base station construction. Specific embodiments for carrying out the invention are described below. 【0665】 The user uses a terminal to input detailed information about the construction work. This information includes, for example, the location and type of base station to be installed, and the frequency band to be used. The terminal transmits this input information to the server in real time. 【0666】 The server receives the input information and stores it in the database. The information processing device installed on the server searches the database for records of similar past construction projects and extracts the necessary information. Based on this data, the generative AI model is activated and begins the process of selecting the optimal components. The generative AI model utilizes various machine learning algorithms to output the optimal antenna and cable types based on the construction conditions. 【0667】 The generated list of components is sent from the server to the user's terminal. The user can then use this list to prepare for construction. Furthermore, the user can review the list and provide feedback on its contents. This feedback is sent back to the server and used as training data for the generated AI model, which will be used to improve the accuracy of future selections. 【0668】 A concrete example is the installation of a base station inside a high-rise building. When the user inputs information such as the building's height, wall materials, and the frequency to be used, the server refers to similar past cases and selects the optimal antenna type and cable type. In this process, a generative AI model functions effectively, quickly providing an optimized list of components. 【0669】 An example of a prompt message is: "What are the optimal antenna and cable types for base station installation in a high-rise building? The building is 200m tall, the walls are made of concrete, and the operating frequency is 3.5GHz." 【0670】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0671】 Step 1: 【0672】 The user operates the terminal to input detailed information about the construction work. Specifically, they enter the location, type, and frequency band of the base station, and write the data in the input form on the terminal. This data is sent to the server when the send button is clicked. 【0673】 Step 2: 【0674】 The server securely receives information from the terminal and stores it in the database. The server then parses and indexes the received data to prepare it for efficient data retrieval. In this scenario, the input is construction information sent by the user, and the output is the parsed data stored in the database. 【0675】 Step 3: 【0676】 The server searches the database based on the stored data and extracts records of similar past construction projects. Specifically, it uses SQL queries to extract relevant data and uses it as basic data for selecting materials. This process uses filtering based on similarity to obtain highly accurate data. The output is relevant past construction data. 【0677】 Step 4: 【0678】 The server launches the generative model, analyzes the extracted historical data, and selects the optimal components. The input is the historical construction data obtained in step 3, and the generative AI model analyzes this data to determine the optimal components. Specifically, the algorithm uses advanced machine learning techniques to scrutinize the data and outputs a list of components that best meet the requirements. 【0679】 Step 5: 【0680】 The server sends the generated parts list to the user's terminal. The output includes details such as the specific names, quantities, and recommended suppliers for each part. This list is delivered to the user via email or in-app message. 【0681】 Step 6: 【0682】 The user reviews the received parts list using a terminal and provides feedback. Specifically, the user evaluates the list and fills in suggested changes or additional information as needed. The resulting feedback data is then sent from the terminal to the server as input. 【0683】 Step 7: 【0684】 The server receives feedback from users and updates the generative AI model. The input is user feedback data, which is added to the generative AI model's training dataset. Specifically, the model's training algorithm takes the feedback into account, aiming to enhance its know-how and improve future analytical accuracy. The output is the updated generative AI model. 【0685】 (Application Example 1) 【0686】 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". 【0687】 Material selection at construction sites is inefficient because it relies on subjective judgment based on experience. Furthermore, inappropriate material selection can lead to delays in the overall construction plan. Solving this problem is essential. 【0688】 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. 【0689】 In this invention, the server includes a mobile information terminal equipped with information processing means, a calculation means for extracting similar records from past work records, and a calculation means for selecting the optimal materials using a generative model. This enables efficient and highly accurate material selection at construction sites. 【0690】 An "information processing device" is a device installed in a mobile information terminal for analyzing and processing input information. 【0691】 A "mobile information terminal" is a portable electronic device used for on-site information input and communication. 【0692】 "Computation means" refers to a device or system for processing data and performing specific computational operations. 【0693】 A "generative model" is an algorithm or mathematical model used to make optimal selections based on historical data. 【0694】 A "materials list" is a collection of data that summarizes the specific names and quantities of selected construction materials. 【0695】 "Information means" refers to a device or method for receiving input information from a user and performing a specific function. 【0696】 A "worker" is a person who performs tasks such as selecting materials and entering information at a construction site. 【0697】 This invention is a system designed to streamline material selection at construction sites. The system consists of a server that receives and processes information, and a mobile information terminal that inputs and receives information. 【0698】 Users input information related to construction projects using mobile information terminals such as smartphones and tablets. This information includes the location of the construction site, building structure information, and required materials. The terminals are equipped with information processing means to transmit data to a server. 【0699】 Upon receiving information, the server uses computational tools to compare it with past construction records in the database and extract similar records. During this process, an AI algorithm called a generative model is used to select the optimal type and quantity of materials. Because the generative model optimizes materials based on historical data, it can address the diverse needs of each construction site. 【0700】 The selected materials are output as a materials list, and the server sends this list back to the terminal. The user can review this list through the information system and modify it as needed. 【0701】 As a concrete example, consider the case of a high-rise building construction project in central Tokyo. For instance, by entering a request into the terminal such as, "Tell me what antenna installation materials are needed for the construction of a 50-story building in Shinjuku Ward," the server can refer to similar past cases to select the most suitable antenna type and accessories, and immediately return a list to the user. 【0702】 An example of a prompt message is as follows: "Project: Base station installation in a high-rise building in Shinjuku Ward, Floors: 50th floor, Frequency used: 2.5 GHz, Wall material: Concrete, Result: 'List of optimal antennas and cables'". 【0703】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0704】 Step 1: 【0705】 The terminal receives information about construction projects entered by the user. This information includes the construction site, building structure information, and technical specifications to be used. The terminal packages this information as digital data and sends it to the server. The input is text data, and the output is packaged digital data. 【0706】 Step 2: 【0707】 The server analyzes the received digital data and extracts similar records from the past construction database. This process involves performing database query operations to filter data that matches specific criteria. The input is digital data received from the terminal, and the output is the extracted similar record data. 【0708】 Step 3: 【0709】 The server uses a generative AI model to analyze extracted similar records and generate an optimal material list. At this stage, the AI ​​algorithm selects materials and determines the optimal type and quantity. The input is similar record data, and the output is the generated material list. 【0710】 Step 4: 【0711】 The server sends the generated material list as digital data to the terminal. The terminal then displays this information in a user-friendly format. The input here is the digital material list, and the output is digital data formatted for display. 【0712】 Step 5: 【0713】 Users can view the material list through their terminal and add or modify information as needed. This process generates user feedback data. The input is the displayed material list, and the output is the modified feedback data. 【0714】 Step 6: 【0715】 The device sends user feedback data to the server. The server receives this data and uses it as training data to improve the accuracy of the generative AI model. The input is the user feedback data, and the output is the updated generative AI model. 【0716】 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. 【0717】 The system according to the present invention streamlines and standardizes the selection of materials in base station construction work, and further provides a more advanced feedback system by taking into account the user's emotional state. In addition to its basic function of processing user input in real time and generating an optimal list of materials using past data and generative models, the system incorporates an emotion engine to understand the user's satisfaction and dissatisfaction. 【0718】 First, the user uses a terminal to input detailed information about the construction project. This information includes the location of the construction, the type of base station to be used, and the frequency to be used. The terminal organizes the information before sending it to the server. Based on the received information, the server searches its database for appropriate past cases and selects materials using a generative model. This process generates a list of selected materials. 【0719】 The emotion engine analyzes data entered by the user on the device and the content of the feedback. This engine utilizes natural language processing technology to evaluate potential satisfaction and dissatisfaction from the user's language, and dynamically adjusts the generative model's learning algorithm based on the results. This is expected to bring future analysis and component selection results closer to the user's expectations. 【0720】 When users review the generated parts list, their emotions are displayed in the interface, allowing them to receive appropriate support. This interface can provide operational guidance and information recommendations tailored to the user's emotional response. For example, if a user feels anxious while reviewing the parts list, the system, sensing this emotion, will immediately provide supplementary information to aid understanding. 【0721】 By introducing this system, it will be possible to move away from traditional, person-dependent methods in the component selection process while improving the user experience and streamlining project management. 【0722】 The following describes the processing flow. 【0723】 Step 1: 【0724】 The user uses a terminal to input details about the construction project. This information includes details about the construction location, base station type, frequency used, and construction environment. The terminal organizes the entered information and prepares it for transmission to the server. 【0725】 Step 2: 【0726】 The terminal sends the input information to the server. The server receives this information in real time and proceeds to the next processing step. 【0727】 Step 3: 【0728】 Based on the received construction information, the server searches the database for similar past construction cases. The server quickly extracts the search results and aggregates data on similar cases. 【0729】 Step 4: 【0730】 The server applies a generative model based on similar cases to select the optimal components for the construction conditions. The generative model uses the accumulated data to create an optimal component list. 【0731】 Step 5: 【0732】 The server generates a list of components and sends it to the user's terminal. The user can then review the received list on their terminal and use it as needed. 【0733】 Step 6: 【0734】 Users input feedback through their devices. Users review the contents of the parts list and provide feedback, including their satisfaction level and any points of dissatisfaction. 【0735】 Step 7: 【0736】 The device sends user feedback to the server. The server receives this feedback and analyzes it using an emotion engine. 【0737】 Step 8: 【0738】 The server's emotion engine analyzes the feedback content and evaluates the user's emotional state. Natural language processing is used to analyze the user's language use and understand their level of satisfaction or dissatisfaction. 【0739】 Step 9: 【0740】 The server adjusts the generative model's learning process based on the results obtained from the emotion engine. This information is fed back into the algorithm and used to improve the accuracy of subsequent analyses and component selections. 【0741】 (Example 2) 【0742】 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". 【0743】 This invention aims to move away from conventional, subjective methods in the selection process of elements in construction work, and to standardize and improve efficiency. Furthermore, it seeks to solve the problem of achieving more sophisticated element selection and improved user experience based on feedback that takes user emotions into consideration. 【0744】 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. 【0745】 In this invention, the server includes a computing device for receiving information, a computing device for extracting similar information from past information sets, and a computing device for selecting the optimal elements using a generative model. This enables efficient element selection that takes user emotions into consideration. 【0746】 "Device" refers to hardware or software means for a user to input or receive information. 【0747】 A "processing unit" is a central processing unit or a means of a computer used to process, analyze, or output information. 【0748】 An "information collection" is a database or data repository that stores past cases and related data. 【0749】 A "generative model" is an algorithm or program that uses machine learning or artificial intelligence techniques to generate the optimal output from target data. 【0750】 An "element" refers to a component, material, or other constituent element that should be selected in a construction or project. 【0751】 "Opinions" refer to feedback and comments provided by users to the system, and are data that helps improve the system. 【0752】 An "operation screen" is an interface used by a user to input information into a system or to view output from the system. 【0753】 The system of this invention achieves efficient element selection in construction through information input, analysis, element selection, and dynamic adjustment based on feedback. This system mainly consists of terminals and a server. 【0754】 First, the user inputs detailed information about the construction project through a terminal. This information includes the construction location, the type of base station to be used, and the frequency to be used. The terminal organizes the input information and sends it to the server. Based on this information, the server searches for similar information from past data sets. This makes it possible to support selection based on experience. 【0755】 The server uses a generative AI model in the selection process. This model is trained using machine learning techniques to suggest the most suitable elements for the input information. For example, if the construction site is in an urban area, the model will prioritize selecting elements with superior durability. This selection generates a list of appropriate elements, which are then sent back to the terminal. 【0756】 User feedback is sent to the server and evaluated by the sentiment engine. This allows the system to dynamically adjust the generative model's algorithm, enabling selections that are more in line with the user's emotions. 【0757】 For example, if a user has concerns about a construction element, the system detects this concern and provides supplementary information to help the user understand. Furthermore, the user interface displays an information guide that allows the user to confidently review the selection results. 【0758】 An example of a prompt message might be, "The construction site is in Minato Ward, Tokyo, and the base station to be installed is a small base station. The operating frequency is the 2.5GHz band. What materials are recommended?" Based on this, the system selects the necessary components. 【0759】 In this way, the system achieves efficient and highly accurate element selection while taking user emotions into consideration. 【0760】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0761】 Step 1: 【0762】 The user uses a terminal to input information about the construction work. Specifically, they input data such as the location of the construction, the type of base station to be built, and the frequency to be used. This information is formatted into the appropriate format within the terminal. Input is in text format, and a formatted JSON object is generated as output. 【0763】 Step 2: 【0764】 The terminal sends formatted information to the server. HTTPS is used as the communication protocol, ensuring that the information is transmitted securely. The input is formatted data, and output is produced when the information correctly reaches the server. The terminal then sends a "POST" request to the server endpoint. 【0765】 Step 3: 【0766】 The server analyzes the received information and extracts similar information from past data sets. It executes SQL queries against the database to retrieve data that matches the criteria. The input is the construction information received by the server, and the output is a data list containing similar information. Specifically, it searches for data that matches past project data. 【0767】 Step 4: 【0768】 The server uses a generative AI model to select the optimal elements based on construction information and similar data. A model algorithm trained through machine learning is used to create a list of elements as selection candidates. The input is extracted similar data, and the output is a list of elements based on the model's predictions. The server then feeds the data into the generative AI model, and the element selection process is executed. 【0769】 Step 5: 【0770】 The server sends a list of selected elements to the terminal. The generated list of elements is sent again using the HTTPS protocol, ensuring secure transmission. The input is the list of elements, and the output is the list displayed on the user's terminal. The server returns data to the terminal using a "GET" request. 【0771】 Step 6: 【0772】 Users can view a list of elements received on their device and provide feedback. This user feedback is transmitted as input to the emotion engine, analyzed, and used to refine future AI model generation. A feedback form is displayed on the device, and the specific action of submitting the feedback is performed. 【0773】 Step 7: 【0774】 The server utilizes user feedback to dynamically adjust the algorithms of the generated AI model. Natural language processing techniques are used for sentiment analysis, and this data is incorporated to improve the model's prediction accuracy. The input is user feedback, and the output is the updating of the model's parameters. The sentiment analysis engine then performs the specific operation of analyzing the feedback. 【0775】 (Application Example 2) 【0776】 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". 【0777】 Traditional base station construction methods for selecting materials tend to be experience-dependent and subjective, limiting efficiency and standardization. Furthermore, the lack of mechanisms to adequately consider user emotions and feedback made it difficult to improve user satisfaction. To address these challenges, a system for efficient material selection that also considers user emotions is needed. 【0778】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0779】 In this invention, the server includes a computing device means for inputting information, a computer means for receiving information from the computing device means, and a computer means for evaluating the user's emotional state using emotion analysis means and providing support information based on the results. This makes it possible to improve efficiency and standardization in the component selection process, and to improve user satisfaction by providing support information that takes the user's emotions into consideration. 【0780】 "Information input device means" refers to a device system for users to input detailed information and feedback on construction work. 【0781】 "Computing means" refers to a server system that processes information received from a computing device and performs necessary calculations. 【0782】 A "data repository" is a database where past cases and data are stored, and it is an information source that computer systems refer to. 【0783】 A "generative model" is an algorithm that generates the optimal list of components based on past data. 【0784】 The "component list" is a list of materials required for base station construction, output by a computer using a generative model. 【0785】 A "computer means for receiving opinions" refers to a server system that receives feedback from users and utilizes it to train generative models. 【0786】 An "emotion analysis tool" is a program or algorithm that evaluates a user's emotional state from their voice, facial expressions, etc., and generates support information based on that evaluation. 【0787】 "Computer means for providing support information" refers to a server system for providing support information generated by emotion analysis means to users. 【0788】 The "display function" is a screen display system that allows users to view and confirm component lists and related information. 【0789】 This invention supports the realization of a system that enables efficient and emotionally conscious selection of components at construction sites. Users can input necessary information via a smart device and select components. The computing means extracts similar past data from a database based on the input information and generates an optimal component list using a generative model. Artificial intelligence technologies such as TensorFlow and PyTorch are applied to this generative model. 【0790】 The server also uses emotion analysis tools to analyze the user's voice and facial expressions to understand their emotions. This utilizes Google Cloud Natural Language API and Azure Text Analytics. Based on the analysis results, the computing tools provide the user with the most appropriate support information and advice. The goal is to enhance the user's sense of security and satisfaction through the presentation of this support information. 【0791】 As a concrete example, when construction workers select components in real time, their feelings of anxiety are analyzed, and information such as "This component complies with the latest building standards" is immediately presented as supporting information. In this way, computing means can provide information that contributes to the success of a project based on the user's emotions. 【0792】 An example prompt might be: "Generate a list of the best materials for this construction project. The target location is an urban area, and we plan to build a 3G LTE base station. The workers seem unsure about material selection." This allows the server to provide appropriate feedback. 【0793】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0794】 Step 1: 【0795】 Users input detailed information about the construction site using a smart device. This information includes the construction location, base station type, and operating frequency. This information is temporarily stored on the device. 【0796】 Step 2: 【0797】 The terminal organizes the entered information and sends it to the server. The server receives this information and searches its database for similar past project data. This search result is temporarily stored for use in the next step. 【0798】 Step 3: 【0799】 The server applies a generative model to generate the optimal component list based on the searched similar data. The generation process uses input construction information and data retrieved from the database. The generative model leverages algorithms from TensorFlow and PyTorch. The resulting component list is stored in the database. 【0800】 Step 4: 【0801】 Users submit feedback via their smart devices. This feedback includes comments and questions about the user's component list. This information is received and temporarily stored by the server. 【0802】 Step 5: 【0803】 The server uses sentiment analysis tools to evaluate the user's emotional state from their feedback and voice. Google Cloud Natural Language API and Azure Text Analytics are used for this analysis. The emotional information obtained from this analysis is then used in the next step. 【0804】 Step 6: 【0805】 Based on the sentiment analysis results, the server generates supportive information for the user. This information includes advice and recommendations designed to enhance the user's sense of security. The server then sends this information to the user's smart device. 【0806】 Step 7: 【0807】 The user receives and reviews the support information provided through their smart device. Specific instructions are displayed to help the user understand the information in more detail. 【0808】 Step 8: 【0809】 The server updates its generative model based on user feedback and sentiment analysis results. This improvement enhances the accuracy of component selection in subsequent uses. 【0810】 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. 【0811】 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. 【0812】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0813】 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. 【0814】 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. 【0815】 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. 【0816】 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. 【0817】 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. 【0818】 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." 【0819】 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. 【0820】 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. 【0821】 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. 【0822】 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. 【0823】 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. 【0824】 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. 【0825】 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. 【0826】 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. 【0827】 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. 【0828】 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. 【0829】 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. 【0830】 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. 【0831】 The following is further disclosed regarding the embodiments described above. 【0832】 (Claim 1) 【0833】 A terminal means for inputting information, 【0834】 A server means that receives information from the terminal means, 【0835】 A server mechanism for extracting similar data from past databases, 【0836】 A server means that selects the optimal component using a generative model, 【0837】 A server means that generates and outputs a list of selected components, 【0838】 A server means that transmits a list of components to the terminal means, 【0839】 A server that receives user feedback and trains a generative model, 【0840】 A system that includes this. 【0841】 (Claim 2) 【0842】 The system according to claim 1, characterized in that the generation model optimizes the components based on know-how related to past construction projects. 【0843】 (Claim 3) 【0844】 The system according to claim 1, characterized in that the feedback means enables the user to check and modify the list of components through a user interface. 【0845】 "Example 1" 【0846】 (Claim 1) 【0847】 An input device means for inputting information, 【0848】 Information processing means that receives and stores information from the input device means, 【0849】 Information processing device means for extracting similar information from past records, 【0850】 Information processing device means for selecting the optimal components using a generative model, 【0851】 Information processing device means that generates and outputs a list of selected components, 【0852】 Information processing means for transmitting a list of components to the input device means, 【0853】 An information processing device means that receives responses from the operator and trains a generative model, 【0854】 A system that includes this. 【0855】 (Claim 2) 【0856】 The system according to claim 1, characterized in that the generation model optimizes its components based on knowledge of past operations. 【0857】 (Claim 3) 【0858】 The system according to claim 1, characterized in that the reaction means enables the operator to verify and modify the list of components through an input / output device. 【0859】 "Application Example 1" 【0860】 (Claim 1) 【0861】 A mobile information terminal equipped with information processing means, 【0862】 A computing means for receiving program information from the aforementioned information processing means, 【0863】 A calculation method for extracting similar records from past work records, 【0864】 A computational means for selecting the optimal materials using a generative model, 【0865】 A calculation means for generating a list of selected materials and outputting the data, 【0866】 A calculation means for transmitting a materials list to the aforementioned mobile information terminal means, 【0867】 A computational means that receives information from the worker and adjusts the generative model, 【0868】 A system that includes this. 【0869】 (Claim 2) 【0870】 The system according to claim 1, characterized in that the generation model optimizes materials based on experience with past work. 【0871】 (Claim 3) 【0872】 The system according to claim 1, characterized in that the information means enables the worker to check and modify the materials list through an interface. 【0873】 "Example 2 of combining an emotion engine" 【0874】 (Claim 1) 【0875】 A device for inputting information, 【0876】 A computing device that receives information from the aforementioned device, 【0877】 A computing device that extracts similar information from past information sets, 【0878】 A computing unit that selects the optimal elements using a generative model, 【0879】 A computing unit that generates and outputs a list of selected elements, 【0880】 A calculation device that transmits a list of elements to the aforementioned device, 【0881】 A computing device that analyzes user feedback and dynamically adjusts the generative model, 【0882】 A device that evaluates the user's language and presents information based on their emotional state, 【0883】 A system that includes this. 【0884】 (Claim 2) 【0885】 The system according to claim 1, characterized in that the generative model optimizes elements based on knowledge of past work. 【0886】 (Claim 3) 【0887】 The system according to claim 1, characterized in that the feedback means enables the user to view and modify the list of elements through the user's operation screen. 【0888】 "Application example 2 when combining with an emotional engine" 【0889】 (Claim 1) 【0890】 A computing device means for inputting information, 【0891】 A computing means that receives information from the aforementioned computing device means, 【0892】 A computing means for extracting similar information from past archives, 【0893】 A computer means for selecting the optimal components using a generative model, 【0894】 A computer means for generating and outputting a list of selected components, 【0895】 A computer means that transmits a list of components to the aforementioned computing device means, 【0896】 A computing means for receiving user feedback and training a generative model, 【0897】 A computer means that evaluates the user's emotional state using emotion analysis means and provides support information based on the results, 【0898】 A means for displaying support information and recommendations that respond to emotions through a computing device, 【0899】 A system that includes this. 【0900】 (Claim 2) 【0901】 The system according to claim 1, characterized in that the generation model optimizes components based on knowledge of past construction work. 【0902】 (Claim 3) 【0903】 The system according to claim 1, characterized in that the opinion means enables the user to confirm and modify the component list through a display function. [Explanation of symbols] 【0904】 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

[Claim 1] A terminal means for inputting information, A server means that receives information from the terminal means, A server mechanism for extracting similar data from past databases, A server means that selects the optimal component using a generative model, A server means that generates and outputs a list of selected components, A server means that transmits a list of components to the terminal means, A server that receives user feedback and trains a generative model, A system that includes this. [Claim 2] The system according to claim 1, characterized in that the generation model optimizes the components based on know-how from past construction projects. [Claim 3] The system according to claim 1, characterized in that the feedback means enables the user to check and modify the list of components through a user interface.

Images