System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data relating to a construction project; means for training a quantum computer based on the collected data; means for providing an interactive interface for a user to input requirements for the construction project; means for sending the user's input data to the quantum computer to predict an optimal cement product; and means for presenting the prediction results to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Currently, selecting the optimal cement product for specific conditions in a construction project is extremely complex and requires specialized knowledge and experience. An incorrect selection can increase project costs, extend project time, and even cause structural problems. Furthermore, many variables must be considered when selecting a cement product, requiring technology to handle this effectively. Furthermore, there is a need for methods that utilize new technologies such as quantum computers to efficiently and accurately select cement products. This invention aims to solve these problems. [Means for solving the problem]

[0005] This invention is a system that includes a means for collecting data specific to construction projects, a means for training a quantum computer based on the collected data, an interactive interface for users to input project requirements, a means for sending user-input data to the quantum computer to predict the optimal cement product, and a means for presenting the predicted results to the user. This system allows users to scientifically and objectively select the optimal cement product, improving the efficiency and accuracy of the project. Furthermore, by using a generative AI model to convert the construction project requirements input by the user into a standard format, it enables rapid computation by the quantum computer and provides the user with recommendations for the optimal cement product.

[0006] A "data collection tool" is a method and device for collecting, organizing, and storing information about a construction project in a database.

[0007] A "quantum computer" is a computer that uses quantum bits to perform complex calculations at high speed.

[0008] "Training methods" are the processes and tools used to build and tune specific predictive models using a quantum computer based on collected data.

[0009] An "interactive interface" is a user interface through which a user can input requirements for a construction project and communicate with the system.

[0010] The "prediction means" refers to the algorithms and calculations used to select the optimal cement product based on input data using a quantum computer.

[0011] "Presentation means" refers to a function and device that displays to the user the optimal cement product proposal results generated by the quantum computer.

[0012] A "generative AI model" is a model that uses artificial intelligence technology to convert natural language requirements entered by a user into a standard format.

[0013] A "standard format" is data that has been converted by a generative AI model into a consistent format that allows efficient computational processing by quantum computers. [Brief explanation of the drawings]

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

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

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

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

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

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0035] This invention relates to a system that utilizes a quantum computer and a generative AI model to recommend optimal cement products for building projects. The system includes a data collection means, a quantum computer training means, a user interface provision means, a prediction means, and a presentation means.

[0036] The server first collects construction project data and cement product property data and stores them in a database, which is categorized based on project conditions such as humidity, temperature, durability, cost, etc. The collected data is then used to train the quantum computer.

[0037] The server then trains a quantum computer on the collected data. The trained model is used to evaluate cement product performance in the building environment and predict optimal products. To ensure effective training of the quantum computer, the data undergoes pre-processing such as normalization and feature engineering.

[0038] The terminal provides a user interface that allows users to input requirements for a building project. Users can enter detailed information into the interface, such as the project's location, climate conditions, building use, budget, etc. The generative AI model converts these input data into a standard format.

[0039] For example, if a user inputs, "I am planning to build a commercial building in a hot and humid region. I have a budget of approximately 50 million yen and am looking for a durable, cost-effective cement," this information is appropriately converted by the generative AI model and sent to the server.

[0040] The server sends the user's input data to a quantum computer, which then uses the trained model to calculate the best cement product for the given conditions, comparing the characteristics of different cement products to select the one that best meets the conditions.

[0041] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0042] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of quantum computers, it is possible to quickly and accurately recommend the optimal product even under complex conditions.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The server collects construction project data and cement product property data, such as humidity, temperature, durability, and cost, and stores them in a database.

[0046] Step 2:

[0047] The server preprocesses the collected data by normalizing it, removing invalid data, and performing any necessary feature engineering so that the data can be efficiently processed by the quantum computer.

[0048] Step 3:

[0049] The server uses the pre-processed data to train a quantum computer, which then learns from the vast amount of data and builds a model to predict the performance of cement products.

[0050] Step 4:

[0051] The terminal provides users with an interactive interface through which they can input details about their construction project, such as the project location, climate conditions, building use, and budget.

[0052] Step 5:

[0053] Users use a conversational interface to input project requirements, such as, "I'm planning to build a commercial building in a hot and humid climate. I have a budget of approximately $500,000 and I'm looking for a durable, cost-effective cement."

[0054] Step 6:

[0055] The device uses generative AI models to convert user-entered information into a standard format, for example, converting the natural language input "hot and humid region" into concrete numerical data that a quantum computer can easily understand.

[0056] Step 7:

[0057] The device then sends the converted data to the server, which receives it and starts the quantum computer calculation.

[0058] Step 8:

[0059] The server inputs data in a standard format into a quantum computer model and runs a simulation, which predicts and identifies candidates for the optimal cement product.

[0060] Step 9:

[0061] The server formats the simulation results and converts them into an easy-to-understand format, including, for example, the name and characteristics of the optimal cement product and the reasons for the recommendation.

[0062] Step 10:

[0063] The server sends the formatted results to the terminal.

[0064] Step 11:

[0065] The device then displays the results to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0066] Step 12:

[0067] Users can review the cement product information presented and, if necessary, ask additional questions or request recalculations under different conditions.

[0068] Example 1

[0069] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0070] Selecting the optimal cement product for a construction project requires considering many variables, but the process requires specialized knowledge, is time-consuming, and costly. Furthermore, conventional systems lack the computing power to simultaneously consider complex conditions, making it difficult to select the right product quickly and accurately. This makes it difficult to find the optimal cement product.

[0071] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0072] In this invention, the server includes means for collecting information about building projects, means for training a quantum computer based on the collected data, means for providing an interactive interface for users to input building project requirements, means for converting the user-input building project requirements into a standard format using a generative AI model, means for sending the user-input data to the quantum computer and predicting the optimal building material product, and means for presenting the prediction result to the user, thereby enabling a user to quickly and accurately select the optimal cement product even without specialized knowledge.

[0073] A "building project" refers to a series of tasks related to the design, construction, and maintenance of a building.

[0074] "Information" refers to all data related to a building project, such as the project location, climatic conditions, materials used, budget, etc.

[0075] A "quantum computer" is a computer that performs calculations using quantum bits, and refers to a device that can quickly perform calculations that are difficult for conventional computers to perform.

[0076] "Training" refers to the process of learning to improve the performance of a computational model using a given data set.

[0077] An "interactive interface" refers to an interactive user interface in which a user provides input to a system and the system operates based on that input.

[0078] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is designed to perform specific tasks.

[0079] A "standard format" refers to the representation of data in a unified format to ensure consistency and compatibility.

[0080] "Building products" refers to various materials and products used in the construction of buildings (e.g., cement, bricks, rebar, etc.).

[0081] "Predicting" refers to estimating future outcomes or trends based on given data.

[0082] "Present" refers to the system showing the results of its calculations or processing to the user visually or in some other way.

[0083] The present invention relates to a system that uses a quantum computer and a generative AI model to propose optimal building material products for a building project. An embodiment of the system will be described below.

[0084] The server first collects and stores information related to the building project in a database, including data on project conditions such as humidity, temperature, durability, cost, etc. The data collected by the server is stored in the database for further processing.

[0085] The server then performs preprocessing on the collected data, including normalization and feature engineering. This enables effective training on a quantum computer. Examples of hardware used include the IBM Q Experience and the D-Wave Quantum Computer. The software used is Qiskit, a quantum programming framework.

[0086] The server then uses a quantum computer to perform training, and the trained model is used to evaluate the performance of building materials in a building environment and predict optimal products.

[0087] An interactive interface is provided on the terminal for users to input building project requirements, and users can enter detailed information such as project location, climatic conditions, building use, budget, etc. into the interface.

[0088] The generative AI model is responsible for converting user input data into a standard format. For example, if a user inputs, "We are planning to build a commercial building in a hot and humid region with a budget of 50 million yen," this information is converted appropriately by the generative AI model and sent to the server.

[0089] The server then sends the user's input data to a quantum computer, which predicts the optimal building material product. The quantum computer uses the trained model to calculate the building material product that best suits the conditions. At this time, it compares the characteristics of different building material products and selects the product that best meets the conditions.

[0090] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0091] This system allows users to efficiently select the optimal building material products, even without specialized knowledge. By utilizing the computational power of quantum computers, it is possible to quickly and accurately suggest optimal products even under complex conditions.

[0092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0093] Step 1:

[0094] The server collects information about the building project, including project conditions such as humidity, temperature, durability, cost, etc. The server stores this data in a database.

[0095] Input: Project conditions (humidity, temperature, durability, cost, etc.)

[0096] Output: Project condition data neatly stored in a database

[0097] Step 2:

[0098] The server performs preprocessing on the collected data, such as normalization and feature engineering, to make it more efficient for training on a quantum computer, for example, scaling humidity data to a range of 0 to 1.

[0099] Input: Project criteria data stored in the database

[0100] Output: Preprocessed project condition data

[0101] Specific behavior: "Humidity data [45, 55, 60] → Normalized humidity data [0.45, 0.55, 0.60]"

[0102] Step 3:

[0103] The server uses a quantum computer to train the model based on the pre-processed data. The trained model is used to evaluate the performance of building materials in the building environment and predict the optimal product.

[0104] Input: Preprocessed project criteria data

[0105] Output: A trained quantum computer model

[0106] Specific operation: Training is performed using the Qiskit framework using the IBM Q Experience and D-Wave Quantum Computer.

[0107] Step 4:

[0108] The terminal provides a user interface that allows users to input building project requirements, including details such as the project location, climate conditions, building use, and budget.

[0109] Input: User's project conditions (location, weather conditions, purpose, budget, etc.)

[0110] Output: User input data

[0111] Specific operation: The user types into the terminal, "We are planning to build a commercial building in a hot and humid region. The budget is 50 million yen."

[0112] Step 5:

[0113] The generative AI model converts user-entered data into a standard format that is easy for a quantum computer to understand.

[0114] Input: User-entered data

[0115] Output: Data converted to a standard format

[0116] Specific behavior: User input: "Hot and humid", "Commercial building", "50 million yen"

[0117] Converted data: {Area: "Hot and Humid", Type: "Commercial Building", Budget: 50000000}

[0118] Step 6:

[0119] The server sends user input data transformed by the generative AI model to a quantum computer, which then uses the trained model to calculate the optimal building material product for the conditions.

[0120] Input: Data converted to a standard format

[0121] Output: Prediction results of optimal building material products

[0122] How it works: A quantum computer evaluates different building materials and calculates the optimal product based on durability and cost performance.

[0123] Step 7:

[0124] The prediction results are sent to the device and presented to the user, who then displays specific suggestions to the user.

[0125] Input: Prediction results for optimal building material products

[0126] Output: Prediction results presented to the user

[0127] What it does: The user is told, "ABC Cement is ideal for this project. It is durable in hot and humid conditions and is cost-effective."

[0128] Through the above processing steps, users can quickly and accurately select the optimal building material products under complex conditions, even without specialized knowledge.

[0129] (Application example 1)

[0130] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0131] In recent years, there has been a demand for optimizing appropriate material selection and inventory management strategies in construction projects and logistics center operations. However, these optimizations are extremely complex and require consideration of numerous conditions and variables, requiring advanced knowledge and skills. In particular, it is difficult to make quick and accurate decisions using conventional methods, making efficient operation difficult.

[0132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0133] In this invention, the server includes means for collecting data related to a construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for collecting data related to inventory management at a logistics center, means for converting the collected inventory data into a standard format using a generative AI model, means for calculating an optimal inventory management strategy using the quantum computer, and means for presenting the optimal inventory management strategy to a user, thereby enabling the selection of optimal cement products for the construction project and the implementation of an efficient inventory management strategy at the logistics center.

[0134] "Building project data" means information related to the design, construction, and operation of a building, including environmental conditions, budget, materials used, and overall project requirements.

[0135] A "quantum computer" is a computing device that, unlike conventional computers, operates based on the principles of quantum mechanics and can efficiently solve certain computational problems.

[0136] "Collection means" refers to the method or device for collecting, storing, and optionally processing data.

[0137] "Training" refers to the process by which an algorithm or model learns from provided data and improves its accuracy in prediction or identification.

[0138] A "means for providing an interactive interface" is a combination of software and hardware that allows a user to interact directly with a system.

[0139] "User Input Data" means information provided by a user to the system, including project requirements and conditions.

[0140] "Data related to inventory management at logistics centers" refers to information related to inventory status, replenishment schedules, sales forecasts, storage capacity, and the like at logistics centers.

[0141] A "generative AI model" is a pre-trained artificial intelligence model capable of natural language processing and data analysis.

[0142] A "means for converting into a standard format" is a method or device for converting input data of various formats into a unified structure or format.

[0143] A "calculating means" is a method or device for deriving a specific result or optimal solution based on given data or conditions.

[0144] A "presentation means" is a method or device for visually or audibly displaying the results of a calculation or prediction to a user.

[0145] The "optimum cement product" is the cement product that best meets and performs best for the conditions and requirements of a particular building project.

[0146] An "optimal inventory management strategy" is the most effective way to efficiently manage the storage, replenishment, and sales of inventory in a distribution center.

[0147] The present invention provides a system for proposing optimal cement products and inventory management strategies for construction projects and logistics center operations. Specific embodiments for carrying out the present invention are described below.

[0148] The system includes the following hardware and software:

[0149] Server: Performs data collection, data processing, model training, and prediction calculations, specifically using quantum computers and generative AI models (e.g., OpenAI APIs).

[0150] Device: The device (e.g., smartphone, tablet) through which a user provides input and receives results.

[0151] Interactive interface: The interface through which a user provides data to a system (e.g., a web application).

[0152] The operation of the system is described below.

[0153] Data collection

[0154] The server collects data about construction projects and logistics center operations. For construction projects, information about the project location, weather conditions, building use, budget, etc. For logistics centers, information about incoming and outgoing shipments, inventory levels, sales forecasts, warehouse status, etc.

[0155] Data Transformation and Prediction

[0156] The server uses a generative AI model to convert the collected data into a standard format for training on a quantum computer. Specifically, the server sends the following prompt to the generative AI model to perform the appropriate format conversion:

[0157] Example prompt sentence:

[0158] Predict the optimal stock management for the following data: {'temperature': 22, 'humidity': 55, 'stock_levels': {'product_A': 150, 'product_B': 250}, 'sales_forecast': {'product_A': 130, 'product_B': 200}, 'warehouse_capacity': 600}

[0159] The generative AI model takes the prompt text, converts it into a standard format, and sends it to a quantum computer to predict the most suitable cement product and inventory management strategy for the specific conditions.

[0160] Results presentation

[0161] The server sends the prediction results to the terminal and displays them to the user, who receives recommendations for optimal cement products and inventory management strategies through the terminal's interactive interface, enabling efficient decision-making.

[0162] For example, for a building project:

[0163] If a user inputs, "We are planning to build a commercial building in a hot and humid region. We have a budget of approximately 50 million yen and are looking for a durable, cost-effective cement," the server will convert this information appropriately using a generative AI model and predict the optimal cement product. The predicted result will be presented to the user in the form, "ABC Cement is ideal for this project. ABC Cement is highly durable under hot and humid conditions and also offers excellent cost performance."

[0164] For distribution centers:

[0165] If a user types, "Please suggest the optimal inventory management strategy based on current inventory, sales forecast, and warehouse capacity," the server will convert the collected data using a generative AI model and calculate the optimal management strategy using a quantum computer. The result will be presented as, "Product A needs replenishment in the next two weeks. Product B's current inventory level is appropriate to meet demand."

[0166] In this way, this invention utilizes quantum computers and generative AI models to quickly and accurately provide optimal product selection and management strategies even under complex conditions.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The server collects data about the construction project and logistics center operations from users and sensors, including project location, weather conditions, building use, budget, incoming and outgoing shipments, inventory levels, sales forecasts, and warehouse conditions, derived through signal or communication analysis.

[0170] Input: Building project and logistics center operational data provided by users and sensors.

[0171] Output: The collected dataset.

[0172] Step 2:

[0173] The server normalizes the collected data and performs feature engineering as needed, including imputing missing values, converting data types, and generating new features.

[0174] Input: The collected dataset.

[0175] Output: The preprocessed dataset.

[0176] Step 3:

[0177] The server inputs the preprocessed data into the generative AI model and converts it into a standard format. Specifically, it uses the API of OpenAI, the generative AI model, to send data through prompts and receive responses.

[0178] Input: A preprocessed dataset and a prompt statement.

[0179] Output: Data converted into a standard format.

[0180] Step 4:

[0181] The server then converts the data into a standard format and sends it to a quantum computer, which then uses the trained model to calculate the best solution for the specific conditions.

[0182] Input: Data converted to a standard format.

[0183] Output: Predicted results of optimal cement product or inventory management strategy.

[0184] Step 5:

[0185] The server receives the prediction results from the quantum computer and sends them to the device, converting the data into a user-friendly format and displaying it visually for easy understanding.

[0186] Input: Prediction results from a quantum computer.

[0187] Output: The results in the form of reports and graphs that are presented to the user.

[0188] Step 6:

[0189] The terminal then presents the received forecast results to the user, who can then review the results through an interactive interface to select the optimal cement product and implement an inventory management strategy.

[0190] Input: Results presented by the server.

[0191] Output: The result that the user sees on the display screen.

[0192] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0193] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0194] A specific embodiment of the system will be described below.

[0195] The server first collects construction project data and cement product property data and stores them in a database, including project conditions such as humidity, temperature, durability, and cost. The collected data is then used to train the quantum computer.

[0196] The server then preprocesses the collected data by normalizing it, removing invalid data, and performing necessary feature engineering to enable efficient processing by the quantum computer. The server then trains the quantum computer using the preprocessed data. The trained model is used to evaluate the performance of cement products in the building environment and predict optimal products.

[0197] The terminal provides a user interface that allows users to input requirements for a construction project. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. In addition, the terminal is equipped with an emotion engine that recognizes the user's emotions in real time. This emotion data is then analyzed along with the input requirements.

[0198] For example, if a user uses a conversational interface to input, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product.", the emotion engine analyzes emotions from the user's voice and text input. The generative AI model converts these input data into a standard format. For example, it converts the natural language input "hot and humid region" into numerical data.

[0199] The device then sends the converted data to the server, which receives it and initiates calculations using a quantum computer. The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The computer also takes into account the emotional data collected by the emotion engine, fine-tuning the recommendations based on the user's emotional state.

[0200] The server formats the calculation results and converts them into an easy-to-understand format. For example, it includes the name and characteristics of the optimal cement product, as well as the reason for the recommendation. The server then sends the formatted results to the device. The device then displays the received results to the user. For example, it may suggest, "XYZ cement is optimal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0201] Additionally, if the emotion engine confirms that the user feels safe, more detailed technical information or additional recommendations may be displayed, while if the user is anxious or skeptical, more concise and reassuring information is provided.

[0202] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of a quantum computer and the emotion recognition function of an emotion engine, it is possible to provide optimal and reassuring recommendations to users.

[0203] The processing flow will be explained below.

[0204] Step 1:

[0205] The server collects construction project data and cement product property data from various data sources, including data on weather conditions, durability test results, costs, etc. The collected data is stored in a database.

[0206] Step 2:

[0207] The server preprocesses the collected data by removing invalid data, normalizing the data, and performing feature engineering, so that the data is in a format that can be efficiently processed by a quantum computer.

[0208] Step 3:

[0209] The server uses the pre-processed data to train a quantum computer, which then builds a model to predict cement product performance in the building environment. The model is designed to learn from large amounts of data and accurately predict the properties of cement products.

[0210] Step 4:

[0211] The terminal displays an interactive interface for users to input information about their construction projects. The interface is designed to be easy to understand, allowing users to easily input project requirements.

[0212] Step 5:

[0213] Using an interactive interface, users input details about the construction project, such as the project's location, climate conditions, intended use, budget, etc. This information is then sent to the system.

[0214] Step 6:

[0215] The device converts the information entered by the user into a standard format using a generative AI model, which converts natural language input into numerical data. For example, "hot and humid region" is converted into specific numerical data.

[0216] Step 7:

[0217] The device transmits the converted data to the emotion engine, which recognizes the user's emotions in real time and evaluates their emotional state. For example, the emotion engine can determine the user's stress level from their tone of voice and facial expression.

[0218] Step 8:

[0219] The device sends the emotional data obtained by the emotion engine to the server, which receives it and provides it to the quantum computer along with the user's input data.

[0220] Step 9:

[0221] The server inputs standard format data and emotional data into the quantum computer model and begins calculations, which then predicts and identifies candidates for the optimal cement product.

[0222] Step 10:

[0223] The server formats the results and converts them into a user-friendly format, including, for example, the name of the specific cement product, its properties, and the reasons for the recommendation.

[0224] Step 11:

[0225] The server sends the formatted results to the terminal.

[0226] Step 12:

[0227] The device then sends the results back to the emotion engine, which then displays the results in a way that adapts to the user's emotional state. For example, if the device determines that the user is feeling anxious, it will display more detailed information or a support message.

[0228] Step 13:

[0229] The user reviews the presented cement product information and can request additional questions or changes using the interface again.

[0230] This process allows users to efficiently select the most suitable cement product, and by using an emotion engine, it provides optimal suggestions based on the user's emotional state.

[0231] Example 2

[0232] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0233] Existing cement product selection methods for construction projects do not adequately consider the characteristics of the project, making it difficult to select the optimal cement product. Furthermore, users may feel uneasy because recommendations do not take into account their technical knowledge or emotional state. Furthermore, the technology required to efficiently process large amounts of data and make accurate predictions is still immature.

[0234] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0235] In this invention, the server includes means for collecting data on construction projects, means for preprocessing the collected data, means for training a quantum computer based on the preprocessed data, means for predicting the cement product best suited to a user's requirements using the trained quantum computer, means for providing an interactive interface for the user to input the construction project requirements, means for analyzing the user's emotional state using an emotion engine and fine-tuning the proposal content, means for converting the construction project requirements input by the user into a standard format using a generative AI model, and means for presenting the prediction results to the user. This enables highly accurate predictions that take into account project characteristics and makes optimal proposals according to the user's emotional state.

[0236] "Data relating to building projects" refers to various information related to the design, construction and management of buildings, including, in particular, project conditions such as humidity, temperature, durability and cost.

[0237] "Means of collection" refers to the methods and devices that collect the necessary data using sensors, APIs, etc. and store it in a database.

[0238] The "preprocessing means" refers to a method or device that converts collected data into a format that is easy to process through a series of operations such as normalization, deletion of invalid data, and feature engineering.

[0239] "Training means" refers to a method or apparatus that optimizes a quantum computer based on preprocessed data to build and tune a target predictive model.

[0240] "Conversational interface" refers to the interactive input screens and software that allow users to input requirements for a building project.

[0241] An "emotion engine" refers to technology or a device that analyzes a user's facial expressions, voice, text input, etc. to evaluate and recognize their emotional state in real time, and provides appropriate feedback based on that.

[0242] A "generative AI model" is a machine learning model used to convert input data into a specified format, serving to standardize diverse input formats.

[0243] "Means for converting into a standard format" refers to the technology or device that analyzes the input construction project requirements and converts them into a specified unified format.

[0244] "Means for presenting predicted results" refers to a method or device for displaying the calculated optimal cement product characteristics and the reasons for recommendation in a manner that is easy for the user to understand.

[0245] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a data preprocessing means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0246] The server first collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. This data is collected using sensors and APIs. For example, weather data is obtained from a weather API, and the database is updated regularly.

[0247] The server then preprocesses the collected data, including normalizing the data, removing invalid data, and performing feature engineering. Specifically, it scales the temperature and humidity values ​​and imputes missing values. This preprocessing allows for efficient processing on a quantum computer.

[0248] Based on the pre-processed data, the server trains the quantum computer, which includes generating a training dataset, encoding the data into qubits, gate operations, and measurement operations, allowing the quantum computer to build an optimized model that can be used to make future predictions.

[0249] The user inputs the requirements for a construction project using a conversational interface on the device. For example, the user might input, "I'm building a commercial building with a budget of 50 million yen, located in a hot and humid region. Please suggest the best cement product." The device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotional state in real time. This emotion data is analyzed along with the user's input data and an emotion tag is attached.

[0250] The generative AI model converts the building project requirements entered by the user into a standard format. For example, the natural language input "hot and humid region" is converted into concrete numerical data. The converted data is then sent from the device to the server.

[0251] The server receives the data and initiates calculations using a quantum computer. The quantum computer uses the trained model to predict the cement product that best suits the user's requirements. This process also takes into account emotional data collected by the emotion engine, fine-tuning the suggestions based on the user's emotional state.

[0252] The calculation results are formatted by the server and converted into an easy-to-understand format. For example, the format is a report that includes the name of the optimal cement product, its characteristics, and the reason for the recommendation. The formatted results are sent to the terminal, which then displays them to the user. An example of a presentation might be, "XYZ cement is ideal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0253] The device also uses an emotion engine to analyze the user's real-time reactions. If the user feels reassured, it displays more detailed technical information and additional recommendations. Conversely, if the user feels anxious or suspicious, it provides more concise and reassuring information. This system allows users to efficiently select the optimal cement product even without specialized knowledge.

[0254] Example of a text prompt

[0255] "If the construction conditions for a commercial building are hot and humid and the budget is 50 million yen, which cement product would be best?"

[0256] "A user is building a commercial building in a hot and humid region with a budget of ¥50 million. Please suggest the best cement product for these conditions."

[0257] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0258] Processing flow

[0259] Step 1: Data collection

[0260] The server collects construction project data and cement product characteristic data through sensors and APIs.

[0261] Input: Weather data, building specification data, cement property data

[0262] Output: Raw data stored in an internal database

[0263] Specific operation: For example, obtain humidity and temperature data using a weather API, collect real-time environmental data from sensors, and store this in a database.

[0264] Step 2: Data Preprocessing

[0265] The server pre-processes the collected data, which includes data normalization, invalid data removal, and feature engineering.

[0266] Input: Raw data stored in an internal database

[0267] Output: Preprocessed data

[0268] Specific operations: Normalize humidity and temperature values, fill in missing values, and generate new features tailored to the project conditions.

[0269] Step 3: Training the quantum computer

[0270] The server uses the pre-processed data to train the quantum computer.

[0271] Input: Preprocessed dataset

[0272] Output: The trained model

[0273] Specific operations: Encode data into qubits, perform gate operations, and build a model to predict the optimal cement product.

[0274] Step 4: Getting User Input

[0275] The user inputs the requirements for the construction project using an interactive interface on the terminal.

[0276] Inputs: Project location, climate conditions, building use, budget, and other details

[0277] Output: User requirement data parsed on the terminal side

[0278] Specific actions: For example, a user enters, "I am building a commercial building. My budget is $500,000, and it is located in a hot and humid area."

[0279] Step 5: Sentiment Analysis

[0280] The terminal uses an emotion engine to analyze the user's emotional state.

[0281] Input: User voice, facial expressions, and text input

[0282] Output: User requirement data with sentiment tags

[0283] Specific behavior: Analyzes voice tone and facial expressions in real time to assess the user's emotional state.

[0284] Step 6: Data Transformation

[0285] The device uses a generative AI model to convert the building project requirements entered by the user into a standard format.

[0286] Input: User requirement data tagged with emotions

[0287] Output: Data converted to a standard format

[0288] Specific operation: For example, convert the expression "hot and humid" into numerical data.

[0289] Step 7: Predictive calculations

[0290] The server receives the data sent from the device and starts calculations on the quantum computer.

[0291] Input: Data converted to a standard format

[0292] Output: Prediction of optimal cement product

[0293] What it does: Uses a trained model to perform predictive calculations and select the cement product that best suits the user's requirements.

[0294] Step 8: Formatting and presenting the results

[0295] The server formats the prediction results, converts them into an easy-to-understand format, and sends them to the device, which then presents them to the user.

[0296] Input: Predicted results of optimal cement product

[0297] Output: Results in the form of a report to present to the user

[0298] Specific behavior: For example, display the following: "XYZ cement is ideal for this project. XYZ cement is highly durable in hot and humid conditions and is cost-effective."

[0299] Step 9: Regulating Emotional Feedback

[0300] The device uses an emotion engine to analyze the user's real-time reactions and provide more detailed technical information or additional recommendations as needed.

[0301] Input: Real-time user responses

[0302] Output: Tailored information

[0303] What it does: If the user is happy, show them detailed technical information; if they are worried, offer them concise, reassuring information.

[0304] (Application example 2)

[0305] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0306] In today's world, data analysis technology is important for improving the efficiency of construction projects and user satisfaction. However, existing technology does not take into account the user's emotional state when making suggestions, which can lead to a decline in the quality of the user experience. Furthermore, technology for displaying appropriate advertisements based on emotions is also underdeveloped. To solve this problem, a system is needed that analyzes the user's emotional state in real time and provides optimal suggestions and advertisements based on that information.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0308] In this invention, the server includes means for collecting data related to the construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for sending the user's input data to the quantum computer to predict the optimal cement product, means for presenting the prediction result to the user, means for analyzing the user's emotional state using an emotion engine, and means for displaying advertisements based on the emotional state using a generative AI model. This enables optimal suggestions based on the user's emotional state, improving the user experience and maximizing the effectiveness of advertisements.

[0309] "Data relating to the construction project" refers to information relating to the various conditions, environmental factors, material properties, etc. required for the implementation of the construction project.

[0310] A "quantum computer" is a next-generation computer that performs calculations using quantum bits, making it possible to analyze large amounts of data and efficiently solve complex optimization problems.

[0311] "Training" refers to the process of training a quantum computer based on collected data to build a model to achieve a specific goal (e.g., predicting the optimal cement product).

[0312] "Interactive interface" refers to an interface function that allows users to input project requirements and conditions and exchange information in a responsive manner with the system.

[0313] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to recognize their emotional state in real time.

[0314] "Generative AI models" refer to artificial intelligence models that convert user-entered information into a standard format, or generate suggestions and advertisements based on emotional states.

[0315] "Means for displaying advertisements" refers to the function for selecting the most appropriate advertisement based on the user's emotional state and displaying it to the user.

[0316] This invention relates to a system that uses a quantum computer, a generative AI model, and an emotion engine to recommend the best cement product for a construction project and display advertisements based on a user's emotional state. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0317] First, the server collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. The collected data is used to train the quantum computer. During this process, the data is preprocessed, specifically, data normalization, invalid data removal, and necessary feature engineering are performed. The server then trains the quantum computer based on the preprocessed data.

[0318] The program implementation uses the following hardware and software:

[0319] Hardware used: smart glasses, camera-equipped devices

[0320] Software used: OpenCV, Keras, emotion engine, generative AI model, quantum computer model

[0321] The device then provides a user interface for users to input their construction project requirements. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. The device also has a built-in emotion engine that recognizes emotions from the user's facial expressions and voice in real time. This emotion data is then analyzed along with the input requirements.

[0322] For example, when a user runs a program using smart glasses, the emotion engine reads the emotion "surprise" from the user's facial expression. At this time, the generative AI model converts the emotion data into a standard format and suggests the most appropriate advertisement. Specifically, if a user inputs, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product," the emotion engine analyzes the user's emotion, and the generative AI model analyzes the input data and converts it into a standard format. This converted data is sent to a quantum computer, which calculates the best cement product. Based on this result, the emotion data is further taken into account and the most appropriate advertisement is also suggested at the same time.

[0323] An example prompt might look like this:

[0324] Using quantum computing and an emotion engine, it will suggest what kind of ads will be most effective based on the user's current emotions. For example, if a user is feeling surprised, it will show them an ad for the latest gadgets.

[0325] This system not only enables users to efficiently select the most suitable cement product without any specialized knowledge, but also displays advertisements based on their emotional state at the optimal time, which is expected to improve the user experience.

[0326] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0327] Step 1:

[0328] The server collects construction project data and cement product characteristic data and stores it in a database. The input is project conditions such as humidity, temperature, durability, and cost, and the output is the data on these conditions stored in the database. Specifically, data is collected from devices such as sensors and transferred to the database via an API.

[0329] Step 2:

[0330] The server preprocesses the collected data. The input is the collected data, and the output is the preprocessed data. Specifically, it normalizes the data, removes invalid data, and performs feature engineering to prepare it for efficient processing by a quantum computer. For example, it performs missing value imputation and data scaling.

[0331] Step 3:

[0332] The server trains the quantum computer based on the preprocessed data. The input is the preprocessed data, and the output is the trained quantum computer model. Specifically, a quantum algorithm is used to train the model to predict the optimal cement product. This is achieved by sending the training data to the quantum computer and applying an iterative algorithm.

[0333] Step 4:

[0334] The terminal provides a user interface that allows users to input building project requirements. The input is the user's building project requirements, and the output is data transmitted through an interactive interface. Specifically, the terminal provides a GUI, allowing users to input information using forms or voice input.

[0335] Step 5:

[0336] The device uses an emotion engine to analyze the user's emotional state. The input is emotional data such as the user's facial expressions and voice, and the output is the analyzed emotional state. Specifically, facial expressions and voice data are collected using a camera and microphone, and the emotion engine analyzes this. For example, this includes processing to detect smiles and recognize the emotion of "joy."

[0337] Step 6:

[0338] The generative AI model converts emotional data into a standard format and sends it to a quantum computer. The input is the emotional data and building project requirements, and the output is the converted data in a standard format. Specifically, it uses natural language processing technology to convert user requirements into numerical data. For example, it converts "hot and humid region" into specific temperature and humidity values.

[0339] Step 7:

[0340] The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The input is data converted into a standard format, and the output is a recommendation for the optimal cement product. Specifically, a quantum algorithm is applied to find the optimal solution and generate the result.

[0341] Step 8:

[0342] The server formats the calculation results and converts them into an easy-to-understand format. The input is the calculation result from the quantum computer, and the output is a formatted recommendation. Specifically, the generative AI model converts the recommendation into an easy-to-understand sentence format. For example, it could express it as "XYZ cement is best for this project."

[0343] Step 9:

[0344] The terminal displays the results to the user. The input is the formatted recommendation, and the output is the information displayed to the user. Specifically, the results are displayed on the screen and visual elements are added to make them easy for the user to understand. For example, this includes displaying graphs of the cement's properties and the reasons for the recommendation.

[0345] Step 10:

[0346] The emotion engine analyzes whether the user feels safe or anxious and provides more detailed or concise information. The input is the user's emotional data, and the output is the detailed or concise information provided. Specifically, if the user feels safe, technical details are displayed, and if the user feels anxious, simple reassuring information is provided.

[0347] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0348] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0349] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0350] [Second embodiment]

[0351] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0352] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0353] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0354] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0355] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0356] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0357] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0358] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0359] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0360] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0361] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0362] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0363] This invention relates to a system that utilizes a quantum computer and a generative AI model to recommend optimal cement products for building projects. The system includes a data collection means, a quantum computer training means, a user interface provision means, a prediction means, and a presentation means.

[0364] The server first collects construction project data and cement product property data and stores them in a database, which is categorized based on project conditions such as humidity, temperature, durability, cost, etc. The collected data is then used to train the quantum computer.

[0365] The server then trains a quantum computer on the collected data. The trained model is used to evaluate cement product performance in the building environment and predict optimal products. To ensure effective training of the quantum computer, the data undergoes pre-processing such as normalization and feature engineering.

[0366] The terminal provides a user interface that allows users to input requirements for a building project. Users can enter detailed information into the interface, such as the project's location, climate conditions, building use, budget, etc. The generative AI model converts these input data into a standard format.

[0367] For example, if a user inputs, "I am planning to build a commercial building in a hot and humid region. I have a budget of approximately 50 million yen and am looking for a durable, cost-effective cement," this information is appropriately converted by the generative AI model and sent to the server.

[0368] The server sends the user's input data to a quantum computer, which then uses the trained model to calculate the best cement product for the given conditions, comparing the characteristics of different cement products to select the one that best meets the conditions.

[0369] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0370] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of quantum computers, it is possible to quickly and accurately recommend the optimal product even under complex conditions.

[0371] The processing flow will be explained below.

[0372] Step 1:

[0373] The server collects construction project data and cement product property data, such as humidity, temperature, durability, and cost, and stores them in a database.

[0374] Step 2:

[0375] The server preprocesses the collected data by normalizing it, removing invalid data, and performing any necessary feature engineering so that the data can be efficiently processed by the quantum computer.

[0376] Step 3:

[0377] The server uses the pre-processed data to train a quantum computer, which then learns from the vast amount of data and builds a model to predict the performance of cement products.

[0378] Step 4:

[0379] The terminal provides users with an interactive interface through which they can input details about their construction project, such as the project location, climate conditions, building use, and budget.

[0380] Step 5:

[0381] Users use a conversational interface to input project requirements, such as, "I'm planning to build a commercial building in a hot and humid climate. I have a budget of approximately $500,000 and I'm looking for a durable, cost-effective cement."

[0382] Step 6:

[0383] The device uses generative AI models to convert user-entered information into a standard format, for example, converting the natural language input "hot and humid region" into concrete numerical data that a quantum computer can easily understand.

[0384] Step 7:

[0385] The device then sends the converted data to the server, which receives it and starts the quantum computer calculation.

[0386] Step 8:

[0387] The server inputs data in a standard format into a quantum computer model and runs a simulation, which predicts and identifies candidates for the optimal cement product.

[0388] Step 9:

[0389] The server formats the simulation results and converts them into an easy-to-understand format, including, for example, the name and characteristics of the optimal cement product and the reasons for the recommendation.

[0390] Step 10:

[0391] The server sends the formatted results to the terminal.

[0392] Step 11:

[0393] The device then displays the results to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0394] Step 12:

[0395] Users can review the cement product information presented and, if necessary, ask additional questions or request recalculations under different conditions.

[0396] Example 1

[0397] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0398] Selecting the optimal cement product for a construction project requires considering many variables, but the process requires specialized knowledge, is time-consuming, and costly. Furthermore, conventional systems lack the computing power to simultaneously consider complex conditions, making it difficult to select the right product quickly and accurately. This makes it difficult to find the optimal cement product.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0400] In this invention, the server includes means for collecting information about building projects, means for training a quantum computer based on the collected data, means for providing an interactive interface for users to input building project requirements, means for converting the user-input building project requirements into a standard format using a generative AI model, means for sending the user-input data to the quantum computer and predicting the optimal building material product, and means for presenting the prediction result to the user, thereby enabling a user to quickly and accurately select the optimal cement product even without specialized knowledge.

[0401] A "building project" refers to a series of tasks related to the design, construction, and maintenance of a building.

[0402] "Information" refers to all data related to a building project, such as the project location, climatic conditions, materials used, budget, etc.

[0403] A "quantum computer" is a computer that performs calculations using quantum bits, and refers to a device that can quickly perform calculations that are difficult for conventional computers to perform.

[0404] "Training" refers to the process of learning to improve the performance of a computational model using a given data set.

[0405] An "interactive interface" refers to an interactive user interface in which a user provides input to a system and the system operates based on that input.

[0406] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is designed to perform specific tasks.

[0407] A "standard format" refers to the representation of data in a unified format to ensure consistency and compatibility.

[0408] "Building products" refers to various materials and products used in the construction of buildings (e.g., cement, bricks, rebar, etc.).

[0409] "Predicting" refers to estimating future outcomes or trends based on given data.

[0410] "Present" refers to the system showing the results of its calculations or processing to the user visually or in some other way.

[0411] The present invention relates to a system that uses a quantum computer and a generative AI model to propose optimal building material products for a building project. An embodiment of the system will be described below.

[0412] The server first collects and stores information related to the building project in a database, including data on project conditions such as humidity, temperature, durability, cost, etc. The data collected by the server is stored in the database for further processing.

[0413] The server then performs preprocessing on the collected data, including normalization and feature engineering. This enables effective training on a quantum computer. Examples of hardware used include the IBM Q Experience and the D-Wave Quantum Computer. The software used is Qiskit, a quantum programming framework.

[0414] The server then uses a quantum computer to perform training, and the trained model is used to evaluate the performance of building materials in a building environment and predict optimal products.

[0415] An interactive interface is provided on the terminal for users to input building project requirements, and users can enter detailed information such as project location, climatic conditions, building use, budget, etc. into the interface.

[0416] The generative AI model is responsible for converting user input data into a standard format. For example, if a user inputs, "We are planning to build a commercial building in a hot and humid region with a budget of 50 million yen," this information is converted appropriately by the generative AI model and sent to the server.

[0417] The server then sends the user's input data to a quantum computer, which predicts the optimal building material product. The quantum computer uses the trained model to calculate the building material product that best suits the conditions. At this time, it compares the characteristics of different building material products and selects the product that best meets the conditions.

[0418] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0419] This system allows users to efficiently select the optimal building material products, even without specialized knowledge. By utilizing the computational power of quantum computers, it is possible to quickly and accurately suggest optimal products even under complex conditions.

[0420] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0421] Step 1:

[0422] The server collects information about the building project, including project conditions such as humidity, temperature, durability, cost, etc. The server stores this data in a database.

[0423] Input: Project conditions (humidity, temperature, durability, cost, etc.)

[0424] Output: Project condition data neatly stored in a database

[0425] Step 2:

[0426] The server performs preprocessing on the collected data, such as normalization and feature engineering, to make it more efficient for training on a quantum computer, for example, scaling humidity data to a range of 0 to 1.

[0427] Input: Project criteria data stored in the database

[0428] Output: Preprocessed project condition data

[0429] Specific behavior: "Humidity data [45, 55, 60] → Normalized humidity data [0.45, 0.55, 0.60]"

[0430] Step 3:

[0431] The server uses a quantum computer to train the model based on the pre-processed data. The trained model is used to evaluate the performance of building materials in the building environment and predict the optimal product.

[0432] Input: Preprocessed project criteria data

[0433] Output: A trained quantum computer model

[0434] Specific operation: Training is performed using the Qiskit framework using the IBM Q Experience and D-Wave Quantum Computer.

[0435] Step 4:

[0436] The terminal provides a user interface that allows users to input building project requirements, including details such as the project location, climate conditions, building use, and budget.

[0437] Input: User's project conditions (location, weather conditions, purpose, budget, etc.)

[0438] Output: User input data

[0439] Specific operation: The user types into the terminal, "We are planning to build a commercial building in a hot and humid region. The budget is 50 million yen."

[0440] Step 5:

[0441] The generative AI model converts user-entered data into a standard format that is easy for a quantum computer to understand.

[0442] Input: User-entered data

[0443] Output: Data converted to a standard format

[0444] Specific behavior: User input: "Hot and humid", "Commercial building", "50 million yen"

[0445] Converted data: {Area: "Hot and Humid", Type: "Commercial Building", Budget: 50000000}

[0446] Step 6:

[0447] The server sends user input data transformed by the generative AI model to a quantum computer, which then uses the trained model to calculate the optimal building material product for the conditions.

[0448] Input: Data converted to a standard format

[0449] Output: Prediction results of optimal building material products

[0450] How it works: A quantum computer evaluates different building materials and calculates the optimal product based on durability and cost performance.

[0451] Step 7:

[0452] The prediction results are sent to the device and presented to the user, who then displays specific suggestions to the user.

[0453] Input: Prediction results for optimal building material products

[0454] Output: Prediction results presented to the user

[0455] What it does: The user is told, "ABC Cement is ideal for this project. It is durable in hot and humid conditions and is cost-effective."

[0456] Through the above processing steps, users can quickly and accurately select the optimal building material products under complex conditions, even without specialized knowledge.

[0457] (Application example 1)

[0458] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0459] In recent years, there has been a demand for optimizing appropriate material selection and inventory management strategies in construction projects and logistics center operations. However, these optimizations are extremely complex and require consideration of numerous conditions and variables, requiring advanced knowledge and skills. In particular, it is difficult to make quick and accurate decisions using conventional methods, making efficient operation difficult.

[0460] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0461] In this invention, the server includes means for collecting data related to a construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for collecting data related to inventory management at a logistics center, means for converting the collected inventory data into a standard format using a generative AI model, means for calculating an optimal inventory management strategy using the quantum computer, and means for presenting the optimal inventory management strategy to a user, thereby enabling the selection of optimal cement products for the construction project and the implementation of an efficient inventory management strategy at the logistics center.

[0462] "Building project data" means information related to the design, construction, and operation of a building, including environmental conditions, budget, materials used, and overall project requirements.

[0463] A "quantum computer" is a computing device that, unlike conventional computers, operates based on the principles of quantum mechanics and can efficiently solve certain computational problems.

[0464] "Collection means" refers to the method or device for collecting, storing, and optionally processing data.

[0465] "Training" refers to the process by which an algorithm or model learns from provided data and improves its accuracy in prediction or identification.

[0466] A "means for providing an interactive interface" is a combination of software and hardware that allows a user to interact directly with a system.

[0467] "User Input Data" means information provided by a user to the system, including project requirements and conditions.

[0468] "Data related to inventory management at logistics centers" refers to information related to inventory status, replenishment schedules, sales forecasts, storage capacity, and the like at logistics centers.

[0469] A "generative AI model" is a pre-trained artificial intelligence model capable of natural language processing and data analysis.

[0470] A "means for converting into a standard format" is a method or device for converting input data of various formats into a unified structure or format.

[0471] A "calculating means" is a method or device for deriving a specific result or optimal solution based on given data or conditions.

[0472] A "presentation means" is a method or device for visually or audibly displaying the results of a calculation or prediction to a user.

[0473] The "optimum cement product" is the cement product that best meets and performs best for the conditions and requirements of a particular building project.

[0474] An "optimal inventory management strategy" is the most effective way to efficiently manage the storage, replenishment, and sales of inventory in a distribution center.

[0475] The present invention provides a system for proposing optimal cement products and inventory management strategies for construction projects and logistics center operations. Specific embodiments for carrying out the present invention are described below.

[0476] The system includes the following hardware and software:

[0477] Server: Performs data collection, data processing, model training, and prediction calculations, specifically using quantum computers and generative AI models (e.g., OpenAI APIs).

[0478] Device: The device (e.g., smartphone, tablet) through which a user provides input and receives results.

[0479] Interactive interface: The interface through which a user provides data to a system (e.g., a web application).

[0480] The operation of the system is described below.

[0481] Data collection

[0482] The server collects data about construction projects and logistics center operations. For construction projects, information about the project location, weather conditions, building use, budget, etc. For logistics centers, information about incoming and outgoing shipments, inventory levels, sales forecasts, warehouse status, etc.

[0483] Data Transformation and Prediction

[0484] The server uses a generative AI model to convert the collected data into a standard format for training on a quantum computer. Specifically, the server sends the following prompt to the generative AI model to perform the appropriate format conversion:

[0485] Example prompt sentence:

[0486] Predict the optimal stock management for the following data: {'temperature': 22, 'humidity': 55, 'stock_levels': {'product_A': 150, 'product_B': 250}, 'sales_forecast': {'product_A': 130, 'product_B': 200}, 'warehouse_capacity': 600}

[0487] The generative AI model takes the prompt text, converts it into a standard format, and sends it to a quantum computer to predict the most suitable cement product and inventory management strategy for the specific conditions.

[0488] Results presentation

[0489] The server sends the prediction results to the terminal and displays them to the user, who receives recommendations for optimal cement products and inventory management strategies through the terminal's interactive interface, enabling efficient decision-making.

[0490] For example, for a building project:

[0491] If a user inputs, "We are planning to build a commercial building in a hot and humid region. We have a budget of approximately 50 million yen and are looking for a durable, cost-effective cement," the server will convert this information appropriately using a generative AI model and predict the optimal cement product. The predicted result will be presented to the user in the form, "ABC Cement is ideal for this project. ABC Cement is highly durable under hot and humid conditions and also offers excellent cost performance."

[0492] For distribution centers:

[0493] If a user types, "Please suggest the optimal inventory management strategy based on current inventory, sales forecast, and warehouse capacity," the server will convert the collected data using a generative AI model and calculate the optimal management strategy using a quantum computer. The result will be presented as, "Product A needs replenishment in the next two weeks. Product B's current inventory level is appropriate to meet demand."

[0494] In this way, this invention utilizes quantum computers and generative AI models to quickly and accurately provide optimal product selection and management strategies even under complex conditions.

[0495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0496] Step 1:

[0497] The server collects data about the construction project and logistics center operations from users and sensors, including project location, weather conditions, building use, budget, incoming and outgoing shipments, inventory levels, sales forecasts, and warehouse conditions, derived through signal or communication analysis.

[0498] Input: Building project and logistics center operational data provided by users and sensors.

[0499] Output: The collected dataset.

[0500] Step 2:

[0501] The server normalizes the collected data and performs feature engineering as needed, including imputing missing values, converting data types, and generating new features.

[0502] Input: The collected dataset.

[0503] Output: The preprocessed dataset.

[0504] Step 3:

[0505] The server inputs the preprocessed data into the generative AI model and converts it into a standard format. Specifically, it uses the API of OpenAI, the generative AI model, to send data through prompts and receive responses.

[0506] Input: A preprocessed dataset and a prompt statement.

[0507] Output: Data converted into a standard format.

[0508] Step 4:

[0509] The server then converts the data into a standard format and sends it to a quantum computer, which then uses the trained model to calculate the best solution for the specific conditions.

[0510] Input: Data converted to a standard format.

[0511] Output: Predicted results of optimal cement product or inventory management strategy.

[0512] Step 5:

[0513] The server receives the prediction results from the quantum computer and sends them to the device, converting the data into a user-friendly format and displaying it visually for easy understanding.

[0514] Input: Prediction results from a quantum computer.

[0515] Output: The results in the form of reports and graphs that are presented to the user.

[0516] Step 6:

[0517] The terminal then presents the received forecast results to the user, who can then review the results through an interactive interface to select the optimal cement product and implement an inventory management strategy.

[0518] Input: Results presented by the server.

[0519] Output: The result that the user sees on the display screen.

[0520] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0521] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0522] A specific embodiment of the system will be described below.

[0523] The server first collects construction project data and cement product property data and stores them in a database, including project conditions such as humidity, temperature, durability, and cost. The collected data is then used to train the quantum computer.

[0524] The server then preprocesses the collected data by normalizing it, removing invalid data, and performing necessary feature engineering to enable efficient processing by the quantum computer. The server then trains the quantum computer using the preprocessed data. The trained model is used to evaluate the performance of cement products in the building environment and predict optimal products.

[0525] The terminal provides a user interface that allows users to input requirements for a construction project. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. In addition, the terminal is equipped with an emotion engine that recognizes the user's emotions in real time. This emotion data is then analyzed along with the input requirements.

[0526] For example, if a user uses a conversational interface to input, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product.", the emotion engine analyzes emotions from the user's voice and text input. The generative AI model converts these input data into a standard format. For example, it converts the natural language input "hot and humid region" into numerical data.

[0527] The device then sends the converted data to the server, which receives it and initiates calculations using a quantum computer. The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The computer also takes into account the emotional data collected by the emotion engine, fine-tuning the recommendations based on the user's emotional state.

[0528] The server formats the calculation results and converts them into an easy-to-understand format. For example, it includes the name and characteristics of the optimal cement product, as well as the reason for the recommendation. The server then sends the formatted results to the device. The device then displays the received results to the user. For example, it may suggest, "XYZ cement is optimal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0529] Additionally, if the emotion engine confirms that the user feels safe, more detailed technical information or additional recommendations may be displayed, while if the user is anxious or skeptical, more concise and reassuring information is provided.

[0530] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of a quantum computer and the emotion recognition function of an emotion engine, it is possible to provide optimal and reassuring recommendations to users.

[0531] The processing flow will be explained below.

[0532] Step 1:

[0533] The server collects construction project data and cement product property data from various data sources, including data on weather conditions, durability test results, costs, etc. The collected data is stored in a database.

[0534] Step 2:

[0535] The server preprocesses the collected data by removing invalid data, normalizing the data, and performing feature engineering, so that the data is in a format that can be efficiently processed by a quantum computer.

[0536] Step 3:

[0537] The server uses the pre-processed data to train a quantum computer, which then builds a model to predict cement product performance in the building environment. The model is designed to learn from large amounts of data and accurately predict the properties of cement products.

[0538] Step 4:

[0539] The terminal displays an interactive interface for users to input information about their construction projects. The interface is designed to be easy to understand, allowing users to easily input project requirements.

[0540] Step 5:

[0541] Using an interactive interface, users input details about the construction project, such as the project's location, climate conditions, intended use, budget, etc. This information is then sent to the system.

[0542] Step 6:

[0543] The device converts the information entered by the user into a standard format using a generative AI model, which converts natural language input into numerical data. For example, "hot and humid region" is converted into concrete numerical data.

[0544] Step 7:

[0545] The device transmits the converted data to the emotion engine, which recognizes the user's emotions in real time and evaluates their emotional state. For example, the emotion engine can determine the user's stress level from their tone of voice and facial expression.

[0546] Step 8:

[0547] The device sends the emotional data obtained by the emotion engine to the server, which receives it and provides it to the quantum computer along with the user's input data.

[0548] Step 9:

[0549] The server inputs standard format data and emotional data into the quantum computer model and begins calculations, which then predicts and identifies candidates for the optimal cement product.

[0550] Step 10:

[0551] The server formats the results and converts them into a user-friendly format, including, for example, the name of the specific cement product, its properties, and the reasons for the recommendation.

[0552] Step 11:

[0553] The server sends the formatted results to the terminal.

[0554] Step 12:

[0555] The device then sends the results back to the emotion engine, which then displays the results in a way that adapts to the user's emotional state. For example, if the device determines that the user is feeling anxious, it will display more detailed information or a support message.

[0556] Step 13:

[0557] The user reviews the presented cement product information and can request additional questions or changes using the interface again.

[0558] This process allows users to efficiently select the most suitable cement product, and by using an emotion engine, it provides optimal suggestions based on the user's emotional state.

[0559] Example 2

[0560] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0561] Existing cement product selection methods for construction projects do not adequately consider the characteristics of the project, making it difficult to select the optimal cement product. Furthermore, users may feel uneasy because recommendations do not take into account their technical knowledge or emotional state. Furthermore, the technology required to efficiently process large amounts of data and make accurate predictions is still immature.

[0562] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0563] In this invention, the server includes means for collecting data on construction projects, means for preprocessing the collected data, means for training a quantum computer based on the preprocessed data, means for predicting the cement product best suited to a user's requirements using the trained quantum computer, means for providing an interactive interface for the user to input the construction project requirements, means for analyzing the user's emotional state using an emotion engine and fine-tuning the proposal content, means for converting the construction project requirements input by the user into a standard format using a generative AI model, and means for presenting the prediction results to the user. This enables highly accurate predictions that take into account project characteristics and makes optimal proposals according to the user's emotional state.

[0564] "Data relating to building projects" refers to various information related to the design, construction and management of buildings, including, in particular, project conditions such as humidity, temperature, durability and cost.

[0565] "Means of collection" refers to the methods and devices that collect the necessary data using sensors, APIs, etc. and store it in a database.

[0566] The "preprocessing means" refers to a method or device that converts collected data into a format that is easy to process through a series of operations such as normalization, deletion of invalid data, and feature engineering.

[0567] "Training means" refers to a method or apparatus that optimizes a quantum computer based on preprocessed data to build and tune a target predictive model.

[0568] "Conversational interface" refers to the interactive input screens and software that allow users to input requirements for a building project.

[0569] An "emotion engine" refers to technology or a device that analyzes a user's facial expressions, voice, text input, etc. to evaluate and recognize their emotional state in real time, and provides appropriate feedback based on that.

[0570] A "generative AI model" is a machine learning model used to convert input data into a specified format, serving to standardize diverse input formats.

[0571] "Means for converting into a standard format" refers to the technology or device that analyzes the input construction project requirements and converts them into a specified unified format.

[0572] "Means for presenting predicted results" refers to a method or device for displaying the calculated optimal cement product characteristics and the reasons for recommendation in a manner that is easy for the user to understand.

[0573] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a data preprocessing means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0574] The server first collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. This data is collected using sensors and APIs. For example, weather data is obtained from a weather API, and the database is updated regularly.

[0575] The server then preprocesses the collected data, including normalizing the data, removing invalid data, and performing feature engineering. Specifically, it scales the temperature and humidity values ​​and imputes missing values. This preprocessing allows for efficient processing on a quantum computer.

[0576] Based on the pre-processed data, the server trains the quantum computer, which includes generating a training dataset, encoding the data into qubits, gate operations, and measurement operations, allowing the quantum computer to build an optimized model that can be used to make future predictions.

[0577] The user inputs the requirements for a construction project using a conversational interface on the device. For example, the user might input, "I'm building a commercial building with a budget of 50 million yen, located in a hot and humid region. Please suggest the best cement product." The device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotional state in real time. This emotion data is analyzed along with the user's input data and an emotion tag is attached.

[0578] The generative AI model converts the building project requirements entered by the user into a standard format. For example, the natural language input "hot and humid region" is converted into concrete numerical data. The converted data is then sent from the device to the server.

[0579] The server receives the data and initiates calculations using a quantum computer. The quantum computer uses the trained model to predict the cement product that best suits the user's requirements. This process also takes into account emotional data collected by the emotion engine, fine-tuning the suggestions based on the user's emotional state.

[0580] The calculation results are formatted by the server and converted into an easy-to-understand format. For example, the format is a report that includes the name of the optimal cement product, its characteristics, and the reason for the recommendation. The formatted results are sent to the terminal, which then displays them to the user. An example of a presentation might be, "XYZ cement is ideal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0581] The device also uses an emotion engine to analyze the user's real-time reactions. If the user feels reassured, it displays more detailed technical information and additional recommendations. Conversely, if the user feels anxious or suspicious, it provides more concise and reassuring information. This system allows users to efficiently select the optimal cement product even without specialized knowledge.

[0582] Example of a text prompt

[0583] "If the construction conditions for a commercial building are hot and humid and the budget is 50 million yen, which cement product would be best?"

[0584] "A user is building a commercial building in a hot and humid region with a budget of ¥50 million. Please suggest the best cement product for these conditions."

[0585] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0586] Processing flow

[0587] Step 1: Data collection

[0588] The server collects construction project data and cement product characteristic data through sensors and APIs.

[0589] Input: Weather data, building specification data, cement property data

[0590] Output: Raw data stored in an internal database

[0591] Specific operation: For example, obtain humidity and temperature data using a weather API, collect real-time environmental data from sensors, and store this in a database.

[0592] Step 2: Data Preprocessing

[0593] The server pre-processes the collected data, which includes data normalization, invalid data removal, and feature engineering.

[0594] Input: Raw data stored in an internal database

[0595] Output: Preprocessed data

[0596] Specific operations: Normalize humidity and temperature values, fill in missing values, and generate new features tailored to the project conditions.

[0597] Step 3: Training the quantum computer

[0598] The server uses the pre-processed data to train the quantum computer.

[0599] Input: Preprocessed dataset

[0600] Output: The trained model

[0601] Specific operations: Encode data into qubits, perform gate operations, and build a model to predict the optimal cement product.

[0602] Step 4: Getting User Input

[0603] The user inputs the requirements for the construction project using an interactive interface on the terminal.

[0604] Inputs: Project location, climate conditions, building use, budget, and other details

[0605] Output: User requirement data parsed on the terminal side

[0606] Specific actions: For example, a user enters, "I am building a commercial building. My budget is $500,000, and it is located in a hot and humid area."

[0607] Step 5: Sentiment Analysis

[0608] The terminal uses an emotion engine to analyze the user's emotional state.

[0609] Input: User voice, facial expressions, and text input

[0610] Output: User requirement data with sentiment tags

[0611] Specific behavior: Analyzes voice tone and facial expressions in real time to assess the user's emotional state.

[0612] Step 6: Data Transformation

[0613] The device uses a generative AI model to convert the building project requirements entered by the user into a standard format.

[0614] Input: User requirement data tagged with emotions

[0615] Output: Data converted to a standard format

[0616] Specific operation: For example, convert the expression "hot and humid" into numerical data.

[0617] Step 7: Predictive calculations

[0618] The server receives the data sent from the device and starts calculations on the quantum computer.

[0619] Input: Data converted to a standard format

[0620] Output: Prediction of optimal cement product

[0621] What it does: Uses a trained model to perform predictive calculations and select the cement product that best suits the user's requirements.

[0622] Step 8: Formatting and presenting the results

[0623] The server formats the prediction results, converts them into an easy-to-understand format, and sends them to the device, which then presents them to the user.

[0624] Input: Predicted results of optimal cement product

[0625] Output: Results in the form of a report to present to the user

[0626] Specific behavior: For example, display the following: "XYZ cement is ideal for this project. XYZ cement is highly durable in hot and humid conditions and is cost-effective."

[0627] Step 9: Regulating Emotional Feedback

[0628] The device uses an emotion engine to analyze the user's real-time reactions and provide more detailed technical information or additional recommendations as needed.

[0629] Input: Real-time user responses

[0630] Output: Tailored information

[0631] What it does: If the user is happy, show them detailed technical information; if they are worried, offer them concise, reassuring information.

[0632] (Application example 2)

[0633] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0634] In today's world, data analysis technology is important for improving the efficiency of construction projects and user satisfaction. However, existing technology does not take into account the user's emotional state when making suggestions, which can lead to a decline in the quality of the user experience. Furthermore, technology for displaying appropriate advertisements based on emotions is also underdeveloped. To solve this problem, a system is needed that analyzes the user's emotional state in real time and provides optimal suggestions and advertisements based on that information.

[0635] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0636] In this invention, the server includes means for collecting data related to the construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for sending the user's input data to the quantum computer to predict the optimal cement product, means for presenting the prediction result to the user, means for analyzing the user's emotional state using an emotion engine, and means for displaying advertisements based on the emotional state using a generative AI model. This enables optimal suggestions based on the user's emotional state, improving the user experience and maximizing the effectiveness of advertisements.

[0637] "Data relating to the construction project" refers to information relating to the various conditions, environmental factors, material properties, etc. required for the implementation of the construction project.

[0638] A "quantum computer" is a next-generation computer that performs calculations using quantum bits, making it possible to analyze large amounts of data and efficiently solve complex optimization problems.

[0639] "Training" refers to the process of training a quantum computer based on collected data to build a model to achieve a specific goal (e.g., predicting the optimal cement product).

[0640] "Interactive interface" refers to an interface function that allows users to input project requirements and conditions and exchange information in a responsive manner with the system.

[0641] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to recognize their emotional state in real time.

[0642] "Generative AI models" refer to artificial intelligence models that convert user-entered information into a standard format, or generate suggestions and advertisements based on emotional states.

[0643] "Means for displaying advertisements" refers to the function for selecting the most appropriate advertisement based on the user's emotional state and displaying it to the user.

[0644] This invention relates to a system that uses a quantum computer, a generative AI model, and an emotion engine to recommend the best cement product for a construction project and display advertisements based on a user's emotional state. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0645] First, the server collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. The collected data is used to train the quantum computer. During this process, the data is preprocessed, specifically, data normalization, invalid data removal, and necessary feature engineering are performed. The server then trains the quantum computer based on the preprocessed data.

[0646] The program implementation uses the following hardware and software:

[0647] Hardware used: smart glasses, camera-equipped devices

[0648] Software used: OpenCV, Keras, emotion engine, generative AI model, quantum computer model

[0649] The device then provides a user interface for users to input their construction project requirements. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. The device also has a built-in emotion engine that recognizes emotions from the user's facial expressions and voice in real time. This emotion data is then analyzed along with the input requirements.

[0650] For example, when a user runs a program using smart glasses, the emotion engine reads the emotion "surprise" from the user's facial expression. At this time, the generative AI model converts the emotion data into a standard format and suggests the most appropriate advertisement. Specifically, if a user inputs, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product," the emotion engine analyzes the user's emotion, and the generative AI model analyzes the input data and converts it into a standard format. This converted data is sent to a quantum computer, which calculates the best cement product. Based on this result, the emotion data is further taken into account and the most appropriate advertisement is also suggested at the same time.

[0651] An example prompt might look like this:

[0652] Using quantum computing and an emotion engine, it will suggest what kind of ads will be most effective based on the user's current emotions. For example, if a user is feeling surprised, it will show them an ad for the latest gadgets.

[0653] This system not only enables users to efficiently select the most suitable cement product without any specialized knowledge, but also displays advertisements based on their emotional state at the optimal time, which is expected to improve the user experience.

[0654] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0655] Step 1:

[0656] The server collects construction project data and cement product characteristic data and stores it in a database. The input is project conditions such as humidity, temperature, durability, and cost, and the output is the data on these conditions stored in the database. Specifically, data is collected from devices such as sensors and transferred to the database via an API.

[0657] Step 2:

[0658] The server preprocesses the collected data. The input is the collected data, and the output is the preprocessed data. Specifically, it normalizes the data, removes invalid data, and performs feature engineering to prepare it for efficient processing by a quantum computer. For example, it performs missing value imputation and data scaling.

[0659] Step 3:

[0660] The server trains the quantum computer based on the preprocessed data. The input is the preprocessed data, and the output is the trained quantum computer model. Specifically, a quantum algorithm is used to train the model to predict the optimal cement product. This is achieved by sending the training data to the quantum computer and applying an iterative algorithm.

[0661] Step 4:

[0662] The terminal provides a user interface that allows users to input building project requirements. The input is the user's building project requirements, and the output is data transmitted through an interactive interface. Specifically, the terminal provides a GUI, allowing users to input information using forms or voice input.

[0663] Step 5:

[0664] The device uses an emotion engine to analyze the user's emotional state. The input is emotional data such as the user's facial expressions and voice, and the output is the analyzed emotional state. Specifically, facial expressions and voice data are collected using a camera and microphone, and the emotion engine analyzes this. For example, this includes processing to detect smiles and recognize the emotion of "joy."

[0665] Step 6:

[0666] The generative AI model converts emotional data into a standard format and sends it to a quantum computer. The input is the emotional data and building project requirements, and the output is the converted data in a standard format. Specifically, it uses natural language processing technology to convert user requirements into numerical data. For example, it converts "hot and humid region" into specific temperature and humidity values.

[0667] Step 7:

[0668] The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The input is data converted into a standard format, and the output is a recommendation for the optimal cement product. Specifically, a quantum algorithm is applied to find the optimal solution and generate the result.

[0669] Step 8:

[0670] The server formats the calculation results and converts them into an easy-to-understand format. The input is the calculation result from the quantum computer, and the output is a formatted recommendation. Specifically, the generative AI model converts the recommendation into an easy-to-understand sentence format. For example, it could express it as "XYZ cement is best for this project."

[0671] Step 9:

[0672] The terminal displays the results to the user. The input is the formatted recommendation, and the output is the information displayed to the user. Specifically, the results are displayed on the screen and visual elements are added to make them easy for the user to understand. For example, this includes displaying graphs of the cement's properties and the reasons for the recommendation.

[0673] Step 10:

[0674] The emotion engine analyzes whether the user feels safe or anxious and provides more detailed or concise information. The input is the user's emotional data, and the output is the detailed or concise information provided. Specifically, if the user feels safe, technical details are displayed, and if the user feels anxious, simple reassuring information is provided.

[0675] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0676] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0677] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0678] [Third embodiment]

[0679] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0680] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0681] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0682] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0683] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0684] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0685] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0686] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0687] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0688] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0689] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0690] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0691] This invention relates to a system that utilizes a quantum computer and a generative AI model to recommend optimal cement products for building projects. The system includes a data collection means, a quantum computer training means, a user interface provision means, a prediction means, and a presentation means.

[0692] The server first collects construction project data and cement product property data and stores them in a database, which is categorized based on project conditions such as humidity, temperature, durability, cost, etc. The collected data is then used to train the quantum computer.

[0693] The server then trains a quantum computer on the collected data. The trained model is used to evaluate cement product performance in the building environment and predict optimal products. To ensure effective training of the quantum computer, the data undergoes pre-processing such as normalization and feature engineering.

[0694] The terminal provides a user interface that allows users to input requirements for a building project. Users can enter detailed information into the interface, such as the project's location, climate conditions, building use, budget, etc. The generative AI model converts these input data into a standard format.

[0695] For example, if a user inputs, "I am planning to build a commercial building in a hot and humid region. I have a budget of approximately 50 million yen and am looking for a durable, cost-effective cement," this information is appropriately converted by the generative AI model and sent to the server.

[0696] The server sends the user's input data to a quantum computer, which then uses the trained model to calculate the best cement product for the given conditions, comparing the characteristics of different cement products to select the one that best meets the conditions.

[0697] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0698] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of quantum computers, it is possible to quickly and accurately recommend the optimal product even under complex conditions.

[0699] The processing flow will be explained below.

[0700] Step 1:

[0701] The server collects construction project data and cement product property data, such as humidity, temperature, durability, and cost, and stores them in a database.

[0702] Step 2:

[0703] The server preprocesses the collected data by normalizing it, removing invalid data, and performing any necessary feature engineering so that the data can be efficiently processed by the quantum computer.

[0704] Step 3:

[0705] The server uses the pre-processed data to train a quantum computer, which then learns from the vast amount of data and builds a model to predict the performance of cement products.

[0706] Step 4:

[0707] The terminal provides users with an interactive interface through which they can input details about their construction project, such as the project location, climate conditions, building use, and budget.

[0708] Step 5:

[0709] Users use a conversational interface to input project requirements, such as, "I'm planning to build a commercial building in a hot and humid climate. I have a budget of approximately $500,000 and I'm looking for a durable, cost-effective cement."

[0710] Step 6:

[0711] The device uses generative AI models to convert user-entered information into a standard format, for example, converting the natural language input "hot and humid region" into concrete numerical data that a quantum computer can easily understand.

[0712] Step 7:

[0713] The device then sends the converted data to the server, which receives it and starts the quantum computer calculation.

[0714] Step 8:

[0715] The server inputs data in a standard format into a quantum computer model and runs a simulation, which predicts and identifies candidates for the optimal cement product.

[0716] Step 9:

[0717] The server formats the simulation results and converts them into an easy-to-understand format, including, for example, the name and characteristics of the optimal cement product and the reasons for the recommendation.

[0718] Step 10:

[0719] The server sends the formatted results to the terminal.

[0720] Step 11:

[0721] The device then displays the results to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0722] Step 12:

[0723] Users can review the cement product information presented and, if necessary, ask additional questions or request recalculations under different conditions.

[0724] Example 1

[0725] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0726] Selecting the optimal cement product for a construction project requires considering many variables, but the process requires specialized knowledge, is time-consuming, and costly. Furthermore, conventional systems lack the computing power to simultaneously consider complex conditions, making it difficult to select the right product quickly and accurately. This makes it difficult to find the optimal cement product.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0728] In this invention, the server includes means for collecting information about building projects, means for training a quantum computer based on the collected data, means for providing an interactive interface for users to input building project requirements, means for converting the user-input building project requirements into a standard format using a generative AI model, means for sending the user-input data to the quantum computer and predicting the optimal building material product, and means for presenting the prediction result to the user, thereby enabling a user to quickly and accurately select the optimal cement product even without specialized knowledge.

[0729] A "building project" refers to a series of tasks related to the design, construction, and maintenance of a building.

[0730] "Information" refers to all data related to a building project, such as the project location, climatic conditions, materials used, budget, etc.

[0731] A "quantum computer" is a computer that performs calculations using quantum bits, and refers to a device that can quickly perform calculations that are difficult for conventional computers to perform.

[0732] "Training" refers to the process of learning to improve the performance of a computational model using a given data set.

[0733] An "interactive interface" refers to an interactive user interface in which a user provides input to a system and the system operates based on that input.

[0734] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is designed to perform specific tasks.

[0735] A "standard format" refers to the representation of data in a unified format to ensure consistency and compatibility.

[0736] "Building products" refers to various materials and products used in the construction of buildings (e.g., cement, bricks, rebar, etc.).

[0737] "Predicting" refers to estimating future outcomes or trends based on given data.

[0738] "Present" refers to the system showing the results of its calculations or processing to the user visually or in some other way.

[0739] The present invention relates to a system that uses a quantum computer and a generative AI model to propose optimal building material products for a building project. An embodiment of the system will be described below.

[0740] The server first collects and stores information related to the building project in a database, including data on project conditions such as humidity, temperature, durability, cost, etc. The data collected by the server is stored in the database for further processing.

[0741] The server then performs preprocessing on the collected data, including normalization and feature engineering. This enables effective training on a quantum computer. Examples of hardware used include the IBM Q Experience and the D-Wave Quantum Computer. The software used is Qiskit, a quantum programming framework.

[0742] The server then uses a quantum computer to perform training, and the trained model is used to evaluate the performance of building materials in a building environment and predict optimal products.

[0743] An interactive interface is provided on the terminal for users to input building project requirements, and users can enter detailed information such as project location, climatic conditions, building use, budget, etc. into the interface.

[0744] The generative AI model is responsible for converting user input data into a standard format. For example, if a user inputs, "We are planning to build a commercial building in a hot and humid region with a budget of 50 million yen," this information is converted appropriately by the generative AI model and sent to the server.

[0745] The server then sends the user's input data to a quantum computer, which predicts the optimal building material product. The quantum computer uses the trained model to calculate the building material product that best suits the conditions. At this time, it compares the characteristics of different building material products and selects the product that best meets the conditions.

[0746] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[0747] This system allows users to efficiently select the optimal building material products, even without specialized knowledge. By utilizing the computational power of quantum computers, it is possible to quickly and accurately suggest optimal products even under complex conditions.

[0748] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0749] Step 1:

[0750] The server collects information about the building project, including project conditions such as humidity, temperature, durability, cost, etc. The server stores this data in a database.

[0751] Input: Project conditions (humidity, temperature, durability, cost, etc.)

[0752] Output: Project condition data neatly stored in a database

[0753] Step 2:

[0754] The server performs preprocessing on the collected data, such as normalization and feature engineering, to make it more efficient for training on a quantum computer, for example, scaling humidity data to a range of 0 to 1.

[0755] Input: Project criteria data stored in the database

[0756] Output: Preprocessed project condition data

[0757] Specific behavior: "Humidity data [45, 55, 60] → Normalized humidity data [0.45, 0.55, 0.60]"

[0758] Step 3:

[0759] The server uses a quantum computer to train the model based on the pre-processed data. The trained model is used to evaluate the performance of building materials in the building environment and predict the optimal product.

[0760] Input: Preprocessed project criteria data

[0761] Output: A trained quantum computer model

[0762] Specific operation: Training is performed using the Qiskit framework using the IBM Q Experience and D-Wave Quantum Computer.

[0763] Step 4:

[0764] The terminal provides a user interface that allows users to input building project requirements, including details such as the project location, climate conditions, building use, and budget.

[0765] Input: User's project conditions (location, weather conditions, purpose, budget, etc.)

[0766] Output: User input data

[0767] Specific operation: The user types into the terminal, "We are planning to build a commercial building in a hot and humid region. The budget is 50 million yen."

[0768] Step 5:

[0769] The generative AI model converts user-entered data into a standard format that is easy for a quantum computer to understand.

[0770] Input: User-entered data

[0771] Output: Data converted to a standard format

[0772] Specific behavior: User input: "Hot and humid", "Commercial building", "50 million yen"

[0773] Converted data: {Area: "Hot and Humid", Type: "Commercial Building", Budget: 50000000}

[0774] Step 6:

[0775] The server sends user input data transformed by the generative AI model to a quantum computer, which then uses the trained model to calculate the optimal building material product for the conditions.

[0776] Input: Data converted to a standard format

[0777] Output: Prediction results of optimal building material products

[0778] How it works: A quantum computer evaluates different building materials and calculates the optimal product based on durability and cost performance.

[0779] Step 7:

[0780] The prediction results are sent to the device and presented to the user, who then displays specific suggestions to the user.

[0781] Input: Prediction results for optimal building material products

[0782] Output: Prediction results presented to the user

[0783] What it does: The user is told, "ABC Cement is ideal for this project. It is durable in hot and humid conditions and is cost-effective."

[0784] Through the above processing steps, users can quickly and accurately select the optimal building material products under complex conditions, even without specialized knowledge.

[0785] (Application example 1)

[0786] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] In recent years, there has been a demand for optimizing appropriate material selection and inventory management strategies in construction projects and logistics center operations. However, these optimizations are extremely complex and require consideration of numerous conditions and variables, requiring advanced knowledge and skills. In particular, it is difficult to make quick and accurate decisions using conventional methods, making efficient operation difficult.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0789] In this invention, the server includes means for collecting data related to a construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for collecting data related to inventory management at a logistics center, means for converting the collected inventory data into a standard format using a generative AI model, means for calculating an optimal inventory management strategy using the quantum computer, and means for presenting the optimal inventory management strategy to a user, thereby enabling the selection of optimal cement products for the construction project and the implementation of an efficient inventory management strategy at the logistics center.

[0790] "Building project data" means information related to the design, construction, and operation of a building, including environmental conditions, budget, materials used, and overall project requirements.

[0791] A "quantum computer" is a computing device that, unlike conventional computers, operates based on the principles of quantum mechanics and can efficiently solve certain computational problems.

[0792] "Collection means" refers to the method or device for collecting, storing, and optionally processing data.

[0793] "Training" refers to the process by which an algorithm or model learns from provided data and improves its accuracy in prediction or identification.

[0794] A "means for providing an interactive interface" is a combination of software and hardware that allows a user to interact directly with a system.

[0795] "User Input Data" means information provided by a user to the system, including project requirements and conditions.

[0796] "Data related to inventory management at logistics centers" refers to information related to inventory status, replenishment schedules, sales forecasts, storage capacity, and the like at logistics centers.

[0797] A "generative AI model" is a pre-trained artificial intelligence model capable of natural language processing and data analysis.

[0798] A "means for converting into a standard format" is a method or device for converting input data of various formats into a unified structure or format.

[0799] A "calculating means" is a method or device for deriving a specific result or optimal solution based on given data or conditions.

[0800] A "presentation means" is a method or device for visually or audibly displaying the results of a calculation or prediction to a user.

[0801] The "optimum cement product" is the cement product that best meets and performs best for the conditions and requirements of a particular building project.

[0802] An "optimal inventory management strategy" is the most effective way to efficiently manage the storage, replenishment, and sales of inventory in a distribution center.

[0803] The present invention provides a system for proposing optimal cement products and inventory management strategies for construction projects and logistics center operations. Specific embodiments for carrying out the present invention are described below.

[0804] The system includes the following hardware and software:

[0805] Server: Performs data collection, data processing, model training, and prediction calculations, specifically using quantum computers and generative AI models (e.g., OpenAI APIs).

[0806] Device: The device (e.g., smartphone, tablet) through which a user provides input and receives results.

[0807] Interactive interface: The interface through which a user provides data to a system (e.g., a web application).

[0808] The operation of the system is described below.

[0809] Data collection

[0810] The server collects data about construction projects and logistics center operations. For construction projects, information about the project location, weather conditions, building use, budget, etc. For logistics centers, information about incoming and outgoing shipments, inventory levels, sales forecasts, warehouse status, etc.

[0811] Data Transformation and Prediction

[0812] The server uses a generative AI model to convert the collected data into a standard format for training on a quantum computer. Specifically, the server sends the following prompt to the generative AI model to perform the appropriate format conversion:

[0813] Example prompt sentence:

[0814] Predict the optimal stock management for the following data: {'temperature': 22, 'humidity': 55, 'stock_levels': {'product_A': 150, 'product_B': 250}, 'sales_forecast': {'product_A': 130, 'product_B': 200}, 'warehouse_capacity': 600}

[0815] The generative AI model takes the prompt text, converts it into a standard format, and sends it to a quantum computer to predict the most suitable cement product and inventory management strategy for the specific conditions.

[0816] Results presentation

[0817] The server sends the prediction results to the terminal and displays them to the user, who receives recommendations for optimal cement products and inventory management strategies through the terminal's interactive interface, enabling efficient decision-making.

[0818] For example, for a building project:

[0819] If a user inputs, "We are planning to build a commercial building in a hot and humid region. We have a budget of approximately 50 million yen and are looking for a durable, cost-effective cement," the server will convert this information appropriately using a generative AI model and predict the optimal cement product. The predicted result will be presented to the user in the form, "ABC Cement is ideal for this project. ABC Cement is highly durable under hot and humid conditions and also offers excellent cost performance."

[0820] For distribution centers:

[0821] If a user types, "Please suggest the optimal inventory management strategy based on current inventory, sales forecast, and warehouse capacity," the server will convert the collected data using a generative AI model and calculate the optimal management strategy using a quantum computer. The result will be presented as, "Product A needs replenishment in the next two weeks. Product B's current inventory level is appropriate to meet demand."

[0822] In this way, this invention utilizes quantum computers and generative AI models to quickly and accurately provide optimal product selection and management strategies even under complex conditions.

[0823] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0824] Step 1:

[0825] The server collects data about the construction project and logistics center operations from users and sensors, including project location, weather conditions, building use, budget, incoming and outgoing shipments, inventory levels, sales forecasts, and warehouse conditions, derived through signal or communication analysis.

[0826] Input: Building project and logistics center operational data provided by users and sensors.

[0827] Output: The collected dataset.

[0828] Step 2:

[0829] The server normalizes the collected data and performs feature engineering as needed, including imputing missing values, converting data types, and generating new features.

[0830] Input: The collected dataset.

[0831] Output: The preprocessed dataset.

[0832] Step 3:

[0833] The server inputs the preprocessed data into the generative AI model and converts it into a standard format. Specifically, it uses the API of OpenAI, the generative AI model, to send data through prompts and receive responses.

[0834] Input: A preprocessed dataset and a prompt statement.

[0835] Output: Data converted into a standard format.

[0836] Step 4:

[0837] The server then converts the data into a standard format and sends it to a quantum computer, which then uses the trained model to calculate the best solution for the specific conditions.

[0838] Input: Data converted to a standard format.

[0839] Output: Predicted results of optimal cement product or inventory management strategy.

[0840] Step 5:

[0841] The server receives the prediction results from the quantum computer and sends them to the device, converting the data into a user-friendly format and displaying it visually for easy understanding.

[0842] Input: Prediction results from a quantum computer.

[0843] Output: The results in the form of reports and graphs that are presented to the user.

[0844] Step 6:

[0845] The terminal then presents the received forecast results to the user, who can then review the results through an interactive interface to select the optimal cement product and implement an inventory management strategy.

[0846] Input: Results presented by the server.

[0847] Output: The result that the user sees on the display screen.

[0848] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0849] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0850] A specific embodiment of the system will be described below.

[0851] The server first collects construction project data and cement product property data and stores them in a database, including project conditions such as humidity, temperature, durability, and cost. The collected data is then used to train the quantum computer.

[0852] The server then preprocesses the collected data by normalizing it, removing invalid data, and performing necessary feature engineering to enable efficient processing by the quantum computer. The server then trains the quantum computer using the preprocessed data. The trained model is used to evaluate the performance of cement products in the building environment and predict optimal products.

[0853] The terminal provides a user interface that allows users to input requirements for a construction project. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. In addition, the terminal is equipped with an emotion engine that recognizes the user's emotions in real time. This emotion data is then analyzed along with the input requirements.

[0854] For example, if a user uses a conversational interface to input, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product.", the emotion engine analyzes emotions from the user's voice and text input. The generative AI model converts these input data into a standard format. For example, it converts the natural language input "hot and humid region" into numerical data.

[0855] The device then sends the converted data to the server, which receives it and initiates calculations using a quantum computer. The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The computer also takes into account the emotional data collected by the emotion engine, fine-tuning the recommendations based on the user's emotional state.

[0856] The server formats the calculation results and converts them into an easy-to-understand format. For example, it includes the name and characteristics of the optimal cement product, as well as the reason for the recommendation. The server then sends the formatted results to the device. The device then displays the received results to the user. For example, it may suggest, "XYZ cement is optimal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0857] Additionally, if the emotion engine confirms that the user feels safe, more detailed technical information or additional recommendations may be displayed, while if the user is anxious or skeptical, more concise and reassuring information is provided.

[0858] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of a quantum computer and the emotion recognition function of an emotion engine, it is possible to provide optimal and reassuring recommendations to users.

[0859] The processing flow will be explained below.

[0860] Step 1:

[0861] The server collects construction project data and cement product property data from various data sources, including data on weather conditions, durability test results, costs, etc. The collected data is stored in a database.

[0862] Step 2:

[0863] The server preprocesses the collected data by removing invalid data, normalizing the data, and performing feature engineering, so that the data is in a format that can be efficiently processed by a quantum computer.

[0864] Step 3:

[0865] The server uses the pre-processed data to train a quantum computer, which then builds a model to predict cement product performance in the building environment. The model is designed to learn from large amounts of data and accurately predict the properties of cement products.

[0866] Step 4:

[0867] The terminal displays an interactive interface for users to input information about their construction projects. The interface is designed to be easy to understand, allowing users to easily input project requirements.

[0868] Step 5:

[0869] Using an interactive interface, users input details about the construction project, such as the project's location, climate conditions, intended use, budget, etc. This information is then sent to the system.

[0870] Step 6:

[0871] The device converts the information entered by the user into a standard format using a generative AI model, which converts natural language input into numerical data. For example, "hot and humid region" is converted into specific numerical data.

[0872] Step 7:

[0873] The device transmits the converted data to the emotion engine, which recognizes the user's emotions in real time and evaluates their emotional state. For example, the emotion engine can determine the user's stress level from their tone of voice and facial expression.

[0874] Step 8:

[0875] The device sends the emotional data obtained by the emotion engine to the server, which receives it and provides it to the quantum computer along with the user's input data.

[0876] Step 9:

[0877] The server inputs standard format data and emotional data into the quantum computer model and begins calculations, which then predicts and identifies candidates for the optimal cement product.

[0878] Step 10:

[0879] The server formats the results and converts them into a user-friendly format, including, for example, the name of the specific cement product, its properties, and the reasons for the recommendation.

[0880] Step 11:

[0881] The server sends the formatted results to the terminal.

[0882] Step 12:

[0883] The device then sends the results back to the emotion engine, which then displays the results in a way that adapts to the user's emotional state. For example, if the device determines that the user is feeling anxious, it will display more detailed information or a support message.

[0884] Step 13:

[0885] The user reviews the presented cement product information and can request additional questions or changes using the interface again.

[0886] This process allows users to efficiently select the most suitable cement product, and by using an emotion engine, it provides optimal suggestions based on the user's emotional state.

[0887] Example 2

[0888] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0889] Existing cement product selection methods for construction projects do not adequately consider the characteristics of the project, making it difficult to select the optimal cement product. Furthermore, users may feel uneasy because recommendations do not take into account their technical knowledge or emotional state. Furthermore, the technology required to efficiently process large amounts of data and make accurate predictions is still immature.

[0890] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0891] In this invention, the server includes means for collecting data on construction projects, means for preprocessing the collected data, means for training a quantum computer based on the preprocessed data, means for predicting the cement product best suited to a user's requirements using the trained quantum computer, means for providing an interactive interface for the user to input the construction project requirements, means for analyzing the user's emotional state using an emotion engine and fine-tuning the proposal content, means for converting the construction project requirements input by the user into a standard format using a generative AI model, and means for presenting the prediction results to the user. This enables highly accurate predictions that take into account project characteristics and makes optimal proposals according to the user's emotional state.

[0892] "Data relating to building projects" refers to various information related to the design, construction and management of buildings, including, in particular, project conditions such as humidity, temperature, durability and cost.

[0893] "Means of collection" refers to the methods and devices that collect the necessary data using sensors, APIs, etc. and store it in a database.

[0894] The "preprocessing means" refers to a method or device that converts collected data into a format that is easy to process through a series of operations such as normalization, deletion of invalid data, and feature engineering.

[0895] "Training means" refers to a method or apparatus that optimizes a quantum computer based on preprocessed data to build and tune a target predictive model.

[0896] "Conversational interface" refers to the interactive input screens and software that allow users to input requirements for a building project.

[0897] An "emotion engine" refers to technology or a device that analyzes a user's facial expressions, voice, text input, etc. to evaluate and recognize their emotional state in real time, and provides appropriate feedback based on that.

[0898] A "generative AI model" is a machine learning model used to convert input data into a specified format, serving to standardize diverse input formats.

[0899] "Means for converting into a standard format" refers to the technology or device that analyzes the input construction project requirements and converts them into a specified unified format.

[0900] "Means for presenting predicted results" refers to a method or device for displaying the calculated optimal cement product characteristics and the reasons for recommendation in a manner that is easy for the user to understand.

[0901] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a data preprocessing means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0902] The server first collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. This data is collected using sensors and APIs. For example, weather data is obtained from a weather API, and the database is updated regularly.

[0903] The server then preprocesses the collected data, including normalizing the data, removing invalid data, and performing feature engineering. Specifically, it scales the temperature and humidity values ​​and imputes missing values. This preprocessing allows for efficient processing on a quantum computer.

[0904] Based on the pre-processed data, the server trains the quantum computer, which includes generating a training dataset, encoding the data into qubits, gate operations, and measurement operations, allowing the quantum computer to build an optimized model that can be used to make future predictions.

[0905] The user inputs the requirements for a construction project using a conversational interface on the device. For example, the user might input, "I'm building a commercial building with a budget of 50 million yen, located in a hot and humid region. Please suggest the best cement product." The device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotional state in real time. This emotion data is analyzed along with the user's input data and an emotion tag is attached.

[0906] The generative AI model converts the building project requirements entered by the user into a standard format. For example, the natural language input "hot and humid region" is converted into concrete numerical data. The converted data is then sent from the device to the server.

[0907] The server receives the data and initiates calculations using a quantum computer. The quantum computer uses the trained model to predict the cement product that best suits the user's requirements. This process also takes into account emotional data collected by the emotion engine, fine-tuning the suggestions based on the user's emotional state.

[0908] The calculation results are formatted by the server and converted into an easy-to-understand format. For example, the format is a report that includes the name of the optimal cement product, its characteristics, and the reason for the recommendation. The formatted results are sent to the terminal, which then displays them to the user. An example of a presentation might be, "XYZ cement is ideal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[0909] The device also uses an emotion engine to analyze the user's real-time reactions. If the user feels reassured, it displays more detailed technical information and additional recommendations. Conversely, if the user feels anxious or suspicious, it provides more concise and reassuring information. This system allows users to efficiently select the optimal cement product even without specialized knowledge.

[0910] Example of a text prompt

[0911] "If the construction conditions for a commercial building are hot and humid and the budget is 50 million yen, which cement product would be best?"

[0912] "A user is building a commercial building in a hot and humid region with a budget of ¥50 million. Please suggest the best cement product for these conditions."

[0913] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0914] Processing flow

[0915] Step 1: Data collection

[0916] The server collects construction project data and cement product characteristic data through sensors and APIs.

[0917] Input: Weather data, building specification data, cement property data

[0918] Output: Raw data stored in an internal database

[0919] Specific operation: For example, obtain humidity and temperature data using a weather API, collect real-time environmental data from sensors, and store this in a database.

[0920] Step 2: Data Preprocessing

[0921] The server pre-processes the collected data, which includes data normalization, invalid data removal, and feature engineering.

[0922] Input: Raw data stored in an internal database

[0923] Output: Preprocessed data

[0924] Specific operations: Normalize humidity and temperature values, fill in missing values, and generate new features tailored to the project conditions.

[0925] Step 3: Training the quantum computer

[0926] The server uses the pre-processed data to train the quantum computer.

[0927] Input: Preprocessed dataset

[0928] Output: The trained model

[0929] Specific operations: Encode data into qubits, perform gate operations, and build a model to predict the optimal cement product.

[0930] Step 4: Getting User Input

[0931] The user inputs the requirements for the construction project using an interactive interface on the terminal.

[0932] Inputs: Project location, climate conditions, building use, budget, and other details

[0933] Output: User requirement data parsed on the terminal side

[0934] Specific actions: For example, a user enters, "I am building a commercial building. My budget is $500,000, and it is located in a hot and humid area."

[0935] Step 5: Sentiment Analysis

[0936] The terminal uses an emotion engine to analyze the user's emotional state.

[0937] Input: User voice, facial expressions, and text input

[0938] Output: User requirement data with sentiment tags

[0939] Specific behavior: Analyzes voice tone and facial expressions in real time to assess the user's emotional state.

[0940] Step 6: Data Transformation

[0941] The device uses a generative AI model to convert the building project requirements entered by the user into a standard format.

[0942] Input: User requirement data tagged with emotions

[0943] Output: Data converted to a standard format

[0944] Specific operation: For example, convert the expression "hot and humid" into numerical data.

[0945] Step 7: Predictive calculations

[0946] The server receives the data sent from the device and starts calculations on the quantum computer.

[0947] Input: Data converted to a standard format

[0948] Output: Prediction of optimal cement product

[0949] What it does: Uses a trained model to perform predictive calculations and select the cement product that best suits the user's requirements.

[0950] Step 8: Formatting and presenting the results

[0951] The server formats the prediction results, converts them into an easy-to-understand format, and sends them to the device, which then presents them to the user.

[0952] Input: Predicted results of optimal cement product

[0953] Output: Results in the form of a report to present to the user

[0954] Specific behavior: For example, display the following: "XYZ cement is ideal for this project. XYZ cement is highly durable in hot and humid conditions and is cost-effective."

[0955] Step 9: Regulating Emotional Feedback

[0956] The device uses an emotion engine to analyze the user's real-time reactions and provide more detailed technical information or additional recommendations as needed.

[0957] Input: Real-time user responses

[0958] Output: Tailored information

[0959] What it does: If the user is happy, show them detailed technical information; if they are worried, offer them concise, reassuring information.

[0960] (Application example 2)

[0961] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0962] In today's world, data analysis technology is important for improving the efficiency of construction projects and user satisfaction. However, existing technology does not take into account the user's emotional state when making suggestions, which can lead to a decline in the quality of the user experience. Furthermore, technology for displaying appropriate advertisements based on emotions is also underdeveloped. To solve this problem, a system is needed that analyzes the user's emotional state in real time and provides optimal suggestions and advertisements based on that information.

[0963] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0964] In this invention, the server includes means for collecting data related to the construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for sending the user's input data to the quantum computer to predict the optimal cement product, means for presenting the prediction result to the user, means for analyzing the user's emotional state using an emotion engine, and means for displaying advertisements based on the emotional state using a generative AI model. This enables optimal suggestions based on the user's emotional state, improving the user experience and maximizing the effectiveness of advertisements.

[0965] "Data relating to the construction project" refers to information relating to the various conditions, environmental factors, material properties, etc. required for the implementation of the construction project.

[0966] A "quantum computer" is a next-generation computer that performs calculations using quantum bits, making it possible to analyze large amounts of data and efficiently solve complex optimization problems.

[0967] "Training" refers to the process of training a quantum computer based on collected data to build a model to achieve a specific goal (e.g., predicting the optimal cement product).

[0968] "Interactive interface" refers to an interface function that allows users to input project requirements and conditions and exchange information in a responsive manner with the system.

[0969] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to recognize their emotional state in real time.

[0970] "Generative AI models" refer to artificial intelligence models that convert user-entered information into a standard format, or generate suggestions and advertisements based on emotional states.

[0971] "Means for displaying advertisements" refers to the function for selecting the most appropriate advertisement based on the user's emotional state and displaying it to the user.

[0972] This invention relates to a system that uses a quantum computer, a generative AI model, and an emotion engine to recommend the best cement product for a construction project and display advertisements based on a user's emotional state. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[0973] First, the server collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. The collected data is used to train the quantum computer. During this process, the data is preprocessed, specifically, data normalization, invalid data removal, and necessary feature engineering are performed. The server then trains the quantum computer based on the preprocessed data.

[0974] The program implementation uses the following hardware and software:

[0975] Hardware used: smart glasses, camera-equipped devices

[0976] Software used: OpenCV, Keras, emotion engine, generative AI model, quantum computer model

[0977] The device then provides a user interface for users to input their construction project requirements. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. The device also has a built-in emotion engine that recognizes emotions from the user's facial expressions and voice in real time. This emotion data is then analyzed along with the input requirements.

[0978] For example, when a user runs a program using smart glasses, the emotion engine reads the emotion "surprise" from the user's facial expression. At this time, the generative AI model converts the emotion data into a standard format and suggests the most appropriate advertisement. Specifically, if a user inputs, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product," the emotion engine analyzes the user's emotion, and the generative AI model analyzes the input data and converts it into a standard format. This converted data is sent to a quantum computer, which calculates the best cement product. Based on this result, the emotion data is further taken into account and the most appropriate advertisement is also suggested at the same time.

[0979] An example prompt might look like this:

[0980] Using quantum computing and an emotion engine, it will suggest what kind of ads will be most effective based on the user's current emotions. For example, if a user is feeling surprised, it will show them an ad for the latest gadgets.

[0981] This system not only enables users to efficiently select the most suitable cement product without any specialized knowledge, but also displays advertisements based on their emotional state at the optimal time, which is expected to improve the user experience.

[0982] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0983] Step 1:

[0984] The server collects construction project data and cement product characteristic data and stores it in a database. The input is project conditions such as humidity, temperature, durability, and cost, and the output is the data on these conditions stored in the database. Specifically, data is collected from devices such as sensors and transferred to the database via an API.

[0985] Step 2:

[0986] The server preprocesses the collected data. The input is the collected data, and the output is the preprocessed data. Specifically, it normalizes the data, removes invalid data, and performs feature engineering to prepare it for efficient processing by a quantum computer. For example, it performs missing value imputation and data scaling.

[0987] Step 3:

[0988] The server trains the quantum computer based on the preprocessed data. The input is the preprocessed data, and the output is the trained quantum computer model. Specifically, a quantum algorithm is used to train the model to predict the optimal cement product. This is achieved by sending the training data to the quantum computer and applying an iterative algorithm.

[0989] Step 4:

[0990] The terminal provides a user interface that allows users to input building project requirements. The input is the user's building project requirements, and the output is data transmitted through an interactive interface. Specifically, the terminal provides a GUI, allowing users to input information using forms or voice input.

[0991] Step 5:

[0992] The device uses an emotion engine to analyze the user's emotional state. The input is emotional data such as the user's facial expressions and voice, and the output is the analyzed emotional state. Specifically, facial expressions and voice data are collected using a camera and microphone, and the emotion engine analyzes this. For example, this includes processing to detect smiles and recognize the emotion of "joy."

[0993] Step 6:

[0994] The generative AI model converts emotional data into a standard format and sends it to a quantum computer. The input is the emotional data and building project requirements, and the output is the converted data in a standard format. Specifically, it uses natural language processing technology to convert user requirements into numerical data. For example, it converts "hot and humid region" into specific temperature and humidity values.

[0995] Step 7:

[0996] The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The input is data converted into a standard format, and the output is a recommendation for the optimal cement product. Specifically, a quantum algorithm is applied to find the optimal solution and generate the result.

[0997] Step 8:

[0998] The server formats the calculation results and converts them into an easy-to-understand format. The input is the calculation result from the quantum computer, and the output is a formatted recommendation. Specifically, the generative AI model converts the recommendation into an easy-to-understand sentence format. For example, it could express it as "XYZ cement is best for this project."

[0999] Step 9:

[1000] The terminal displays the results to the user. The input is the formatted recommendation, and the output is the information displayed to the user. Specifically, the results are displayed on the screen and visual elements are added to make them easy for the user to understand. For example, this includes displaying graphs of the cement's properties and the reasons for the recommendation.

[1001] Step 10:

[1002] The emotion engine analyzes whether the user feels safe or anxious and provides more detailed or concise information. The input is the user's emotional data, and the output is the detailed or concise information provided. Specifically, if the user feels safe, technical details are displayed, and if the user feels anxious, simple reassuring information is provided.

[1003] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1004] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1005] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1006] [Fourth embodiment]

[1007] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1008] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1009] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1010] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1011] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1012] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1013] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1014] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1015] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1016] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1017] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1018] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1019] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1020] This invention relates to a system that utilizes a quantum computer and a generative AI model to recommend optimal cement products for building projects. The system includes a data collection means, a quantum computer training means, a user interface provision means, a prediction means, and a presentation means.

[1021] The server first collects construction project data and cement product property data and stores them in a database, which is categorized based on project conditions such as humidity, temperature, durability, cost, etc. The collected data is then used to train the quantum computer.

[1022] The server then trains a quantum computer on the collected data. The trained model is used to evaluate cement product performance in the building environment and predict optimal products. To ensure effective training of the quantum computer, the data undergoes pre-processing such as normalization and feature engineering.

[1023] The terminal provides a user interface that allows users to input requirements for a building project. Users can enter detailed information into the interface, such as the project's location, climate conditions, building use, budget, etc. The generative AI model converts these input data into a standard format.

[1024] For example, if a user inputs, "I am planning to build a commercial building in a hot and humid region. I have a budget of approximately 50 million yen and am looking for a durable, cost-effective cement," this information is appropriately converted by the generative AI model and sent to the server.

[1025] The server sends the user's input data to a quantum computer, which then uses the trained model to calculate the best cement product for the given conditions, comparing the characteristics of different cement products to select the one that best meets the conditions.

[1026] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[1027] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of quantum computers, it is possible to quickly and accurately recommend the optimal product even under complex conditions.

[1028] The processing flow will be explained below.

[1029] Step 1:

[1030] The server collects construction project data and cement product property data, such as humidity, temperature, durability, and cost, and stores them in a database.

[1031] Step 2:

[1032] The server preprocesses the collected data by normalizing it, removing invalid data, and performing any necessary feature engineering so that the data can be efficiently processed by the quantum computer.

[1033] Step 3:

[1034] The server uses the pre-processed data to train a quantum computer, which then learns from the vast amount of data and builds a model to predict the performance of cement products.

[1035] Step 4:

[1036] The terminal provides users with an interactive interface through which they can input details about their construction project, such as the project location, climate conditions, building use, and budget.

[1037] Step 5:

[1038] Users use a conversational interface to input project requirements, such as, "I'm planning to build a commercial building in a hot and humid climate. I have a budget of approximately $500,000 and I'm looking for a durable, cost-effective cement."

[1039] Step 6:

[1040] The device uses generative AI models to convert user-entered information into a standard format, for example, converting the natural language input "hot and humid region" into concrete numerical data that a quantum computer can easily understand.

[1041] Step 7:

[1042] The device then sends the converted data to the server, which receives it and starts the quantum computer calculation.

[1043] Step 8:

[1044] The server inputs data in a standard format into a quantum computer model and runs a simulation, which predicts and identifies candidates for the optimal cement product.

[1045] Step 9:

[1046] The server formats the simulation results and converts them into an easy-to-understand format, including, for example, the name and characteristics of the optimal cement product and the reasons for the recommendation.

[1047] Step 10:

[1048] The server sends the formatted results to the terminal.

[1049] Step 11:

[1050] The device then displays the results to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[1051] Step 12:

[1052] Users can review the cement product information presented and, if necessary, ask additional questions or request recalculations under different conditions.

[1053] Example 1

[1054] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1055] Selecting the optimal cement product for a construction project requires considering many variables, but the process requires specialized knowledge, is time-consuming, and costly. Furthermore, conventional systems lack the computing power to simultaneously consider complex conditions, making it difficult to select the right product quickly and accurately. This makes it difficult to find the optimal cement product.

[1056] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1057] In this invention, the server includes means for collecting information about building projects, means for training a quantum computer based on the collected data, means for providing an interactive interface for users to input building project requirements, means for converting the user-input building project requirements into a standard format using a generative AI model, means for sending the user-input data to the quantum computer and predicting the optimal building material product, and means for presenting the prediction result to the user, thereby enabling a user to quickly and accurately select the optimal cement product even without specialized knowledge.

[1058] A "building project" refers to a series of tasks related to the design, construction, and maintenance of a building.

[1059] "Information" refers to all data related to a building project, such as the project location, climatic conditions, materials used, budget, etc.

[1060] A "quantum computer" is a computer that performs calculations using quantum bits, and refers to a device that can quickly perform calculations that are difficult for conventional computers to perform.

[1061] "Training" refers to the process of learning to improve the performance of a computational model using a given data set.

[1062] An "interactive interface" refers to an interactive user interface in which a user provides input to a system and the system operates based on that input.

[1063] A "generative AI model" refers to an artificial intelligence model that learns from large amounts of data and is designed to perform specific tasks.

[1064] A "standard format" refers to the representation of data in a unified format to ensure consistency and compatibility.

[1065] "Building products" refers to various materials and products used in the construction of buildings (e.g., cement, bricks, rebar, etc.).

[1066] "Predicting" refers to estimating future outcomes or trends based on given data.

[1067] "Present" refers to the system showing the results of its calculations or processing to the user visually or in some other way.

[1068] The present invention relates to a system that uses a quantum computer and a generative AI model to propose optimal building material products for a building project. An embodiment of the system will be described below.

[1069] The server first collects and stores information related to the building project in a database, including data on project conditions such as humidity, temperature, durability, cost, etc. The data collected by the server is stored in the database for further processing.

[1070] The server then performs preprocessing on the collected data, including normalization and feature engineering. This enables effective training on a quantum computer. Examples of hardware used include the IBM Q Experience and the D-Wave Quantum Computer. The software used is Qiskit, a quantum programming framework.

[1071] The server then uses a quantum computer to perform training, and the trained model is used to evaluate the performance of building materials in a building environment and predict optimal products.

[1072] An interactive interface is provided on the terminal for users to input building project requirements, and users can enter detailed information such as project location, climatic conditions, building use, budget, etc. into the interface.

[1073] The generative AI model is responsible for converting user input data into a standard format. For example, if a user inputs, "We are planning to build a commercial building in a hot and humid region with a budget of 50 million yen," this information is converted appropriately by the generative AI model and sent to the server.

[1074] The server then sends the user's input data to a quantum computer, which predicts the optimal building material product. The quantum computer uses the trained model to calculate the building material product that best suits the conditions. At this time, it compares the characteristics of different building material products and selects the product that best meets the conditions.

[1075] Finally, the prediction results are sent to the terminal and presented to the user, suggesting, for example, "ABC cement is ideal for this project. ABC cement is highly durable under high temperature and humidity conditions and offers excellent cost performance."

[1076] This system allows users to efficiently select the optimal building material products, even without specialized knowledge. By utilizing the computational power of quantum computers, it is possible to quickly and accurately suggest optimal products even under complex conditions.

[1077] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1078] Step 1:

[1079] The server collects information about the building project, including project conditions such as humidity, temperature, durability, cost, etc. The server stores this data in a database.

[1080] Input: Project conditions (humidity, temperature, durability, cost, etc.)

[1081] Output: Project condition data neatly stored in a database

[1082] Step 2:

[1083] The server performs preprocessing on the collected data, such as normalization and feature engineering, to make it more efficient for training on a quantum computer, for example, scaling humidity data to a range of 0 to 1.

[1084] Input: Project criteria data stored in the database

[1085] Output: Preprocessed project condition data

[1086] Specific behavior: "Humidity data [45, 55, 60] → Normalized humidity data [0.45, 0.55, 0.60]"

[1087] Step 3:

[1088] The server uses a quantum computer to train the model based on the pre-processed data. The trained model is used to evaluate the performance of building materials in the building environment and predict the optimal product.

[1089] Input: Preprocessed project criteria data

[1090] Output: A trained quantum computer model

[1091] Specific operation: Training is performed using the Qiskit framework using the IBM Q Experience and D-Wave Quantum Computer.

[1092] Step 4:

[1093] The terminal provides a user interface that allows users to input building project requirements, including details such as the project location, climate conditions, building use, and budget.

[1094] Input: User's project conditions (location, weather conditions, purpose, budget, etc.)

[1095] Output: User input data

[1096] Specific operation: The user types into the terminal, "We are planning to build a commercial building in a hot and humid region. The budget is 50 million yen."

[1097] Step 5:

[1098] The generative AI model converts user-entered data into a standard format that is easy for a quantum computer to understand.

[1099] Input: User-entered data

[1100] Output: Data converted to a standard format

[1101] Specific behavior: User input: "Hot and humid", "Commercial building", "50 million yen"

[1102] Converted data: {Area: "Hot and Humid", Type: "Commercial Building", Budget: 50000000}

[1103] Step 6:

[1104] The server sends user input data transformed by the generative AI model to a quantum computer, which then uses the trained model to calculate the optimal building material product for the conditions.

[1105] Input: Data converted to a standard format

[1106] Output: Prediction results of optimal building material products

[1107] How it works: A quantum computer evaluates different building materials and calculates the optimal product based on durability and cost performance.

[1108] Step 7:

[1109] The prediction results are sent to the device and presented to the user, who then displays specific suggestions to the user.

[1110] Input: Prediction results for optimal building material products

[1111] Output: Prediction results presented to the user

[1112] What it does: The user is told, "ABC Cement is ideal for this project. It is durable in hot and humid conditions and is cost-effective."

[1113] Through the above processing steps, users can quickly and accurately select the optimal building material products under complex conditions, even without specialized knowledge.

[1114] (Application example 1)

[1115] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1116] In recent years, there has been a demand for optimizing appropriate material selection and inventory management strategies in construction projects and logistics center operations. However, these optimizations are extremely complex and require consideration of numerous conditions and variables, requiring advanced knowledge and skills. In particular, it is difficult to make quick and accurate decisions using conventional methods, making efficient operation difficult.

[1117] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1118] In this invention, the server includes means for collecting data related to a construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for collecting data related to inventory management at a logistics center, means for converting the collected inventory data into a standard format using a generative AI model, means for calculating an optimal inventory management strategy using the quantum computer, and means for presenting the optimal inventory management strategy to a user, thereby enabling the selection of optimal cement products for the construction project and the implementation of an efficient inventory management strategy at the logistics center.

[1119] "Building project data" means information related to the design, construction, and operation of a building, including environmental conditions, budget, materials used, and overall project requirements.

[1120] A "quantum computer" is a computing device that, unlike conventional computers, operates based on the principles of quantum mechanics and can efficiently solve certain computational problems.

[1121] "Collection means" refers to the method or device for collecting, storing, and optionally processing data.

[1122] "Training" refers to the process by which an algorithm or model learns from provided data and improves its accuracy in prediction or identification.

[1123] A "means for providing an interactive interface" is a combination of software and hardware that allows a user to interact directly with a system.

[1124] "User Input Data" means information provided by a user to the system, including project requirements and conditions.

[1125] "Data related to inventory management at logistics centers" refers to information related to inventory status, replenishment schedules, sales forecasts, storage capacity, and the like at logistics centers.

[1126] A "generative AI model" is a pre-trained artificial intelligence model capable of natural language processing and data analysis.

[1127] A "means for converting into a standard format" is a method or device for converting input data of various formats into a unified structure or format.

[1128] A "calculating means" is a method or device for deriving a specific result or optimal solution based on given data or conditions.

[1129] A "presentation means" is a method or device for visually or audibly displaying the results of a calculation or prediction to a user.

[1130] The "optimum cement product" is the cement product that best meets and performs best for the conditions and requirements of a particular building project.

[1131] An "optimal inventory management strategy" is the most effective way to efficiently manage the storage, replenishment, and sales of inventory in a distribution center.

[1132] The present invention provides a system for proposing optimal cement products and inventory management strategies for construction projects and logistics center operations. Specific embodiments for carrying out the present invention are described below.

[1133] The system includes the following hardware and software:

[1134] Server: Performs data collection, data processing, model training, and prediction calculations, specifically using quantum computers and generative AI models (e.g., OpenAI APIs).

[1135] Device: The device (e.g., smartphone, tablet) through which a user provides input and receives results.

[1136] Interactive interface: The interface through which a user provides data to a system (e.g., a web application).

[1137] The operation of the system is described below.

[1138] Data collection

[1139] The server collects data about construction projects and logistics center operations. For construction projects, information about the project location, weather conditions, building use, budget, etc. For logistics centers, information about incoming and outgoing shipments, inventory levels, sales forecasts, warehouse status, etc.

[1140] Data Transformation and Prediction

[1141] The server uses a generative AI model to convert the collected data into a standard format for training on a quantum computer. Specifically, the server sends the following prompt to the generative AI model to perform the appropriate format conversion:

[1142] Example prompt sentence:

[1143] Predict the optimal stock management for the following data: {'temperature': 22, 'humidity': 55, 'stock_levels': {'product_A': 150, 'product_B': 250}, 'sales_forecast': {'product_A': 130, 'product_B': 200}, 'warehouse_capacity': 600}

[1144] The generative AI model takes the prompt text, converts it into a standard format, and sends it to a quantum computer to predict the most suitable cement product and inventory management strategy for the specific conditions.

[1145] Results presentation

[1146] The server sends the prediction results to the terminal and displays them to the user, who receives recommendations for optimal cement products and inventory management strategies through the terminal's interactive interface, enabling efficient decision-making.

[1147] For example, for a building project:

[1148] If a user inputs, "We are planning to build a commercial building in a hot and humid region. We have a budget of approximately 50 million yen and are looking for a durable, cost-effective cement," the server will convert this information appropriately using a generative AI model and predict the optimal cement product. The predicted result will be presented to the user in the form, "ABC Cement is ideal for this project. ABC Cement is highly durable under hot and humid conditions and also offers excellent cost performance."

[1149] For distribution centers:

[1150] If a user types, "Please suggest the optimal inventory management strategy based on current inventory, sales forecast, and warehouse capacity," the server will convert the collected data using a generative AI model and calculate the optimal management strategy using a quantum computer. The result will be presented as, "Product A needs replenishment in the next two weeks. Product B's current inventory level is appropriate to meet demand."

[1151] In this way, this invention utilizes quantum computers and generative AI models to quickly and accurately provide optimal product selection and management strategies even under complex conditions.

[1152] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1153] Step 1:

[1154] The server collects data about the construction project and logistics center operations from users and sensors, including project location, weather conditions, building use, budget, incoming and outgoing shipments, inventory levels, sales forecasts, and warehouse conditions, derived through signal or communication analysis.

[1155] Input: Building project and logistics center operational data provided by users and sensors.

[1156] Output: The collected dataset.

[1157] Step 2:

[1158] The server normalizes the collected data and performs feature engineering as needed, including imputing missing values, converting data types, and generating new features.

[1159] Input: The collected dataset.

[1160] Output: The preprocessed dataset.

[1161] Step 3:

[1162] The server inputs the preprocessed data into the generative AI model and converts it into a standard format. Specifically, it uses the API of OpenAI, the generative AI model, to send data through prompts and receive responses.

[1163] Input: A preprocessed dataset and a prompt statement.

[1164] Output: Data converted into a standard format.

[1165] Step 4:

[1166] The server then converts the data into a standard format and sends it to a quantum computer, which then uses the trained model to calculate the best solution for the specific conditions.

[1167] Input: Data converted to a standard format.

[1168] Output: Predicted results of optimal cement product or inventory management strategy.

[1169] Step 5:

[1170] The server receives the prediction results from the quantum computer and sends them to the device, converting the data into a user-friendly format and displaying it visually for easy understanding.

[1171] Input: Prediction results from a quantum computer.

[1172] Output: The results in the form of reports and graphs that are presented to the user.

[1173] Step 6:

[1174] The terminal then presents the received forecast results to the user, who can then review the results through an interactive interface to select the optimal cement product and implement an inventory management strategy.

[1175] Input: Results presented by the server.

[1176] Output: The result that the user sees on the display screen.

[1177] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1178] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[1179] A specific embodiment of the system will be described below.

[1180] The server first collects construction project data and cement product property data and stores them in a database, including project conditions such as humidity, temperature, durability, and cost. The collected data is then used to train the quantum computer.

[1181] The server then preprocesses the collected data by normalizing it, removing invalid data, and performing necessary feature engineering to enable efficient processing by the quantum computer. The server then trains the quantum computer using the preprocessed data. The trained model is used to evaluate the performance of cement products in the building environment and predict optimal products.

[1182] The terminal provides a user interface that allows users to input requirements for a construction project. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. In addition, the terminal is equipped with an emotion engine that recognizes the user's emotions in real time. This emotion data is then analyzed along with the input requirements.

[1183] For example, if a user uses a conversational interface to input, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product.", the emotion engine analyzes emotions from the user's voice and text input. The generative AI model converts these input data into a standard format. For example, it converts the natural language input "hot and humid region" into numerical data.

[1184] The device then sends the converted data to the server, which receives it and initiates calculations using a quantum computer. The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The computer also takes into account the emotional data collected by the emotion engine, fine-tuning the recommendations based on the user's emotional state.

[1185] The server formats the calculation results and converts them into an easy-to-understand format. For example, it includes the name and characteristics of the optimal cement product, as well as the reason for the recommendation. The server then sends the formatted results to the device. The device then displays the received results to the user. For example, it may suggest, "XYZ cement is optimal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[1186] Additionally, if the emotion engine confirms that the user feels safe, more detailed technical information or additional recommendations may be displayed, while if the user is anxious or skeptical, more concise and reassuring information is provided.

[1187] This system allows users to efficiently select the optimal cement product without any specialized knowledge, and by utilizing the computational power of a quantum computer and the emotion recognition function of an emotion engine, it is possible to provide optimal and reassuring recommendations to users.

[1188] The processing flow will be explained below.

[1189] Step 1:

[1190] The server collects construction project data and cement product property data from various data sources, including data on weather conditions, durability test results, costs, etc. The collected data is stored in a database.

[1191] Step 2:

[1192] The server preprocesses the collected data by removing invalid data, normalizing the data, and performing feature engineering, so that the data is in a format that can be efficiently processed by a quantum computer.

[1193] Step 3:

[1194] The server uses the pre-processed data to train a quantum computer, which then builds a model to predict cement product performance in the building environment. The model is designed to learn from large amounts of data and accurately predict the properties of cement products.

[1195] Step 4:

[1196] The terminal displays an interactive interface for users to input information about their construction projects. The interface is designed to be easy to understand, allowing users to easily input project requirements.

[1197] Step 5:

[1198] Using an interactive interface, users input details about the construction project, such as the project's location, climate conditions, intended use, budget, etc. This information is then sent to the system.

[1199] Step 6:

[1200] The device converts the information entered by the user into a standard format using a generative AI model, which converts natural language input into numerical data. For example, "hot and humid region" is converted into specific numerical data.

[1201] Step 7:

[1202] The device transmits the converted data to the emotion engine, which recognizes the user's emotions in real time and evaluates their emotional state. For example, the emotion engine can determine the user's stress level from their tone of voice and facial expression.

[1203] Step 8:

[1204] The device sends the emotional data obtained by the emotion engine to the server, which receives it and provides it to the quantum computer along with the user's input data.

[1205] Step 9:

[1206] The server inputs standard format data and emotional data into the quantum computer model and begins calculations, which then predicts and identifies candidates for the optimal cement product.

[1207] Step 10:

[1208] The server formats the results and converts them into a user-friendly format, including, for example, the name of the specific cement product, its properties, and the reasons for the recommendation.

[1209] Step 11:

[1210] The server sends the formatted results to the terminal.

[1211] Step 12:

[1212] The device then sends the results back to the emotion engine, which then displays the results in a way that adapts to the user's emotional state. For example, if the device determines that the user is feeling anxious, it will display more detailed information or a support message.

[1213] Step 13:

[1214] The user reviews the presented cement product information and can request additional questions or changes using the interface again.

[1215] This process allows users to efficiently select the most suitable cement product, and by using an emotion engine, it provides optimal suggestions based on the user's emotional state.

[1216] Example 2

[1217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1218] Existing cement product selection methods for construction projects do not adequately consider the characteristics of the project, making it difficult to select the optimal cement product. Furthermore, users may feel uneasy because recommendations do not take into account their technical knowledge or emotional state. Furthermore, the technology for efficiently processing large amounts of data and making accurate predictions is still immature.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1220] In this invention, the server includes means for collecting data on construction projects, means for preprocessing the collected data, means for training a quantum computer based on the preprocessed data, means for predicting the cement product best suited to a user's requirements using the trained quantum computer, means for providing an interactive interface for the user to input the construction project requirements, means for analyzing the user's emotional state using an emotion engine and fine-tuning the proposal content, means for converting the construction project requirements input by the user into a standard format using a generative AI model, and means for presenting the prediction results to the user. This enables highly accurate predictions that take into account project characteristics and makes optimal proposals according to the user's emotional state.

[1221] "Data relating to building projects" refers to various information related to the design, construction and management of buildings, including, in particular, project conditions such as humidity, temperature, durability and cost.

[1222] "Means of collection" refers to the methods and devices that collect the necessary data using sensors, APIs, etc. and store it in a database.

[1223] The "preprocessing means" refers to a method or device that converts collected data into a format that is easy to process through a series of operations such as normalization, deletion of invalid data, and feature engineering.

[1224] "Training means" refers to a method or apparatus that optimizes a quantum computer based on preprocessed data to build and tune a target predictive model.

[1225] "Conversational interface" refers to the interactive input screens and software that allow users to input requirements for a building project.

[1226] An "emotion engine" refers to technology or a device that analyzes a user's facial expressions, voice, text input, etc. to evaluate and recognize their emotional state in real time, and provides appropriate feedback based on that.

[1227] A "generative AI model" is a machine learning model used to convert input data into a specified format, serving to standardize diverse input formats.

[1228] "Means for converting into a standard format" refers to the technology or device that analyzes the input construction project requirements and converts them into a specified unified format.

[1229] "Means for presenting predicted results" refers to a method or device for displaying the calculated optimal cement product characteristics and the reasons for recommendation in a manner that is easy for the user to understand.

[1230] The present invention relates to a system for recommending optimal cement products for construction projects using a quantum computer, a generative AI model, and an emotion engine. The system includes a data collection means, a data preprocessing means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[1231] The server first collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. This data is collected using sensors and APIs. For example, weather data is obtained from a weather API, and the database is updated regularly.

[1232] The server then preprocesses the collected data, including normalizing the data, removing invalid data, and performing feature engineering. Specifically, it scales the temperature and humidity values ​​and imputes missing values. This preprocessing allows for efficient processing on a quantum computer.

[1233] Based on the pre-processed data, the server trains the quantum computer, which includes generating a training dataset, encoding the data into qubits, gate operations, and measurement operations, allowing the quantum computer to build an optimized model that can be used to make future predictions.

[1234] The user inputs the requirements for a construction project using a conversational interface on the device. For example, the user might input, "I'm building a commercial building with a budget of 50 million yen, located in a hot and humid region. Please suggest the best cement product." The device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotional state in real time. This emotion data is analyzed along with the user's input data and an emotion tag is attached.

[1235] The generative AI model converts the building project requirements entered by the user into a standard format. For example, the natural language input "hot and humid region" is converted into concrete numerical data. The converted data is then sent from the device to the server.

[1236] The server receives the data and initiates calculations using a quantum computer. The quantum computer uses the trained model to predict the cement product that best suits the user's requirements. This process also takes into account emotional data collected by the emotion engine, fine-tuning the suggestions based on the user's emotional state.

[1237] The calculation results are formatted by the server and converted into an easy-to-understand format. For example, the format is a report that includes the name of the optimal cement product, its characteristics, and the reason for the recommendation. The formatted results are sent to the terminal, which then displays them to the user. An example of a presentation might be, "XYZ cement is ideal for this project. XYZ cement has excellent durability under high temperature and humidity conditions and is also cost-effective."

[1238] The device also uses an emotion engine to analyze the user's real-time reactions. If the user feels reassured, it displays more detailed technical information and additional recommendations. Conversely, if the user feels anxious or suspicious, it provides more concise and reassuring information. This system allows users to efficiently select the optimal cement product, even if they do not have specialized knowledge.

[1239] Example of a text prompt

[1240] "If the construction conditions for a commercial building are hot and humid and the budget is 50 million yen, which cement product would be best?"

[1241] "A user is building a commercial building in a hot and humid region with a budget of ¥50 million. Please suggest the best cement product for these conditions."

[1242] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1243] Processing flow

[1244] Step 1: Data collection

[1245] The server collects construction project data and cement product characteristic data through sensors and APIs.

[1246] Input: Weather data, building specification data, cement property data

[1247] Output: Raw data stored in an internal database

[1248] Specific operation: For example, obtain humidity and temperature data using a weather API, collect real-time environmental data from sensors, and store this in a database.

[1249] Step 2: Data Preprocessing

[1250] The server pre-processes the collected data, which includes data normalization, invalid data removal, and feature engineering.

[1251] Input: Raw data stored in an internal database

[1252] Output: Preprocessed data

[1253] Specific operations: Normalize humidity and temperature values, fill in missing values, and generate new features tailored to the project conditions.

[1254] Step 3: Training the quantum computer

[1255] The server uses the pre-processed data to train the quantum computer.

[1256] Input: Preprocessed dataset

[1257] Output: The trained model

[1258] Specific operations: Encode data into qubits, perform gate operations, and build a model to predict the optimal cement product.

[1259] Step 4: Getting User Input

[1260] The user inputs the requirements for the construction project using an interactive interface on the terminal.

[1261] Inputs: Project location, climate conditions, building use, budget, and other details

[1262] Output: User requirement data parsed on the terminal side

[1263] Specific actions: For example, a user enters, "I am building a commercial building. My budget is $500,000, and it is located in a hot and humid area."

[1264] Step 5: Sentiment Analysis

[1265] The terminal uses an emotion engine to analyze the user's emotional state.

[1266] Input: User voice, facial expressions, and text input

[1267] Output: User requirement data with sentiment tags

[1268] Specific behavior: Analyzes voice tone and facial expressions in real time to assess the user's emotional state.

[1269] Step 6: Data Transformation

[1270] The device uses a generative AI model to convert the building project requirements entered by the user into a standard format.

[1271] Input: User requirement data tagged with emotions

[1272] Output: Data converted to a standard format

[1273] Specific operation: For example, convert the expression "hot and humid" into numerical data.

[1274] Step 7: Predictive calculations

[1275] The server receives the data sent from the device and starts calculations on the quantum computer.

[1276] Input: Data converted to a standard format

[1277] Output: Prediction of optimal cement product

[1278] What it does: Uses a trained model to perform predictive calculations and select the cement product that best suits the user's requirements.

[1279] Step 8: Formatting and presenting the results

[1280] The server formats the prediction results, converts them into an easy-to-understand format, and sends them to the device, which then presents them to the user.

[1281] Input: Predicted results of optimal cement product

[1282] Output: Results in the form of a report to present to the user

[1283] Specific behavior: For example, display the following: "XYZ cement is ideal for this project. XYZ cement is highly durable in hot and humid conditions and is cost-effective."

[1284] Step 9: Regulating Emotional Feedback

[1285] The device uses an emotion engine to analyze the user's real-time reactions and provide more detailed technical information or additional recommendations as needed.

[1286] Input: Real-time user responses

[1287] Output: Tailored information

[1288] What it does: If the user is happy, show them detailed technical information; if they are worried, offer them concise, reassuring information.

[1289] (Application example 2)

[1290] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1291] In today's world, data analysis technology is important for improving the efficiency of construction projects and user satisfaction. However, existing technology does not take into account the user's emotional state when making suggestions, which can lead to a decline in the quality of the user experience. Furthermore, technology for displaying appropriate advertisements based on emotions is also underdeveloped. To solve this problem, a system is needed that analyzes the user's emotional state in real time and provides optimal suggestions and advertisements based on that information.

[1292] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1293] In this invention, the server includes means for collecting data related to the construction project, means for training a quantum computer based on the collected data, means for providing an interactive interface for a user to input requirements for the construction project, means for sending the user's input data to the quantum computer to predict the optimal cement product, means for presenting the prediction result to the user, means for analyzing the user's emotional state using an emotion engine, and means for displaying advertisements based on the emotional state using a generative AI model. This enables optimal suggestions based on the user's emotional state, improving the user experience and maximizing the effectiveness of advertisements.

[1294] "Data relating to the construction project" refers to information relating to the various conditions, environmental factors, material properties, etc. required for the implementation of the construction project.

[1295] A "quantum computer" is a next-generation computer that performs calculations using quantum bits, making it possible to analyze large amounts of data and efficiently solve complex optimization problems.

[1296] "Training" refers to the process of training a quantum computer based on collected data to build a model to achieve a specific goal (e.g., predicting the optimal cement product).

[1297] "Interactive interface" refers to an interface function that allows users to input project requirements and conditions and exchange information in a responsive manner with the system.

[1298] An "emotion engine" refers to technology that analyzes a user's facial expressions, voice, text input, etc. to recognize their emotional state in real time.

[1299] "Generative AI models" refer to artificial intelligence models that convert user-entered information into a standard format, or generate suggestions and advertisements based on emotional states.

[1300] "Means for displaying advertisements" refers to the function for selecting the most appropriate advertisement based on the user's emotional state and displaying it to the user.

[1301] This invention relates to a system that uses a quantum computer, a generative AI model, and an emotion engine to recommend the best cement product for a construction project and display advertisements based on a user's emotional state. The system includes a data collection means, a quantum computer training means, a user interface providing means, a prediction means including an emotion engine, and a presentation means.

[1302] First, the server collects construction project data and cement product characteristic data and stores them in a database. This database includes project conditions such as humidity, temperature, durability, and cost. The collected data is used to train the quantum computer. During this process, the data is preprocessed, specifically, data normalization, invalid data removal, and necessary feature engineering are performed. The server then trains the quantum computer based on the preprocessed data.

[1303] The program implementation uses the following hardware and software:

[1304] Hardware used: smart glasses, camera-equipped devices

[1305] Software used: OpenCV, Keras, emotion engine, generative AI model, quantum computer model

[1306] The device then provides a user interface for users to input their construction project requirements. Through this interface, users input details such as the project's location, climate conditions, building use, and budget. The device also has a built-in emotion engine that recognizes emotions from the user's facial expressions and voice in real time. This emotion data is then analyzed along with the input requirements.

[1307] For example, when a user runs a program using smart glasses, the emotion engine reads the emotion "surprise" from the user's facial expression. At this time, the generative AI model converts the emotion data into a standard format and suggests the most appropriate advertisement. Specifically, if a user inputs, "I'm building a commercial building. My budget is 50 million yen, and it's located in a hot and humid region. Please suggest the best cement product," the emotion engine analyzes the user's emotion, and the generative AI model analyzes the input data and converts it into a standard format. This converted data is sent to a quantum computer, which calculates the best cement product. Based on this result, the emotion data is further taken into account and the most appropriate advertisement is also suggested at the same time.

[1308] An example prompt might look like this:

[1309] Using quantum computing and an emotion engine, it will suggest what kind of ads will be most effective based on the user's current emotions. For example, if a user is feeling surprised, it will show them an ad for the latest gadgets.

[1310] This system not only enables users to efficiently select the most suitable cement product without any specialized knowledge, but also displays advertisements based on their emotional state at the optimal time, which is expected to improve the user experience.

[1311] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1312] Step 1:

[1313] The server collects construction project data and cement product characteristic data and stores it in a database. The input is project conditions such as humidity, temperature, durability, and cost, and the output is the data on these conditions stored in the database. Specifically, data is collected from devices such as sensors and transferred to the database via an API.

[1314] Step 2:

[1315] The server preprocesses the collected data. The input is the collected data, and the output is the preprocessed data. Specifically, it normalizes the data, removes invalid data, and performs feature engineering to prepare it for efficient processing by a quantum computer. For example, it performs missing value imputation and data scaling.

[1316] Step 3:

[1317] The server trains the quantum computer based on the preprocessed data. The input is the preprocessed data, and the output is the trained quantum computer model. Specifically, a quantum algorithm is used to train the model to predict the optimal cement product. This is achieved by sending the training data to the quantum computer and applying an iterative algorithm.

[1318] Step 4:

[1319] The terminal provides a user interface that allows users to input building project requirements. The input is the user's building project requirements, and the output is data transmitted through an interactive interface. Specifically, the terminal provides a GUI, allowing users to input information using forms or voice input.

[1320] Step 5:

[1321] The device uses an emotion engine to analyze the user's emotional state. The input is emotional data such as the user's facial expressions and voice, and the output is the analyzed emotional state. Specifically, facial expressions and voice data are collected using a camera and microphone, and the emotion engine analyzes this. For example, this includes processing to detect smiles and recognize the emotion of "joy."

[1322] Step 6:

[1323] The generative AI model converts emotional data into a standard format and sends it to a quantum computer. The input is the emotional data and building project requirements, and the output is the converted data in a standard format. Specifically, it uses natural language processing technology to convert user requirements into numerical data. For example, it converts "hot and humid region" into specific temperature and humidity values.

[1324] Step 7:

[1325] The quantum computer uses the trained model to calculate the cement product that best suits the user's requirements. The input is data converted into a standard format, and the output is a recommendation for the optimal cement product. Specifically, a quantum algorithm is applied to find the optimal solution and generate the result.

[1326] Step 8:

[1327] The server formats the calculation results and converts them into an easy-to-understand format. The input is the calculation result from the quantum computer, and the output is a formatted recommendation. Specifically, the generative AI model converts the recommendation into an easy-to-understand sentence format. For example, it could express it as "XYZ cement is best for this project."

[1328] Step 9:

[1329] The terminal displays the results to the user. The input is the formatted recommendation, and the output is the information displayed to the user. Specifically, the results are displayed on the screen and visual elements are added to make them easy for the user to understand. For example, this includes displaying graphs of the cement's properties and the reasons for the recommendation.

[1330] Step 10:

[1331] The emotion engine analyzes whether the user feels safe or anxious and provides more detailed or concise information. The input is the user's emotional data, and the output is the detailed or concise information provided. Specifically, if the user feels safe, technical details are displayed, and if the user feels anxious, simple reassuring information is provided.

[1332] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1333] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1334] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1335] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1336] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1337] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1338] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1339] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1340] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1341] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1342] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1343] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1344] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1345] 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.

[1346] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1347] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1348] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1349] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1350] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1351] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1352] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1353] The following is further disclosed regarding the above embodiment.

[1354] (Claim 1)

[1355] a means of collecting data on building projects;

[1356] a means for training a quantum computer based on the collected data; and

[1357] means for providing an interactive interface for a user to input requirements for a building project;

[1358] A means to send user input data to a quantum computer to predict the optimal cement product;

[1359] The system includes a means for presenting the prediction results to a user.

[1360] (Claim 2)

[1361] 10. The system of claim 1, wherein the training model for predicting optimal cement products using a quantum computer is designed for evaluating cement product performance in a built environment.

[1362] (Claim 3)

[1363] 10. The system of claim 1, further comprising means for converting user-entered building project requirements into a standard format using a generative AI model.

[1364] "Example 1"

[1365] (Claim 1)

[1366] a means of gathering information about building projects;

[1367] means for training a quantum computer based on the collected data;

[1368] means for providing an interactive interface for a user to input building project requirements;

[1369] a means for converting user-entered building project requirements into a standard format using a generative AI model; and

[1370] A means to send user input data to a quantum computer and predict the optimal building material product;

[1371] The system includes a means for presenting the prediction results to a user.

[1372] (Claim 2)

[1373] The system of claim 1, wherein the training model for predicting optimal building material products using a quantum computer is designed to evaluate the performance of building material products in a building environment.

[1374] (Claim 3)

[1375] 10. The system of claim 1, further comprising means for converting user-entered building project requirements into a standard format using a generative AI model.

[1376] "Application Example 1"

[1377] (Claim 1)

[1378] a means of collecting data on building projects;

[1379] a means for training a quantum computer based on the collected data; and

[1380] means for providing an interactive interface for a user to input requirements for a building project;

[1381] A means to send user input data to a quantum computer to predict the optimal cement product;

[1382] A means for presenting the prediction results to a user;

[1383] a means for collecting data relating to inventory management at the distribution center;

[1384] A means to convert collected inventory data into a standard format using a generative AI model; and

[1385] A quantum computer can be used to calculate optimal inventory management strategies.

[1386] The system includes a means for presenting optimal inventory management strategies to a user.

[1387] (Claim 2)

[1388] 10. The system of claim 1, wherein the quantum computer-generated training model for predicting optimal cement products is designed to evaluate cement product performance in a building environment and further to evaluate inventory management strategies in a logistics center.

[1389] (Claim 3)

[1390] 2. The system of claim 1, further comprising: means for converting user-entered construction project requirements into a standard format using a generative AI model; and means for converting logistics center inventory management data into the standard format.

[1391] "Example 2: Combining Emotion Engines"

[1392] (Claim 1)

[1393] a means of collecting data on building projects;

[1394] means for pre-processing the collected data;

[1395] means for training a quantum computer based on the preprocessed data; and

[1396] A means of using a trained quantum computer to predict the cement product that best suits a user's requirements; and

[1397] means for providing an interactive interface for a user to input requirements for a building project;

[1398] A means of analyzing the user's emotional state using an emotion engine and fine-tuning the content of suggestions;

[1399] A means of converting user-entered building project requirements into a standard format using a generative AI model; and

[1400] The system includes a means for presenting the prediction results to a user.

[1401] (Claim 2)

[1402] 10. The system of claim 1, wherein the training model for predicting optimal cement products using a quantum computer is designed for evaluating cement product performance in a built environment.

[1403] (Claim 3)

[1404] 10. The system of claim 1, further comprising means for providing information based on the emotional state of the user by taking into account the emotional data collected by the emotion engine.

[1405] "Application example 2 when combining emotion engines"

[1406] (Claim 1)

[1407] a means of collecting data on building projects;

[1408] a means for training a quantum computer based on the collected data; and

[1409] means for providing an interactive interface for a user to input requirements for a building project;

[1410] A means to send user input data to a quantum computer to predict the optimal cement product;

[1411] A means for presenting the prediction results to a user;

[1412] means for analyzing the emotional state of a user using an emotion engine;

[1413] A system including means for displaying advertisements based on emotional states using a generative AI model.

[1414] (Claim 2)

[1415] 10. The system of claim 1, wherein the training model for predicting optimal cement products using a quantum computer is designed for evaluating cement product performance in a built environment.

[1416] (Claim 3)

[1417] 10. The system of claim 1, further comprising means for converting advertisements based on a user's emotional state into a standard format using a generative AI model. [Explanation of symbols]

[1418] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data on building projects; a means for training a quantum computer based on the collected data; and means for providing an interactive interface for a user to input requirements for a building project; A means to send user input data to a quantum computer to predict the optimal cement product; The system includes a means for presenting the prediction results to a user.

2. The system of claim 1 , wherein the training model for predicting optimal cement products using a quantum computer is designed to evaluate the performance of cement products in a built environment.

3. 10. The system of claim 1, further comprising means for converting user-entered building project requirements into a standard format using a generative AI model.

Images