system

Abstract

Provide a system. A means for inputting information on the location of the property and installation conditions; means for preprocessing the input information and converting it into a required format; a generating artificial intelligence-based means for automatically generating design drawings of a base station using the pre-processed data; means for reviewing and modifying said automatically generated design drawings; A means for storing and sharing the final design drawings with stakeholders; A system including:

Description

[Technical Field]

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

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

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

[0004] In the design of base stations, there is a problem that designers have to manually create drawings due to the wide variety of properties and installation conditions. This has led to a demand for improved design efficiency and accuracy. Furthermore, efficient review and revision of drawings is difficult, and the lack of prompt information sharing among stakeholders leads to project delays. The present invention aims to solve these problems and improve the efficiency and accuracy of base station drawing creation. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting information on the location and installation conditions of a property, a means for preprocessing the input information and converting it into a required format, a means based on artificial intelligence for automatically generating design drawings of a base station using the preprocessed data, a means for reviewing and correcting the automatically generated design drawings, and a means for saving and sharing the final design drawings with relevant parties. This significantly reduces the designer's manual work and enables efficient and accurate drawing creation. Furthermore, since designers can quickly review and correct the drawings, information can be shared smoothly with relevant parties, preventing project delays.

[0006] ---

[0007] "Property location" refers to the address and latitude and longitude information of the specific location where a base station is to be installed, and is information used to identify the exact installation location.

[0008] "Installation conditions" refers to specific requirements and restrictions regarding the installation of base stations, including height restrictions, the influence of surrounding buildings and structures, and factors that may interfere with radio waves.

[0009] "Preprocessing" refers to the process of analyzing and converting raw data input by the user and preparing it into the format required for processing by the generative AI.

[0010] "Generative AI" refers to AI that automatically generates base station design drawings based on input data, and operates by taking into account past design data and current installation conditions.

[0011] "Means for automatically generating design drawings" refers to the process and function by which the generative artificial intelligence automatically creates design drawings for base stations based on data.

[0012] "Means for reviewing and correcting" refers to a function that allows a designer to check the generated design drawings and manually make any necessary corrections.

[0013] "Means for storage and sharing with stakeholders" refers to the ability to store the final design drawings in a database and efficiently share them with other members and teams involved in the project.

[0014] "Latitude and longitude" is coordinate information that indicates a specific location on Earth and is used to indicate the exact location of a base station.

[0015] "Input form" refers to the interface that allows users to input information about the property location and installation conditions into the system.

[0016] "Height restriction" refers to the maximum height permitted for a property or installation location, and refers to the restriction that installation at a height greater than this is not permitted. [Brief explanation of the drawings]

[0017] [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 illustrating 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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] ---

[0039] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, pre-processing, creating drawings using generation AI, reviewing and correcting the drawings, and saving and sharing the final drawings.

[0040] Program processing explanation

[0041] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[0042] 1. Acquiring input information

[0043] The user enters information about the property location and installation conditions into the system's input form, such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings."

[0044] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[0045] 2. Preprocessing of input data

[0046] The server calls an external navigation API to convert address information to latitude and longitude, and also normalizes numeric data (such as height restrictions) and converts it into the appropriate format for internal processing. For example, it converts "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E".

[0047] Once preprocessed, the data is tagged and sent to the next generation step.

[0048] 3. Drawing generation using generative AI

[0049] The server runs a generative artificial intelligence (generative AI) using the pre-processed data.

[0050] The AI ​​automatically generates base station design drawings based on past design data and current installation conditions, for example, taking into account neighboring buildings and determining the optimal antenna placement.

[0051] The generated design drawings are stored on the server.

[0052] 4. Review and revise drawings

[0053] The terminal (designer) receives the generated drawings and performs a detailed review, adding comments to the drawings and manually making specific modifications, such as adjusting the antenna direction or reflecting design changes.

[0054] The revised design drawings are sent back to the server and saved as the final version.

[0055] 5. Save and share your final drawing

[0056] The server stores the final design drawings in a database, while simultaneously recording the design change history for future review.

[0057] The server generates a shared link for the saved design drawings to be shared with the relevant parties and notifies the members involved in the project, allowing the installation team to quickly receive the latest design drawings.

[0058] Specific examples

[0059] Consider the installation of a new base station in an urban area:

[0060] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[0061] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[0062] 3. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[0063] 4. The terminal (designer) reviews the generated drawing and makes any necessary adjustments, such as fine-tuning the antenna direction.

[0064] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[0065] Through this process, the creation of drawings for base station installation is made more efficient and the amount of manual work required by designers is reduced, enabling the entire project, from design to installation, to proceed quickly and accurately.

[0066] The processing flow will be explained below.

[0067] ---

[0068] Step 1:

[0069] The user enters the property location (e.g., "Shibuya-ku, Tokyo") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure accurate and complete data is entered.

[0070] Step 2:

[0071] The server receives the data sent by the user, including address information, numerical data, installation conditions, etc. The server temporarily stores the received data and prepares it for the next process.

[0072] Step 3:

[0073] The server calls the navigation API to convert address information into latitude and longitude. For example, "Shibuya-ku, Tokyo" becomes "35.6895° N, 139.6917° E." It also standardizes numerical data such as height restrictions for internal use.

[0074] Step 4:

[0075] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0076] Step 5:

[0077] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0078] Step 6:

[0079] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[0080] Step 7:

[0081] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0082] Step 8:

[0083] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[0084] Step 9:

[0085] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0086] This is the specific process flow from creating base station design drawings to final sharing, which significantly improves the efficiency and accuracy of the design process.

[0087] Example 1

[0088] 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."

[0089] Designing base stations requires a lot of data processing and manual work, which increases time and costs. Furthermore, the accuracy and consistency of design drawings can be compromised by human error. Furthermore, if information is not shared smoothly among stakeholders, the progress of the entire project can be delayed. The present invention aims to solve these problems and improve the efficiency and accuracy of base station design.

[0090] 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.

[0091] In this invention, the server includes a means for inputting information on the location and installation conditions of the property, a means for preprocessing the input information and converting it into a required format, a means for automatically generating design drawings of the base station based on a generative model using the preprocessed data, a means for a designer to review and correct the generated design drawings, and a means for saving the final design drawings in a database and generating a sharing link for related parties, thereby automating the base station design process, improving overall efficiency, and maintaining the accuracy and consistency of the design drawings.

[0092] "Property Location" refers to the specific geographic location information for installing a base station.

[0093] "Installation Conditions" refers to the physical, legal and environmental constraints and requirements when installing a base station.

[0094] "Preprocessing" refers to a series of data processing steps that convert the information entered by the user into a format that is easy for the system to use.

[0095] A "generative model" refers to an algorithm or program that uses artificial intelligence technology to automatically generate base station design drawings.

[0096] "Design Drawings" means drawings showing the physical layout, structure, and technical details of a Base Station.

[0097] "Review" refers to the process in which a designer reviews the generated design drawings and makes appropriate corrections.

[0098] "Saving" refers to the act of recording the generated design drawings and their change history in a database.

[0099] A "shared link" refers to the URL or access method for sharing design drawings online with relevant parties.

[0100] The system of the present invention automates and streamlines the creation of base station design drawings. This system functions through a series of processes: inputting the property location and installation conditions, preprocessing the input data, generating drawings using AI, reviewing and correcting the drawings, and saving and sharing the final drawings. Specific embodiments are described in detail below.

[0101] 1. Acquiring input information

[0102] The user enters information about the property location and installation conditions into the system's input form. The input includes specific data such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings." This allows the user to communicate the planned installation location and conditions to the system. The input information is sent to the server.

[0103] 2. Preprocessing of input data

[0104] The server preprocesses the received input data. This preprocessing includes converting address information to latitude and longitude using an external navigation API (e.g., converting "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E") and standardizing numerical data (e.g., height restrictions). Specifically, Google® Maps API is used. After preprocessing, the data is tagged and sent to the next generation step.

[0105] 3. Drawing generation using generative AI

[0106] The server runs a generation AI using the preprocessed data. The generation AI automatically generates base station design drawings based on past design data and current installation conditions. For example, a prompt such as "Please create a design drawing for a base station at 35.6895° N, 139.6917° E. The height limit is 50m, and information on nearby buildings is as follows" is used. Based on this information, the generation AI determines the optimal antenna placement and generates the associated design drawings. The generated design drawings are stored on the server.

[0107] 4. Review and revise drawings

[0108] The terminal (designer) receives the generated drawings from the server and performs a detailed review. The designer can add comments to the drawings or manually make specific modifications. For example, they can adjust the direction of the antenna or reflect changes in the design. The modified design drawings are then sent back to the server and saved as the final version.

[0109] 5. Save and share your final drawing

[0110] The server saves the final design drawings to a database, simultaneously recording the design change history for future review. It also generates a shared link for sharing the saved design drawings with stakeholders and notifies all project members, allowing the installation team to quickly receive the latest design drawings.

[0111] Specific examples

[0112] Consider the installation of a new base station in an urban area. Here's what happens:

[0113] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[0114] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[0115] 3. Generative AI automatically creates a base station design based on the input data. This design is optimized taking into account the surrounding location conditions.

[0116] 4. The device (designer) reviews the generated drawings and makes any necessary adjustments, such as fine-tuning the antenna direction.

[0117] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[0118] Through this series of processes, the present invention significantly improves the efficiency of base station design, enabling the entire project to proceed quickly and accurately.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Program processing flow

[0121] Step 1: Obtaining input information

[0122] The user accesses the system's input form and enters the property location (Shibuya-ku, Tokyo) and installation conditions such as a height limit of 50m and the location and height of surrounding buildings.

[0123] Input: Property location information, and specific numbers and ratios for installation conditions

[0124] The server receives the information obtained from the input form.

[0125] Output: Received input data

[0126] Specific behavior: When a user clicks the "Submit" button on an input form, the information is sent to the server.

[0127] Step 2: Preprocessing input data

[0128] The server uses the Google Maps API to convert the received data into geographic information (e.g., "Shibuya-ku, Tokyo") into latitude and longitude coordinates of "35.6895° N, 139.6917° E."

[0129] Input: Address information and numeric data (e.g. height restrictions)

[0130] Data processing: Address information is converted to latitude and longitude using the navigation API, and the numerical data is standardized.

[0131] Output: Preprocessed latitude and longitude information and standardized numerical data

[0132] Specific operation: Calls the Google Maps API, converts address information into latitude and longitude, and standardizes the unit of numeric data to meters.

[0133] Step 3: Generate drawings using generative AI

[0134] The server runs a generative AI model based on the pre-processed data.

[0135] Input: Latitude and longitude information, standardized height restrictions, etc.

[0136] Data calculation: Generative AI automatically generates base station design drawings based on past design data and current installation conditions.

[0137] Output: Generated base station design drawings

[0138] Specific operation: A prompt is input into the generation AI, and the AI ​​generates the drawing based on instructions such as, "Please create a design drawing for a base station located at 35.6895° N, 139.6917° E. The height limit is 50m, and the nearby buildings are as follows: Building 1, Building 2. Please determine the optimal antenna placement taking into account the surrounding environment."

[0139] Step 4: Review and revise the drawing

[0140] The terminal (designer) accesses and reviews the design drawings sent from the server.

[0141] Input: Generated design drawings

[0142] Data processing: review and manual corrections as needed

[0143] Output: Revised final design drawings

[0144] Specific operations: The designer adds comments to the drawing, adjusts the direction and height of the antenna, and resends the revised drawing to the server.

[0145] Step 5: Save and share your final drawing

[0146] The server stores the final design drawings in a database.

[0147] Input: Revised final design drawings

[0148] Data storage: The final design drawings and change history are recorded in a database.

[0149] Output: Link for sharing

[0150] Specific operation: The design drawings are saved in a database, a shared link is generated to notify relevant parties, and the link is notified to project members.

[0151] Through the above processing steps, a series of processes from creating base station design drawings to sharing them can be efficiently carried out.

[0152] (Application example 1)

[0153] 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."

[0154] Conventional factory robot installation and workflow design requires a great deal of time and effort, and is often inefficient because it depends heavily on the skill level of the designer. Furthermore, creating and modifying blueprints and workflows is time-consuming, making it difficult to achieve optimal robot placement and workflows. To solve these problems, a system is needed that can efficiently and automatically create robot installation plans and workflows based on input information.

[0155] 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.

[0156] In this invention, the server includes a means for inputting information on the location of the property and installation conditions, a means for preprocessing the input information and converting it into a required format, a means based on artificial intelligence for automatically generating design drawings and workflows using the preprocessed data, a means for reviewing and modifying the automatically generated design drawings and workflows, and a means for saving and sharing the final design drawings and workflows with relevant parties. This allows users to efficiently create and modify robot installation plans and workflows and quickly share optimized design drawings.

[0157] - "Property Location" refers to the geographic location where a particular property is located.

[0158] "Installation conditions" refers to information about the various conditions and restrictions regarding installation at the property.

[0159] "Preprocessing" is the process of converting input information into an appropriate format and preparing the data for use in the next processing step.

[0160] "Generative AI" is an AI technology that automatically generates design drawings and workflows based on past data and current conditions.

[0161] "Design drawings" are detailed drawing information regarding the layout and installation of properties and equipment.

[0162] A "work flow" is a flow diagram showing specific work procedures and processes, along with detailed step information.

[0163] "Review" is the process of checking the generated design drawings and work flow and making any necessary corrections or additions.

[0164] "Final version" refers to the final version of the design drawings and work flow that has been finalized after all revisions and reviews have been completed.

[0165] "Storage" is the process of recording the created and modified design drawings and work flows in a database or storage.

[0166] "Sharing" is the process of coordinating and making accessible the design drawings and workflows created by stakeholders.

[0167] The present invention provides a system for efficiently and automatically generating installation plans and work flows for factory robots. Below, we will explain in detail each of the main processes from the perspectives of the server, terminal, and user.

[0168] System Overview

[0169] The main elements of the system consist of a means for inputting information on the property location and installation conditions, a means for pre-processing, a means for generating design drawings and workflows using generative artificial intelligence, a means for reviewing and correcting, and a means for saving and sharing the final design drawings and workflows.

[0170] Hardware and Software Configuration

[0171] Hardware:

[0172] Server: Cloud server (e.g., AWS (registered trademark) EC2)

[0173] Device: Smartphone

[0174] software:

[0175] Server side: Django (backend framework), PyTorch, TENSORFLOW (registered trademark) (generative AI model)

[0176] Client side: React Native (cross-platform mobile development framework)

[0177] Data storage: AWS S3 (storage), AWS RDS (relational database)

[0178] Program processing explanation

[0179] 1. Obtaining input information:

[0180] Users use a smartphone app to input the layout and installation conditions of specific areas within the factory, such as "warehouse section A," "transport line layout," and "safety zone settings."

[0181] The server receives these input data and performs immediate validation.

[0182] 2. Preprocessing the input data:

[0183] The server converts the input data into an appropriate format and standardizes it as internal data. For example, it converts area information into a specific coordinate system and processes installation conditions as numerical data.

[0184] 3. Generative AI for blueprint and workflow generation:

[0185] The server uses the preprocessed data to launch generative artificial intelligence (generative AI) to generate optimal layouts and workflows for factory robots. The generated design drawings and workflows are stored on the server.

[0186] 4. Review and revise blueprints and workflows:

[0187] The user can check the design drawings and workflow generated on their smartphone and make any necessary corrections, for example by changing the robot's position on the smartphone screen using drag and drop, and then send the corrected data to the server.

[0188] 5. Save and share your final design and workflow:

[0189] The server stores the final design drawings and workflow in a database and generates a shared link for stakeholders, allowing the installation team to quickly receive the latest design drawings and workflow.

[0190] Specific examples

[0191] For example, a user inputs "warehouse section A," "transport line layout," and "safety zone settings," and the server receives the request. The server converts "warehouse section A" into coordinate system information (35.6895°N, 139.6917°E), and the generation AI creates and proposes the optimal robot layout and work flow. The user fine-tunes the layout on their smartphone, and once finalized, it is sent to the server. The server saves the final design, generates a link, and notifies relevant parties.

[0192] Prompt Sentence Examples

[0193] Input data:

[0194] Facility Layout: Warehouse Section A

[0195] Installation conditions: Layout of conveying lines, setting of safety zones

[0196] Requests for Generative AI:

[0197] Using the layout information for Warehouse Section A, generate the optimal robot placement and transport line work flow. Establish the most efficient placement while taking safety zones into consideration.

[0198] Example output:

[0199] Robot 1: Transfer point A -> B

[0200] Robot 2: Transfer point C -> D"

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Processing Steps

[0203] Step 1: Obtaining input information

[0204] (explanation)

[0205] The user uses the smartphone app's input form to input specific sections within the factory and installation conditions, such as "warehouse section A," "transport line layout," and "safety zone settings."

[0206] (input)

[0207] Information on property location and installation conditions.

[0208] (output)

[0209] User-entered data sent to the server.

[0210] (operation)

[0211] The user inputs "warehouse section A," "transport line layout," and "safety zone settings" on their smartphone.

[0212] Sends input data to the server.

[0213] Step 2: Preprocessing the input data

[0214] (explanation)

[0215] The server preprocesses the received data and converts it into the required format, for example converting address information into coordinate data and installation conditions into standardized numerical data.

[0216] (input)

[0217] Information on property location and installation conditions sent by the user.

[0218] (output)

[0219] Preprocessed data (e.g., coordinate data, standardized numerical data).

[0220] (operation)

[0221] The server converts the address information to "(35.6895° N, 139.6917° E)".

[0222] Height restrictions and other installation conditions are standardized as numerical data.

[0223] Step 3: Generative AI creates blueprints and workflows

[0224] (explanation)

[0225] The server uses the pre-processed data to automatically generate blueprints and workflows using generative AI models.

[0226] (input)

[0227] Preprocessed data (coordinate and numerical data).

[0228] (output)

[0229] Generated blueprints and work flows.

[0230] (operation)

[0231] The server inputs the preprocessed data into the generative AI model.

[0232] Generative AI generates optimal placement and work flow for factory robots, and outputs blueprints and flow.

[0233] The generated data is stored on the server.

[0234] Step 4: Review and revise the design and workflow

[0235] (explanation)

[0236] The user can check the generated design drawings and workflow on their smartphone and make corrections as necessary.

[0237] (input)

[0238] Generated blueprints and work flows.

[0239] (output)

[0240] User-modified blueprints and workflows.

[0241] (operation)

[0242] Users can check the blueprints on their smartphone screens.

[0243] Modify the robot position and workflow as needed with drag and drop.

[0244] Resubmit the revised blueprint to the server.

[0245] Step 5: Save and share your final design and workflow

[0246] (explanation)

[0247] The server stores the final design drawings and workflows modified by the user in a database and generates a sharing link for the relevant parties.

[0248] (input)

[0249] User-modified blueprints and workflows.

[0250] (output)

[0251] Saved final design and workflow, shareable links.

[0252] (operation)

[0253] The server stores the final version of the data in the database.

[0254] Generate a shared link and notify relevant parties via email, etc.

[0255] 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.

[0256] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, preprocessing, creating drawings using generative AI, reviewing and correcting the drawings, saving and sharing the final drawings, and even including an emotion engine that recognizes the user's emotions, thereby adjusting the user interface.

[0257] Program processing explanation

[0258] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[0259] 1. Acquiring input information

[0260] The user enters information about the property location and installation conditions into the system's input form, such as "City A," "height limit 50m," and "location and height of surrounding buildings."

[0261] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[0262] 2. Starting Emotion Recognition

[0263] The server analyzes the user's behavior and input while using the input form and activates the emotion engine in real time, which analyzes the data to identify the user's emotions, such as stress or frustration.

[0264] 3. Preprocessing of input data

[0265] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[0266] 4. Tagging preprocessed data

[0267] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0268] 5. Drawing generation using generative AI

[0269] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0270] The generated design drawings are stored on the server.

[0271] 6. Review and revise drawings

[0272] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0273] 7. Emotion-Based User Interface Adjustment

[0274] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance.

[0275] If necessary, generate and display appropriate feedback messages to the user.

[0276] 8. Save and share your final drawing

[0277] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[0278] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0279] Specific examples

[0280] Consider the installation of a new base station in an urban area:

[0281] 1. The user inputs "City A," "Height limit 50m," and "Information about surrounding buildings."

[0282] 2. The server receives this data, converts the address to latitude and longitude (35.0000° N, 135.0000° E), and standardizes the height restriction as numeric data.

[0283] 3. The server analyzes the user's input behavior and delays and uses an emotion engine to determine whether the user is feeling frustrated. For example, if the user repeatedly tries to enter something, it determines that frustration is increasing.

[0284] 4. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[0285] 5. The designer reviews the generated drawings, performs detailed checks, and makes fine adjustments as needed.

[0286] 6. If the emotion engine identifies frustration, the server adjusts the user interface to display an operation guide, clearly showing the user the operation procedure, and displays appropriate feedback messages to support the user.

[0287] 7. The server shares the final design drawings with stakeholders, ensuring the installation team can start work quickly and with the most up-to-date information.

[0288] The above process streamlines the process of creating base station design drawings and improves the user experience, reducing the manual work required by designers and enabling user feedback, facilitating the overall progress of the project.

[0289] The processing flow will be explained below.

[0290] ---

[0291] Step 1:

[0292] The user enters the property location (e.g., "City A") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure that accurate and complete data is entered.

[0293] Step 2:

[0294] The server receives the data sent by the user. This includes information such as address information ("City A") and installation conditions ("Height limit 50m"). The received data is temporarily saved and prepared for the next process.

[0295] Step 3:

[0296] The server runs an emotion engine to analyze the user's input behavior and identify the user's emotions (e.g., stress or frustration) through specific input patterns (e.g., repeated inputs, delayed inputs, etc.).

[0297] Step 4:

[0298] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[0299] Step 5:

[0300] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0301] Step 6:

[0302] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0303] Step 7:

[0304] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[0305] Step 8:

[0306] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0307] Step 9:

[0308] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance. It also generates and displays appropriate feedback messages to the user.

[0309] Step 10:

[0310] The terminal (designer) uploads the revised design drawing back to the server, which saves the uploaded drawing as the final version and also keeps a revision history.

[0311] Step 11:

[0312] The server saves the final design drawings to a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0313] These are the specific processing steps of the base station design drawing creation system that combines an emotion engine. This enables interface adjustments according to the user's emotions and efficient drawing creation, facilitating the overall progress of the project.

[0314] Example 2

[0315] 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."

[0316] The traditional process of creating base station design drawings involves a lot of manual work, making it inefficient and time-consuming. There is also a lack of mechanisms to address the stress and frustration felt by users during the input process, which hinders the overall user experience. Furthermore, there are sometimes delays in sharing design drawings with stakeholders, which can impact project progress.

[0317] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for inputting information on the property location and installation conditions; means for preprocessing the input information and converting it into a required format; means based on a generation artificial intelligence for automatically generating design drawings of a base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving and sharing the automatically generated design drawings with relevant parties; and means based on an emotion engine for recognizing user emotions and adjusting the user interface. This automates and streamlines the process of creating base station design drawings, enables interface adjustment according to the user's emotions, and improves the overall operating experience. Furthermore, it enables rapid sharing of design drawings, facilitating project progress.

[0318] "Property location" is information about the specific geographical location where the base station is installed.

[0319] "Installation conditions" refer to restrictions and requirements for installing a base station, including, for example, height restrictions and the layout of surrounding buildings.

[0320] "Preprocessing" refers to converting input information into an appropriate format, including converting addresses to latitude and longitude coordinates and standardizing numeric data.

[0321] "Generative AI" refers to artificial intelligence technology that automatically generates base station design drawings based on input data.

[0322] An "emotion engine" refers to a system that analyzes a user's behavior and input content to identify the user's emotional state in real time.

[0323] "Design drawings" are drawings that show the specific installation location and structure of the base station, and are automatically generated by a generative AI model.

[0324] "User interface" refers to the screens and operating means that provide interaction for the user to interact with the system.

[0325] "Preprocessed data" refers to data where input information has been converted into an appropriate format and tagged.

[0326] "Tagging" refers to the process of adding classification information and metadata to data to organize it.

[0327] "Review and correction" refers to the process in which a designer checks the generated design drawings and makes fine adjustments as necessary.

[0328] "Storage and sharing" refers to the process in which the final design drawings are stored on a server and provided to stakeholders in the form of a link or similar.

[0329] This invention is a system that automates and streamlines the creation of base station design drawings. The system uses a generative AI model to generate drawings after the user inputs information about the property location and installation conditions, and the server performs preprocessing. The system also provides functions for reviewing and modifying the drawings, as well as saving and sharing the final drawings. Furthermore, the system includes an emotion engine that recognizes the user's emotions and adjusts the user interface accordingly.

[0330] To implement this system, the following hardware and software are used.

[0331] 1. Hardware and software configuration:

[0332] A server is a computer equipped with a high-performance processor and a large amount of memory, and processes and calculates data.

[0333] The terminal is a personal computer or mobile device operated by a designer or user to display and modify drawings.

[0334] The generative AI model is a cloud-based system on which generative AI software (e.g., AutoCAD's AI functions) is installed.

[0335] The emotion engine is a machine learning model for analyzing user input behavior and is implemented on the server.

[0336] 2. Data processing and calculation procedures:

[0337] Users use the system's web interface or mobile app to input information about the property location and installation conditions, including data such as "City A," "50m height limit," and "location and height of surrounding buildings."

[0338] The server receives this input data and performs some basic validation. For example, for City A, it calls a navigation API (e.g., Google Maps API) to convert the address into latitude and longitude (35.0000° N, 135.0000° E). ​​It also standardizes numerical data such as height restrictions into a unified format.

[0339] The emotion engine analyzes the user's input speed, number of corrections, etc. in real time to determine whether the user is feeling stressed or frustrated.

[0340] 3. How generative AI models work:

[0341] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[0342] The generated design drawings are stored in the server's database.

[0343] 4. Review and revise drawings:

[0344] The terminal (designer) displays the generated design drawing and checks and modifies the details. For example, the designer uses design software such as AutoCAD to fine-tune the direction and height of the antenna.

[0345] 5. Save and Share:

[0346] The server saves the final version of the design drawings revised by the designer in a database and generates a sharing link for the relevant parties, which is automatically sent via email to the members involved in the project.

[0347] Examples of specific prompts include:

[0348] "Enter an address in City A and set the height limit to 50m."

[0349] "Enter the location and height of surrounding buildings and generate the optimal design drawing for your base station."

[0350] "Check the antenna placement in the automatically generated design drawing and correct it if necessary."

[0351] The above is an embodiment of the present invention, which not only automates the process of creating base station design drawings, but also improves the user's operation experience.

[0352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0353] Step 1:

[0354] Obtaining input information

[0355] The user enters information about the property location and installation conditions into the system's input form, providing data such as "City A," "height limit of 50m," and "location and height of surrounding buildings."

[0356] The server receives the data entered by the user, stores it in the system, and performs basic data integrity checks (e.g., checking the format of numbers).

[0357] Output: Verified property location and installation information.

[0358] Step 2:

[0359] Starting emotion recognition

[0360] The server collects real-time data while the user is using the input form, specifically analyzing the user's emotional state based on input speed, number of corrections, frequency of typing errors, etc.

[0361] For example, if a series of typing errors occur, the server determines that the user is irritated and updates the emotional status.

[0362] Output: Real-time emotional status information.

[0363] Step 3:

[0364] Preprocessing of input data

[0365] The server calls a navigation API (e.g., Google Maps API) to convert the property address into latitude and longitude. As a result, "City A" is obtained as "35.0000° N, 135.0000° E."

[0366] The server standardizes numerical data such as height restrictions and converts them into a unified format internally.

[0367] Output: Geographic information converted to latitude and longitude and standardized height restriction information.

[0368] Step 4:

[0369] Tagging preprocessed data

[0370] The server then tags the preprocessed data with metadata, adding tags such as "urban area," "office building," and "50m height limit." This tagging organizes the data and allows the generative AI model to process it efficiently.

[0371] Output: Tagged preprocessed data.

[0372] Step 5:

[0373] Drawing generation using generative AI

[0374] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[0375] The server stores the generated design drawings in a database.

[0376] Output: Auto-generated engineering drawings.

[0377] Step 6:

[0378] Drawing review and revision

[0379] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes fine adjustments using design software such as AutoCAD. For example, they may make slight changes to the direction or placement of the antenna.

[0380] The terminal (designer) uploads the revised design drawing back to the server.

[0381] Output: Modified engineering drawings.

[0382] Step 7:

[0383] Emotion-Based User Interface Adjustment

[0384] The server adjusts the user interface in real time based on the user's emotional status recognized by the emotion engine. For example, if the user is feeling frustrated, it may pop up an operation guide or enhance input assistance functions.

[0385] The server displays an appropriate feedback message (e.g., "Thank you for your input. Is there anything we can help you with?") in the user interface.

[0386] Output: Tailored user interface and feedback messages.

[0387] Step 8:

[0388] Save and share your final drawing

[0389] The terminal (designer) uploads the revised design drawing to the server, which saves the uploaded drawing as the final version and stores it in the database along with the revision history.

[0390] The server generates a shared link for the final design drawing and sends an automatic email notification to stakeholders, allowing them to access the latest version of the drawing.

[0391] Output: Final design drawings saved and shared links.

[0392] (Application example 2)

[0393] 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."

[0394] The process of creating factory design drawings involves a lot of manual work, which requires time and effort. Furthermore, the design process is carried out without consideration of the user's emotions and stress levels, which can result in a poor user experience and hinder productivity. Furthermore, it is difficult to automatically determine the optimal layout of robot movement paths and work stations within the factory.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information on the location and installation conditions of the property; means for preprocessing the input information and converting it into a required format; means based on generative artificial intelligence for automatically generating design drawings of the base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving the final design drawings and sharing them with relevant parties; and means for recognizing user emotions and adjusting the user interface. This enables the automatic generation and correction of design drawings to be performed efficiently, and operation guides and feedback according to the user's emotions to be provided, thereby improving the user experience and increasing productivity.

[0396] "Property location" refers to the location of the new production line within a particular factory.

[0397] "Installation conditions" refers to factors that indicate the installation environment, such as layout restrictions within the factory, equipment size, traffic flow and altitude restrictions.

[0398] "Input means" refers to a mechanism that provides an interface for users to input the property location and installation conditions.

[0399] The "preprocessing means" is a mechanism for standardizing input information and converting it into latitude and longitude coordinates and numerical data.

[0400] "Generative AI" is an AI technology that uses algorithms and programs to automatically generate optimal design drawings based on past design data and current installation conditions.

[0401] "Review and correction means" refers to functions and interfaces for checking the generated design drawings and making corrections as necessary.

[0402] "Storage and sharing means" is a mechanism for storing the final design drawings in a database and generating a sharing link for relevant parties.

[0403] "Means for recognizing user emotions" refers to technology that analyzes emotions such as stress and frustration based on the user's input behavior and data.

[0404] The "user interface adjustment means" is a mechanism that displays operation guides and feedback messages according to the recognized user emotions, thereby improving the operation experience.

[0405] The "tagging means" is a function for assigning tags to preprocessed data and organizing the data efficiently.

[0406] The "latitude and longitude conversion means" is a function for converting address information of a property location into latitude and longitude.

[0407] The "numerical value conversion means" is a function for converting conditions such as height restrictions into numerical data.

[0408] This invention is a system that automatically generates optimal design drawings for new production lines in factories and adjusts the interface based on the user's emotions. This system operates by combining a server, user terminals, and various software.

[0409] The server first receives information on the property location and installation conditions entered by the user in real time. The user inputs the factory layout, equipment size, constraints, etc. via their terminal. The server also analyzes the user's behavior while entering data and recognizes the user's stress and frustration in real time through an emotion engine. This improves the user experience.

[0410] The server then preprocesses the input data, converting address information into latitude and longitude using a navigation API (e.g., Google Maps API) and standardizing numerical data such as height restrictions. The preprocessed data is also tagged with terms such as "semiconductor manufacturing equipment" and "transport robot," allowing the generative AI to efficiently generate blueprints.

[0411] A generative AI model (e.g., OpenAI's GPT-4) automatically generates optimal design drawings based on past production line design data and current installation conditions. These generated design drawings are stored on a server and can be accessed by designers for modification and review. Designers can also check the generated drawings in detail and make modifications as necessary.

[0412] The server generates a link to share the final design drawings with all stakeholders. This link is provided to all members involved in the project, enabling them to work quickly and with the latest information.

[0413] As a specific example, consider the case where the user inputs the following conditions:

[0414] Factory size: 500 square meters

[0415] Device size: 2 meters x 3 meters

[0416] Restricting robot movement

[0417] Height limit: 3 meters

[0418] An example of a prompt is:

[0419] New production line design requirements:

[0420] Factory size: 500 square meters

[0421] Equipment size: 2 meters x 3 meters

[0422] Restricting robot movement

[0423] Height limit: 3 meters

[0424] Next, a helpful message is displayed to reduce the user's stress.

[0425] In this way, the system of the present invention can automatically generate, review, modify, save, and share design drawings efficiently while responding to user emotions. It also improves the user experience by displaying operation guides and support messages.

[0426] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0427] Step 1:

[0428] The user uses an input form on the terminal to input information about the property location and installation conditions, such as the size of the factory and the size of the equipment, placement restrictions, etc. This information is then sent to the server.

[0429] input:

[0430] Factory size: 500 square meters

[0431] Equipment size: 2 meters x 3 meters

[0432] Restricting robot movement

[0433] Height limit: 3 meters

[0434] output:

[0435] Information on the property location and installation conditions sent to the server

[0436] Step 2:

[0437] The server analyzes the received input data in real time and performs basic validation to check for inconsistencies in the input. If there are any inconsistencies, it returns an error message to the user. If validation is successful, it proceeds to the next step.

[0438] input:

[0439] Property location and installation conditions information entered by the user

[0440] output:

[0441] Verification result (normal / error)

[0442] Step 3:

[0443] The server analyzes the user's input behavior and content using an emotion engine to determine whether the user is feeling stressed or frustrated, thereby understanding the user's emotions.

[0444] input:

[0445] User input behavior and input content

[0446] output:

[0447] User emotion information (e.g., normal, highly frustrated)

[0448] Step 4:

[0449] The server uses a navigation API to convert address information into latitude and longitude coordinates and standardizes numerical data such as height restrictions for installation conditions. This preprocessing prepares the data in a format suitable for further processing.

[0450] input:

[0451] Property address information

[0452] Height restrictions for installation conditions

[0453] output:

[0454] Latitude and longitude information

[0455] Standardized Height Limit Measures

[0456] Step 5:

[0457] The server tags the preprocessed data and supplies organized data such as "semiconductor manufacturing equipment" and "transport robot" to the generative AI model. This tagging efficiently organizes the data.

[0458] input:

[0459] Preprocessed data

[0460] output:

[0461] Tagged data

[0462] Step 6:

[0463] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings for the production line based on past design data and current installation conditions. The generated design drawings are stored on a server.

[0464] input:

[0465] Tagged data

[0466] Past design data

[0467] output:

[0468] Procedurally generated blueprints

[0469] Step 7:

[0470] Designers can use their devices to review the generated design drawings and make any necessary corrections, which are then uploaded back to the server.

[0471] input:

[0472] Procedurally generated blueprints

[0473] output:

[0474] Modified blueprints

[0475] Step 8:

[0476] The server adjusts the user interface based on the recognized user emotion, for example, by displaying operation guides or encouraging messages to improve the user experience.

[0477] input:

[0478] User emotion information

[0479] output:

[0480] Adjusted User Interface

[0481] Step 9:

[0482] The server stores the final, revised version of the blueprint and generates a shared link that can be sent to all stakeholders, making the latest blueprint accessible to all project members.

[0483] input:

[0484] Modified blueprints

[0485] output:

[0486] Generated Shared Link

[0487] 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.

[0488] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0489] 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.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0502] 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."

[0503] ---

[0504] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, pre-processing, creating drawings using generation AI, reviewing and correcting the drawings, and saving and sharing the final drawings.

[0505] Program processing explanation

[0506] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[0507] 1. Acquiring input information

[0508] The user enters information about the property location and installation conditions into the system's input form, such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings."

[0509] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[0510] 2. Preprocessing of input data

[0511] The server calls an external navigation API to convert address information to latitude and longitude, and also normalizes numeric data (such as height restrictions) and converts it into the appropriate format for internal processing. For example, it converts "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E".

[0512] Once preprocessed, the data is tagged and sent to the next generation step.

[0513] 3. Drawing generation using generative AI

[0514] The server runs a generative artificial intelligence (generative AI) using the pre-processed data.

[0515] The AI ​​automatically generates base station design drawings based on past design data and current installation conditions, for example, taking into account neighboring buildings and determining the optimal antenna placement.

[0516] The generated design drawings are stored on the server.

[0517] 4. Review and revise drawings

[0518] The terminal (designer) receives the generated drawings and performs a detailed review, adding comments to the drawings and manually making specific modifications, such as adjusting the antenna direction or reflecting design changes.

[0519] The revised design drawings are sent back to the server and saved as the final version.

[0520] 5. Save and share your final drawing

[0521] The server stores the final design drawings in a database, while simultaneously recording the design change history for future review.

[0522] The server generates a shared link for the saved design drawings to be shared with the relevant parties and notifies the members involved in the project, allowing the installation team to quickly receive the latest design drawings.

[0523] Specific examples

[0524] Consider the installation of a new base station in an urban area:

[0525] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[0526] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[0527] 3. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[0528] 4. The terminal (designer) reviews the generated drawing and makes any necessary adjustments, such as fine-tuning the antenna direction.

[0529] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[0530] Through this process, the creation of drawings for base station installation is made more efficient and the amount of manual work required by designers is reduced, enabling the entire project, from design to installation, to proceed quickly and accurately.

[0531] The processing flow will be explained below.

[0532] ---

[0533] Step 1:

[0534] The user enters the property location (e.g., "Shibuya-ku, Tokyo") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure accurate and complete data is entered.

[0535] Step 2:

[0536] The server receives the data sent by the user, including address information, numerical data, installation conditions, etc. The server temporarily stores the received data and prepares it for the next process.

[0537] Step 3:

[0538] The server calls the navigation API to convert address information into latitude and longitude. For example, "Shibuya-ku, Tokyo" becomes "35.6895° N, 139.6917° E." It also standardizes numerical data such as height restrictions for internal use.

[0539] Step 4:

[0540] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0541] Step 5:

[0542] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0543] Step 6:

[0544] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[0545] Step 7:

[0546] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0547] Step 8:

[0548] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[0549] Step 9:

[0550] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0551] This is the specific process flow from creating base station design drawings to final sharing, which significantly improves the efficiency and accuracy of the design process.

[0552] Example 1

[0553] 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."

[0554] Designing base stations requires a lot of data processing and manual work, which increases time and costs. Furthermore, the accuracy and consistency of design drawings can be compromised by human error. Furthermore, if information is not shared smoothly among stakeholders, the progress of the entire project can be delayed. The present invention aims to solve these problems and improve the efficiency and accuracy of base station design.

[0555] 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.

[0556] In this invention, the server includes a means for inputting information on the location and installation conditions of the property, a means for preprocessing the input information and converting it into a required format, a means for automatically generating design drawings of the base station based on a generative model using the preprocessed data, a means for a designer to review and correct the generated design drawings, and a means for saving the final design drawings in a database and generating a sharing link for related parties, thereby automating the base station design process, improving overall efficiency, and maintaining the accuracy and consistency of the design drawings.

[0557] "Property Location" refers to the specific geographic location information for installing a base station.

[0558] "Installation Conditions" refers to the physical, legal and environmental constraints and requirements when installing a base station.

[0559] "Preprocessing" refers to a series of data processing steps that convert the information entered by the user into a format that is easy for the system to use.

[0560] A "generative model" refers to an algorithm or program that uses artificial intelligence technology to automatically generate base station design drawings.

[0561] "Design Drawings" means drawings showing the physical layout, structure, and technical details of a Base Station.

[0562] "Review" refers to the process in which a designer reviews the generated design drawings and makes appropriate corrections.

[0563] "Saving" refers to the act of recording the generated design drawings and their change history in a database.

[0564] A "shared link" refers to the URL or access method for sharing design drawings online with relevant parties.

[0565] The system of the present invention automates and streamlines the creation of base station design drawings. This system functions through a series of processes: inputting the property location and installation conditions, preprocessing the input data, generating drawings using AI, reviewing and correcting the drawings, and saving and sharing the final drawings. Specific embodiments are described in detail below.

[0566] 1. Acquiring input information

[0567] The user enters information about the property location and installation conditions into the system's input form. The input includes specific data such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings." This allows the user to communicate the planned installation location and conditions to the system. The input information is sent to the server.

[0568] 2. Preprocessing of input data

[0569] The server preprocesses the received input data. This preprocessing includes converting address information to latitude and longitude using an external navigation API (e.g., converting "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E") and standardizing numerical data (e.g., height restrictions). Specifically, Google Maps API is used. After preprocessing, the data is tagged and sent to the next generation step.

[0570] 3. Drawing generation using generative AI

[0571] The server runs a generation AI using the preprocessed data. The generation AI automatically generates base station design drawings based on past design data and current installation conditions. For example, a prompt such as "Please create a design drawing for a base station at 35.6895° N, 139.6917° E. The height limit is 50m, and information on nearby buildings is as follows" is used. Based on this information, the generation AI determines the optimal antenna placement and generates the associated design drawings. The generated design drawings are stored on the server.

[0572] 4. Review and revise drawings

[0573] The terminal (designer) receives the generated drawings from the server and performs a detailed review. The designer can add comments to the drawings or manually make specific modifications. For example, they can adjust the direction of the antenna or reflect changes in the design. The modified design drawings are then sent back to the server and saved as the final version.

[0574] 5. Save and share your final drawing

[0575] The server saves the final design drawings to a database, simultaneously recording the design change history for future review. It also generates a shared link for sharing the saved design drawings with stakeholders and notifies all project members, allowing the installation team to quickly receive the latest design drawings.

[0576] Specific examples

[0577] Consider the installation of a new base station in an urban area. Here's what happens:

[0578] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[0579] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[0580] 3. Generative AI automatically creates a base station design based on the input data. This design is optimized taking into account the surrounding location conditions.

[0581] 4. The device (designer) reviews the generated drawings and makes any necessary adjustments, such as fine-tuning the antenna direction.

[0582] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[0583] Through this series of processes, the present invention significantly improves the efficiency of base station design, enabling the entire project to proceed quickly and accurately.

[0584] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0585] Program processing flow

[0586] Step 1: Obtaining input information

[0587] The user accesses the system's input form and enters the property location (Shibuya-ku, Tokyo) and installation conditions such as a height limit of 50m and the location and height of surrounding buildings.

[0588] Input: Property location information, and specific numbers and ratios for installation conditions

[0589] The server receives the information obtained from the input form.

[0590] Output: Received input data

[0591] Specific behavior: When a user clicks the "Submit" button on an input form, the information is sent to the server.

[0592] Step 2: Preprocessing input data

[0593] The server uses the Google Maps API to convert the received data into geographic information (e.g., "Shibuya-ku, Tokyo") into latitude and longitude coordinates of "35.6895° N, 139.6917° E."

[0594] Input: Address information and numeric data (e.g. height restrictions)

[0595] Data processing: Address information is converted to latitude and longitude using the navigation API, and the numerical data is standardized.

[0596] Output: Preprocessed latitude and longitude information and standardized numerical data

[0597] Specific operation: Calls the Google Maps API, converts address information into latitude and longitude, and standardizes the unit of numeric data to meters.

[0598] Step 3: Generate drawings using generative AI

[0599] The server runs a generative AI model based on the pre-processed data.

[0600] Input: Latitude and longitude information, standardized height restrictions, etc.

[0601] Data calculation: Generative AI automatically generates base station design drawings based on past design data and current installation conditions.

[0602] Output: Generated base station design drawings

[0603] Specific operation: A prompt is input into the generation AI, and the AI ​​generates the drawing based on instructions such as, "Please create a design drawing for a base station located at 35.6895° N, 139.6917° E. The height limit is 50m, and the nearby buildings are as follows: Building 1, Building 2. Please determine the optimal antenna placement taking into account the surrounding environment."

[0604] Step 4: Review and revise the drawing

[0605] The terminal (designer) accesses and reviews the design drawings sent from the server.

[0606] Input: Generated design drawings

[0607] Data processing: review and manual corrections as needed

[0608] Output: Revised final design drawings

[0609] Specific operations: The designer adds comments to the drawing, adjusts the direction and height of the antenna, and resends the revised drawing to the server.

[0610] Step 5: Save and share your final drawing

[0611] The server stores the final design drawings in a database.

[0612] Input: Revised final design drawings

[0613] Data storage: The final design drawings and change history are recorded in a database.

[0614] Output: Link for sharing

[0615] Specific operation: The design drawings are saved in a database, a shared link is generated to notify relevant parties, and the link is notified to project members.

[0616] Through the above processing steps, a series of processes from creating base station design drawings to sharing them can be efficiently carried out.

[0617] (Application example 1)

[0618] 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."

[0619] Conventional factory robot installation and workflow design requires a great deal of time and effort, and is often inefficient because it depends heavily on the skill level of the designer. Furthermore, creating and modifying blueprints and workflows is time-consuming, making it difficult to achieve optimal robot placement and workflows. To solve these problems, a system is needed that can efficiently and automatically create robot installation plans and workflows based on input information.

[0620] 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.

[0621] In this invention, the server includes a means for inputting information on the location of the property and installation conditions, a means for preprocessing the input information and converting it into a required format, a means based on artificial intelligence for automatically generating design drawings and workflows using the preprocessed data, a means for reviewing and modifying the automatically generated design drawings and workflows, and a means for saving and sharing the final design drawings and workflows with relevant parties. This allows users to efficiently create and modify robot installation plans and workflows and quickly share optimized design drawings.

[0622] - "Property Location" refers to the geographic location where a particular property is located.

[0623] "Installation conditions" refers to information about the various conditions and restrictions regarding installation at the property.

[0624] "Preprocessing" is the process of converting input information into an appropriate format and preparing the data for use in the next processing step.

[0625] "Generative AI" is an AI technology that automatically generates design drawings and workflows based on past data and current conditions.

[0626] "Design drawings" are detailed drawing information regarding the layout and installation of properties and equipment.

[0627] A "work flow" is a flow diagram showing specific work procedures and processes, along with detailed step information.

[0628] "Review" is the process of checking the generated design drawings and work flow and making any necessary corrections or additions.

[0629] "Final version" refers to the final version of the design drawings and work flow that has been finalized after all revisions and reviews have been completed.

[0630] "Storage" is the process of recording the created and modified design drawings and work flows in a database or storage.

[0631] "Sharing" is the process of coordinating and making accessible the design drawings and workflows created by stakeholders.

[0632] The present invention provides a system for efficiently and automatically generating installation plans and work flows for factory robots. Below, we will explain in detail each of the main processes from the perspectives of the server, terminal, and user.

[0633] System Overview

[0634] The main elements of the system consist of a means for inputting information on the property location and installation conditions, a means for pre-processing, a means for generating design drawings and workflows using generative artificial intelligence, a means for reviewing and correcting, and a means for saving and sharing the final design drawings and workflows.

[0635] Hardware and Software Configuration

[0636] Hardware:

[0637] Server: Cloud server (e.g. AWS EC2)

[0638] Device: Smartphone

[0639] software:

[0640] Server side: Django (backend framework), PyTorch, TensorFlow (generative AI model)

[0641] Client side: React Native (cross-platform mobile development framework)

[0642] Data storage: AWS S3 (storage), AWS RDS (relational database)

[0643] Program processing explanation

[0644] 1. Obtaining input information:

[0645] Users use a smartphone app to input the layout and installation conditions of specific areas within the factory, such as "warehouse section A," "transport line layout," and "safety zone settings."

[0646] The server receives these input data and performs immediate validation.

[0647] 2. Preprocessing the input data:

[0648] The server converts the input data into an appropriate format and standardizes it as internal data. For example, it converts area information into a specific coordinate system and processes installation conditions as numerical data.

[0649] 3. Generative AI for blueprint and workflow generation:

[0650] The server uses the preprocessed data to launch generative artificial intelligence (generative AI) to generate optimal layouts and workflows for factory robots. The generated design drawings and workflows are stored on the server.

[0651] 4. Review and revise blueprints and workflows:

[0652] The user can check the design drawings and workflow generated on their smartphone and make any necessary corrections, for example by changing the robot's position on the smartphone screen using drag and drop, and then send the corrected data to the server.

[0653] 5. Save and share your final design and workflow:

[0654] The server stores the final design drawings and workflow in a database and generates a shared link for stakeholders, allowing the installation team to quickly receive the latest design drawings and workflow.

[0655] Specific examples

[0656] For example, a user inputs "warehouse section A," "transport line layout," and "safety zone settings," and the server receives the request. The server converts "warehouse section A" into coordinate system information (35.6895°N, 139.6917°E), and the generation AI creates and proposes the optimal robot layout and work flow. The user fine-tunes the layout on their smartphone, and once finalized, it is sent to the server. The server saves the final design, generates a link, and notifies relevant parties.

[0657] Prompt Sentence Examples

[0658] Input data:

[0659] Facility Layout: Warehouse Section A

[0660] Installation conditions: Layout of conveying lines, setting of safety zones

[0661] Requests for Generative AI:

[0662] Using the layout information for Warehouse Section A, generate the optimal robot placement and transport line work flow. Establish the most efficient placement while taking safety zones into consideration.

[0663] Example output:

[0664] Robot 1: Transfer point A -> B

[0665] Robot 2: Transfer point C -> D"

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Processing Steps

[0668] Step 1: Obtaining input information

[0669] (explanation)

[0670] The user uses the smartphone app's input form to input specific sections within the factory and installation conditions, such as "warehouse section A," "transport line layout," and "safety zone settings."

[0671] (input)

[0672] Information on property location and installation conditions.

[0673] (output)

[0674] User-entered data sent to the server.

[0675] (operation)

[0676] The user inputs "warehouse section A," "transport line layout," and "safety zone settings" on their smartphone.

[0677] Sends input data to the server.

[0678] Step 2: Preprocessing the input data

[0679] (explanation)

[0680] The server preprocesses the received data and converts it into the required format, for example converting address information into coordinate data and installation conditions into standardized numerical data.

[0681] (input)

[0682] Information on property location and installation conditions sent by the user.

[0683] (output)

[0684] Preprocessed data (e.g., coordinate data, standardized numerical data).

[0685] (operation)

[0686] The server converts the address information to "(35.6895° N, 139.6917° E)".

[0687] Height restrictions and other installation conditions are standardized as numerical data.

[0688] Step 3: Generative AI creates blueprints and workflows

[0689] (explanation)

[0690] The server uses the pre-processed data to automatically generate blueprints and workflows using generative AI models.

[0691] (input)

[0692] Preprocessed data (coordinate and numerical data).

[0693] (output)

[0694] Generated blueprints and work flows.

[0695] (operation)

[0696] The server inputs the preprocessed data into the generative AI model.

[0697] Generative AI generates optimal placement and work flow for factory robots, and outputs blueprints and flow.

[0698] The generated data is stored on the server.

[0699] Step 4: Review and revise the design and workflow

[0700] (explanation)

[0701] The user can check the generated design drawings and workflow on their smartphone and make corrections as necessary.

[0702] (input)

[0703] Generated blueprints and work flows.

[0704] (output)

[0705] User-modified blueprints and workflows.

[0706] (operation)

[0707] Users can check the blueprints on their smartphone screens.

[0708] Modify the robot position and workflow as needed with drag and drop.

[0709] Resubmit the revised blueprint to the server.

[0710] Step 5: Save and share your final design and workflow

[0711] (explanation)

[0712] The server stores the final design drawings and workflows modified by the user in a database and generates a sharing link for the relevant parties.

[0713] (input)

[0714] User-modified blueprints and workflows.

[0715] (output)

[0716] Saved final design and workflow, shareable links.

[0717] (operation)

[0718] The server stores the final version of the data in the database.

[0719] Generate a shared link and notify relevant parties via email, etc.

[0720] 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.

[0721] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, preprocessing, creating drawings using generative AI, reviewing and correcting the drawings, saving and sharing the final drawings, and even including an emotion engine that recognizes the user's emotions, thereby adjusting the user interface.

[0722] Program processing explanation

[0723] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[0724] 1. Acquiring input information

[0725] The user enters information about the property location and installation conditions into the system's input form, such as "City A," "height limit 50m," and "location and height of surrounding buildings."

[0726] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[0727] 2. Starting Emotion Recognition

[0728] The server analyzes the user's behavior and input while using the input form and activates the emotion engine in real time, which analyzes the data to identify the user's emotions, such as stress or frustration.

[0729] 3. Preprocessing of input data

[0730] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[0731] 4. Tagging preprocessed data

[0732] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0733] 5. Drawing generation using generative AI

[0734] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0735] The generated design drawings are stored on the server.

[0736] 6. Review and revise drawings

[0737] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0738] 7. Emotion-Based User Interface Adjustment

[0739] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance.

[0740] If necessary, generate and display appropriate feedback messages to the user.

[0741] 8. Save and share your final drawing

[0742] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[0743] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0744] Specific examples

[0745] Consider the installation of a new base station in an urban area:

[0746] 1. The user inputs "City A," "Height limit 50m," and "Information about surrounding buildings."

[0747] 2. The server receives this data, converts the address to latitude and longitude (35.0000° N, 135.0000° E), and standardizes the height restriction as numeric data.

[0748] 3. The server analyzes the user's input behavior and delays and uses an emotion engine to determine whether the user is feeling frustrated. For example, if the user repeatedly tries to enter something, it determines that frustration is increasing.

[0749] 4. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[0750] 5. The designer reviews the generated drawings, performs detailed checks, and makes fine adjustments as needed.

[0751] 6. If the emotion engine identifies frustration, the server adjusts the user interface to display an operation guide, clearly showing the user the operation procedure, and displays appropriate feedback messages to support the user.

[0752] 7. The server shares the final design drawings with stakeholders, ensuring the installation team can start work quickly and with the most up-to-date information.

[0753] The above process streamlines the process of creating base station design drawings and improves the user experience, reducing the manual work required by designers and enabling user feedback, facilitating the overall progress of the project.

[0754] The processing flow will be explained below.

[0755] ---

[0756] Step 1:

[0757] The user enters the property location (e.g., "City A") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure that accurate and complete data is entered.

[0758] Step 2:

[0759] The server receives the data sent by the user. This includes information such as address information ("City A") and installation conditions ("Height limit 50m"). The received data is temporarily saved and prepared for the next process.

[0760] Step 3:

[0761] The server runs an emotion engine to analyze the user's input behavior and identify the user's emotions (e.g., stress or frustration) through specific input patterns (e.g., repeated inputs, delayed inputs, etc.).

[0762] Step 4:

[0763] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[0764] Step 5:

[0765] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[0766] Step 6:

[0767] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[0768] Step 7:

[0769] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[0770] Step 8:

[0771] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[0772] Step 9:

[0773] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance. It also generates and displays appropriate feedback messages to the user.

[0774] Step 10:

[0775] The terminal (designer) uploads the revised design drawing back to the server, which saves the uploaded drawing as the final version and also keeps a revision history.

[0776] Step 11:

[0777] The server saves the final design drawings to a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[0778] These are the specific processing steps of the base station design drawing creation system that combines an emotion engine. This enables interface adjustments according to the user's emotions and efficient drawing creation, facilitating the overall progress of the project.

[0779] Example 2

[0780] 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."

[0781] The traditional process of creating base station design drawings involves a lot of manual work, making it inefficient and time-consuming. There is also a lack of mechanisms to address the stress and frustration felt by users during the input process, which hinders the overall user experience. Furthermore, there are sometimes delays in sharing design drawings with stakeholders, which can impact project progress.

[0782] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for inputting information on the property location and installation conditions; means for preprocessing the input information and converting it into a required format; means based on a generation artificial intelligence for automatically generating design drawings of a base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving and sharing the automatically generated design drawings with relevant parties; and means based on an emotion engine for recognizing user emotions and adjusting the user interface. This automates and streamlines the process of creating base station design drawings, enables interface adjustment according to the user's emotions, and improves the overall operating experience. Furthermore, it enables rapid sharing of design drawings, facilitating project progress.

[0783] "Property location" is information about the specific geographical location where the base station is installed.

[0784] "Installation conditions" refer to restrictions and requirements for installing a base station, including, for example, height restrictions and the layout of surrounding buildings.

[0785] "Preprocessing" refers to converting input information into an appropriate format, including converting addresses to latitude and longitude coordinates and standardizing numeric data.

[0786] "Generative AI" refers to artificial intelligence technology that automatically generates base station design drawings based on input data.

[0787] An "emotion engine" refers to a system that analyzes a user's behavior and input content to identify the user's emotional state in real time.

[0788] "Design drawings" are drawings that show the specific installation location and structure of the base station, and are automatically generated by a generative AI model.

[0789] "User interface" refers to the screens and operating means that provide interaction for the user to interact with the system.

[0790] "Preprocessed data" refers to data where input information has been converted into an appropriate format and tagged.

[0791] "Tagging" refers to the process of adding classification information and metadata to data to organize it.

[0792] "Review and correction" refers to the process in which a designer checks the generated design drawings and makes fine adjustments as necessary.

[0793] "Storage and sharing" refers to the process in which the final design drawings are stored on a server and provided to stakeholders in the form of a link or similar.

[0794] This invention is a system that automates and streamlines the creation of base station design drawings. The system uses a generative AI model to generate drawings after the user inputs information about the property location and installation conditions, and the server performs preprocessing. The system also provides functions for reviewing and modifying the drawings, as well as saving and sharing the final drawings. Furthermore, the system includes an emotion engine that recognizes the user's emotions and adjusts the user interface accordingly.

[0795] To implement this system, the following hardware and software are used.

[0796] 1. Hardware and software configuration:

[0797] A server is a computer equipped with a high-performance processor and a large amount of memory, and processes and calculates data.

[0798] The terminal is a personal computer or mobile device operated by a designer or user to display and modify drawings.

[0799] The generative AI model is a cloud-based system on which generative AI software (e.g., AutoCAD's AI functions) is installed.

[0800] The emotion engine is a machine learning model for analyzing user input behavior and is implemented on the server.

[0801] 2. Data processing and calculation procedures:

[0802] Users use the system's web interface or mobile app to input information about the property location and installation conditions, including data such as "City A," "50m height limit," and "location and height of surrounding buildings."

[0803] The server receives this input data and performs some basic validation. For example, for City A, it calls a navigation API (e.g., Google Maps API) to convert the address into latitude and longitude (35.0000° N, 135.0000° E). ​​It also standardizes numerical data such as height restrictions into a unified format.

[0804] The emotion engine analyzes the user's input speed, number of corrections, etc. in real time to determine whether the user is feeling stressed or frustrated.

[0805] 3. How generative AI models work:

[0806] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[0807] The generated design drawings are stored in the server's database.

[0808] 4. Review and revise drawings:

[0809] The terminal (designer) displays the generated design drawing and checks and modifies the details. For example, the designer uses design software such as AutoCAD to fine-tune the direction and height of the antenna.

[0810] 5. Save and Share:

[0811] The server saves the final version of the design drawings revised by the designer in a database and generates a sharing link for the relevant parties, which is automatically sent via email to the members involved in the project.

[0812] Examples of specific prompts include:

[0813] "Enter an address in City A and set the height limit to 50m."

[0814] "Enter the location and height of surrounding buildings and generate the optimal design drawing for your base station."

[0815] "Check the antenna placement in the automatically generated design drawing and correct it if necessary."

[0816] The above is an embodiment of the present invention, which not only automates the process of creating base station design drawings, but also improves the user's operation experience.

[0817] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0818] Step 1:

[0819] Obtaining input information

[0820] The user enters information about the property location and installation conditions into the system's input form, providing data such as "City A," "height limit of 50m," and "location and height of surrounding buildings."

[0821] The server receives the data entered by the user, stores it in the system, and performs basic data integrity checks (e.g., checking the format of numbers).

[0822] Output: Verified property location and installation information.

[0823] Step 2:

[0824] Starting emotion recognition

[0825] The server collects real-time data while the user is using the input form, specifically analyzing the user's emotional state based on input speed, number of corrections, frequency of typing errors, etc.

[0826] For example, if a series of typing errors occur, the server determines that the user is irritated and updates the emotional status.

[0827] Output: Real-time emotional status information.

[0828] Step 3:

[0829] Preprocessing of input data

[0830] The server calls a navigation API (e.g., Google Maps API) to convert the property address into latitude and longitude. As a result, "City A" is obtained as "35.0000° N, 135.0000° E."

[0831] The server standardizes numerical data such as height restrictions and converts them into a unified format internally.

[0832] Output: Geographic information converted to latitude and longitude and standardized height restriction information.

[0833] Step 4:

[0834] Tagging preprocessed data

[0835] The server then tags the preprocessed data with metadata, adding tags such as "urban area," "office building," and "50m height limit." This tagging organizes the data and allows the generative AI model to process it efficiently.

[0836] Output: Tagged preprocessed data.

[0837] Step 5:

[0838] Drawing generation using generative AI

[0839] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[0840] The server stores the generated design drawings in a database.

[0841] Output: Auto-generated engineering drawings.

[0842] Step 6:

[0843] Drawing review and revision

[0844] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes fine adjustments using design software such as AutoCAD. For example, they may make slight changes to the direction or placement of the antenna.

[0845] The terminal (designer) uploads the revised design drawing back to the server.

[0846] Output: Modified engineering drawings.

[0847] Step 7:

[0848] Emotion-Based User Interface Adjustment

[0849] The server adjusts the user interface in real time based on the user's emotional status recognized by the emotion engine. For example, if the user is feeling frustrated, it may pop up an operation guide or enhance input assistance functions.

[0850] The server displays an appropriate feedback message (e.g., "Thank you for your input. Is there anything we can help you with?") in the user interface.

[0851] Output: Tailored user interface and feedback messages.

[0852] Step 8:

[0853] Save and share your final drawing

[0854] The terminal (designer) uploads the revised design drawing to the server, which saves the uploaded drawing as the final version and stores it in the database along with the revision history.

[0855] The server generates a shared link for the final design drawing and sends an automatic email notification to stakeholders, allowing them to access the latest version of the drawing.

[0856] Output: Final design drawings saved and shared links.

[0857] (Application example 2)

[0858] 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."

[0859] The process of creating factory design drawings involves a lot of manual work, which requires time and effort. Furthermore, the design process is carried out without consideration of the user's emotions and stress levels, which can result in a poor user experience and hinder productivity. Furthermore, it is difficult to automatically determine the optimal layout of robot movement paths and work stations within the factory.

[0860] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information on the location and installation conditions of the property; means for preprocessing the input information and converting it into a required format; means based on generative artificial intelligence for automatically generating design drawings of the base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving the final design drawings and sharing them with relevant parties; and means for recognizing user emotions and adjusting the user interface. This enables the automatic generation and correction of design drawings to be performed efficiently, and operation guides and feedback according to the user's emotions to be provided, thereby improving the user experience and increasing productivity.

[0861] "Property location" refers to the location of the new production line within a particular factory.

[0862] "Installation conditions" refers to factors that indicate the installation environment, such as layout restrictions within the factory, equipment size, traffic flow and altitude restrictions.

[0863] "Input means" refers to a mechanism that provides an interface for users to input the property location and installation conditions.

[0864] The "preprocessing means" is a mechanism for standardizing input information and converting it into latitude and longitude coordinates and numerical data.

[0865] "Generative AI" is an AI technology that uses algorithms and programs to automatically generate optimal design drawings based on past design data and current installation conditions.

[0866] "Review and correction means" refers to functions and interfaces for checking the generated design drawings and making corrections as necessary.

[0867] "Storage and sharing means" is a mechanism for storing the final design drawings in a database and generating a sharing link for relevant parties.

[0868] "Means for recognizing user emotions" refers to technology that analyzes emotions such as stress and frustration based on the user's input behavior and data.

[0869] The "user interface adjustment means" is a mechanism that displays operation guides and feedback messages according to the recognized user emotions, thereby improving the operation experience.

[0870] The "tagging means" is a function for assigning tags to preprocessed data and organizing the data efficiently.

[0871] The "latitude and longitude conversion means" is a function for converting address information of a property location into latitude and longitude.

[0872] The "numerical value conversion means" is a function for converting conditions such as height restrictions into numerical data.

[0873] This invention is a system that automatically generates optimal design drawings for new production lines in factories and adjusts the interface based on the user's emotions. This system operates by combining a server, user terminals, and various software.

[0874] The server first receives information on the property location and installation conditions entered by the user in real time. The user inputs the factory layout, equipment size, constraints, etc. via their terminal. The server also analyzes the user's behavior while entering data and recognizes the user's stress and frustration in real time through an emotion engine. This improves the user experience.

[0875] The server then preprocesses the input data, converting address information into latitude and longitude using a navigation API (e.g., Google Maps API) and standardizing numerical data such as height restrictions. The preprocessed data is also tagged with terms such as "semiconductor manufacturing equipment" and "transport robot," allowing the generative AI to efficiently generate blueprints.

[0876] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings based on past production line design data and current installation conditions. These generated designs are stored on a server and can be accessed by designers for modification and review. Designers can also review the generated drawings in detail and make modifications as necessary.

[0877] The server generates a link to share the final design drawings with all stakeholders. This link is provided to all members involved in the project, enabling them to work quickly and with the latest information.

[0878] As a specific example, consider the case where the user inputs the following conditions:

[0879] Factory size: 500 square meters

[0880] Device size: 2 meters x 3 meters

[0881] Restricting robot movement

[0882] Height limit: 3 meters

[0883] An example of a prompt is:

[0884] New production line design requirements:

[0885] Factory size: 500 square meters

[0886] Equipment size: 2 meters x 3 meters

[0887] Restricting robot movement

[0888] Height limit: 3 meters

[0889] Next, a helpful message is displayed to reduce the user's stress.

[0890] In this way, the system of the present invention can automatically generate, review, modify, save, and share design drawings efficiently while responding to user emotions. It also improves the user experience by displaying operation guides and support messages.

[0891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0892] Step 1:

[0893] The user uses an input form on the terminal to input information about the property location and installation conditions, such as the size of the factory and the size of the equipment, placement restrictions, etc. This information is then sent to the server.

[0894] input:

[0895] Factory size: 500 square meters

[0896] Equipment size: 2 meters x 3 meters

[0897] Restricting robot movement

[0898] Height limit: 3 meters

[0899] output:

[0900] Information on the property location and installation conditions sent to the server

[0901] Step 2:

[0902] The server analyzes the received input data in real time and performs basic validation to check for inconsistencies in the input. If there are any inconsistencies, it returns an error message to the user. If validation is successful, it proceeds to the next step.

[0903] input:

[0904] Property location and installation conditions information entered by the user

[0905] output:

[0906] Verification result (normal / error)

[0907] Step 3:

[0908] The server analyzes the user's input behavior and content using an emotion engine to determine whether the user is feeling stressed or frustrated, thereby understanding the user's emotions.

[0909] input:

[0910] User input behavior and input content

[0911] output:

[0912] User emotion information (e.g., normal, highly frustrated)

[0913] Step 4:

[0914] The server uses a navigation API to convert address information into latitude and longitude coordinates and standardizes numerical data such as height restrictions for installation conditions. This preprocessing prepares the data in a format suitable for further processing.

[0915] input:

[0916] Property address information

[0917] Height restrictions for installation conditions

[0918] output:

[0919] Latitude and longitude information

[0920] Standardized Height Limit Measures

[0921] Step 5:

[0922] The server tags the preprocessed data and supplies organized data such as "semiconductor manufacturing equipment" and "transport robot" to the generative AI model. This tagging efficiently organizes the data.

[0923] input:

[0924] Preprocessed data

[0925] output:

[0926] Tagged data

[0927] Step 6:

[0928] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings for the production line based on past design data and current installation conditions. The generated design drawings are stored on a server.

[0929] input:

[0930] Tagged data

[0931] Past design data

[0932] output:

[0933] Procedurally generated blueprints

[0934] Step 7:

[0935] Designers can use their devices to review the generated design drawings and make any necessary corrections, which are then uploaded back to the server.

[0936] input:

[0937] Procedurally generated blueprints

[0938] output:

[0939] Modified blueprints

[0940] Step 8:

[0941] The server adjusts the user interface based on the recognized user emotion, for example, by displaying operation guides or encouraging messages to improve the user experience.

[0942] input:

[0943] User emotion information

[0944] output:

[0945] Adjusted User Interface

[0946] Step 9:

[0947] The server stores the final, revised version of the blueprint and generates a shared link that can be sent to all stakeholders, making the latest blueprint accessible to all project members.

[0948] input:

[0949] Modified blueprints

[0950] output:

[0951] Generated Shared Link

[0952] 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.

[0953] 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.

[0954] 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.

[0955] [Third embodiment]

[0956] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0957] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0958] 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).

[0959] 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.

[0960] 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.

[0961] 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).

[0962] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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."

[0968] ---

[0969] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, pre-processing, creating drawings using generation AI, reviewing and correcting the drawings, and saving and sharing the final drawings.

[0970] Program processing explanation

[0971] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[0972] 1. Acquiring input information

[0973] The user enters information about the property location and installation conditions into the system's input form, such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings."

[0974] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[0975] 2. Preprocessing of input data

[0976] The server calls an external navigation API to convert address information to latitude and longitude, and also normalizes numeric data (such as height restrictions) and converts it into the appropriate format for internal processing. For example, it converts "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E".

[0977] Once preprocessed, the data is tagged and sent to the next generation step.

[0978] 3. Drawing generation using generative AI

[0979] The server runs a generative artificial intelligence (generative AI) using the pre-processed data.

[0980] The AI ​​automatically generates base station design drawings based on past design data and current installation conditions, for example, taking into account neighboring buildings and determining the optimal antenna placement.

[0981] The generated design drawings are stored on the server.

[0982] 4. Review and revise drawings

[0983] The terminal (designer) receives the generated drawings and performs a detailed review, adding comments to the drawings and manually making specific modifications, such as adjusting the antenna direction or reflecting design changes.

[0984] The revised design drawings are sent back to the server and saved as the final version.

[0985] 5. Save and share your final drawing

[0986] The server stores the final design drawings in a database, while simultaneously recording the design change history for future review.

[0987] The server generates a shared link for the saved design drawings to be shared with the relevant parties and notifies the members involved in the project, allowing the installation team to quickly receive the latest design drawings.

[0988] Specific examples

[0989] Consider the installation of a new base station in an urban area:

[0990] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[0991] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[0992] 3. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[0993] 4. The terminal (designer) reviews the generated drawing and makes any necessary adjustments, such as fine-tuning the antenna direction.

[0994] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[0995] Through this process, the creation of drawings for base station installation is made more efficient and the amount of manual work required by designers is reduced, enabling the entire project, from design to installation, to proceed quickly and accurately.

[0996] The processing flow will be explained below.

[0997] ---

[0998] Step 1:

[0999] The user enters the property location (e.g., "Shibuya-ku, Tokyo") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure accurate and complete data is entered.

[1000] Step 2:

[1001] The server receives the data sent by the user, including address information, numerical data, installation conditions, etc. The server temporarily stores the received data and prepares it for the next process.

[1002] Step 3:

[1003] The server calls the navigation API to convert address information into latitude and longitude. For example, "Shibuya-ku, Tokyo" becomes "35.6895° N, 139.6917° E." It also standardizes numerical data such as height restrictions for internal use.

[1004] Step 4:

[1005] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1006] Step 5:

[1007] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1008] Step 6:

[1009] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[1010] Step 7:

[1011] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1012] Step 8:

[1013] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[1014] Step 9:

[1015] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1016] This is the specific process flow from creating base station design drawings to final sharing, which significantly improves the efficiency and accuracy of the design process.

[1017] Example 1

[1018] 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."

[1019] Designing base stations requires a lot of data processing and manual work, which increases time and costs. Furthermore, the accuracy and consistency of design drawings can be compromised by human error. Furthermore, if information is not shared smoothly among stakeholders, the progress of the entire project can be delayed. The present invention aims to solve these problems and improve the efficiency and accuracy of base station design.

[1020] 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.

[1021] In this invention, the server includes a means for inputting information on the location and installation conditions of the property, a means for preprocessing the input information and converting it into a required format, a means for automatically generating design drawings of the base station based on a generative model using the preprocessed data, a means for a designer to review and correct the generated design drawings, and a means for saving the final design drawings in a database and generating a sharing link for related parties, thereby automating the base station design process, improving overall efficiency, and maintaining the accuracy and consistency of the design drawings.

[1022] "Property Location" refers to the specific geographic location information for installing a base station.

[1023] "Installation Conditions" refers to the physical, legal and environmental constraints and requirements when installing a base station.

[1024] "Preprocessing" refers to a series of data processing steps that convert the information entered by the user into a format that is easy for the system to use.

[1025] A "generative model" refers to an algorithm or program that uses artificial intelligence technology to automatically generate base station design drawings.

[1026] "Design Drawings" means drawings showing the physical layout, structure, and technical details of a Base Station.

[1027] "Review" refers to the process in which a designer reviews the generated design drawings and makes appropriate corrections.

[1028] "Saving" refers to the act of recording the generated design drawings and their change history in a database.

[1029] A "shared link" refers to the URL or access method for sharing design drawings online with relevant parties.

[1030] The system of the present invention automates and streamlines the creation of base station design drawings. This system functions through a series of processes: inputting the property location and installation conditions, preprocessing the input data, generating drawings using AI, reviewing and correcting the drawings, and saving and sharing the final drawings. Specific embodiments are described in detail below.

[1031] 1. Acquiring input information

[1032] The user enters information about the property location and installation conditions into the system's input form. The input includes specific data such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings." This allows the user to communicate the planned installation location and conditions to the system. The input information is sent to the server.

[1033] 2. Preprocessing of input data

[1034] The server preprocesses the received input data. This preprocessing includes converting address information to latitude and longitude using an external navigation API (e.g., converting "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E") and standardizing numerical data (e.g., height restrictions). Specifically, Google Maps API is used. After preprocessing, the data is tagged and sent to the next generation step.

[1035] 3. Drawing generation using generative AI

[1036] The server runs a generation AI using the preprocessed data. The generation AI automatically generates base station design drawings based on past design data and current installation conditions. For example, a prompt such as "Please create a design drawing for a base station at 35.6895° N, 139.6917° E. The height limit is 50m, and information on nearby buildings is as follows" is used. Based on this information, the generation AI determines the optimal antenna placement and generates the associated design drawings. The generated design drawings are stored on the server.

[1037] 4. Review and revise drawings

[1038] The terminal (designer) receives the generated drawings from the server and performs a detailed review. The designer can add comments to the drawings or manually make specific modifications. For example, they can adjust the direction of the antenna or reflect changes in the design. The modified design drawings are then sent back to the server and saved as the final version.

[1039] 5. Save and share your final drawing

[1040] The server saves the final design drawings to a database, simultaneously recording the design change history for future review. It also generates a shared link for sharing the saved design drawings with stakeholders and notifies all project members, allowing the installation team to quickly receive the latest design drawings.

[1041] Specific examples

[1042] Consider the installation of a new base station in an urban area. Here's what happens:

[1043] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[1044] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[1045] 3. Generative AI automatically creates a base station design based on the input data. This design is optimized taking into account the surrounding location conditions.

[1046] 4. The device (designer) reviews the generated drawings and makes any necessary adjustments, such as fine-tuning the antenna direction.

[1047] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[1048] Through this series of processes, the present invention significantly improves the efficiency of base station design, enabling the entire project to proceed quickly and accurately.

[1049] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1050] Program processing flow

[1051] Step 1: Obtaining input information

[1052] The user accesses the system's input form and enters the property location (Shibuya-ku, Tokyo) and installation conditions such as a height limit of 50m and the location and height of surrounding buildings.

[1053] Input: Property location information, and specific numbers and ratios for installation conditions

[1054] The server receives the information obtained from the input form.

[1055] Output: Received input data

[1056] Specific behavior: When a user clicks the "Submit" button on an input form, the information is sent to the server.

[1057] Step 2: Preprocessing input data

[1058] The server uses the Google Maps API to convert the received data into geographic information (e.g., "Shibuya-ku, Tokyo") into latitude and longitude coordinates of "35.6895° N, 139.6917° E."

[1059] Input: Address information and numeric data (e.g. height restrictions)

[1060] Data processing: Address information is converted to latitude and longitude using the navigation API, and the numerical data is standardized.

[1061] Output: Preprocessed latitude and longitude information and standardized numerical data

[1062] Specific operation: Calls the Google Maps API, converts address information into latitude and longitude, and standardizes the unit of numeric data to meters.

[1063] Step 3: Generate drawings using generative AI

[1064] The server runs a generative AI model based on the pre-processed data.

[1065] Input: Latitude and longitude information, standardized height restrictions, etc.

[1066] Data calculation: Generative AI automatically generates base station design drawings based on past design data and current installation conditions.

[1067] Output: Generated base station design drawings

[1068] Specific operation: A prompt is input into the generation AI, and the AI ​​generates the drawing based on instructions such as, "Please create a design drawing for a base station located at 35.6895° N, 139.6917° E. The height limit is 50m, and the nearby buildings are as follows: Building 1, Building 2. Please determine the optimal antenna placement taking into account the surrounding environment."

[1069] Step 4: Review and revise the drawing

[1070] The terminal (designer) accesses and reviews the design drawings sent from the server.

[1071] Input: Generated design drawings

[1072] Data processing: review and manual corrections as needed

[1073] Output: Revised final design drawings

[1074] Specific operations: The designer adds comments to the drawing, adjusts the direction and height of the antenna, and resends the revised drawing to the server.

[1075] Step 5: Save and share your final drawing

[1076] The server stores the final design drawings in a database.

[1077] Input: Revised final design drawings

[1078] Data storage: The final design drawings and change history are recorded in a database.

[1079] Output: Link for sharing

[1080] Specific operation: The design drawings are saved in a database, a shared link is generated to notify relevant parties, and the link is notified to project members.

[1081] Through the above processing steps, a series of processes from creating base station design drawings to sharing them can be efficiently carried out.

[1082] (Application example 1)

[1083] 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."

[1084] Conventional factory robot installation and workflow design requires a great deal of time and effort, and is often inefficient because it depends heavily on the skill level of the designer. Furthermore, creating and modifying blueprints and workflows is time-consuming, making it difficult to achieve optimal robot placement and workflows. To solve these problems, a system is needed that can efficiently and automatically create robot installation plans and workflows based on input information.

[1085] 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.

[1086] In this invention, the server includes a means for inputting information on the location of the property and installation conditions, a means for preprocessing the input information and converting it into a required format, a means based on artificial intelligence for automatically generating design drawings and workflows using the preprocessed data, a means for reviewing and modifying the automatically generated design drawings and workflows, and a means for saving and sharing the final design drawings and workflows with relevant parties. This allows users to efficiently create and modify robot installation plans and workflows and quickly share optimized design drawings.

[1087] - "Property Location" refers to the geographic location where a particular property is located.

[1088] "Installation conditions" refers to information about the various conditions and restrictions regarding installation at the property.

[1089] "Preprocessing" is the process of converting input information into an appropriate format and preparing the data for use in the next processing step.

[1090] "Generative AI" is an AI technology that automatically generates design drawings and workflows based on past data and current conditions.

[1091] "Design drawings" are detailed drawing information regarding the layout and installation of properties and equipment.

[1092] A "work flow" is a flow diagram showing specific work procedures and processes, along with detailed step information.

[1093] "Review" is the process of checking the generated design drawings and work flow and making any necessary corrections or additions.

[1094] "Final version" refers to the final version of the design drawings and work flow that has been finalized after all revisions and reviews have been completed.

[1095] "Storage" is the process of recording the created and modified design drawings and work flows in a database or storage.

[1096] "Sharing" is the process of coordinating and making accessible the design drawings and workflows created by stakeholders.

[1097] The present invention provides a system for efficiently and automatically generating installation plans and work flows for factory robots. Below, we will explain in detail each of the main processes from the perspectives of the server, terminal, and user.

[1098] System Overview

[1099] The main elements of the system consist of a means for inputting information on the property location and installation conditions, a means for pre-processing, a means for generating design drawings and workflows using generative artificial intelligence, a means for reviewing and correcting, and a means for saving and sharing the final design drawings and workflows.

[1100] Hardware and Software Configuration

[1101] Hardware:

[1102] Server: Cloud server (e.g. AWS EC2)

[1103] Device: Smartphone

[1104] software:

[1105] Server side: Django (backend framework), PyTorch, TensorFlow (generative AI model)

[1106] Client side: React Native (cross-platform mobile development framework)

[1107] Data storage: AWS S3 (storage), AWS RDS (relational database)

[1108] Program processing explanation

[1109] 1. Obtaining input information:

[1110] Users use a smartphone app to input the layout and installation conditions of specific areas within the factory, such as "warehouse section A," "transport line layout," and "safety zone settings."

[1111] The server receives these input data and performs immediate validation.

[1112] 2. Preprocessing the input data:

[1113] The server converts the input data into an appropriate format and standardizes it as internal data. For example, it converts area information into a specific coordinate system and processes installation conditions as numerical data.

[1114] 3. Generative AI for blueprint and workflow generation:

[1115] The server uses the preprocessed data to launch generative artificial intelligence (generative AI) to generate optimal layouts and workflows for factory robots. The generated design drawings and workflows are stored on the server.

[1116] 4. Review and revise blueprints and workflows:

[1117] The user can check the design drawings and workflow generated on their smartphone and make any necessary corrections, for example by changing the robot's position on the smartphone screen using drag and drop, and then send the corrected data to the server.

[1118] 5. Save and share your final design and workflow:

[1119] The server stores the final design drawings and workflow in a database and generates a shared link for stakeholders, allowing the installation team to quickly receive the latest design drawings and workflow.

[1120] Specific examples

[1121] For example, a user inputs "warehouse section A," "transport line layout," and "safety zone settings," and the server receives the request. The server converts "warehouse section A" into coordinate system information (35.6895°N, 139.6917°E), and the generation AI creates and proposes the optimal robot layout and work flow. The user fine-tunes the layout on their smartphone, and once finalized, it is sent to the server. The server saves the final design, generates a link, and notifies relevant parties.

[1122] Prompt Sentence Examples

[1123] Input data:

[1124] Facility Layout: Warehouse Section A

[1125] Installation conditions: Layout of conveying lines, setting of safety zones

[1126] Requests for Generative AI:

[1127] Using the layout information for Warehouse Section A, generate the optimal robot placement and transport line work flow. Establish the most efficient placement while taking safety zones into consideration.

[1128] Example output:

[1129] Robot 1: Transfer point A -> B

[1130] Robot 2: Transfer point C -> D"

[1131] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1132] Processing Steps

[1133] Step 1: Obtaining input information

[1134] (explanation)

[1135] The user uses the smartphone app's input form to input specific sections within the factory and installation conditions, such as "warehouse section A," "transport line layout," and "safety zone settings."

[1136] (input)

[1137] Information on property location and installation conditions.

[1138] (output)

[1139] User-entered data sent to the server.

[1140] (operation)

[1141] The user inputs "warehouse section A," "transport line layout," and "safety zone settings" on their smartphone.

[1142] Sends input data to the server.

[1143] Step 2: Preprocessing the input data

[1144] (explanation)

[1145] The server preprocesses the received data and converts it into the required format, for example converting address information into coordinate data and installation conditions into standardized numerical data.

[1146] (input)

[1147] Information on property location and installation conditions sent by the user.

[1148] (output)

[1149] Preprocessed data (e.g., coordinate data, standardized numerical data).

[1150] (operation)

[1151] The server converts the address information to "(35.6895° N, 139.6917° E)".

[1152] Height restrictions and other installation conditions are standardized as numerical data.

[1153] Step 3: Generative AI creates blueprints and workflows

[1154] (explanation)

[1155] The server uses the pre-processed data to automatically generate blueprints and workflows using generative AI models.

[1156] (input)

[1157] Preprocessed data (coordinate and numerical data).

[1158] (output)

[1159] Generated blueprints and work flows.

[1160] (operation)

[1161] The server inputs the preprocessed data into the generative AI model.

[1162] Generative AI generates optimal placement and work flow for factory robots, and outputs blueprints and flow.

[1163] The generated data is stored on the server.

[1164] Step 4: Review and revise the design and workflow

[1165] (explanation)

[1166] The user can check the generated design drawings and workflow on their smartphone and make corrections as necessary.

[1167] (input)

[1168] Generated blueprints and work flows.

[1169] (output)

[1170] User-modified blueprints and workflows.

[1171] (operation)

[1172] Users can check the blueprints on their smartphone screens.

[1173] Modify the robot position and workflow as needed with drag and drop.

[1174] Resubmit the revised blueprint to the server.

[1175] Step 5: Save and share your final design and workflow

[1176] (explanation)

[1177] The server stores the final design drawings and workflows modified by the user in a database and generates a sharing link for the relevant parties.

[1178] (input)

[1179] User-modified blueprints and workflows.

[1180] (output)

[1181] Saved final design and workflow, shareable links.

[1182] (operation)

[1183] The server stores the final version of the data in the database.

[1184] Generate a shared link and notify relevant parties via email, etc.

[1185] 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.

[1186] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, preprocessing, creating drawings using generative AI, reviewing and correcting the drawings, saving and sharing the final drawings, and even including an emotion engine that recognizes the user's emotions, thereby adjusting the user interface.

[1187] Program processing explanation

[1188] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[1189] 1. Acquiring input information

[1190] The user enters information about the property location and installation conditions into the system's input form, such as "City A," "height limit 50m," and "location and height of surrounding buildings."

[1191] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[1192] 2. Starting Emotion Recognition

[1193] The server analyzes the user's behavior and input while using the input form and activates the emotion engine in real time, which analyzes the data to identify the user's emotions, such as stress or frustration.

[1194] 3. Preprocessing of input data

[1195] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[1196] 4. Tagging preprocessed data

[1197] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1198] 5. Drawing generation using generative AI

[1199] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1200] The generated design drawings are stored on the server.

[1201] 6. Review and revise drawings

[1202] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1203] 7. Emotion-Based User Interface Adjustment

[1204] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance.

[1205] If necessary, generate and display appropriate feedback messages to the user.

[1206] 8. Save and share your final drawing

[1207] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[1208] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1209] Specific examples

[1210] Consider the installation of a new base station in an urban area:

[1211] 1. The user inputs "City A," "Height limit 50m," and "Information about surrounding buildings."

[1212] 2. The server receives this data, converts the address to latitude and longitude (35.0000° N, 135.0000° E), and standardizes the height restriction as numeric data.

[1213] 3. The server analyzes the user's input behavior and delays and uses an emotion engine to determine whether the user is feeling frustrated. For example, if the user repeatedly tries to enter something, it determines that frustration is increasing.

[1214] 4. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[1215] 5. The designer reviews the generated drawings, performs detailed checks, and makes fine adjustments as needed.

[1216] 6. If the emotion engine identifies frustration, the server adjusts the user interface to display an operation guide, clearly showing the user the operation procedure, and displays appropriate feedback messages to support the user.

[1217] 7. The server shares the final design drawings with stakeholders, ensuring the installation team can start work quickly and with the most up-to-date information.

[1218] The above process streamlines the process of creating base station design drawings and improves the user experience, reducing the manual work required by designers and enabling user feedback, facilitating the overall progress of the project.

[1219] The processing flow will be explained below.

[1220] ---

[1221] Step 1:

[1222] The user enters the property location (e.g., "City A") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure that accurate and complete data is entered.

[1223] Step 2:

[1224] The server receives the data sent by the user. This includes information such as address information ("City A") and installation conditions ("Height limit 50m"). The received data is temporarily saved and prepared for the next process.

[1225] Step 3:

[1226] The server runs an emotion engine to analyze the user's input behavior and identify the user's emotions (e.g., stress or frustration) through specific input patterns (e.g., repeated inputs, delayed inputs, etc.).

[1227] Step 4:

[1228] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[1229] Step 5:

[1230] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1231] Step 6:

[1232] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1233] Step 7:

[1234] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[1235] Step 8:

[1236] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1237] Step 9:

[1238] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance. It also generates and displays appropriate feedback messages to the user.

[1239] Step 10:

[1240] The terminal (designer) uploads the revised design drawing back to the server, which saves the uploaded drawing as the final version and also keeps a revision history.

[1241] Step 11:

[1242] The server saves the final design drawings to a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1243] These are the specific processing steps of the base station design drawing creation system that combines an emotion engine. This enables interface adjustments according to the user's emotions and efficient drawing creation, facilitating the overall progress of the project.

[1244] Example 2

[1245] 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."

[1246] The traditional process of creating base station design drawings involves a lot of manual work, making it inefficient and time-consuming. There is also a lack of mechanisms to address the stress and frustration felt by users during the input process, which hinders the overall user experience. Furthermore, there are sometimes delays in sharing design drawings with stakeholders, which can impact project progress.

[1247] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for inputting information on the property location and installation conditions; means for preprocessing the input information and converting it into a required format; means based on a generation artificial intelligence for automatically generating design drawings of a base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving and sharing the automatically generated design drawings with relevant parties; and means based on an emotion engine for recognizing user emotions and adjusting the user interface. This automates and streamlines the process of creating base station design drawings, enables interface adjustment according to the user's emotions, and improves the overall operating experience. Furthermore, it enables rapid sharing of design drawings, facilitating project progress.

[1248] "Property location" is information about the specific geographical location where the base station is installed.

[1249] "Installation conditions" refer to restrictions and requirements for installing a base station, including, for example, height restrictions and the layout of surrounding buildings.

[1250] "Preprocessing" refers to converting input information into an appropriate format, including converting addresses to latitude and longitude coordinates and standardizing numeric data.

[1251] "Generative AI" refers to artificial intelligence technology that automatically generates base station design drawings based on input data.

[1252] An "emotion engine" refers to a system that analyzes a user's behavior and input content to identify the user's emotional state in real time.

[1253] "Design drawings" are drawings that show the specific installation location and structure of the base station, and are automatically generated by a generative AI model.

[1254] "User interface" refers to the screens and operating means that provide interaction for the user to interact with the system.

[1255] "Preprocessed data" refers to data where input information has been converted into an appropriate format and tagged.

[1256] "Tagging" refers to the process of adding classification information and metadata to data to organize it.

[1257] "Review and correction" refers to the process in which a designer checks the generated design drawings and makes fine adjustments as necessary.

[1258] "Storage and sharing" refers to the process in which the final design drawings are stored on a server and provided to stakeholders in the form of a link or similar.

[1259] This invention is a system that automates and streamlines the creation of base station design drawings. The system uses a generative AI model to generate drawings after the user inputs information about the property location and installation conditions, and the server performs preprocessing. The system also provides functions for reviewing and modifying the drawings, as well as saving and sharing the final drawings. Furthermore, the system includes an emotion engine that recognizes the user's emotions and adjusts the user interface accordingly.

[1260] To implement this system, the following hardware and software are used.

[1261] 1. Hardware and software configuration:

[1262] A server is a computer equipped with a high-performance processor and a large amount of memory, and processes and calculates data.

[1263] The terminal is a personal computer or mobile device operated by a designer or user to display and modify drawings.

[1264] The generative AI model is a cloud-based system on which generative AI software (e.g., AutoCAD's AI functions) is installed.

[1265] The emotion engine is a machine learning model for analyzing user input behavior and is implemented on the server.

[1266] 2. Data processing and calculation procedures:

[1267] Users use the system's web interface or mobile app to input information about the property location and installation conditions, including data such as "City A," "50m height limit," and "location and height of surrounding buildings."

[1268] The server receives this input data and performs some basic validation. For example, for City A, it calls a navigation API (e.g., Google Maps API) to convert the address into latitude and longitude (35.0000° N, 135.0000° E). ​​It also standardizes numerical data such as height restrictions into a unified format.

[1269] The emotion engine analyzes the user's input speed, number of corrections, etc. in real time to determine whether the user is feeling stressed or frustrated.

[1270] 3. How generative AI models work:

[1271] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[1272] The generated design drawings are stored in the server's database.

[1273] 4. Review and revise drawings:

[1274] The terminal (designer) displays the generated design drawing and checks and modifies the details. For example, the designer uses design software such as AutoCAD to fine-tune the direction and height of the antenna.

[1275] 5. Save and Share:

[1276] The server saves the final version of the design drawings revised by the designer in a database and generates a sharing link for the relevant parties, which is automatically sent via email to the members involved in the project.

[1277] Examples of specific prompts include:

[1278] "Enter an address in City A and set the height limit to 50m."

[1279] "Enter the location and height of surrounding buildings and generate the optimal design drawing for your base station."

[1280] "Check the antenna placement in the automatically generated design drawing and correct it if necessary."

[1281] The above is an embodiment of the present invention, which not only automates the process of creating base station design drawings, but also improves the user's operation experience.

[1282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1283] Step 1:

[1284] Obtaining input information

[1285] The user enters information about the property location and installation conditions into the system's input form, providing data such as "City A," "height limit of 50m," and "location and height of surrounding buildings."

[1286] The server receives the data entered by the user, stores it in the system, and performs basic data integrity checks (e.g., checking the format of numbers).

[1287] Output: Verified property location and installation information.

[1288] Step 2:

[1289] Starting emotion recognition

[1290] The server collects real-time data while the user is using the input form, specifically analyzing the user's emotional state based on input speed, number of corrections, frequency of typing errors, etc.

[1291] For example, if a series of typing errors occur, the server determines that the user is irritated and updates the emotional status.

[1292] Output: Real-time emotional status information.

[1293] Step 3:

[1294] Preprocessing of input data

[1295] The server calls a navigation API (e.g., Google Maps API) to convert the property address into latitude and longitude. As a result, "City A" is obtained as "35.0000° N, 135.0000° E."

[1296] The server standardizes numerical data such as height restrictions and converts them into a unified format internally.

[1297] Output: Geographic information converted to latitude and longitude and standardized height restriction information.

[1298] Step 4:

[1299] Tagging preprocessed data

[1300] The server then tags the preprocessed data with metadata, adding tags such as "urban area," "office building," and "50m height limit." This tagging organizes the data and allows the generative AI model to process it efficiently.

[1301] Output: Tagged preprocessed data.

[1302] Step 5:

[1303] Drawing generation using generative AI

[1304] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[1305] The server stores the generated design drawings in a database.

[1306] Output: Auto-generated engineering drawings.

[1307] Step 6:

[1308] Drawing review and revision

[1309] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes fine adjustments using design software such as AutoCAD. For example, they may make slight changes to the direction or placement of the antenna.

[1310] The terminal (designer) uploads the revised design drawing back to the server.

[1311] Output: Modified engineering drawings.

[1312] Step 7:

[1313] Emotion-Based User Interface Adjustment

[1314] The server adjusts the user interface in real time based on the user's emotional status recognized by the emotion engine. For example, if the user is feeling frustrated, it may pop up an operation guide or enhance input assistance functions.

[1315] The server displays an appropriate feedback message (e.g., "Thank you for your input. Is there anything we can help you with?") in the user interface.

[1316] Output: Tailored user interface and feedback messages.

[1317] Step 8:

[1318] Save and share your final drawing

[1319] The terminal (designer) uploads the revised design drawing to the server, which saves the uploaded drawing as the final version and stores it in the database along with the revision history.

[1320] The server generates a shared link for the final design drawing and sends an automatic email notification to stakeholders, allowing them to access the latest version of the drawing.

[1321] Output: Final design drawings saved and shared links.

[1322] (Application example 2)

[1323] 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."

[1324] The process of creating factory design drawings involves a lot of manual work, which requires time and effort. Furthermore, the design process is carried out without consideration of the user's emotions and stress levels, which can result in a poor user experience and hinder productivity. Furthermore, it is difficult to automatically determine the optimal layout of robot movement paths and work stations within the factory.

[1325] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information on the location and installation conditions of the property; means for preprocessing the input information and converting it into a required format; means based on generative artificial intelligence for automatically generating design drawings of the base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving the final design drawings and sharing them with relevant parties; and means for recognizing user emotions and adjusting the user interface. This enables the automatic generation and correction of design drawings to be performed efficiently, and operation guides and feedback according to the user's emotions to be provided, thereby improving the user experience and increasing productivity.

[1326] "Property location" refers to the location of the new production line within a particular factory.

[1327] "Installation conditions" refers to factors that indicate the installation environment, such as layout restrictions within the factory, equipment size, traffic flow and altitude restrictions.

[1328] "Input means" refers to a mechanism that provides an interface for users to input the property location and installation conditions.

[1329] The "preprocessing means" is a mechanism for standardizing input information and converting it into latitude and longitude coordinates and numerical data.

[1330] "Generative AI" is an AI technology that uses algorithms and programs to automatically generate optimal design drawings based on past design data and current installation conditions.

[1331] "Review and correction means" refers to functions and interfaces for checking the generated design drawings and making corrections as necessary.

[1332] "Storage and sharing means" is a mechanism for storing the final design drawings in a database and generating a sharing link for relevant parties.

[1333] "Means for recognizing user emotions" refers to technology that analyzes emotions such as stress and frustration based on the user's input behavior and data.

[1334] The "user interface adjustment means" is a mechanism that displays operation guides and feedback messages according to the recognized user emotions, thereby improving the operation experience.

[1335] The "tagging means" is a function for assigning tags to preprocessed data and organizing the data efficiently.

[1336] The "latitude and longitude conversion means" is a function for converting address information of a property location into latitude and longitude.

[1337] The "numerical value conversion means" is a function for converting conditions such as height restrictions into numerical data.

[1338] This invention is a system that automatically generates optimal design drawings for new production lines in factories and adjusts the interface based on the user's emotions. This system operates by combining a server, user terminals, and various software.

[1339] The server first receives information on the property location and installation conditions entered by the user in real time. The user inputs the factory layout, equipment size, constraints, etc. via their terminal. The server also analyzes the user's behavior while entering data and recognizes the user's stress and frustration in real time through an emotion engine. This improves the user experience.

[1340] The server then preprocesses the input data, converting address information into latitude and longitude using a navigation API (e.g., Google Maps API) and standardizing numerical data such as height restrictions. The preprocessed data is also tagged with terms such as "semiconductor manufacturing equipment" and "transport robot," allowing the generative AI to efficiently generate blueprints.

[1341] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings based on past production line design data and current installation conditions. These generated designs are stored on a server and can be accessed by designers for modification and review. Designers can also review the generated drawings in detail and make modifications as necessary.

[1342] The server generates a link to share the final design drawings with all stakeholders. This link is provided to all members involved in the project, enabling them to work quickly and with the latest information.

[1343] As a specific example, consider the case where the user inputs the following conditions:

[1344] Factory size: 500 square meters

[1345] Device size: 2 meters x 3 meters

[1346] Restricting robot movement

[1347] Height limit: 3 meters

[1348] An example of a prompt is:

[1349] New production line design requirements:

[1350] Factory size: 500 square meters

[1351] Equipment size: 2 meters x 3 meters

[1352] Restricting robot movement

[1353] Height limit: 3 meters

[1354] Next, a helpful message is displayed to reduce the user's stress.

[1355] In this way, the system of the present invention can automatically generate, review, modify, save, and share design drawings efficiently while responding to user emotions. It also improves the user experience by displaying operation guides and support messages.

[1356] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1357] Step 1:

[1358] The user uses an input form on the terminal to input information about the property location and installation conditions, such as the size of the factory and the size of the equipment, placement restrictions, etc. This information is then sent to the server.

[1359] input:

[1360] Factory size: 500 square meters

[1361] Equipment size: 2 meters x 3 meters

[1362] Restricting robot movement

[1363] Height limit: 3 meters

[1364] output:

[1365] Information on the property location and installation conditions sent to the server

[1366] Step 2:

[1367] The server analyzes the received input data in real time and performs basic validation to check for inconsistencies in the input. If there are any inconsistencies, it returns an error message to the user. If validation is successful, it proceeds to the next step.

[1368] input:

[1369] Property location and installation conditions information entered by the user

[1370] output:

[1371] Verification result (normal / error)

[1372] Step 3:

[1373] The server analyzes the user's input behavior and content using an emotion engine to determine whether the user is feeling stressed or frustrated, thereby understanding the user's emotions.

[1374] input:

[1375] User input behavior and input content

[1376] output:

[1377] User emotion information (e.g., normal, highly frustrated)

[1378] Step 4:

[1379] The server uses a navigation API to convert address information into latitude and longitude coordinates and standardizes numerical data such as height restrictions for installation conditions. This preprocessing prepares the data in a format suitable for further processing.

[1380] input:

[1381] Property address information

[1382] Height restrictions for installation conditions

[1383] output:

[1384] Latitude and longitude information

[1385] Standardized Height Limit Measures

[1386] Step 5:

[1387] The server tags the preprocessed data and supplies organized data such as "semiconductor manufacturing equipment" and "transport robot" to the generative AI model. This tagging efficiently organizes the data.

[1388] input:

[1389] Preprocessed data

[1390] output:

[1391] Tagged data

[1392] Step 6:

[1393] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings for the production line based on past design data and current installation conditions. The generated design drawings are stored on a server.

[1394] input:

[1395] Tagged data

[1396] Past design data

[1397] output:

[1398] Procedurally generated blueprints

[1399] Step 7:

[1400] Designers can use their devices to review the generated design drawings and make any necessary corrections, which are then uploaded back to the server.

[1401] input:

[1402] Procedurally generated blueprints

[1403] output:

[1404] Modified blueprints

[1405] Step 8:

[1406] The server adjusts the user interface based on the recognized user emotion, for example, by displaying operation guides or encouraging messages to improve the user experience.

[1407] input:

[1408] User emotion information

[1409] output:

[1410] Adjusted User Interface

[1411] Step 9:

[1412] The server stores the final, revised version of the blueprint and generates a shared link that can be sent to all stakeholders, making the latest blueprint accessible to all project members.

[1413] input:

[1414] Modified blueprints

[1415] output:

[1416] Generated Shared Link

[1417] 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.

[1418] 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.

[1419] 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.

[1420] [Fourth embodiment]

[1421] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1422] 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.

[1423] 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).

[1424] 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.

[1425] 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.

[1426] 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).

[1427] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1428] 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.

[1429] 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.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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."

[1434] ---

[1435] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, pre-processing, creating drawings using generation AI, reviewing and correcting the drawings, and saving and sharing the final drawings.

[1436] Program processing explanation

[1437] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[1438] 1. Acquiring input information

[1439] The user enters information about the property location and installation conditions into the system's input form, such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings."

[1440] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[1441] 2. Preprocessing of input data

[1442] The server calls an external navigation API to convert address information to latitude and longitude, and also normalizes numeric data (such as height restrictions) and converts it into the appropriate format for internal processing. For example, it converts "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E".

[1443] Once preprocessed, the data is tagged and sent to the next generation step.

[1444] 3. Drawing generation using generative AI

[1445] The server runs a generative artificial intelligence (generative AI) using the pre-processed data.

[1446] The AI ​​automatically generates base station design drawings based on past design data and current installation conditions, for example, taking into account neighboring buildings and determining the optimal antenna placement.

[1447] The generated design drawings are stored on the server.

[1448] 4. Review and revise drawings

[1449] The terminal (designer) receives the generated drawings and performs a detailed review, adding comments to the drawings and manually making specific modifications, such as adjusting the antenna direction or reflecting design changes.

[1450] The revised design drawings are sent back to the server and saved as the final version.

[1451] 5. Save and share your final drawing

[1452] The server stores the final design drawings in a database, while simultaneously recording the design change history for future review.

[1453] The server generates a shared link for the saved design drawings to be shared with the relevant parties and notifies the members involved in the project, allowing the installation team to quickly receive the latest design drawings.

[1454] Specific examples

[1455] Consider the installation of a new base station in an urban area:

[1456] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[1457] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[1458] 3. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[1459] 4. The terminal (designer) reviews the generated drawing and makes any necessary adjustments, such as fine-tuning the antenna direction.

[1460] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[1461] Through this process, the creation of drawings for base station installation is made more efficient and the amount of manual work required by designers is reduced, enabling the entire project, from design to installation, to proceed quickly and accurately.

[1462] The processing flow will be explained below.

[1463] ---

[1464] Step 1:

[1465] The user enters the property location (e.g., "Shibuya-ku, Tokyo") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure accurate and complete data is entered.

[1466] Step 2:

[1467] The server receives the data sent by the user, including address information, numerical data, installation conditions, etc. The server temporarily stores the received data and prepares it for the next process.

[1468] Step 3:

[1469] The server calls the navigation API to convert address information into latitude and longitude. For example, "Shibuya-ku, Tokyo" becomes "35.6895° N, 139.6917° E." It also standardizes numerical data such as height restrictions for internal use.

[1470] Step 4:

[1471] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1472] Step 5:

[1473] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1474] Step 6:

[1475] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[1476] Step 7:

[1477] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1478] Step 8:

[1479] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[1480] Step 9:

[1481] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1482] This is the specific process flow from creating base station design drawings to final sharing, which significantly improves the efficiency and accuracy of the design process.

[1483] Example 1

[1484] 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."

[1485] Designing base stations requires a lot of data processing and manual work, which increases time and costs. Furthermore, the accuracy and consistency of design drawings can be compromised by human error. Furthermore, if information is not shared smoothly among stakeholders, the progress of the entire project can be delayed. The present invention aims to solve these problems and improve the efficiency and accuracy of base station design.

[1486] 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.

[1487] In this invention, the server includes a means for inputting information on the location and installation conditions of the property, a means for preprocessing the input information and converting it into a required format, a means for automatically generating design drawings of the base station based on a generative model using the preprocessed data, a means for a designer to review and correct the generated design drawings, and a means for saving the final design drawings in a database and generating a sharing link for related parties, thereby automating the base station design process, improving overall efficiency, and maintaining the accuracy and consistency of the design drawings.

[1488] "Property Location" refers to the specific geographic location information for installing a base station.

[1489] "Installation Conditions" refers to the physical, legal and environmental constraints and requirements when installing a base station.

[1490] "Preprocessing" refers to a series of data processing steps that convert the information entered by the user into a format that is easy for the system to use.

[1491] A "generative model" refers to an algorithm or program that uses artificial intelligence technology to automatically generate base station design drawings.

[1492] "Design Drawings" means drawings showing the physical layout, structure, and technical details of a Base Station.

[1493] "Review" refers to the process in which a designer reviews the generated design drawings and makes appropriate corrections.

[1494] "Saving" refers to the act of recording the generated design drawings and their change history in a database.

[1495] A "shared link" refers to the URL or access method for sharing design drawings online with relevant parties.

[1496] The system of the present invention automates and streamlines the creation of base station design drawings. This system functions through a series of processes: inputting the property location and installation conditions, preprocessing the input data, generating drawings using AI, reviewing and correcting the drawings, and saving and sharing the final drawings. Specific embodiments are described in detail below.

[1497] 1. Acquiring input information

[1498] The user enters information about the property location and installation conditions into the system's input form. The input includes specific data such as "Shibuya Ward, Tokyo," "height limit of 50m," and "location and height of surrounding buildings." This allows the user to communicate the planned installation location and conditions to the system. The input information is sent to the server.

[1499] 2. Preprocessing of input data

[1500] The server preprocesses the received input data. This preprocessing includes converting address information to latitude and longitude using an external navigation API (e.g., converting "Shibuya-ku, Tokyo" to "35.6895° N, 139.6917° E") and standardizing numerical data (e.g., height restrictions). Specifically, Google Maps API is used. After preprocessing, the data is tagged and sent to the next generation step.

[1501] 3. Drawing generation using generative AI

[1502] The server runs a generation AI using the preprocessed data. The generation AI automatically generates base station design drawings based on past design data and current installation conditions. For example, a prompt such as "Please create a design drawing for a base station at 35.6895° N, 139.6917° E. The height limit is 50m, and information on nearby buildings is as follows" is used. Based on this information, the generation AI determines the optimal antenna placement and generates the associated design drawings. The generated design drawings are stored on the server.

[1503] 4. Review and revise drawings

[1504] The terminal (designer) receives the generated drawings from the server and performs a detailed review. The designer can add comments to the drawings or manually make specific modifications. For example, they can adjust the direction of the antenna or reflect changes in the design. The modified design drawings are then sent back to the server and saved as the final version.

[1505] 5. Save and share your final drawing

[1506] The server saves the final design drawings to a database, simultaneously recording the design change history for future review. It also generates a shared link for sharing the saved design drawings with stakeholders and notifies all project members, allowing the installation team to quickly receive the latest design drawings.

[1507] Specific examples

[1508] Consider the installation of a new base station in an urban area. Here's what happens:

[1509] 1. The user enters "Shibuya Ward, Tokyo," "height limit 50m," and "information about surrounding buildings."

[1510] 2. The server receives this data, converts the address to latitude and longitude (35.6895° N, 139.6917° E), and standardizes the height restriction as numeric data.

[1511] 3. Generative AI automatically creates a base station design based on the input data. This design is optimized taking into account the surrounding location conditions.

[1512] 4. The device (designer) reviews the generated drawings and makes any necessary adjustments, such as fine-tuning the antenna direction.

[1513] 5. The server saves the final design drawings to the database and generates a shared link to send to the relevant parties. The installation team downloads the latest design drawings from the link and begins installation.

[1514] Through this series of processes, the present invention significantly improves the efficiency of base station design, enabling the entire project to proceed quickly and accurately.

[1515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1516] Program processing flow

[1517] Step 1: Obtaining input information

[1518] The user accesses the system's input form and enters the property location (Shibuya-ku, Tokyo) and installation conditions such as a height limit of 50m and the location and height of surrounding buildings.

[1519] Input: Property location information, and specific numbers and ratios for installation conditions

[1520] The server receives the information obtained from the input form.

[1521] Output: Received input data

[1522] Specific behavior: When a user clicks the "Submit" button on an input form, the information is sent to the server.

[1523] Step 2: Preprocessing input data

[1524] The server uses the Google Maps API to convert the received data into geographic information (e.g., "Shibuya-ku, Tokyo") into latitude and longitude coordinates of "35.6895° N, 139.6917° E."

[1525] Input: Address information and numeric data (e.g. height restrictions)

[1526] Data processing: Address information is converted to latitude and longitude using the navigation API, and the numerical data is standardized.

[1527] Output: Preprocessed latitude and longitude information and standardized numerical data

[1528] Specific operation: Calls the Google Maps API, converts address information into latitude and longitude, and standardizes the unit of numeric data to meters.

[1529] Step 3: Generate drawings using generative AI

[1530] The server runs a generative AI model based on the pre-processed data.

[1531] Input: Latitude and longitude information, standardized height restrictions, etc.

[1532] Data calculation: Generative AI automatically generates base station design drawings based on past design data and current installation conditions.

[1533] Output: Generated base station design drawings

[1534] Specific operation: A prompt is input into the generation AI, and the AI ​​generates the drawing based on instructions such as, "Please create a design drawing for a base station located at 35.6895° N, 139.6917° E. The height limit is 50m, and the nearby buildings are as follows: Building 1, Building 2. Please determine the optimal antenna placement taking into account the surrounding environment."

[1535] Step 4: Review and revise the drawing

[1536] The terminal (designer) accesses and reviews the design drawings sent from the server.

[1537] Input: Generated design drawings

[1538] Data processing: review and manual corrections as needed

[1539] Output: Revised final design drawings

[1540] Specific operations: The designer adds comments to the drawing, adjusts the direction and height of the antenna, and resends the revised drawing to the server.

[1541] Step 5: Save and share your final drawing

[1542] The server stores the final design drawings in a database.

[1543] Input: Revised final design drawings

[1544] Data storage: The final design drawings and change history are recorded in a database.

[1545] Output: Link for sharing

[1546] Specific operation: The design drawings are saved in a database, a shared link is generated to notify relevant parties, and the link is notified to project members.

[1547] Through the above processing steps, a series of processes from creating base station design drawings to sharing them can be efficiently carried out.

[1548] (Application example 1)

[1549] 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."

[1550] Conventional factory robot installation and workflow design requires a great deal of time and effort, and is often inefficient because it depends heavily on the skill level of the designer. Furthermore, creating and modifying blueprints and workflows is time-consuming, making it difficult to achieve optimal robot placement and workflows. To solve these problems, a system is needed that can efficiently and automatically create robot installation plans and workflows based on input information.

[1551] 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.

[1552] In this invention, the server includes a means for inputting information on the location of the property and installation conditions, a means for preprocessing the input information and converting it into a required format, a means based on artificial intelligence for automatically generating design drawings and workflows using the preprocessed data, a means for reviewing and modifying the automatically generated design drawings and workflows, and a means for saving and sharing the final design drawings and workflows with relevant parties. This allows users to efficiently create and modify robot installation plans and workflows and quickly share optimized design drawings.

[1553] - "Property Location" refers to the geographic location where a particular property is located.

[1554] "Installation conditions" refers to information about the various conditions and restrictions regarding installation at the property.

[1555] "Preprocessing" is the process of converting input information into an appropriate format and preparing the data for use in the next processing step.

[1556] "Generative AI" is an AI technology that automatically generates design drawings and workflows based on past data and current conditions.

[1557] "Design drawings" are detailed drawing information regarding the layout and installation of properties and equipment.

[1558] A "work flow" is a flow diagram showing specific work procedures and processes, along with detailed step information.

[1559] "Review" is the process of checking the generated design drawings and work flow and making any necessary corrections or additions.

[1560] "Final version" refers to the final version of the design drawings and work flow that has been finalized after all revisions and reviews have been completed.

[1561] "Storage" is the process of recording the created and modified design drawings and work flows in a database or storage.

[1562] "Sharing" is the process of coordinating and making accessible the design drawings and workflows created by stakeholders.

[1563] The present invention provides a system for efficiently and automatically generating installation plans and work flows for factory robots. Below, we will explain in detail each of the main processes from the perspectives of the server, terminal, and user.

[1564] System Overview

[1565] The main elements of the system consist of a means for inputting information on the property location and installation conditions, a means for pre-processing, a means for generating design drawings and workflows using generative artificial intelligence, a means for reviewing and correcting, and a means for saving and sharing the final design drawings and workflows.

[1566] Hardware and Software Configuration

[1567] Hardware:

[1568] Server: Cloud server (e.g. AWS EC2)

[1569] Device: Smartphone

[1570] software:

[1571] Server side: Django (backend framework), PyTorch, TensorFlow (generative AI model)

[1572] Client side: React Native (cross-platform mobile development framework)

[1573] Data storage: AWS S3 (storage), AWS RDS (relational database)

[1574] Program processing explanation

[1575] 1. Obtaining input information:

[1576] Users use a smartphone app to input the layout and installation conditions of specific areas within the factory, such as "warehouse section A," "transport line layout," and "safety zone settings."

[1577] The server receives these input data and performs immediate validation.

[1578] 2. Preprocessing the input data:

[1579] The server converts the input data into an appropriate format and standardizes it as internal data. For example, it converts area information into a specific coordinate system and processes installation conditions as numerical data.

[1580] 3. Generative AI for blueprint and workflow generation:

[1581] The server uses the preprocessed data to launch generative artificial intelligence (generative AI) to generate optimal layouts and workflows for factory robots. The generated design drawings and workflows are stored on the server.

[1582] 4. Review and revise blueprints and workflows:

[1583] The user can check the design drawings and workflow generated on their smartphone and make any necessary corrections, for example by changing the robot's position on the smartphone screen using drag and drop, and then send the corrected data to the server.

[1584] 5. Save and share your final design and workflow:

[1585] The server stores the final design drawings and workflow in a database and generates a shared link for stakeholders, allowing the installation team to quickly receive the latest design drawings and workflow.

[1586] Specific examples

[1587] For example, a user inputs "warehouse section A," "transport line layout," and "safety zone settings," and the server receives the request. The server converts "warehouse section A" into coordinate system information (35.6895°N, 139.6917°E), and the generation AI creates and proposes the optimal robot layout and work flow. The user fine-tunes the layout on their smartphone, and once finalized, it is sent to the server. The server saves the final design, generates a link, and notifies relevant parties.

[1588] Prompt Sentence Examples

[1589] Input data:

[1590] Facility Layout: Warehouse Section A

[1591] Installation conditions: Layout of conveying lines, setting of safety zones

[1592] Requests for Generative AI:

[1593] Using the layout information for Warehouse Section A, generate the optimal robot placement and transport line work flow. Establish the most efficient placement while taking safety zones into consideration.

[1594] Example output:

[1595] Robot 1: Transfer point A -> B

[1596] Robot 2: Transfer point C -> D"

[1597] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1598] Processing Steps

[1599] Step 1: Obtaining input information

[1600] (explanation)

[1601] The user uses the smartphone app's input form to input specific sections within the factory and installation conditions, such as "warehouse section A," "transport line layout," and "safety zone settings."

[1602] (input)

[1603] Information on property location and installation conditions.

[1604] (output)

[1605] User-entered data sent to the server.

[1606] (operation)

[1607] The user inputs "warehouse section A," "transport line layout," and "safety zone settings" on their smartphone.

[1608] Sends input data to the server.

[1609] Step 2: Preprocessing the input data

[1610] (explanation)

[1611] The server preprocesses the received data and converts it into the required format, for example converting address information into coordinate data and installation conditions into standardized numerical data.

[1612] (input)

[1613] Information on property location and installation conditions sent by the user.

[1614] (output)

[1615] Preprocessed data (e.g., coordinate data, standardized numerical data).

[1616] (operation)

[1617] The server converts the address information to "(35.6895° N, 139.6917° E)".

[1618] Height restrictions and other installation conditions are standardized as numerical data.

[1619] Step 3: Generative AI creates blueprints and workflows

[1620] (explanation)

[1621] The server uses the pre-processed data to automatically generate blueprints and workflows using generative AI models.

[1622] (input)

[1623] Preprocessed data (coordinate and numerical data).

[1624] (output)

[1625] Generated blueprints and work flows.

[1626] (operation)

[1627] The server inputs the preprocessed data into the generative AI model.

[1628] Generative AI generates optimal placement and work flow for factory robots, and outputs blueprints and flow.

[1629] The generated data is stored on the server.

[1630] Step 4: Review and revise the design and workflow

[1631] (explanation)

[1632] The user can check the generated design drawings and workflow on their smartphone and make corrections as necessary.

[1633] (input)

[1634] Generated blueprints and work flows.

[1635] (output)

[1636] User-modified blueprints and workflows.

[1637] (operation)

[1638] Users can check the blueprints on their smartphone screens.

[1639] Modify the robot position and workflow as needed with drag and drop.

[1640] Resubmit the revised blueprint to the server.

[1641] Step 5: Save and share your final design and workflow

[1642] (explanation)

[1643] The server stores the final design drawings and workflows modified by the user in a database and generates a sharing link for the relevant parties.

[1644] (input)

[1645] User-modified blueprints and workflows.

[1646] (output)

[1647] Saved final design and workflow, shareable links.

[1648] (operation)

[1649] The server stores the final version of the data in the database.

[1650] Generate a shared link and notify relevant parties via email, etc.

[1651] 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.

[1652] This invention is a system for automating and streamlining the creation of base station design drawings. It involves inputting the property location and installation conditions, preprocessing, creating drawings using generative AI, reviewing and correcting the drawings, saving and sharing the final drawings, and even including an emotion engine that recognizes the user's emotions, thereby adjusting the user interface.

[1653] Program processing explanation

[1654] The system of the present invention performs various operations. Below, each major process will be explained in natural language from the viewpoints of the server, the terminal, and the user.

[1655] 1. Acquiring input information

[1656] The user enters information about the property location and installation conditions into the system's input form, such as "City A," "height limit 50m," and "location and height of surrounding buildings."

[1657] The server receives these inputs and performs basic validation immediately to ensure that the information entered is consistent.

[1658] 2. Starting Emotion Recognition

[1659] The server analyzes the user's behavior and input while using the input form and activates the emotion engine in real time, which analyzes the data to identify the user's emotions, such as stress or frustration.

[1660] 3. Preprocessing of input data

[1661] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[1662] 4. Tagging preprocessed data

[1663] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1664] 5. Drawing generation using generative AI

[1665] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1666] The generated design drawings are stored on the server.

[1667] 6. Review and revise drawings

[1668] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1669] 7. Emotion-Based User Interface Adjustment

[1670] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance.

[1671] If necessary, generate and display appropriate feedback messages to the user.

[1672] 8. Save and share your final drawing

[1673] The terminal (designer) uploads the revised design drawing back to the server. The server saves the uploaded drawing as the final version. The revision history is also saved.

[1674] The server stores the final design drawings in a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1675] Specific examples

[1676] Consider the installation of a new base station in an urban area:

[1677] 1. The user inputs "City A," "Height limit 50m," and "Information about surrounding buildings."

[1678] 2. The server receives this data, converts the address to latitude and longitude (35.0000° N, 135.0000° E), and standardizes the height restriction as numeric data.

[1679] 3. The server analyzes the user's input behavior and delays and uses an emotion engine to determine whether the user is feeling frustrated. For example, if the user repeatedly tries to enter something, it determines that frustration is increasing.

[1680] 4. Generative AI automatically creates base station design drawings based on the input data. This design is optimized taking into account the surrounding location conditions.

[1681] 5. The designer reviews the generated drawings, performs detailed checks, and makes fine adjustments as needed.

[1682] 6. If the emotion engine identifies frustration, the server adjusts the user interface to display an operation guide, clearly showing the user the operation procedure, and displays appropriate feedback messages to support the user.

[1683] 7. The server shares the final design drawings with stakeholders, ensuring the installation team can start work quickly and with the most up-to-date information.

[1684] The above process streamlines the process of creating base station design drawings and improves the user experience, reducing the manual work required by designers and enabling user feedback, facilitating the overall progress of the project.

[1685] The processing flow will be explained below.

[1686] ---

[1687] Step 1:

[1688] The user enters the property location (e.g., "City A") and installation conditions (e.g., "height limit 50m" and "location and height of surrounding buildings") into the system's input form. The input form undergoes basic validation to ensure that accurate and complete data is entered.

[1689] Step 2:

[1690] The server receives the data sent by the user. This includes information such as address information ("City A") and installation conditions ("Height limit 50m"). The received data is temporarily saved and prepared for the next process.

[1691] Step 3:

[1692] The server runs an emotion engine to analyze the user's input behavior and identify the user's emotions (e.g., stress or frustration) through specific input patterns (e.g., repeated inputs, delayed inputs, etc.).

[1693] Step 4:

[1694] The server calls the navigation API to convert address information into latitude and longitude, for example, "City A" becomes "35.0000° N, 135.0000° E," and standardizes numerical data such as height restrictions for internal use.

[1695] Step 5:

[1696] The server then tags the preprocessed data, for example, adding tags such as "urban area," "office building," and "height limit 50m." This organizes the data and allows the generation AI to process it efficiently.

[1697] Step 6:

[1698] The server then supplies the preprocessed data and tagged information to the generation AI, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement, taking into account surrounding buildings.

[1699] Step 7:

[1700] The server stores the design drawings created by the generative AI, which are then placed in an environment where designers can access them.

[1701] Step 8:

[1702] The terminal (designer) receives the design drawings generated from the server and performs detailed checks. The designer reviews the drawings and makes corrections as necessary. For example, specific corrections such as fine-tuning the antenna direction are made.

[1703] Step 9:

[1704] The server adjusts the user interface according to the user's emotions recognized by the emotion engine. For example, if the user is feeling frustrated, it will respond by displaying operation guides or enhancing input assistance. It also generates and displays appropriate feedback messages to the user.

[1705] Step 10:

[1706] The terminal (designer) uploads the revised design drawing back to the server, which saves the uploaded drawing as the final version and also keeps a revision history.

[1707] Step 11:

[1708] The server saves the final design drawings to a database and generates a shared link for stakeholders, which is sent to everyone involved in the project, allowing the installation team to quickly retrieve the latest design drawings.

[1709] These are the specific processing steps of the base station design drawing creation system that combines an emotion engine. This enables interface adjustments according to the user's emotions and efficient drawing creation, facilitating the overall progress of the project.

[1710] Example 2

[1711] 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."

[1712] The traditional process of creating base station design drawings involves a lot of manual work, making it inefficient and time-consuming. There is also a lack of mechanisms to address the stress and frustration felt by users during the input process, which hinders the overall user experience. Furthermore, there are sometimes delays in sharing design drawings with stakeholders, which can impact project progress.

[1713] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for inputting information on the property location and installation conditions; means for preprocessing the input information and converting it into a required format; means based on a generation artificial intelligence for automatically generating design drawings of a base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving and sharing the automatically generated design drawings with relevant parties; and means based on an emotion engine for recognizing user emotions and adjusting the user interface. This automates and streamlines the process of creating base station design drawings, enables interface adjustment according to the user's emotions, and improves the overall operating experience. Furthermore, it enables rapid sharing of design drawings, facilitating project progress.

[1714] "Property location" is information about the specific geographical location where the base station is installed.

[1715] "Installation conditions" refer to restrictions and requirements for installing a base station, including, for example, height restrictions and the layout of surrounding buildings.

[1716] "Preprocessing" refers to converting input information into an appropriate format, including converting addresses to latitude and longitude coordinates and standardizing numeric data.

[1717] "Generative AI" refers to artificial intelligence technology that automatically generates base station design drawings based on input data.

[1718] An "emotion engine" refers to a system that analyzes a user's behavior and input content to identify the user's emotional state in real time.

[1719] "Design drawings" are drawings that show the specific installation location and structure of the base station, and are automatically generated by a generative AI model.

[1720] "User interface" refers to the screens and operating means that provide interaction for the user to interact with the system.

[1721] "Preprocessed data" refers to data where input information has been converted into an appropriate format and tagged.

[1722] "Tagging" refers to the process of adding classification information and metadata to data to organize it.

[1723] "Review and correction" refers to the process in which a designer checks the generated design drawings and makes fine adjustments as necessary.

[1724] "Storage and sharing" refers to the process in which the final design drawings are stored on a server and provided to stakeholders in the form of a link or similar.

[1725] This invention is a system that automates and streamlines the creation of base station design drawings. The system uses a generative AI model to generate drawings after the user inputs information about the property location and installation conditions, and the server performs preprocessing. The system also provides functions for reviewing and modifying the drawings, as well as saving and sharing the final drawings. Furthermore, the system includes an emotion engine that recognizes the user's emotions and adjusts the user interface accordingly.

[1726] To implement this system, the following hardware and software are used.

[1727] 1. Hardware and software configuration:

[1728] A server is a computer equipped with a high-performance processor and a large amount of memory, and processes and calculates data.

[1729] The terminal is a personal computer or mobile device operated by a designer or user to display and modify drawings.

[1730] The generative AI model is a cloud-based system on which generative AI software (e.g., AutoCAD's AI functions) is installed.

[1731] The emotion engine is a machine learning model for analyzing user input behavior and is implemented on the server.

[1732] 2. Data processing and calculation procedures:

[1733] Users use the system's web interface or mobile app to input information about the property location and installation conditions, including data such as "City A," "50m height limit," and "location and height of surrounding buildings."

[1734] The server receives this input data and performs some basic validation. For example, for City A, it calls a navigation API (e.g., Google Maps API) to convert the address into latitude and longitude (35.0000° N, 135.0000° E). ​​It also standardizes numerical data such as height restrictions into a unified format.

[1735] The emotion engine analyzes the user's input speed, number of corrections, etc. in real time to determine whether the user is feeling stressed or frustrated.

[1736] 3. How generative AI models work:

[1737] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[1738] The generated design drawings are stored in the server's database.

[1739] 4. Review and revise drawings:

[1740] The terminal (designer) displays the generated design drawing and checks and modifies the details. For example, the designer uses design software such as AutoCAD to fine-tune the direction and height of the antenna.

[1741] 5. Save and Share:

[1742] The server saves the final version of the design drawings revised by the designer in a database and generates a sharing link for the relevant parties, which is automatically sent via email to the members involved in the project.

[1743] Examples of specific prompts include:

[1744] "Enter an address in City A and set the height limit to 50m."

[1745] "Enter the location and height of surrounding buildings and generate the optimal design drawing for your base station."

[1746] "Check the antenna placement in the automatically generated design drawing and correct it if necessary."

[1747] The above is an embodiment of the present invention, which not only automates the process of creating base station design drawings, but also improves the user's operation experience.

[1748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1749] Step 1:

[1750] Obtaining input information

[1751] The user enters information about the property location and installation conditions into the system's input form, providing data such as "City A," "height limit of 50m," and "location and height of surrounding buildings."

[1752] The server receives the data entered by the user, stores it in the system, and performs basic data integrity checks (e.g., checking the format of numbers).

[1753] Output: Verified property location and installation information.

[1754] Step 2:

[1755] Starting emotion recognition

[1756] The server collects real-time data while the user is using the input form, specifically analyzing the user's emotional state based on input speed, number of corrections, frequency of typing errors, etc.

[1757] For example, if a series of typing errors occur, the server determines that the user is irritated and updates the emotional status.

[1758] Output: Real-time emotional status information.

[1759] Step 3:

[1760] Preprocessing of input data

[1761] The server calls a navigation API (e.g., Google Maps API) to convert the property address into latitude and longitude. As a result, "City A" is obtained as "35.0000° N, 135.0000° E."

[1762] The server standardizes numerical data such as height restrictions and converts them into a unified format internally.

[1763] Output: Geographic information converted to latitude and longitude and standardized height restriction information.

[1764] Step 4:

[1765] Tagging preprocessed data

[1766] The server then tags the preprocessed data with metadata, adding tags such as "urban area," "office building," and "50m height limit." This tagging organizes the data and allows the generative AI model to process it efficiently.

[1767] Output: Tagged preprocessed data.

[1768] Step 5:

[1769] Drawing generation using generative AI

[1770] The server then supplies the preprocessed data and tagged information to a generative AI model, which then automatically generates base station design drawings based on past design data and current installation conditions. For example, it determines the optimal antenna placement by taking into account the location and height of surrounding buildings.

[1771] The server stores the generated design drawings in a database.

[1772] Output: Auto-generated engineering drawings.

[1773] Step 6:

[1774] Drawing review and revision

[1775] The terminal (designer) receives the generated drawings and performs detailed checks. The designer reviews the drawings and makes fine adjustments using design software such as AutoCAD. For example, they may make slight changes to the direction or placement of the antenna.

[1776] The terminal (designer) uploads the revised design drawing back to the server.

[1777] Output: Modified engineering drawings.

[1778] Step 7:

[1779] Emotion-Based User Interface Adjustment

[1780] The server adjusts the user interface in real time based on the user's emotional status recognized by the emotion engine. For example, if the user is feeling frustrated, it may pop up an operation guide or enhance input assistance functions.

[1781] The server displays an appropriate feedback message (e.g., "Thank you for your input. Is there anything we can help you with?") in the user interface.

[1782] Output: Tailored user interface and feedback messages.

[1783] Step 8:

[1784] Save and share your final drawing

[1785] The terminal (designer) uploads the revised design drawing to the server, which saves the uploaded drawing as the final version and stores it in the database along with the revision history.

[1786] The server generates a shared link for the final design drawing and sends an automatic email notification to stakeholders, allowing them to access the latest version of the drawing.

[1787] Output: Final design drawings saved and shared links.

[1788] (Application example 2)

[1789] 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."

[1790] The process of creating factory design drawings involves a lot of manual work, which requires time and effort. Furthermore, the design process is carried out without consideration of the user's emotions and stress levels, which can result in a poor user experience and hinder productivity. Furthermore, it is difficult to automatically determine the optimal layout of robot movement paths and work stations within the factory.

[1791] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting information on the location and installation conditions of the property; means for preprocessing the input information and converting it into a required format; means based on generative artificial intelligence for automatically generating design drawings of the base station using the preprocessed data; means for reviewing and correcting the automatically generated design drawings; means for saving the final design drawings and sharing them with relevant parties; and means for recognizing user emotions and adjusting the user interface. This enables the automatic generation and correction of design drawings to be performed efficiently, and operation guides and feedback according to the user's emotions to be provided, thereby improving the user experience and increasing productivity.

[1792] "Property location" refers to the location of the new production line within a particular factory.

[1793] "Installation conditions" refers to factors that indicate the installation environment, such as layout restrictions within the factory, equipment size, traffic flow and altitude restrictions.

[1794] "Input means" refers to a mechanism that provides an interface for users to input the property location and installation conditions.

[1795] The "preprocessing means" is a mechanism for standardizing input information and converting it into latitude and longitude coordinates and numerical data.

[1796] "Generative AI" is an AI technology that uses algorithms and programs to automatically generate optimal design drawings based on past design data and current installation conditions.

[1797] "Review and correction means" refers to functions and interfaces for checking the generated design drawings and making corrections as necessary.

[1798] "Storage and sharing means" is a mechanism for storing the final design drawings in a database and generating a sharing link for relevant parties.

[1799] "Means for recognizing user emotions" refers to technology that analyzes emotions such as stress and frustration based on the user's input behavior and data.

[1800] The "user interface adjustment means" is a mechanism that displays operation guides and feedback messages according to the recognized user emotions, thereby improving the operation experience.

[1801] The "tagging means" is a function for assigning tags to preprocessed data and organizing the data efficiently.

[1802] The "latitude and longitude conversion means" is a function for converting address information of a property location into latitude and longitude.

[1803] The "numerical value conversion means" is a function for converting conditions such as height restrictions into numerical data.

[1804] This invention is a system that automatically generates optimal design drawings for new production lines in factories and adjusts the interface based on the user's emotions. This system operates by combining a server, user terminals, and various software.

[1805] The server first receives information on the property location and installation conditions entered by the user in real time. The user inputs the factory layout, equipment size, constraints, etc. via their terminal. The server also analyzes the user's behavior while entering data and recognizes the user's stress and frustration in real time through an emotion engine. This improves the user experience.

[1806] The server then preprocesses the input data, converting address information into latitude and longitude using a navigation API (e.g., Google Maps API) and standardizing numerical data such as height restrictions. The preprocessed data is also tagged with terms such as "semiconductor manufacturing equipment" and "transport robot," allowing the generative AI to efficiently generate blueprints.

[1807] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings based on past production line design data and current installation conditions. These generated designs are stored on a server and can be accessed by designers for modification and review. Designers can also review the generated drawings in detail and make modifications as necessary.

[1808] The server generates a link to share the final design drawings with all stakeholders. This link is provided to all members involved in the project, enabling them to work quickly and with the latest information.

[1809] As a specific example, consider the case where the user inputs the following conditions:

[1810] Factory size: 500 square meters

[1811] Device size: 2 meters x 3 meters

[1812] Restricting robot movement

[1813] Height limit: 3 meters

[1814] An example of a prompt is:

[1815] New production line design requirements:

[1816] Factory size: 500 square meters

[1817] Equipment size: 2 meters x 3 meters

[1818] Restricting robot movement

[1819] Height limit: 3 meters

[1820] Next, a helpful message is displayed to reduce the user's stress.

[1821] In this way, the system of the present invention can automatically generate, review, modify, save, and share design drawings efficiently while responding to user emotions. It also improves the user experience by displaying operation guides and support messages.

[1822] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1823] Step 1:

[1824] The user uses an input form on the terminal to input information about the property location and installation conditions, such as the size of the factory and the size of the equipment, placement restrictions, etc. This information is then sent to the server.

[1825] input:

[1826] Factory size: 500 square meters

[1827] Equipment size: 2 meters x 3 meters

[1828] Restricting robot movement

[1829] Height limit: 3 meters

[1830] output:

[1831] Information on the property location and installation conditions sent to the server

[1832] Step 2:

[1833] The server analyzes the received input data in real time and performs basic validation to check for inconsistencies in the input. If there are any inconsistencies, it returns an error message to the user. If validation is successful, it proceeds to the next step.

[1834] input:

[1835] Property location and installation conditions information entered by the user

[1836] output:

[1837] Verification result (normal / error)

[1838] Step 3:

[1839] The server analyzes the user's input behavior and content using an emotion engine to determine whether the user is feeling stressed or frustrated, thereby understanding the user's emotions.

[1840] input:

[1841] User input behavior and input content

[1842] output:

[1843] User emotion information (e.g., normal, highly frustrated)

[1844] Step 4:

[1845] The server uses a navigation API to convert address information into latitude and longitude coordinates and standardizes numerical data such as height restrictions for installation conditions. This preprocessing prepares the data in a format suitable for further processing.

[1846] input:

[1847] Property address information

[1848] Height restrictions for installation conditions

[1849] output:

[1850] Latitude and longitude information

[1851] Standardized Height Limit Measures

[1852] Step 5:

[1853] The server tags the preprocessed data and supplies organized data such as "semiconductor manufacturing equipment" and "transport robot" to the generative AI model. This tagging efficiently organizes the data.

[1854] input:

[1855] Preprocessed data

[1856] output:

[1857] Tagged data

[1858] Step 6:

[1859] A generative AI model (such as OpenAI's GPT-4) automatically generates optimal design drawings for the production line based on past design data and current installation conditions. The generated design drawings are stored on a server.

[1860] input:

[1861] Tagged data

[1862] Past design data

[1863] output:

[1864] Procedurally generated blueprints

[1865] Step 7:

[1866] Designers can use their devices to review the generated design drawings and make any necessary corrections, which are then uploaded back to the server.

[1867] input:

[1868] Procedurally generated blueprints

[1869] output:

[1870] Modified blueprints

[1871] Step 8:

[1872] The server adjusts the user interface based on the recognized user emotion, for example, by displaying operation guides or encouraging messages to improve the user experience.

[1873] input:

[1874] User emotion information

[1875] output:

[1876] Adjusted User Interface

[1877] Step 9:

[1878] The server stores the final, revised version of the blueprint and generates a shared link that can be sent to all stakeholders, making the latest blueprint accessible to all project members.

[1879] input:

[1880] Modified blueprints

[1881] output:

[1882] Generated Shared Link

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] 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.

[1889] 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).

[1890] 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.

[1891] 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."

[1892] 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.

[1893] 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).

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] 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.

[1903] 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.

[1904] The following is further disclosed regarding the above embodiment.

[1905] (Claim 1)

[1906] A means for inputting information on the location of the property and installation conditions;

[1907] means for preprocessing the input information and converting it into a required format;

[1908] a generating artificial intelligence-based means for automatically generating design drawings of a base station using the pre-processed data;

[1909] means for reviewing and modifying said automatically generated design drawings;

[1910] A means for storing and sharing the final design drawings with stakeholders;

[1911] A system including:

[1912] (Claim 2)

[1913] 2. The system according to claim 1, wherein the generating artificial intelligence includes generating means for generating base station design drawings based on past design data and current installation conditions.

[1914] (Claim 3)

[1915] 2. The system of claim 1, wherein the preprocessing means includes means for converting geographic information into latitude and longitude and means for converting height restrictions into numeric values.

[1916] "Example 1"

[1917] (Claim 1)

[1918] A means for inputting information on the location of the property and installation conditions;

[1919] means for preprocessing the input information and converting it into a required format;

[1920] a generative model-based means for automatically generating design drawings of a base station using the preprocessed data; and

[1921] a means for reviewing and modifying the generated design drawings by a designer;

[1922] A means for storing the final design drawings in a database and generating a sharing link for the relevant parties;

[1923] A system including:

[1924] (Claim 2)

[1925] The system of claim 1 , wherein the generative model includes a generating means for generating base station design drawings based on past design data and current installation conditions.

[1926] (Claim 3)

[1927] The system of claim 1 , wherein the preprocessing means includes means for converting geographic information to latitude and longitude and means for standardizing height restrictions.

[1928] "Application Example 1"

[1929] (Claim 1)

[1930] a means for inputting information about the property location and installation conditions;

[1931] means for preprocessing the input information and converting it into a required format;

[1932] means based on generative artificial intelligence for automatically generating design drawings and workflows using the pre-processed data;

[1933] means for reviewing and modifying said automatically generated design drawings and workflows;

[1934] A means for storing and sharing the final design drawings and workflow with stakeholders;

[1935] A system including:

[1936] (Claim 2)

[1937] The system of claim 1 , wherein the generative artificial intelligence includes a generating means for generating design drawings and workflows based on past design data and current installation conditions.

[1938] (Claim 3)

[1939] 2. The system of claim 1, wherein the preprocessing means includes means for converting geographic information into latitude and longitude, and means for converting various constraints into numerical values.

[1940] "Example 2: Combining Emotion Engines"

[1941] (Claim 1)

[1942] A means for inputting information on the location of the property and installation conditions;

[1943] means for preprocessing the input information and converting it into a required format;

[1944] a generating artificial intelligence-based means for automatically generating design drawings of a base station using the pre-processed data;

[1945] means for reviewing and modifying said automatically generated design drawings;

[1946] A means for storing the automatically generated design drawings and sharing them with related parties;

[1947] means based on an emotion engine for recognizing user emotions and adjusting the user interface;

[1948] A system including:

[1949] (Claim 2)

[1950] 2. The system according to claim 1, wherein the generating artificial intelligence includes generating means for generating base station design drawings based on past design data and current installation conditions.

[1951] (Claim 3)

[1952] 2. The system of claim 1, wherein the preprocessing means includes means for converting geographic information into latitude and longitude and means for converting height restrictions into numeric values.

[1953] "Application example 2 when combining emotion engines"

[1954] (Claim 1)

[1955] A means for inputting information on the location of the property and installation conditions;

[1956] means for preprocessing the input information and converting it into a required format;

[1957] a generating artificial intelligence-based means for automatically generating design drawings of a base station using the pre-processed data;

[1958] means for reviewing and modifying said automatically generated design drawings;

[1959] A means for storing and sharing the final design drawings with stakeholders;

[1960] means for recognizing a user's emotion and adjusting the user interface;

[1961] A system including:

[1962] (Claim 2)

[1963] The system of claim 1 , wherein the generating artificial intelligence includes a generating means and a tagging means for generating base station design drawings based on past design data and current installation conditions.

[1964] (Claim 3)

[1965] 2. The system of claim 1, wherein the preprocessing means includes means for converting geographic information into latitude and longitude and means for converting height restrictions into numeric values. [Explanation of symbols]

[1966] 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 for inputting information on the location of the property and installation conditions; means for preprocessing the input information and converting it into a required format; a generating artificial intelligence-based means for automatically generating design drawings of a base station using the pre-processed data; means for reviewing and modifying said automatically generated design drawings; A means for storing and sharing the final design drawings with stakeholders; A system including:

2. The system according to claim 1 , wherein the generating artificial intelligence includes generating means for generating base station design drawings based on past design data and current installation conditions.

3. 2. The system of claim 1, wherein the preprocessing means includes means for converting geographic information into latitude and longitude and means for converting height restrictions into numeric values.

Images