system

Abstract

We provide the system. [Solution] A means of collecting external structural data of the current equipment, Means for preprocessing the external structural data and converting it into an analyzable format, A means for training the transformed data using an artificial intelligence model, Means for generating a miniaturized novel structure based on the aforementioned learning, Means for evaluating the generated structure and optimizing it economically and technically, A system including means for outputting the optimized structure.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The current external structure in communication equipment has problems such as being large-sized, difficult to secure an installation space, and high construction costs. Also, when the materials and designs used are not optimal, problems may occur in durability and economy. To solve these problems, miniaturization of the structure itself and reduction of the total cost for installation and operation are required.

Means for Solving the Problems

[0005] This system collects external structural data from existing equipment, preprocesses it, and then uses an artificial intelligence model to train on this data. Through this process, it generates miniaturized new structures and provides a system for evaluating and optimizing them. In particular, the evaluation of the generated structures incorporates economic and technical perspectives, and an optimization process is introduced that considers installation area, weight, and durability. Furthermore, a feedback loop is formed based on the evaluation results to improve the accuracy of the artificial intelligence model, thereby achieving continuous optimization.

[0006] "Current equipment" refers to the components and devices of the communication infrastructure currently in use.

[0007] "External structural data" refers to information related to the physical shape and design of communication equipment, and includes formats such as drawings, 3D models, and photographs.

[0008] "Preprocessing" refers to the process of converting raw data into a format that can be easily analyzed by artificial intelligence models, and includes data normalization and structuring.

[0009] An "artificial intelligence model" refers to an algorithm or computational method designed to learn from a large dataset and perform a specific task.

[0010] "Miniaturized new structure" refers to a communication equipment configuration that is physically smaller than conventional equipment and has been newly designed.

[0011] "Generation" refers to the process of creating new designs and structures based on learned data.

[0012] "Evaluation" refers to the process of determining whether the generated structure meets the technically and economically required standards.

[0013] "Optimization" refers to the activity of improving designs and processes to maximize results while minimizing costs under current conditions.

[0014] A "feedback loop" refers to a process that takes the output of a system back into the input to improve its performance. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system for miniaturizing the external structure of existing communication equipment. Specifically, it is a technology in which a server is central to collecting external structure data of existing equipment and analyzing this data using an artificial intelligence model to generate a new and miniaturized structure. This system performs processing at each stage: data collection, preprocessing, AI learning, design generation, evaluation, and optimization.

[0037] First, the server efficiently collects diverse data related to the external structure of the existing equipment from a database. This data includes information about the physical design of the equipment and specific constraints related to its installation. Next, the server performs preprocessing on this data for handling by an artificial intelligence model. After the data is in an appropriate analytical format, the server builds an artificial intelligence model based on the collected data and trains the model with the data. Through this process, the server gains the ability to generate new, miniaturized equipment designs.

[0038] The generated design can be viewed on the user's device. The user evaluates the generated design and provides optimization feedback as needed. This feedback is used to further improve the server-generated design and is incorporated into the next design generation. The server utilizes this feedback loop to continuously improve the accuracy and applicability of the model.

[0039] For example, if a user wants to install a base station on the roof of a building, traditional large-scale equipment would not have enough space. However, by using this system, the server can generate a small-scale device that is suitable for the specific conditions of the rooftop. This makes it possible to overcome the constraints of installation location and reduce the costs associated with installation and operation.

[0040] This process will ultimately be implemented in a way that meets the diverse needs of users, with the aim of expanding communication infrastructure and improving cost efficiency.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects external structural data of existing equipment related to communication facilities from a database. This includes design drawings, photographs, 3D models, and technical specifications, and is also obtained from external data sources as needed.

[0044] Step 2:

[0045] The server performs preprocessing to convert the collected data into a format that can be analyzed. Image data is resized to a specific size, and technical specifications are structured for text analysis.

[0046] Step 3:

[0047] The server uses pre-processed data to train an artificial intelligence model. This training step extracts patterns and characteristics from the data and learns the design requirements for miniaturization.

[0048] Step 4:

[0049] The server uses the learned model to generate new, miniaturized equipment designs. It outputs multiple design options and generates evaluation criteria that take into account installation area and material costs.

[0050] Step 5:

[0051] The server evaluates the generated design and optimizes it based on technical and economic criteria, including durability and cost-effectiveness. Further design adjustments are made as needed.

[0052] Step 6:

[0053] Users connect to the server via their devices to review the optimized design. They can then download the design, provide feedback, and further consider its practical application.

[0054] Step 7:

[0055] The server collects user feedback and continuously improves the accuracy of the design generation process through retraining of the artificial intelligence model. This improves the quality of subsequent designs.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Current telecommunications equipment often has a large, space-consuming external structure, which imposes many constraints in terms of installation conditions and cost. These problems make flexible installation and improved operational efficiency difficult. Therefore, to solve these problems, there is a need for technologies that can miniaturize the external structure of the equipment, enabling more flexible and economical installation.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for collecting information related to the external structure of the existing equipment from information sources, means for standardizing the information and converting it into an analyzable format, and means for using a generating AI model to machine learn the converted information. This streamlines the entire process from information collection to analysis and design generation, enabling the creation of miniaturized equipment structures.

[0061] "Information source" refers to a location or medium, including databases, sensors, and design drawings, used to acquire data on the external structure of existing communication equipment.

[0062] "Standardization" refers to the process of converting collected information into an analyzable format, ensuring data consistency and accuracy.

[0063] A "generative AI model" refers to an algorithm or system that uses machine learning technology to generate new designs and patterns, and is used to realize design generation for miniaturization of equipment.

[0064] "Machine learning" is the process by which computer systems learn patterns and trends based on information they collect, and automatically acquire new designs and skills.

[0065] A "feedback loop" refers to a cycle of collecting evaluation information on the generated design and using it to improve future design generation and model updates.

[0066] "Physical characteristics" refer to specific features of equipment such as weight, size, and durability, and are factors that also influence installation conditions.

[0067] "Functional stability" refers to the ability of equipment to properly perform its function over a long period of time, and is an attribute related to reliability and robustness.

[0068] As an embodiment of this invention, a specific example of a system for miniaturizing the external structure of communication equipment is shown below.

[0069] First, the server, acting as a central processing unit, collects information related to the external structure of the existing equipment from various sources. This process utilizes databases and network sensors, employing data acquisition techniques such as SQL queries to efficiently obtain the necessary information. The collected data includes the size, shape, materials used, and installation conditions of the equipment.

[0070] Next, the server standardizes the collected information and converts it into an analyzable format. At this stage, data cleaning and formatting are performed, including data imputation and conversion to unified units to improve the accuracy and consistency of the information. This allows the generative AI model to process the data accurately.

[0071] Furthermore, the server performs machine learning using a generative AI model based on standardized information. This process utilizes machine learning libraries in Python and R (e.g., TENSORFLOW® and PyTorch) to train a neural network model and generate miniaturized equipment structures. The AI ​​model continuously improves the accuracy of the design by integrating historical data and user feedback.

[0072] The generated designs can be viewed on the user's device. Users evaluate the suitability and practicality of the generated miniaturized designs. For example, it is envisioned that users will input a request such as, "Generate a design for a small base station suitable for a building rooftop." The evaluation information from the user is fed back to the server and used to retrain the AI ​​model. This further improves the accuracy and flexibility of the model, enabling it to meet a wider range of installation needs.

[0073] This system allows for smaller communication equipment, reducing constraints on installation and operation, and also leads to cost reductions and more efficient installation.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects information related to the external structure of the communication equipment from databases and sensors. This information includes the dimensions, materials, and installation conditions of the equipment. The collected data is stored on the server in a raw data format that reflects the characteristics of the structure.

[0077] Step 2:

[0078] The server standardizes the collected data and converts it into an analyzable format. Specifically, it imputes missing data values ​​and unifies inconsistent formats and units. It cleans and normalizes the raw data received as input and outputs it in a format that is easy for artificial intelligence models to learn from.

[0079] Step 3:

[0080] The server builds a generative AI model based on preprocessed data and begins machine learning. It uses standardized data as input to learn patterns in equipment design. It trains a neural network using Python's TensorFlow or PyTorch libraries to generate new miniaturized designs. Through this process, the AI ​​model acquires the ability to design miniaturized structures and outputs the results as design data.

[0081] Step 4:

[0082] The terminal presents the generated design to the user. Through the user interface, the AI-generated miniaturized equipment design can be visually confirmed. A 2D or 3D model of the design is displayed to inform the user of its specific design features.

[0083] Step 5:

[0084] The user evaluates the provided design and sends feedback to the server regarding areas for improvement and suggestions. Through prompts, the user specifically describes how they want to improve the generated design and returns this information to the server. This feedback information is used for retraining.

[0085] Step 6:

[0086] The server updates and retrains the AI ​​model based on user feedback. This process incorporates evaluation information and retrains the model to improve its accuracy. It uses user feedback data as input and generates an improved design algorithm as output. This ensures that subsequent design generation is more optimized.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Current industrial equipment and machinery are constrained by space and weight, making efficient operation difficult in many manufacturing sites. Furthermore, the lack of methods for on-site personnel to directly optimize equipment and provide rapid feedback results in lengthy design improvement cycles. Therefore, there is a need for a system that enables efficient and rapid miniaturization of equipment and machinery, and allows for direct feedback via visual devices for work.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for collecting external structural data of existing equipment, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to quickly reflect feedback obtained by field personnel via visual devices into the system, and to efficiently achieve miniaturization and optimization of equipment.

[0092] "Current equipment" refers to the external structure of the equipment and devices currently used in factories and manufacturing sites.

[0093] "External structural data" refers to information related to the physical characteristics of equipment or devices, such as their shape, external dimensions, and installation conditions.

[0094] "Visual devices" refer to devices that workers wear or use to visually confirm and receive information. Specifically, this includes smart glasses and head-mounted displays.

[0095] An "artificial intelligence model" refers to a computer program that learns from large datasets and performs specific pattern recognition or prediction.

[0096] "Feedback" refers to real-time information obtained from the work site that is necessary for evaluation and improvement.

[0097] "Optimization" refers to adjusting the design and operation of a product or process to maximize its performance.

[0098] "Retraining" refers to the process of improving the accuracy of an existing artificial intelligence model by having it learn again based on new data and feedback information.

[0099] This invention deals with a system that generates new miniature structures using external structural data of existing equipment. The server collects external structural data from equipment within a factory. The collected data is preprocessed on the server using a library such as OpenCV and converted into an analyzable format.

[0100] Subsequently, the server uses software such as PyTorch to build an artificial intelligence model. By training the built model with the transformed data, it generates new, miniaturized structures. The generated structures are visually confirmed by the worker through smart glasses or a head-mounted display.

[0101] A key feature of this system is its continuous incorporation of user feedback, which is then used to retrain the model. This optimizes the generated designs economically and technically, enabling them to quickly meet the needs of each site. For example, by executing a prompt such as, "Scan the robotic arm on the work line and propose a new, miniaturized design," the system can present a practical structural design, resulting in efficient use of space and efficient equipment operation.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user scans specific equipment within the factory using a visual device (e.g., smart glasses). Input includes the equipment's shape and existing dimensional information. This data is collected from the visual device. Output is the raw data transmitted from the visual device to the server.

[0105] Step 2:

[0106] The server uses OpenCV to preprocess the received data. This processing includes denoising the equipment shape and normalizing the images. The input is the raw data obtained in step 1, and the output is clean data converted into an analyzable format.

[0107] Step 3:

[0108] The server uses PyTorch with preprocessed data to build an artificial intelligence model and trains that model with data. The input is the preprocessed data, and the output is a design proposal for a new, miniaturized structure.

[0109] Step 4:

[0110] The generated structural proposal is transferred to the terminal and displayed on the user's visual device. The user evaluates this new design proposal and provides feedback through the terminal. The input is the user's feedback, which is then returned to the server via the terminal.

[0111] Step 5:

[0112] The server retrains the AI ​​model based on the collected user feedback. This retraining process improves the model's accuracy and applicability. The input is user feedback information, and the output is the improved AI model.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] This invention is a system for achieving efficient miniaturization of communication equipment and includes a design evaluation and optimization process that takes user emotions into consideration. In particular, it primarily uses a server to collect, process, generate, evaluate, and optimize equipment data, and also incorporates an emotion engine that recognizes user emotions.

[0115] First, the server collects external structural data about the current communication equipment from a database. Next, this data is preprocessed and converted into a format that can be trained by an artificial intelligence model. Subsequently, the server uses the converted data to train the AI ​​model and generate a newly miniaturized equipment design. The generated design is evaluated from technical and economic perspectives and optimized.

[0116] On the other hand, when users view designs generated on the server via their devices, the system recognizes the user's emotions through an emotion engine. This emotion data is incorporated into the design evaluation and used to determine how to display the design or how to incorporate it into future optimizations.

[0117] Information derived from user emotions is returned to the server as part of a feedback loop and used by the emotion engine to improve design quality by reflecting user emotions. For example, if a user expresses positive emotions towards a particular design, the server uses those features to generate the next design. Conversely, if negative emotions are recognized, optimization is performed to avoid those elements.

[0118] Throughout this entire process, the system continuously generates improved designs, contributing to the efficient installation of communication equipment. Furthermore, it can enhance user satisfaction through emotion-recognition-based feedback.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server collects current data on the external structure of the communication equipment from the database. This data includes design drawings, photographs, 3D models, and technical specifications. The server manages this data comprehensively and prepares it for the next processing step.

[0122] Step 2:

[0123] The server preprocesses the collected data. Depending on the data type, image data is normalized in size and its resolution is appropriately adjusted. Technical specifications are converted into a format that can be analyzed using natural language processing techniques. This preprocessing prepares the data for efficient training by artificial intelligence models.

[0124] Step 3:

[0125] The server trains an artificial intelligence model using pre-processed data. The purpose of this model training is to recognize patterns in the given data and extract the design elements necessary for miniaturization. After training is complete, the model will be able to generate new and miniaturized equipment designs.

[0126] Step 4:

[0127] The server receives the new equipment design generated by the artificial intelligence model and evaluates it from a technical and economic perspective. Evaluation metrics include the required installation area, manufacturing cost, and durability. Optimization and design improvements are made as needed.

[0128] Step 5:

[0129] Users connect to the server via a terminal to review the generated equipment design. The terminal uses an emotion engine to recognize the user's emotions in real time and incorporates the emotion data into the design evaluation process. This emotion analysis allows for a detailed understanding of the user's reactions.

[0130] Step 6:

[0131] The server uses user emotion data obtained from the emotion engine to form a feedback loop. This feedback is fed back into the design generation process and used to improve subsequent models.

[0132] Step 7:

[0133] The server regenerates a new design incorporating the feedback and presents it to the user. This allows for the continuous delivery of a design optimized to the user's emotions.

[0134] (Example 2)

[0135] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0136] In current communication equipment, there is a growing need for miniaturization and efficient design improvements. However, existing design processes fail to adequately incorporate user emotions and feedback, resulting in time-consuming and costly development of optimal designs. Furthermore, there is a lack of systems for evaluating designs from both technical and economic perspectives and for continuous improvement.

[0137] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0138] In this invention, the server includes means for acquiring external structural data relating to the current equipment, means for processing the external structural data and converting it into a format recognizable by a machine learning model, and means for using the converted data for training using machine learning techniques. This makes it possible not only to efficiently generate miniaturized structures but also to incorporate user emotion-based feedback into design improvements.

[0139] "External structural data related to current equipment" refers to a dataset that shows the current design information and specifications of communication equipment, and includes data such as design drawings, material information, and performance metrics.

[0140] A "machine learning model" is a computer program that uses computational algorithms to extract insights from data, enabling decision-making and prediction.

[0141] A "miniaturized structure" refers to a design or structure that is physically smaller and lighter than conventional equipment, with the aim of improving efficiency.

[0142] An "emotion analysis engine" is a software technology that identifies a user's facial expressions and voice, and analyzes their emotional state as numerical data.

[0143] A "feedback loop" is a process in which results and data generated within a system are reused as input to enable continuous improvement and adjustment.

[0144] This invention is a system that enables the efficient miniaturization of existing communication equipment while also allowing for design improvements that reflect user sentiment. Specific embodiments are described below.

[0145] The server first retrieves external structural data related to the communication equipment from the database. This data includes equipment design information and material specifications. The server accesses the database using SQL queries and extracts the relevant information.

[0146] Next, the server processes this data into a format that can be trained by a machine learning model. This involves cleaning, normalizing, and extracting features from the data, and then preparing it using the Python Pandas library.

[0147] Using well-organized data, the server trains a generative AI model using the TensorFlow library. This AI model generates optimal miniaturization designs for communication equipment, which are then visualized using design software such as AutoCAD.

[0148] Subsequently, the server performs a technical and economic evaluation of the generated design. Simulation tools such as MATLAB® are used to assess the efficiency, strength, and cost of the design, and optimization is performed as needed.

[0149] As users view the design displayed on their devices, an emotion analysis engine recognizes their emotions in real time. Using OpenCV and speech recognition APIs, emotions are extracted as numerical data from the user's facial expressions and voice.

[0150] This sentiment data is returned to the server and used as part of a feedback loop. Based on user evaluations of the design, the next design generation process is adjusted, resulting in design improvements tailored to user preferences.

[0151] For example, if a user expresses an emotional response to a design, such as "it's modern and cool," that positive feedback will be taken into consideration in the next design process.

[0152] An example of a prompt message would be: "Generate a design for communication equipment that meets the following conditions: miniaturization, cost-effectiveness, and positive user feedback."

[0153] This system makes it possible to continuously improve and streamline the design of communication equipment, while also increasing user satisfaction.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The server retrieves external structural data related to the current communication equipment from the database. This data includes design information and material specifications, and the server accesses the database using SQL queries. The input is the raw design data stored in the database, and the output is the retrieved raw data.

[0157] Step 2:

[0158] The server preprocesses the collected external structured data into a format that the machine learning model can understand. Specifically, it performs data cleaning, normalization, and feature extraction. Using the Pandas library in Python, it removes unnecessary data and standardizes numerical data. The input is the raw data obtained in step 1, and the output is the preprocessed training data.

[0159] Step 3:

[0160] The server uses preprocessed data to train a generative AI model using TensorFlow. The training process involves identifying data patterns and learning the optimal, miniaturized structural design. The input is the training data from step 2, and the output is the trained AI model.

[0161] Step 4:

[0162] The server uses a trained AI model to generate designs for miniaturized communication equipment. The results are visualized in design software such as AutoCAD and output as concrete blueprints. The input is the trained AI model, and the output is a blueprint of the new design.

[0163] Step 5:

[0164] The server evaluates and optimizes the generated designs from both technical and economic perspectives. Here, tools like MATLAB are used to simulate the efficiency, strength, and cost of each design, and necessary adjustments are made. The input is the design drawing from step 4, and the output is the optimized structure.

[0165] Step 6:

[0166] When a user views a new design displayed on their device, the emotion analysis engine analyzes the user's facial expressions and voice. Using OpenCV and speech recognition APIs, the user's emotions are recorded as numerical data. The input is the user's facial expressions and voice information, and the output is the numerical representation of the emotion data.

[0167] Step 7:

[0168] The server uses user emotional data as part of a feedback loop and incorporates it into the next design generation process. Positive emotional characteristics are utilized in the next generation, while negative feedback is used to adjust the design. The input is the emotional data obtained in step 6, and the output is the adjustment data for the next design generation.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] Traditional store design and structural design processes have made it difficult to directly consider and optimize user emotions and satisfaction. Therefore, there is a need to improve the user experience and efficiently generate highly satisfying designs.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for collecting external structural data of the current device, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to evaluate and optimize the design by incorporating user sentiment data.

[0174] "External structural data of the current equipment" refers to information related to the physical shape and structure of the equipment and facilities currently in use.

[0175] "Means of preprocessing and converting into an analyzable format" refers to a series of processes and methods performed to transform raw data into a form suitable for analysis and learning.

[0176] "Means for training the transformed data using an artificial intelligence model" refers to the process of using an AI algorithm to recognize patterns based on processed data and acquire knowledge.

[0177] "Means for generating scaled-down new structures" refers to methods for creating new designs and structures that are smaller than conventional ones, based on data.

[0178] "Means of collecting user emotions towards generated structures using an emotion engine" refers to methods of collecting emotions and reactions that users show to a presented design using specific technologies.

[0179] "Means for incorporating emotional data into the evaluation and optimization process of the aforementioned structure" refers to a method for reflecting collected emotional information in the design evaluation and improvement process.

[0180] "Means of optimizing and presenting designs based on user emotional feedback in a store environment" refers to a method of adjusting designs based on users' emotions within the store and presenting them in the most optimal way for the user.

[0181] This invention is a system aimed at optimizing store design. The server collects external structural data of the current equipment, preprocesses it, and converts it into an analyzable format. This data conversion uses techniques such as data cleansing and format conversion. Subsequently, an artificial intelligence model is used to train the converted data. This AI model is often implemented using machine learning frameworks such as TensorFlow or PyTorch.

[0182] The server generates new designs based on the learning results and uses an emotion engine to collect user reactions to those designs. The emotion engine uses services such as the Emotion API to analyze facial expressions from the user's camera data and obtain emotion data. This emotion data is fed back to the server and incorporated into the evaluation and optimization of the designs.

[0183] Ultimately, users see the improved design through their devices. For example, an emotion engine analyzes whether customers are smiling when they see the in-store display; if there are many smiles, that design is prioritized, and if there are few, other designs are considered. In this way, the store design is optimized based on user emotions and then presented in the actual store.

[0184] As a concrete example, when designing the interior of a cafe, the server presents various design options, and the user responds through the app. The following is an example of a prompt to the generating AI model: "Please propose cafe interior designs. The current user emotion is 'joyful'. Please generate a design that takes this emotion into consideration." This method makes it possible to propose the optimal design that reflects the user's emotions in real time.

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server collects external structural data of the current equipment from a database. This data is often stored in CSV or JSON format. The input data includes store layout information and design requirements. The server extracts this data and proceeds to the next processing step.

[0188] Step 2:

[0189] The server preprocesses the collected external structured data and converts it into an analyzable format. Specifically, it performs data cleansing, imputing inaccurate data and missing values. It also converts the data into a numerical format that is easy for AI models to handle. The output at this stage is a clean and standardized dataset.

[0190] Step 3:

[0191] The server trains an artificial intelligence model using pre-processed data. This process typically uses machine learning libraries such as TensorFlow, and the training algorithm is usually backpropagation. The input is a pre-processed dataset, and the output is a trained AI model.

[0192] Step 4:

[0193] The server uses a pre-trained AI model to generate a simplified, new structural design. In this process, the generating AI model creates multiple design proposals based on the prompt text. The output is a new design structural proposal.

[0194] Step 5:

[0195] The user reviews the structural design generated through the device, and the device's camera captures the user's facial expressions in real time. The input is the design proposal, and the output is the user's visual feedback. This feedback is analyzed by an emotion engine.

[0196] Step 6:

[0197] The server uses an emotion engine to analyze the user's facial expression data to determine their emotions. Specifically, it utilizes the Emotion API to obtain numerical data representing emotions such as smiles and surprise. The input is the user's visual feedback, and the output is the analyzed emotion data.

[0198] Step 7:

[0199] The server uses emotional data to evaluate the generated designs and optimize them from economic and technical perspectives. At this stage, the emotional data is fed back into the AI ​​model to readjust the design proposals. The output is the optimized design proposal.

[0200] Step 8:

[0201] The user reviews the optimized design on their device and provides further feedback. This feedback is used as reference data for future design generation. The input is the optimized design, and the output is the feedback information.

[0202] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0203] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0218] This invention is a system for miniaturizing the external structure of existing communication equipment. Specifically, it is a technology in which a server is central to collecting external structure data of existing equipment and analyzing this data using an artificial intelligence model to generate a new and miniaturized structure. This system performs processing at each stage: data collection, preprocessing, AI learning, design generation, evaluation, and optimization.

[0219] First, the server efficiently collects diverse data related to the external structure of the existing equipment from a database. This data includes information about the physical design of the equipment and specific constraints related to its installation. Next, the server performs preprocessing on this data for handling by an artificial intelligence model. After the data is in an appropriate analytical format, the server builds an artificial intelligence model based on the collected data and trains the model with the data. Through this process, the server gains the ability to generate new, miniaturized equipment designs.

[0220] The generated design can be viewed on the user's device. The user evaluates the generated design and provides optimization feedback as needed. This feedback is used to further improve the server-generated design and is incorporated into the next design generation. The server utilizes this feedback loop to continuously improve the accuracy and applicability of the model.

[0221] For example, if a user wants to install a base station on the roof of a building, traditional large-scale equipment would not have enough space. However, by using this system, the server can generate a small-scale device that is suitable for the specific conditions of the rooftop. This makes it possible to overcome the constraints of installation location and reduce the costs associated with installation and operation.

[0222] This process will ultimately be implemented in a way that meets the diverse needs of users, with the aim of expanding communication infrastructure and improving cost efficiency.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The server collects external structural data of existing equipment related to communication facilities from a database. This includes design drawings, photographs, 3D models, and technical specifications, and is also obtained from external data sources as needed.

[0226] Step 2:

[0227] The server performs preprocessing to convert the collected data into a format that can be analyzed. Image data is resized to a specific size, and technical specifications are structured for text analysis.

[0228] Step 3:

[0229] The server uses pre-processed data to train an artificial intelligence model. This training step extracts patterns and characteristics from the data and learns the design requirements for miniaturization.

[0230] Step 4:

[0231] The server uses the learned model to generate new, miniaturized equipment designs. It outputs multiple design options and generates evaluation criteria that take into account installation area and material costs.

[0232] Step 5:

[0233] The server evaluates the generated design and optimizes it based on technical and economic criteria, including durability and cost-effectiveness. Further design adjustments are made as needed.

[0234] Step 6:

[0235] Users connect to the server via their devices to review the optimized design. They can then download the design, provide feedback, and further consider its practical application.

[0236] Step 7:

[0237] The server collects user feedback and continuously improves the accuracy of the design generation process through retraining of the artificial intelligence model. This improves the quality of subsequent designs.

[0238] (Example 1)

[0239] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0240] Current telecommunications equipment often has a large, space-consuming external structure, which imposes many constraints in terms of installation conditions and cost. These problems make flexible installation and improved operational efficiency difficult. Therefore, to solve these problems, there is a need for technologies that can miniaturize the external structure of the equipment, enabling more flexible and economical installation.

[0241] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0242] In this invention, the server includes means for collecting information related to the external structure of the existing equipment from information sources, means for standardizing the information and converting it into an analyzable format, and means for using a generating AI model to machine learn the converted information. This streamlines the entire process from information collection to analysis and design generation, enabling the creation of miniaturized equipment structures.

[0243] "Information source" refers to a location or medium, including databases, sensors, and design drawings, used to acquire data on the external structure of existing communication equipment.

[0244] "Standardization" refers to the process of converting collected information into an analyzable format, ensuring data consistency and accuracy.

[0245] A "generative AI model" refers to an algorithm or system that uses machine learning technology to generate new designs and patterns, and is used to realize design generation for miniaturization of equipment.

[0246] "Machine learning" is the process by which computer systems learn patterns and trends based on information they collect, and automatically acquire new designs and skills.

[0247] A "feedback loop" refers to a cycle of collecting evaluation information on the generated design and using it to improve future design generation and model updates.

[0248] "Physical characteristics" refer to specific features of equipment such as weight, size, and durability, and are factors that also influence installation conditions.

[0249] "Functional stability" refers to the ability of equipment to properly perform its function over a long period of time, and is an attribute related to reliability and robustness.

[0250] As an embodiment of this invention, a specific example of a system for miniaturizing the external structure of communication equipment is shown below.

[0251] First, the server, acting as a central processing unit, collects information related to the external structure of the existing equipment from various sources. This process utilizes databases and network sensors, employing data acquisition techniques such as SQL queries to efficiently obtain the necessary information. The collected data includes the size, shape, materials used, and installation conditions of the equipment.

[0252] Next, the server standardizes the collected information and converts it into an analyzable format. At this stage, data cleaning and formatting are performed, including data imputation and conversion to unified units to improve the accuracy and consistency of the information. This allows the generative AI model to process the data accurately.

[0253] Furthermore, the server performs machine learning using a generative AI model based on standardized information. This process utilizes machine learning libraries in Python or R (e.g., TensorFlow and PyTorch) to train a neural network model and generate miniaturized equipment structures. The AI ​​model continuously improves the accuracy of the design by integrating historical data and user feedback.

[0254] The generated designs can be viewed on the user's device. Users evaluate the suitability and practicality of the generated miniaturized designs. For example, it is envisioned that users will input a request such as, "Generate a design for a small base station suitable for a building rooftop." The evaluation information from the user is fed back to the server and used to retrain the AI ​​model. This further improves the accuracy and flexibility of the model, enabling it to meet a wider range of installation needs.

[0255] This system allows for smaller communication equipment, reducing constraints on installation and operation, and also leads to cost reductions and more efficient installation.

[0256] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0257] Step 1:

[0258] The server collects information related to the external structure of the communication equipment from databases and sensors. This information includes the dimensions, materials, and installation conditions of the equipment. The collected data is stored on the server in a raw data format that reflects the characteristics of the structure.

[0259] Step 2:

[0260] The server standardizes the collected data and converts it into an analyzable format. Specifically, it imputes missing data values ​​and unifies inconsistent formats and units. It cleans and normalizes the raw data received as input and outputs it in a format that is easy for artificial intelligence models to learn from.

[0261] Step 3:

[0262] The server builds a generative AI model based on preprocessed data and begins machine learning. It uses standardized data as input to learn patterns in equipment design. It trains a neural network using Python's TensorFlow or PyTorch libraries to generate new miniaturized designs. Through this process, the AI ​​model acquires the ability to design miniaturized structures and outputs the results as design data.

[0263] Step 4:

[0264] The terminal presents the generated design to the user. Through the user interface, the AI-generated miniaturized equipment design can be visually confirmed. A 2D or 3D model of the design is displayed to inform the user of its specific design features.

[0265] Step 5:

[0266] The user evaluates the provided design and sends feedback to the server regarding areas for improvement and suggestions. Through prompts, the user specifically describes how they want to improve the generated design and returns this information to the server. This feedback information is used for retraining.

[0267] Step 6:

[0268] The server updates and retrains the AI ​​model based on user feedback. This process incorporates evaluation information and retrains the model to improve its accuracy. It uses user feedback data as input and generates an improved design algorithm as output. This ensures that subsequent design generation is more optimized.

[0269] (Application Example 1)

[0270] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] Current industrial equipment and machinery are constrained by space and weight, making efficient operation difficult in many manufacturing sites. Furthermore, the lack of methods for on-site personnel to directly optimize equipment and provide rapid feedback results in lengthy design improvement cycles. Therefore, there is a need for a system that enables efficient and rapid miniaturization of equipment and machinery, and allows for direct feedback via visual devices for work.

[0272] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0273] In this invention, the server includes means for collecting external structural data of existing equipment, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to quickly reflect feedback obtained by field personnel via visual devices into the system, and to efficiently achieve miniaturization and optimization of equipment.

[0274] "Current equipment" refers to the external structure of the equipment and devices currently used in factories and manufacturing sites.

[0275] "External structural data" refers to information related to the physical characteristics of equipment or devices, such as their shape, external dimensions, and installation conditions.

[0276] "Visual devices" refer to devices that workers wear or use to visually confirm and receive information. Specifically, this includes smart glasses and head-mounted displays.

[0277] An "artificial intelligence model" refers to a computer program that learns from large datasets and performs specific pattern recognition or prediction.

[0278] "Feedback" refers to real-time evaluations and information necessary for improvement obtained from the work site.

[0279] "Optimization" refers to making adjustments to the design and operation in order to maximize the performance of products and processes.

[0280] "Retraining" refers to the process of making an existing artificial intelligence model learn again based on new data and feedback information to enhance accuracy.

[0281] This invention deals with a system that generates a new small structure using the external structure data of existing equipment. The server collects the external structure data of the equipment in the factory. The collected data is preprocessed on the server using a library such as OpenCV and converted into an analyzable format.

[0282] After that, the server constructs an artificial intelligence model using software such as PyTorch. By making the constructed model learn the converted data, a new miniaturized structure is generated. The generated structure is visually confirmed via smart glasses or a head-mounted display worn by the operator.

[0283] The characteristic part of this system is that it continuously incorporates feedback provided by the user and utilizes it for retraining the model. As a result, the generated design is optimized economically and technically and can quickly respond to the needs of each site. As a specific example, for instance, by executing a prompt such as "Scan the robotic arm on the production line and propose a new miniaturized design," the system presents a practical structural design, enabling effective utilization of space and efficient operation of equipment.

[0284] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0285] Step 1:

[0286] The user scans specific equipment in the factory using a visual device (e.g., smart glasses). The input includes the shape of the equipment and existing dimensional information. This data is collected from the visual device. As output, raw data transmitted from the visual device to the server is obtained.

[0287] Step 2:

[0288] The server pre - processes the received data using OpenCV. In this process, noise removal of the equipment shape and image normalization are performed. The input is the raw data obtained in Step 1, and the output is clean data converted into an analyzable format.

[0289] Step 3:

[0290] The server utilizes PyTorch with the pre - processed data to build an artificial intelligence model and train the model with the data. As input, the pre - processed data is used, and as output, a design proposal for a new miniaturized structure is generated.

[0291] Step 4:

[0292] The generated structure proposal is transferred to the terminal and displayed on the user's visual device. The user evaluates this new design proposal and provides feedback through the terminal. The input is the user's feedback, and this feedback is sent back to the server via the terminal.

[0293] Step 5:

[0294] The server performs retraining of the AI model based on the collected user feedback. Through this retraining process, the accuracy and application range of the model are improved. The input is the user's feedback information, and the output is an improved AI model.

[0295] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0296] This invention is a system for achieving efficient miniaturization of communication equipment and includes a design evaluation and optimization process that takes user emotions into consideration. In particular, it primarily uses a server to collect, process, generate, evaluate, and optimize equipment data, and also incorporates an emotion engine that recognizes user emotions.

[0297] First, the server collects external structural data about the current communication equipment from a database. Next, this data is preprocessed and converted into a format that can be trained by an artificial intelligence model. Subsequently, the server uses the converted data to train the AI ​​model and generate a newly miniaturized equipment design. The generated design is evaluated from technical and economic perspectives and optimized.

[0298] On the other hand, when users view designs generated on the server via their devices, the system recognizes the user's emotions through an emotion engine. This emotion data is incorporated into the design evaluation and used to determine how to display the design or how to incorporate it into future optimizations.

[0299] Information derived from user emotions is returned to the server as part of a feedback loop and used by the emotion engine to improve design quality by reflecting user emotions. For example, if a user expresses positive emotions towards a particular design, the server uses those features to generate the next design. Conversely, if negative emotions are recognized, optimization is performed to avoid those elements.

[0300] Throughout this entire process, the system continuously generates improved designs, contributing to the efficient installation of communication equipment. Furthermore, it can enhance user satisfaction through emotion-recognition-based feedback.

[0301] The processing flow is described below.

[0302] Step 1:

[0303] The server collects current data on the external structure of the communication equipment from the database. This data includes design drawings, photos, 3D models, and technical specifications. The server manages these data integrally and prepares for the next processing step.

[0304] Step 2:

[0305] The server preprocesses the collected data. Depending on the type of data, the image data is normalized in size and the resolution is appropriately adjusted. The technical specifications are converted into a form that can be analyzed using natural language processing technology. This preprocessing prepares the data in a form that allows the artificial intelligence model to learn efficiently.

[0306] Step 3:

[0307] The server trains an artificial intelligence model using the preprocessed data. The purpose of this model training is to recognize the patterns of the given data and extract the design elements necessary for miniaturization. After the training is completed, the model will be able to generate a new and miniaturized equipment design.

[0308] Step 4:

[0309] The server receives the new equipment design generated by the artificial intelligence model and evaluates it from a technical and economic perspective. The evaluation indicators include the area required for installation, manufacturing cost, and durability. Optimization is performed as needed to improve the design.

[0310] Step 5:

[0311] Users connect to the server via a terminal to review the generated equipment design. The terminal uses an emotion engine to recognize the user's emotions in real time and incorporates the emotion data into the design evaluation process. This emotion analysis allows for a detailed understanding of the user's reactions.

[0312] Step 6:

[0313] The server uses user emotion data obtained from the emotion engine to form a feedback loop. This feedback is fed back into the design generation process and used to improve subsequent models.

[0314] Step 7:

[0315] The server regenerates a new design incorporating the feedback and presents it to the user. This allows for the continuous delivery of a design optimized to the user's emotions.

[0316] (Example 2)

[0317] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0318] In current communication equipment, there is a growing need for miniaturization and efficient design improvements. However, existing design processes fail to adequately incorporate user emotions and feedback, resulting in time-consuming and costly development of optimal designs. Furthermore, there is a lack of systems for evaluating designs from both technical and economic perspectives and for continuous improvement.

[0319] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0320] In this invention, the server includes means for acquiring external structural data relating to the current equipment, means for processing the external structural data and converting it into a format recognizable by a machine learning model, and means for using the converted data for training using machine learning techniques. This makes it possible not only to efficiently generate miniaturized structures but also to incorporate user emotion-based feedback into design improvements.

[0321] "External structural data related to current equipment" refers to a dataset that shows the current design information and specifications of communication equipment, and includes data such as design drawings, material information, and performance metrics.

[0322] A "machine learning model" is a computer program that uses computational algorithms to extract insights from data, enabling decision-making and prediction.

[0323] A "miniaturized structure" refers to a design or structure that is physically smaller and lighter than conventional equipment, with the aim of improving efficiency.

[0324] An "emotion analysis engine" is a software technology that identifies a user's facial expressions and voice, and analyzes their emotional state as numerical data.

[0325] A "feedback loop" is a process in which results and data generated within a system are reused as input to enable continuous improvement and adjustment.

[0326] This invention is a system that enables the efficient miniaturization of existing communication equipment while also allowing for design improvements that reflect user sentiment. Specific embodiments are described below.

[0327] The server first retrieves external structural data related to the communication equipment from the database. This data includes equipment design information and material specifications. The server accesses the database using SQL queries and extracts the relevant information.

[0328] Next, the server processes this data into a format that can be trained by a machine learning model. This involves cleaning, normalizing, and extracting features from the data, and then preparing it using the Python Pandas library.

[0329] Using well-organized data, the server trains a generative AI model using the TensorFlow library. This AI model generates optimal miniaturization designs for communication equipment, which are then visualized using design software such as AutoCAD.

[0330] Subsequently, the server performs a technical and economic evaluation of the generated design. Simulation tools such as MATLAB are used to assess the efficiency, strength, and cost of the design, and optimization is performed as needed.

[0331] As users view the design displayed on their devices, an emotion analysis engine recognizes their emotions in real time. Using OpenCV and speech recognition APIs, emotions are extracted as numerical data from the user's facial expressions and voice.

[0332] This sentiment data is returned to the server and used as part of a feedback loop. Based on user evaluations of the design, the next design generation process is adjusted, resulting in design improvements tailored to user preferences.

[0333] For example, if a user expresses an emotional response to a design, such as "it's modern and cool," that positive feedback will be taken into consideration in the next design process.

[0334] An example of a prompt message would be: "Generate a design for communication equipment that meets the following conditions: miniaturization, cost-effectiveness, and positive user feedback."

[0335] This system makes it possible to continuously improve and streamline the design of communication equipment, while also increasing user satisfaction.

[0336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0337] Step 1:

[0338] The server retrieves external structural data related to the current communication equipment from the database. This data includes design information and material specifications, and the server accesses the database using SQL queries. The input is the raw design data stored in the database, and the output is the retrieved raw data.

[0339] Step 2:

[0340] The server preprocesses the collected external structured data into a format that the machine learning model can understand. Specifically, it performs data cleaning, normalization, and feature extraction. Using the Pandas library in Python, it removes unnecessary data and standardizes numerical data. The input is the raw data obtained in step 1, and the output is the preprocessed training data.

[0341] Step 3:

[0342] The server uses preprocessed data to train a generative AI model using TensorFlow. The training process involves identifying data patterns and learning the optimal, miniaturized structural design. The input is the training data from step 2, and the output is the trained AI model.

[0343] Step 4:

[0344] The server uses a trained AI model to generate designs for miniaturized communication equipment. The results are visualized in design software such as AutoCAD and output as concrete blueprints. The input is the trained AI model, and the output is a blueprint of the new design.

[0345] Step 5:

[0346] The server evaluates and optimizes the generated designs from both technical and economic perspectives. Here, tools like MATLAB are used to simulate the efficiency, strength, and cost of each design, and necessary adjustments are made. The input is the design drawing from step 4, and the output is the optimized structure.

[0347] Step 6:

[0348] When a user views a new design displayed on their device, the emotion analysis engine analyzes the user's facial expressions and voice. Using OpenCV and speech recognition APIs, the user's emotions are recorded as numerical data. The input is the user's facial expressions and voice information, and the output is the numerical representation of the emotion data.

[0349] Step 7:

[0350] The server uses user emotional data as part of a feedback loop and incorporates it into the next design generation process. Positive emotional characteristics are utilized in the next generation, while negative feedback is used to adjust the design. The input is the emotional data obtained in step 6, and the output is the adjustment data for the next design generation.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0353] Traditional store design and structural design processes have made it difficult to directly consider and optimize user emotions and satisfaction. Therefore, there is a need to improve the user experience and efficiently generate highly satisfying designs.

[0354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0355] In this invention, the server includes means for collecting external structural data of the current device, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to evaluate and optimize the design by incorporating user sentiment data.

[0356] "External structural data of the current equipment" refers to information related to the physical shape and structure of the equipment and facilities currently in use.

[0357] "Means of preprocessing and converting into an analyzable format" refers to a series of processes and methods performed to transform raw data into a form suitable for analysis and learning.

[0358] "Means for training the transformed data using an artificial intelligence model" refers to the process of using an AI algorithm to recognize patterns based on processed data and acquire knowledge.

[0359] "Means for generating scaled-down new structures" refers to methods for creating new designs and structures that are smaller than conventional ones, based on data.

[0360] "Means of collecting user emotions towards generated structures using an emotion engine" refers to methods of collecting emotions and reactions that users show to a presented design using specific technologies.

[0361] "Means for incorporating emotional data into the evaluation and optimization process of the aforementioned structure" refers to a method for reflecting collected emotional information in the design evaluation and improvement process.

[0362] "Means of optimizing and presenting designs based on user emotional feedback in a store environment" refers to a method of adjusting designs based on users' emotions within the store and presenting them in the most optimal way for the user.

[0363] This invention is a system aimed at optimizing store design. The server collects external structural data of the current equipment, preprocesses it, and converts it into an analyzable format. This data conversion uses techniques such as data cleansing and format conversion. Subsequently, an artificial intelligence model is used to train the converted data. This AI model is often implemented using machine learning frameworks such as TensorFlow or PyTorch.

[0364] The server generates new designs based on the learning results and uses an emotion engine to collect user reactions to those designs. The emotion engine uses services such as the Emotion API to analyze facial expressions from the user's camera data and obtain emotion data. This emotion data is fed back to the server and incorporated into the evaluation and optimization of the designs.

[0365] Ultimately, users see the improved design through their devices. For example, an emotion engine analyzes whether customers are smiling when they see the in-store display; if there are many smiles, that design is prioritized, and if there are few, other designs are considered. In this way, the store design is optimized based on user emotions and then presented in the actual store.

[0366] As a concrete example, when designing the interior of a cafe, the server presents various design options, and the user responds through the app. The following is an example of a prompt to the generating AI model: "Please propose cafe interior designs. The current user emotion is 'joyful'. Please generate a design that takes this emotion into consideration." This method makes it possible to propose the optimal design that reflects the user's emotions in real time.

[0367] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0368] Step 1:

[0369] The server collects external structural data of the current equipment from a database. This data is often stored in CSV or JSON format. The input data includes store layout information and design requirements. The server extracts this data and proceeds to the next processing step.

[0370] Step 2:

[0371] The server preprocesses the collected external structured data and converts it into an analyzable format. Specifically, it performs data cleansing, imputing inaccurate data and missing values. It also converts the data into a numerical format that is easy for AI models to handle. The output at this stage is a clean and standardized dataset.

[0372] Step 3:

[0373] The server trains an artificial intelligence model using pre-processed data. This process typically uses machine learning libraries such as TensorFlow, and the training algorithm is usually backpropagation. The input is a pre-processed dataset, and the output is a trained AI model.

[0374] Step 4:

[0375] The server uses a pre-trained AI model to generate a simplified, new structural design. In this process, the generating AI model creates multiple design proposals based on the prompt text. The output is a new design structural proposal.

[0376] Step 5:

[0377] The user reviews the structural design generated through the device, and the device's camera captures the user's facial expressions in real time. The input is the design proposal, and the output is the user's visual feedback. This feedback is analyzed by an emotion engine.

[0378] Step 6:

[0379] The server uses an emotion engine to analyze the user's facial expression data to determine their emotions. Specifically, it utilizes the Emotion API to obtain numerical data representing emotions such as smiles and surprise. The input is the user's visual feedback, and the output is the analyzed emotion data.

[0380] Step 7:

[0381] The server uses emotional data to evaluate the generated designs and optimize them from economic and technical perspectives. At this stage, the emotional data is fed back into the AI ​​model to readjust the design proposals. The output is the optimized design proposal.

[0382] Step 8:

[0383] The user reviews the optimized design on their device and provides further feedback. This feedback is used as reference data for future design generation. The input is the optimized design, and the output is the feedback information.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0390] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0392] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0394] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0395] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0396] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] This invention is a system for miniaturizing the external structure of existing communication equipment. Specifically, it is a technology in which a server is central to collecting external structure data of existing equipment and analyzing this data using an artificial intelligence model to generate a new and miniaturized structure. This system performs processing at each stage: data collection, preprocessing, AI learning, design generation, evaluation, and optimization.

[0401] First, the server efficiently collects diverse data related to the external structure of the existing equipment from a database. This data includes information about the physical design of the equipment and specific constraints related to its installation. Next, the server performs preprocessing on this data for handling by an artificial intelligence model. After the data is in an appropriate analytical format, the server builds an artificial intelligence model based on the collected data and trains the model with the data. Through this process, the server gains the ability to generate new, miniaturized equipment designs.

[0402] The generated design can be viewed on the user's device. The user evaluates the generated design and provides optimization feedback as needed. This feedback is used to further improve the server-generated design and is incorporated into the next design generation. The server utilizes this feedback loop to continuously improve the accuracy and applicability of the model.

[0403] For example, if a user wants to install a base station on the roof of a building, traditional large-scale equipment would not have enough space. However, by using this system, the server can generate a small-scale device that is suitable for the specific conditions of the rooftop. This makes it possible to overcome the constraints of installation location and reduce the costs associated with installation and operation.

[0404] This process will ultimately be implemented in a way that meets the diverse needs of users, with the aim of expanding communication infrastructure and improving cost efficiency.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] The server collects external structural data of existing equipment related to communication facilities from a database. This includes design drawings, photographs, 3D models, and technical specifications, and is also obtained from external data sources as needed.

[0408] Step 2:

[0409] The server performs preprocessing to convert the collected data into a format that can be analyzed. Image data is resized to a specific size, and technical specifications are structured for text analysis.

[0410] Step 3:

[0411] The server uses pre-processed data to train an artificial intelligence model. This training step extracts patterns and characteristics from the data and learns the design requirements for miniaturization.

[0412] Step 4:

[0413] The server uses the learned model to generate new, miniaturized equipment designs. It outputs multiple design options and generates evaluation criteria that take into account installation area and material costs.

[0414] Step 5:

[0415] The server evaluates the generated design and optimizes it based on technical and economic criteria, including durability and cost-effectiveness. Further design adjustments are made as needed.

[0416] Step 6:

[0417] Users connect to the server via their devices to review the optimized design. They can then download the design, provide feedback, and further consider its practical application.

[0418] Step 7:

[0419] The server collects user feedback and continuously improves the accuracy of the design generation process through retraining of the artificial intelligence model. This improves the quality of subsequent designs.

[0420] (Example 1)

[0421] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0422] Current telecommunications equipment often has a large, space-consuming external structure, which imposes many constraints in terms of installation conditions and cost. These problems make flexible installation and improved operational efficiency difficult. Therefore, to solve these problems, there is a need for technologies that can miniaturize the external structure of the equipment, enabling more flexible and economical installation.

[0423] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0424] In this invention, the server includes means for collecting information related to the external structure of the existing equipment from information sources, means for standardizing the information and converting it into an analyzable format, and means for using a generating AI model to machine learn the converted information. This streamlines the entire process from information collection to analysis and design generation, enabling the creation of miniaturized equipment structures.

[0425] "Information source" refers to a location or medium, including databases, sensors, and design drawings, used to acquire data on the external structure of existing communication equipment.

[0426] "Standardization" refers to the process of converting collected information into an analyzable format, ensuring data consistency and accuracy.

[0427] A "generative AI model" refers to an algorithm or system that uses machine learning technology to generate new designs and patterns, and is used to realize design generation for miniaturization of equipment.

[0428] "Machine learning" is the process by which computer systems learn patterns and trends based on information they collect, and automatically acquire new designs and skills.

[0429] A "feedback loop" refers to a cycle of collecting evaluation information on the generated design and using it to improve future design generation and model updates.

[0430] "Physical characteristics" refer to specific features of equipment such as weight, size, and durability, and are factors that also influence installation conditions.

[0431] "Functional stability" refers to the ability of equipment to properly perform its function over a long period of time, and is an attribute related to reliability and robustness.

[0432] As an embodiment of this invention, a specific example of a system for miniaturizing the external structure of communication equipment is shown below.

[0433] First, the server, acting as a central processing unit, collects information related to the external structure of the existing equipment from various sources. This process utilizes databases and network sensors, employing data acquisition techniques such as SQL queries to efficiently obtain the necessary information. The collected data includes the size, shape, materials used, and installation conditions of the equipment.

[0434] Next, the server standardizes the collected information and converts it into an analyzable format. At this stage, data cleaning and formatting are performed, including data imputation and conversion to unified units to improve the accuracy and consistency of the information. This allows the generative AI model to process the data accurately.

[0435] Furthermore, the server performs machine learning using a generative AI model based on standardized information. This process utilizes machine learning libraries in Python or R (e.g., TensorFlow and PyTorch) to train a neural network model and generate miniaturized equipment structures. The AI ​​model continuously improves the accuracy of the design by integrating historical data and user feedback.

[0436] The generated designs can be viewed on the user's device. Users evaluate the suitability and practicality of the generated miniaturized designs. For example, it is envisioned that users will input a request such as, "Generate a design for a small base station suitable for a building rooftop." The evaluation information from the user is fed back to the server and used to retrain the AI ​​model. This further improves the accuracy and flexibility of the model, enabling it to meet a wider range of installation needs.

[0437] This system allows for smaller communication equipment, reducing constraints on installation and operation, and also leads to cost reductions and more efficient installation.

[0438] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0439] Step 1:

[0440] The server collects information related to the external structure of the communication equipment from databases and sensors. This information includes the dimensions, materials, and installation conditions of the equipment. The collected data is stored on the server in a raw data format that reflects the characteristics of the structure.

[0441] Step 2:

[0442] The server standardizes the collected data and converts it into an analyzable format. Specifically, it imputes missing data values ​​and unifies inconsistent formats and units. It cleans and normalizes the raw data received as input and outputs it in a format that is easy for artificial intelligence models to learn from.

[0443] Step 3:

[0444] The server builds a generative AI model based on preprocessed data and begins machine learning. It uses standardized data as input to learn patterns in equipment design. It trains a neural network using Python's TensorFlow or PyTorch libraries to generate new miniaturized designs. Through this process, the AI ​​model acquires the ability to design miniaturized structures and outputs the results as design data.

[0445] Step 4:

[0446] The terminal presents the generated design to the user. Through the user interface, the AI-generated miniaturized equipment design can be visually confirmed. A 2D or 3D model of the design is displayed to inform the user of its specific design features.

[0447] Step 5:

[0448] The user evaluates the provided design and sends feedback to the server regarding areas for improvement and suggestions. Through prompts, the user specifically describes how they want to improve the generated design and returns this information to the server. This feedback information is used for retraining.

[0449] Step 6:

[0450] The server updates and retrains the AI ​​model based on user feedback. This process incorporates evaluation information and retrains the model to improve its accuracy. It uses user feedback data as input and generates an improved design algorithm as output. This ensures that subsequent design generation is more optimized.

[0451] (Application Example 1)

[0452] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0453] Current industrial equipment and machinery are constrained by space and weight, making efficient operation difficult in many manufacturing sites. Furthermore, the lack of methods for on-site personnel to directly optimize equipment and provide rapid feedback results in lengthy design improvement cycles. Therefore, there is a need for a system that enables efficient and rapid miniaturization of equipment and machinery, and allows for direct feedback via visual devices for work.

[0454] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0455] In this invention, the server includes means for collecting external structural data of existing equipment, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to quickly reflect feedback obtained by field personnel via visual devices into the system, and to efficiently achieve miniaturization and optimization of equipment.

[0456] "Current equipment" refers to the external structure of the equipment and devices currently used in factories and manufacturing sites.

[0457] "External structural data" refers to information related to the physical characteristics of equipment or devices, such as their shape, external dimensions, and installation conditions.

[0458] "Visual devices" refer to devices that workers wear or use to visually confirm and receive information. Specifically, this includes smart glasses and head-mounted displays.

[0459] An "artificial intelligence model" refers to a computer program that learns from large datasets and performs specific pattern recognition or prediction.

[0460] "Feedback" refers to real-time information obtained from the work site that is necessary for evaluation and improvement.

[0461] "Optimization" refers to adjusting the design and operation of a product or process to maximize its performance.

[0462] "Retraining" refers to the process of improving the accuracy of an existing artificial intelligence model by having it learn again based on new data and feedback information.

[0463] This invention deals with a system that generates new miniature structures using external structural data of existing equipment. The server collects external structural data from equipment within a factory. The collected data is preprocessed on the server using a library such as OpenCV and converted into an analyzable format.

[0464] Subsequently, the server uses software such as PyTorch to build an artificial intelligence model. By training the built model with the transformed data, it generates new, miniaturized structures. The generated structures are visually confirmed by the worker through smart glasses or a head-mounted display.

[0465] A key feature of this system is its continuous incorporation of user feedback, which is then used to retrain the model. This optimizes the generated designs economically and technically, enabling them to quickly meet the needs of each site. For example, by executing a prompt such as, "Scan the robotic arm on the work line and propose a new, miniaturized design," the system can present a practical structural design, resulting in efficient use of space and efficient equipment operation.

[0466] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0467] Step 1:

[0468] The user scans specific equipment within the factory using a visual device (e.g., smart glasses). Input includes the equipment's shape and existing dimensional information. This data is collected from the visual device. Output is the raw data transmitted from the visual device to the server.

[0469] Step 2:

[0470] The server uses OpenCV to preprocess the received data. This processing includes denoising the equipment shape and normalizing the images. The input is the raw data obtained in step 1, and the output is clean data converted into an analyzable format.

[0471] Step 3:

[0472] The server uses PyTorch with preprocessed data to build an artificial intelligence model and trains that model with data. The input is the preprocessed data, and the output is a design proposal for a new, miniaturized structure.

[0473] Step 4:

[0474] The generated structural proposal is transferred to the terminal and displayed on the user's visual device. The user evaluates this new design proposal and provides feedback through the terminal. The input is the user's feedback, which is then returned to the server via the terminal.

[0475] Step 5:

[0476] The server retrains the AI ​​model based on the collected user feedback. This retraining process improves the model's accuracy and applicability. The input is user feedback information, and the output is the improved AI model.

[0477] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0478] This invention is a system for achieving efficient miniaturization of communication equipment and includes a design evaluation and optimization process that takes user emotions into consideration. In particular, it primarily uses a server to collect, process, generate, evaluate, and optimize equipment data, and also incorporates an emotion engine that recognizes user emotions.

[0479] First, the server collects external structural data about the current communication equipment from a database. Next, this data is preprocessed and converted into a format that can be trained by an artificial intelligence model. Subsequently, the server uses the converted data to train the AI ​​model and generate a newly miniaturized equipment design. The generated design is evaluated from technical and economic perspectives and optimized.

[0480] On the other hand, when users view designs generated on the server via their devices, the system recognizes the user's emotions through an emotion engine. This emotion data is incorporated into the design evaluation and used to determine how to display the design or how to incorporate it into future optimizations.

[0481] Information derived from user emotions is returned to the server as part of a feedback loop and used by the emotion engine to improve design quality by reflecting user emotions. For example, if a user expresses positive emotions towards a particular design, the server uses those features to generate the next design. Conversely, if negative emotions are recognized, optimization is performed to avoid those elements.

[0482] Throughout this entire process, the system continuously generates improved designs, contributing to the efficient installation of communication equipment. Furthermore, it can enhance user satisfaction through emotion-recognition-based feedback.

[0483] The following describes the processing flow.

[0484] Step 1:

[0485] The server collects current data on the external structure of the communication equipment from the database. This data includes design drawings, photographs, 3D models, and technical specifications. The server manages this data comprehensively and prepares it for the next processing step.

[0486] Step 2:

[0487] The server preprocesses the collected data. Depending on the data type, image data is normalized in size and its resolution is appropriately adjusted. Technical specifications are converted into a format that can be analyzed using natural language processing techniques. This preprocessing prepares the data for efficient training by artificial intelligence models.

[0488] Step 3:

[0489] The server trains an artificial intelligence model using pre-processed data. The purpose of this model training is to recognize patterns in the given data and extract the design elements necessary for miniaturization. After training is complete, the model will be able to generate new and miniaturized equipment designs.

[0490] Step 4:

[0491] The server receives the new equipment design generated by the artificial intelligence model and evaluates it from a technical and economic perspective. Evaluation metrics include the required installation area, manufacturing cost, and durability. Optimization and design improvements are made as needed.

[0492] Step 5:

[0493] Users connect to the server via a terminal to review the generated equipment design. The terminal uses an emotion engine to recognize the user's emotions in real time and incorporates the emotion data into the design evaluation process. This emotion analysis allows for a detailed understanding of the user's reactions.

[0494] Step 6:

[0495] The server uses user emotion data obtained from the emotion engine to form a feedback loop. This feedback is fed back into the design generation process and used to improve subsequent models.

[0496] Step 7:

[0497] The server regenerates a new design incorporating the feedback and presents it to the user. This allows for the continuous delivery of a design optimized to the user's emotions.

[0498] (Example 2)

[0499] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] In current communication equipment, there is a growing need for miniaturization and efficient design improvements. However, existing design processes fail to adequately incorporate user emotions and feedback, resulting in time-consuming and costly development of optimal designs. Furthermore, there is a lack of systems for evaluating designs from both technical and economic perspectives and for continuous improvement.

[0501] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0502] In this invention, the server includes means for acquiring external structural data relating to the current equipment, means for processing the external structural data and converting it into a format recognizable by a machine learning model, and means for using the converted data for training using machine learning techniques. This makes it possible not only to efficiently generate miniaturized structures but also to incorporate user emotion-based feedback into design improvements.

[0503] "External structural data related to current equipment" refers to a dataset that shows the current design information and specifications of communication equipment, and includes data such as design drawings, material information, and performance metrics.

[0504] A "machine learning model" is a computer program that uses computational algorithms to extract insights from data, enabling decision-making and prediction.

[0505] A "miniaturized structure" refers to a design or structure that is physically smaller and lighter than conventional equipment, with the aim of improving efficiency.

[0506] An "emotion analysis engine" is a software technology that identifies a user's facial expressions and voice, and analyzes their emotional state as numerical data.

[0507] A "feedback loop" is a process in which results and data generated within a system are reused as input to enable continuous improvement and adjustment.

[0508] This invention is a system that enables the efficient miniaturization of existing communication equipment while also allowing for design improvements that reflect user sentiment. Specific embodiments are described below.

[0509] The server first retrieves external structural data related to the communication equipment from the database. This data includes equipment design information and material specifications. The server accesses the database using SQL queries and extracts the relevant information.

[0510] Next, the server processes this data into a format that can be trained by a machine learning model. This involves cleaning, normalizing, and extracting features from the data, and then preparing it using the Python Pandas library.

[0511] Using well-organized data, the server trains a generative AI model using the TensorFlow library. This AI model generates optimal miniaturization designs for communication equipment, which are then visualized using design software such as AutoCAD.

[0512] Subsequently, the server performs a technical and economic evaluation of the generated design. Simulation tools such as MATLAB are used to assess the efficiency, strength, and cost of the design, and optimization is performed as needed.

[0513] As users view the design displayed on their devices, an emotion analysis engine recognizes their emotions in real time. Using OpenCV and speech recognition APIs, emotions are extracted as numerical data from the user's facial expressions and voice.

[0514] This sentiment data is returned to the server and used as part of a feedback loop. Based on user evaluations of the design, the next design generation process is adjusted, resulting in design improvements tailored to user preferences.

[0515] For example, if a user expresses an emotional response to a design, such as "it's modern and cool," that positive feedback will be taken into consideration in the next design process.

[0516] An example of a prompt message would be: "Generate a design for communication equipment that meets the following conditions: miniaturization, cost-effectiveness, and positive user feedback."

[0517] This system makes it possible to continuously improve and streamline the design of communication equipment, while also increasing user satisfaction.

[0518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0519] Step 1:

[0520] The server retrieves external structural data related to the current communication equipment from the database. This data includes design information and material specifications, and the server accesses the database using SQL queries. The input is the raw design data stored in the database, and the output is the retrieved raw data.

[0521] Step 2:

[0522] The server preprocesses the collected external structured data into a format that the machine learning model can understand. Specifically, it performs data cleaning, normalization, and feature extraction. Using the Pandas library in Python, it removes unnecessary data and standardizes numerical data. The input is the raw data obtained in step 1, and the output is the preprocessed training data.

[0523] Step 3:

[0524] The server uses preprocessed data to train a generative AI model using TensorFlow. The training process involves identifying data patterns and learning the optimal, miniaturized structural design. The input is the training data from step 2, and the output is the trained AI model.

[0525] Step 4:

[0526] The server uses a trained AI model to generate designs for miniaturized communication equipment. The results are visualized in design software such as AutoCAD and output as concrete blueprints. The input is the trained AI model, and the output is a blueprint of the new design.

[0527] Step 5:

[0528] The server evaluates and optimizes the generated designs from both technical and economic perspectives. Here, tools like MATLAB are used to simulate the efficiency, strength, and cost of each design, and necessary adjustments are made. The input is the design drawing from step 4, and the output is the optimized structure.

[0529] Step 6:

[0530] When a user views a new design displayed on their device, the emotion analysis engine analyzes the user's facial expressions and voice. Using OpenCV and speech recognition APIs, the user's emotions are recorded as numerical data. The input is the user's facial expressions and voice information, and the output is the numerical representation of the emotion data.

[0531] Step 7:

[0532] The server uses user emotional data as part of a feedback loop and incorporates it into the next design generation process. Positive emotional characteristics are utilized in the next generation, while negative feedback is used to adjust the design. The input is the emotional data obtained in step 6, and the output is the adjustment data for the next design generation.

[0533] (Application Example 2)

[0534] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0535] Traditional store design and structural design processes have made it difficult to directly consider and optimize user emotions and satisfaction. Therefore, there is a need to improve the user experience and efficiently generate highly satisfying designs.

[0536] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0537] In this invention, the server includes means for collecting external structural data of the current device, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to evaluate and optimize the design by incorporating user sentiment data.

[0538] "External structural data of the current equipment" refers to information related to the physical shape and structure of the equipment and facilities currently in use.

[0539] "Means of preprocessing and converting into an analyzable format" refers to a series of processes and methods performed to transform raw data into a form suitable for analysis and learning.

[0540] "Means for training the transformed data using an artificial intelligence model" refers to the process of using an AI algorithm to recognize patterns based on processed data and acquire knowledge.

[0541] "Means for generating scaled-down new structures" refers to methods for creating new designs and structures that are smaller than conventional ones, based on data.

[0542] "Means of collecting user emotions towards generated structures using an emotion engine" refers to methods of collecting emotions and reactions that users show to a presented design using specific technologies.

[0543] "Means for incorporating emotional data into the evaluation and optimization process of the aforementioned structure" refers to a method for reflecting collected emotional information in the design evaluation and improvement process.

[0544] "Means of optimizing and presenting designs based on user emotional feedback in a store environment" refers to a method of adjusting designs based on users' emotions within the store and presenting them in the most optimal way for the user.

[0545] This invention is a system aimed at optimizing store design. The server collects external structural data of the current equipment, preprocesses it, and converts it into an analyzable format. This data conversion uses techniques such as data cleansing and format conversion. Subsequently, an artificial intelligence model is used to train the converted data. This AI model is often implemented using machine learning frameworks such as TensorFlow or PyTorch.

[0546] The server generates new designs based on the learning results and uses an emotion engine to collect user reactions to those designs. The emotion engine uses services such as the Emotion API to analyze facial expressions from the user's camera data and obtain emotion data. This emotion data is fed back to the server and incorporated into the evaluation and optimization of the designs.

[0547] Ultimately, users see the improved design through their devices. For example, an emotion engine analyzes whether customers are smiling when they see the in-store display; if there are many smiles, that design is prioritized, and if there are few, other designs are considered. In this way, the store design is optimized based on user emotions and then presented in the actual store.

[0548] As a concrete example, when designing the interior of a cafe, the server presents various design options, and the user responds through the app. The following is an example of a prompt to the generating AI model: "Please propose cafe interior designs. The current user emotion is 'joyful'. Please generate a design that takes this emotion into consideration." This method makes it possible to propose the optimal design that reflects the user's emotions in real time.

[0549] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0550] Step 1:

[0551] The server collects external structural data of the current equipment from a database. This data is often stored in CSV or JSON format. The input data includes store layout information and design requirements. The server extracts this data and proceeds to the next processing step.

[0552] Step 2:

[0553] The server preprocesses the collected external structured data and converts it into an analyzable format. Specifically, it performs data cleansing, imputing inaccurate data and missing values. It also converts the data into a numerical format that is easy for AI models to handle. The output at this stage is a clean and standardized dataset.

[0554] Step 3:

[0555] The server trains an artificial intelligence model using pre-processed data. This process typically uses machine learning libraries such as TensorFlow, and the training algorithm is usually backpropagation. The input is a pre-processed dataset, and the output is a trained AI model.

[0556] Step 4:

[0557] The server uses a pre-trained AI model to generate a simplified, new structural design. In this process, the generating AI model creates multiple design proposals based on the prompt text. The output is a new design structural proposal.

[0558] Step 5:

[0559] The user reviews the structural design generated through the device, and the device's camera captures the user's facial expressions in real time. The input is the design proposal, and the output is the user's visual feedback. This feedback is analyzed by an emotion engine.

[0560] Step 6:

[0561] The server uses an emotion engine to analyze the user's facial expression data to determine their emotions. Specifically, it utilizes the Emotion API to obtain numerical data representing emotions such as smiles and surprise. The input is the user's visual feedback, and the output is the analyzed emotion data.

[0562] Step 7:

[0563] The server uses emotional data to evaluate the generated designs and optimize them from economic and technical perspectives. At this stage, the emotional data is fed back into the AI ​​model to readjust the design proposals. The output is the optimized design proposal.

[0564] Step 8:

[0565] The user reviews the optimized design on their device and provides further feedback. This feedback is used as reference data for future design generation. The input is the optimized design, and the output is the feedback information.

[0566] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0567] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0568] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0569] [Fourth Embodiment]

[0570] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0571] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0572] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0573] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0574] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0575] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0576] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0577] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0578] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0579] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0580] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0581] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0582] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0583] This invention is a system for miniaturizing the external structure of existing communication equipment. Specifically, it is a technology in which a server is central to collecting external structure data of existing equipment and analyzing this data using an artificial intelligence model to generate a new and miniaturized structure. This system performs processing at each stage: data collection, preprocessing, AI learning, design generation, evaluation, and optimization.

[0584] First, the server efficiently collects diverse data related to the external structure of the existing equipment from a database. This data includes information about the physical design of the equipment and specific constraints related to its installation. Next, the server performs preprocessing on this data for handling by an artificial intelligence model. After the data is in an appropriate analytical format, the server builds an artificial intelligence model based on the collected data and trains the model with the data. Through this process, the server gains the ability to generate new, miniaturized equipment designs.

[0585] The generated design can be viewed on the user's device. The user evaluates the generated design and provides optimization feedback as needed. This feedback is used to further improve the server-generated design and is incorporated into the next design generation. The server utilizes this feedback loop to continuously improve the accuracy and applicability of the model.

[0586] For example, if a user wants to install a base station on the roof of a building, traditional large-scale equipment would not have enough space. However, by using this system, the server can generate a small-scale device that is suitable for the specific conditions of the rooftop. This makes it possible to overcome the constraints of installation location and reduce the costs associated with installation and operation.

[0587] This process will ultimately be implemented in a way that meets the diverse needs of users, with the aim of expanding communication infrastructure and improving cost efficiency.

[0588] The following describes the processing flow.

[0589] Step 1:

[0590] The server collects external structural data of existing equipment related to communication facilities from a database. This includes design drawings, photographs, 3D models, and technical specifications, and is also obtained from external data sources as needed.

[0591] Step 2:

[0592] The server performs preprocessing to convert the collected data into a format that can be analyzed. Image data is resized to a specific size, and technical specifications are structured for text analysis.

[0593] Step 3:

[0594] The server uses pre-processed data to train an artificial intelligence model. This training step extracts patterns and characteristics from the data and learns the design requirements for miniaturization.

[0595] Step 4:

[0596] The server uses the learned model to generate new, miniaturized equipment designs. It outputs multiple design options and generates evaluation criteria that take into account installation area and material costs.

[0597] Step 5:

[0598] The server evaluates the generated design and optimizes it based on technical and economic criteria, including durability and cost-effectiveness. Further design adjustments are made as needed.

[0599] Step 6:

[0600] Users connect to the server via their devices to review the optimized design. They can then download the design, provide feedback, and further consider its practical application.

[0601] Step 7:

[0602] The server collects user feedback and continuously improves the accuracy of the design generation process through retraining of the artificial intelligence model. This improves the quality of subsequent designs.

[0603] (Example 1)

[0604] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] Current telecommunications equipment often has a large, space-consuming external structure, which imposes many constraints in terms of installation conditions and cost. These problems make flexible installation and improved operational efficiency difficult. Therefore, to solve these problems, there is a need for technologies that can miniaturize the external structure of the equipment, enabling more flexible and economical installation.

[0606] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0607] In this invention, the server includes means for collecting information related to the external structure of the existing equipment from information sources, means for standardizing the information and converting it into an analyzable format, and means for using a generating AI model to machine learn the converted information. This streamlines the entire process from information collection to analysis and design generation, enabling the creation of miniaturized equipment structures.

[0608] "Information source" refers to a location or medium, including databases, sensors, and design drawings, used to acquire data on the external structure of existing communication equipment.

[0609] "Standardization" refers to the process of converting collected information into an analyzable format, ensuring data consistency and accuracy.

[0610] A "generative AI model" refers to an algorithm or system that uses machine learning technology to generate new designs and patterns, and is used to realize design generation for miniaturization of equipment.

[0611] "Machine learning" is the process by which computer systems learn patterns and trends based on information they collect, and automatically acquire new designs and skills.

[0612] A "feedback loop" refers to a cycle of collecting evaluation information on the generated design and using it to improve future design generation and model updates.

[0613] "Physical characteristics" refer to specific features of equipment such as weight, size, and durability, and are factors that also influence installation conditions.

[0614] "Functional stability" refers to the ability of equipment to properly perform its function over a long period of time, and is an attribute related to reliability and robustness.

[0615] As an embodiment of this invention, a specific example of a system for miniaturizing the external structure of communication equipment is shown below.

[0616] First, the server, acting as a central processing unit, collects information related to the external structure of the existing equipment from various sources. This process utilizes databases and network sensors, employing data acquisition techniques such as SQL queries to efficiently obtain the necessary information. The collected data includes the size, shape, materials used, and installation conditions of the equipment.

[0617] Next, the server standardizes the collected information and converts it into an analyzable format. At this stage, data cleaning and formatting are performed, including data imputation and conversion to unified units to improve the accuracy and consistency of the information. This allows the generative AI model to process the data accurately.

[0618] Furthermore, the server performs machine learning using a generative AI model based on standardized information. This process utilizes machine learning libraries in Python or R (e.g., TensorFlow and PyTorch) to train a neural network model and generate miniaturized equipment structures. The AI ​​model continuously improves the accuracy of the design by integrating historical data and user feedback.

[0619] The generated designs can be viewed on the user's device. Users evaluate the suitability and practicality of the generated miniaturized designs. For example, it is envisioned that users will input a request such as, "Generate a design for a small base station suitable for a building rooftop." The evaluation information from the user is fed back to the server and used to retrain the AI ​​model. This further improves the accuracy and flexibility of the model, enabling it to meet a wider range of installation needs.

[0620] This system allows for smaller communication equipment, reducing constraints on installation and operation, and also leads to cost reductions and more efficient installation.

[0621] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0622] Step 1:

[0623] The server collects information related to the external structure of the communication equipment from databases and sensors. This information includes the dimensions, materials, and installation conditions of the equipment. The collected data is stored on the server in a raw data format that reflects the characteristics of the structure.

[0624] Step 2:

[0625] The server standardizes the collected data and converts it into an analyzable format. Specifically, it imputes missing data values ​​and unifies inconsistent formats and units. It cleans and normalizes the raw data received as input and outputs it in a format that is easy for artificial intelligence models to learn from.

[0626] Step 3:

[0627] The server builds a generative AI model based on preprocessed data and begins machine learning. It uses standardized data as input to learn patterns in equipment design. It trains a neural network using Python's TensorFlow or PyTorch libraries to generate new miniaturized designs. Through this process, the AI ​​model acquires the ability to design miniaturized structures and outputs the results as design data.

[0628] Step 4:

[0629] The terminal presents the generated design to the user. Through the user interface, the AI-generated miniaturized equipment design can be visually confirmed. A 2D or 3D model of the design is displayed to inform the user of its specific design features.

[0630] Step 5:

[0631] The user evaluates the provided design and sends feedback to the server regarding areas for improvement and suggestions. Through prompts, the user specifically describes how they want to improve the generated design and returns this information to the server. This feedback information is used for retraining.

[0632] Step 6:

[0633] The server updates and retrains the AI ​​model based on user feedback. This process incorporates evaluation information and retrains the model to improve its accuracy. It uses user feedback data as input and generates an improved design algorithm as output. This ensures that subsequent design generation is more optimized.

[0634] (Application Example 1)

[0635] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] Current industrial equipment and machinery are constrained by space and weight, making efficient operation difficult in many manufacturing sites. Furthermore, the lack of methods for on-site personnel to directly optimize equipment and provide rapid feedback results in lengthy design improvement cycles. Therefore, there is a need for a system that enables efficient and rapid miniaturization of equipment and machinery, and allows for direct feedback via visual devices for work.

[0637] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0638] In this invention, the server includes means for collecting external structural data of existing equipment, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to quickly reflect feedback obtained by field personnel via visual devices into the system, and to efficiently achieve miniaturization and optimization of equipment.

[0639] "Current equipment" refers to the external structure of the equipment and devices currently used in factories and manufacturing sites.

[0640] "External structural data" refers to information related to the physical characteristics of equipment or devices, such as their shape, external dimensions, and installation conditions.

[0641] "Visual devices" refer to devices that workers wear or use to visually confirm and receive information. Specifically, this includes smart glasses and head-mounted displays.

[0642] An "artificial intelligence model" refers to a computer program that learns from large datasets and performs specific pattern recognition or prediction.

[0643] "Feedback" refers to real-time information obtained from the work site that is necessary for evaluation and improvement.

[0644] "Optimization" refers to adjusting the design and operation of a product or process to maximize its performance.

[0645] "Retraining" refers to the process of improving the accuracy of an existing artificial intelligence model by having it learn again based on new data and feedback information.

[0646] This invention deals with a system that generates new miniature structures using external structural data of existing equipment. The server collects external structural data from equipment within a factory. The collected data is preprocessed on the server using a library such as OpenCV and converted into an analyzable format.

[0647] Subsequently, the server uses software such as PyTorch to build an artificial intelligence model. By training the built model with the transformed data, it generates new, miniaturized structures. The generated structures are visually confirmed by the worker through smart glasses or a head-mounted display.

[0648] A key feature of this system is its continuous incorporation of user feedback, which is then used to retrain the model. This optimizes the generated designs economically and technically, enabling them to quickly meet the needs of each site. For example, by executing a prompt such as, "Scan the robotic arm on the work line and propose a new, miniaturized design," the system can present a practical structural design, resulting in efficient use of space and efficient equipment operation.

[0649] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0650] Step 1:

[0651] The user scans specific equipment within the factory using a visual device (e.g., smart glasses). Input includes the equipment's shape and existing dimensional information. This data is collected from the visual device. Output is the raw data transmitted from the visual device to the server.

[0652] Step 2:

[0653] The server uses OpenCV to preprocess the received data. This processing includes denoising the equipment shape and normalizing the images. The input is the raw data obtained in step 1, and the output is clean data converted into an analyzable format.

[0654] Step 3:

[0655] The server uses PyTorch with preprocessed data to build an artificial intelligence model and trains that model with data. The input is the preprocessed data, and the output is a design proposal for a new, miniaturized structure.

[0656] Step 4:

[0657] The generated structural proposal is transferred to the terminal and displayed on the user's visual device. The user evaluates this new design proposal and provides feedback through the terminal. The input is the user's feedback, which is then returned to the server via the terminal.

[0658] Step 5:

[0659] The server retrains the AI ​​model based on the collected user feedback. This retraining process improves the model's accuracy and applicability. The input is user feedback information, and the output is the improved AI model.

[0660] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0661] This invention is a system for achieving efficient miniaturization of communication equipment and includes a design evaluation and optimization process that takes user emotions into consideration. In particular, it primarily uses a server to collect, process, generate, evaluate, and optimize equipment data, and also incorporates an emotion engine that recognizes user emotions.

[0662] First, the server collects external structural data about the current communication equipment from a database. Next, this data is preprocessed and converted into a format that can be trained by an artificial intelligence model. Subsequently, the server uses the converted data to train the AI ​​model and generate a newly miniaturized equipment design. The generated design is evaluated from technical and economic perspectives and optimized.

[0663] On the other hand, when users view designs generated on the server via their devices, the system recognizes the user's emotions through an emotion engine. This emotion data is incorporated into the design evaluation and used to determine how to display the design or how to incorporate it into future optimizations.

[0664] Information derived from user emotions is returned to the server as part of a feedback loop and used by the emotion engine to improve design quality by reflecting user emotions. For example, if a user expresses positive emotions towards a particular design, the server uses those features to generate the next design. Conversely, if negative emotions are recognized, optimization is performed to avoid those elements.

[0665] Throughout this entire process, the system continuously generates improved designs, contributing to the efficient installation of communication equipment. Furthermore, it can enhance user satisfaction through emotion-recognition-based feedback.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The server collects current data on the external structure of the communication equipment from the database. This data includes design drawings, photographs, 3D models, and technical specifications. The server manages this data comprehensively and prepares it for the next processing step.

[0669] Step 2:

[0670] The server preprocesses the collected data. Depending on the data type, image data is normalized in size and its resolution is appropriately adjusted. Technical specifications are converted into a format that can be analyzed using natural language processing techniques. This preprocessing prepares the data for efficient training by artificial intelligence models.

[0671] Step 3:

[0672] The server trains an artificial intelligence model using pre-processed data. The purpose of this model training is to recognize patterns in the given data and extract the design elements necessary for miniaturization. After training is complete, the model will be able to generate new and miniaturized equipment designs.

[0673] Step 4:

[0674] The server receives the new equipment design generated by the artificial intelligence model and evaluates it from a technical and economic perspective. Evaluation metrics include the required installation area, manufacturing cost, and durability. Optimization and design improvements are made as needed.

[0675] Step 5:

[0676] Users connect to the server via a terminal to review the generated equipment design. The terminal uses an emotion engine to recognize the user's emotions in real time and incorporates the emotion data into the design evaluation process. This emotion analysis allows for a detailed understanding of the user's reactions.

[0677] Step 6:

[0678] The server uses user emotion data obtained from the emotion engine to form a feedback loop. This feedback is fed back into the design generation process and used to improve subsequent models.

[0679] Step 7:

[0680] The server regenerates a new design incorporating the feedback and presents it to the user. This allows for the continuous delivery of a design optimized to the user's emotions.

[0681] (Example 2)

[0682] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] In current communication equipment, there is a growing need for miniaturization and efficient design improvements. However, existing design processes fail to adequately incorporate user emotions and feedback, resulting in time-consuming and costly development of optimal designs. Furthermore, there is a lack of systems for evaluating designs from both technical and economic perspectives and for continuous improvement.

[0684] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0685] In this invention, the server includes means for acquiring external structural data relating to the current equipment, means for processing the external structural data and converting it into a format recognizable by a machine learning model, and means for using the converted data for training using machine learning techniques. This makes it possible not only to efficiently generate miniaturized structures but also to incorporate user emotion-based feedback into design improvements.

[0686] "External structural data related to current equipment" refers to a dataset that shows the current design information and specifications of communication equipment, and includes data such as design drawings, material information, and performance metrics.

[0687] A "machine learning model" is a computer program that uses computational algorithms to extract insights from data, enabling decision-making and prediction.

[0688] A "miniaturized structure" refers to a design or structure that is physically smaller and lighter than conventional equipment, with the aim of improving efficiency.

[0689] An "emotion analysis engine" is a software technology that identifies a user's facial expressions and voice, and analyzes their emotional state as numerical data.

[0690] A "feedback loop" is a process in which results and data generated within a system are reused as input to enable continuous improvement and adjustment.

[0691] This invention is a system that enables the efficient miniaturization of existing communication equipment while also allowing for design improvements that reflect user sentiment. Specific embodiments are described below.

[0692] The server first retrieves external structural data related to the communication equipment from the database. This data includes equipment design information and material specifications. The server accesses the database using SQL queries and extracts the relevant information.

[0693] Next, the server processes this data into a format that can be trained by a machine learning model. This involves cleaning, normalizing, and extracting features from the data, and then preparing it using the Python Pandas library.

[0694] Using well-organized data, the server trains a generative AI model using the TensorFlow library. This AI model generates optimal miniaturization designs for communication equipment, which are then visualized using design software such as AutoCAD.

[0695] Subsequently, the server performs a technical and economic evaluation of the generated design. Simulation tools such as MATLAB are used to assess the efficiency, strength, and cost of the design, and optimization is performed as needed.

[0696] As users view the design displayed on their devices, an emotion analysis engine recognizes their emotions in real time. Using OpenCV and speech recognition APIs, emotions are extracted as numerical data from the user's facial expressions and voice.

[0697] This sentiment data is returned to the server and used as part of a feedback loop. Based on user evaluations of the design, the next design generation process is adjusted, resulting in design improvements tailored to user preferences.

[0698] For example, if a user expresses an emotional response to a design, such as "it's modern and cool," that positive feedback will be taken into consideration in the next design process.

[0699] An example of a prompt message would be: "Generate a design for communication equipment that meets the following conditions: miniaturization, cost-effectiveness, and positive user feedback."

[0700] This system makes it possible to continuously improve and streamline the design of communication equipment, while also increasing user satisfaction.

[0701] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0702] Step 1:

[0703] The server retrieves external structural data related to the current communication equipment from the database. This data includes design information and material specifications, and the server accesses the database using SQL queries. The input is the raw design data stored in the database, and the output is the retrieved raw data.

[0704] Step 2:

[0705] The server preprocesses the collected external structured data into a format that the machine learning model can understand. Specifically, it performs data cleaning, normalization, and feature extraction. Using the Pandas library in Python, it removes unnecessary data and standardizes numerical data. The input is the raw data obtained in step 1, and the output is the preprocessed training data.

[0706] Step 3:

[0707] The server uses preprocessed data to train a generative AI model using TensorFlow. The training process involves identifying data patterns and learning the optimal, miniaturized structural design. The input is the training data from step 2, and the output is the trained AI model.

[0708] Step 4:

[0709] The server uses a trained AI model to generate designs for miniaturized communication equipment. The results are visualized in design software such as AutoCAD and output as concrete blueprints. The input is the trained AI model, and the output is a blueprint of the new design.

[0710] Step 5:

[0711] The server evaluates and optimizes the generated designs from both technical and economic perspectives. Here, tools like MATLAB are used to simulate the efficiency, strength, and cost of each design, and necessary adjustments are made. The input is the design drawing from step 4, and the output is the optimized structure.

[0712] Step 6:

[0713] When a user views a new design displayed on their device, the emotion analysis engine analyzes the user's facial expressions and voice. Using OpenCV and speech recognition APIs, the user's emotions are recorded as numerical data. The input is the user's facial expressions and voice information, and the output is the numerical representation of the emotion data.

[0714] Step 7:

[0715] The server uses user emotional data as part of a feedback loop and incorporates it into the next design generation process. Positive emotional characteristics are utilized in the next generation, while negative feedback is used to adjust the design. The input is the emotional data obtained in step 6, and the output is the adjustment data for the next design generation.

[0716] (Application Example 2)

[0717] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0718] Traditional store design and structural design processes have made it difficult to directly consider and optimize user emotions and satisfaction. Therefore, there is a need to improve the user experience and efficiently generate highly satisfying designs.

[0719] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0720] In this invention, the server includes means for collecting external structural data of the current device, means for preprocessing the external structural data and converting it into an analyzable format, and means for training the converted data using an artificial intelligence model. This makes it possible to evaluate and optimize the design by incorporating user sentiment data.

[0721] "External structural data of the current equipment" refers to information related to the physical shape and structure of the equipment and facilities currently in use.

[0722] "Means of preprocessing and converting into an analyzable format" refers to a series of processes and methods performed to transform raw data into a form suitable for analysis and learning.

[0723] "Means for training the transformed data using an artificial intelligence model" refers to the process of using an AI algorithm to recognize patterns based on processed data and acquire knowledge.

[0724] "Means for generating scaled-down new structures" refers to methods for creating new designs and structures that are smaller than conventional ones, based on data.

[0725] "Means of collecting user emotions towards generated structures using an emotion engine" refers to methods of collecting emotions and reactions that users show to a presented design using specific technologies.

[0726] "Means for incorporating emotional data into the evaluation and optimization process of the aforementioned structure" refers to a method for reflecting collected emotional information in the design evaluation and improvement process.

[0727] "Means of optimizing and presenting designs based on user emotional feedback in a store environment" refers to a method of adjusting designs based on users' emotions within the store and presenting them in the most optimal way for the user.

[0728] This invention is a system aimed at optimizing store design. The server collects external structural data of the current equipment, preprocesses it, and converts it into an analyzable format. This data conversion uses techniques such as data cleansing and format conversion. Subsequently, an artificial intelligence model is used to train the converted data. This AI model is often implemented using machine learning frameworks such as TensorFlow or PyTorch.

[0729] The server generates new designs based on the learning results and uses an emotion engine to collect user reactions to those designs. The emotion engine uses services such as the Emotion API to analyze facial expressions from the user's camera data and obtain emotion data. This emotion data is fed back to the server and incorporated into the evaluation and optimization of the designs.

[0730] Ultimately, users see the improved design through their devices. For example, an emotion engine analyzes whether customers are smiling when they see the in-store display; if there are many smiles, that design is prioritized, and if there are few, other designs are considered. In this way, the store design is optimized based on user emotions and then presented in the actual store.

[0731] As a concrete example, when designing the interior of a cafe, the server presents various design options, and the user responds through the app. The following is an example of a prompt to the generating AI model: "Please propose cafe interior designs. The current user emotion is 'joyful'. Please generate a design that takes this emotion into consideration." This method makes it possible to propose the optimal design that reflects the user's emotions in real time.

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0733] Step 1:

[0734] The server collects external structural data of the current equipment from a database. This data is often stored in CSV or JSON format. The input data includes store layout information and design requirements. The server extracts this data and proceeds to the next processing step.

[0735] Step 2:

[0736] The server preprocesses the collected external structured data and converts it into an analyzable format. Specifically, it performs data cleansing, imputing inaccurate data and missing values. It also converts the data into a numerical format that is easy for AI models to handle. The output at this stage is a clean and standardized dataset.

[0737] Step 3:

[0738] The server trains an artificial intelligence model using pre-processed data. This process typically uses machine learning libraries such as TensorFlow, and the training algorithm is usually backpropagation. The input is a pre-processed dataset, and the output is a trained AI model.

[0739] Step 4:

[0740] The server uses a pre-trained AI model to generate a simplified, new structural design. In this process, the generating AI model creates multiple design proposals based on the prompt text. The output is a new design structural proposal.

[0741] Step 5:

[0742] The user reviews the structural design generated through the device, and the device's camera captures the user's facial expressions in real time. The input is the design proposal, and the output is the user's visual feedback. This feedback is analyzed by an emotion engine.

[0743] Step 6:

[0744] The server uses an emotion engine to analyze the user's facial expression data to determine their emotions. Specifically, it utilizes the Emotion API to obtain numerical data representing emotions such as smiles and surprise. The input is the user's visual feedback, and the output is the analyzed emotion data.

[0745] Step 7:

[0746] The server uses emotional data to evaluate the generated designs and optimize them from economic and technical perspectives. At this stage, the emotional data is fed back into the AI ​​model to readjust the design proposals. The output is the optimized design proposal.

[0747] Step 8:

[0748] The user reviews the optimized design on their device and provides further feedback. This feedback is used as reference data for future design generation. The input is the optimized design, and the output is the feedback information.

[0749] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0750] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0751] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0752] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0753] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0754] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0755] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0756] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0757] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0758] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0759] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0760] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0761] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0762] 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.

[0763] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0764] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0765] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0766] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0767] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0768] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0769] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] A means of collecting external structural data of the current equipment,

[0773] Means for preprocessing the external structural data and converting it into an analyzable format,

[0774] A means for training the transformed data using an artificial intelligence model,

[0775] Means for generating a miniaturized novel structure based on the aforementioned learning,

[0776] Means for evaluating the generated structure and optimizing it economically and technically,

[0777] A system including means for outputting the optimized structure.

[0778] (Claim 2)

[0779] The system according to claim 1, further comprising means for forming a feedback loop based on evaluation results for the generated novel structure and using it to retrain the artificial intelligence model.

[0780] (Claim 3)

[0781] The system according to claim 1, wherein the evaluation and optimization means take into account the installation area, weight, and durability.

[0782] "Example 1"

[0783] (Claim 1)

[0784] Means for collecting information related to the external structure of the current equipment from various sources,

[0785] Means for standardizing the aforementioned information and converting it into an analyzable format,

[0786] A means for machine learning the transformed information using a generative AI model,

[0787] Means for generating a miniaturized novel structure based on the aforementioned machine learning,

[0788] A means for analyzing the generated structure and incorporating evaluation information for optimization,

[0789] A means for forming a feedback loop that improves the structure based on the aforementioned evaluation information and utilizes it for the next generation,

[0790] A system including means for outputting an optimized structure through a display device.

[0791] (Claim 2)

[0792] The system according to claim 1, further comprising means for a feedback loop to update the generated AI model for retraining based on evaluation information for the generated novel structure.

[0793] (Claim 3)

[0794] The system according to claim 1, wherein the analysis and optimization means take into account installation requirements, physical characteristics, and functional stability.

[0795] "Application Example 1"

[0796] (Claim 1)

[0797] A means of collecting external structural data of the current equipment,

[0798] Means for preprocessing the external structural data and converting it into an analyzable format,

[0799] A means for training the transformed data using an artificial intelligence model,

[0800] Means for generating a miniaturized novel structure based on the aforementioned learning,

[0801] Means for evaluating the generated structure and optimizing it economically and technically,

[0802] Means for outputting the optimized structure and providing it to an individual via a working visual device,

[0803] A system including means for retraining the generated new structure based on feedback from an individual.

[0804] (Claim 2)

[0805] The system according to claim 1, further comprising means for incorporating feedback confirmed by an individual using a visual device based on the evaluation results of the generated novel structure and using it to retrain the artificial intelligence model.

[0806] (Claim 3)

[0807] The system according to claim 1, wherein the evaluation and optimization means take into account the installation space, overall weight, and structural durability.

[0808] "Example 2 of combining an emotion engine"

[0809] (Claim 1)

[0810] Means for obtaining external structural data related to the current equipment,

[0811] The means for processing the aforementioned external structure data and converting it into a format recognizable by the machine learning model,

[0812] A means for using the transformed data for training using machine learning technology,

[0813] Means for generating a miniaturized structure based on the aforementioned training results,

[0814] Means for technically and economically evaluating and optimizing the generated structure,

[0815] A means of analyzing user emotions using an emotion analysis engine and reflecting that data in design evaluation,

[0816] A system including means for outputting the optimized structure.

[0817] (Claim 2)

[0818] The system according to claim 1, further comprising means for forming a feedback loop based on user sentiment data regarding the generated structure and utilizing it for retraining the machine learning model.

[0819] (Claim 3)

[0820] The system according to claim 1, wherein the evaluation and optimization means take into account user emotional feedback in addition to installation area, weight, and durability.

[0821] "Application example 2 when combining with an emotional engine"

[0822] (Claim 1)

[0823] A means of collecting external structural data of the current device,

[0824] Means for preprocessing the external structural data and converting it into an analyzable format,

[0825] A means for training the transformed data using an artificial intelligence model,

[0826] Means for generating a reduced novel structure based on the aforementioned learning,

[0827] Means for evaluating the generated structure and optimizing it economically and technically,

[0828] A means for collecting user emotions regarding a generated structure using an emotion engine that recognizes user emotions,

[0829] Means for incorporating the aforementioned emotional data into the evaluation and optimization process of the aforementioned structure,

[0830] A means of optimizing and presenting design based on user emotional feedback in a retail environment,

[0831] A system including means for outputting the optimized structure.

[0832] (Claim 2)

[0833] The system according to claim 1, further comprising means for forming a feedback loop based on evaluation results and sentiment data for the generated novel structure and using it to retrain the artificial intelligence model.

[0834] (Claim 3)

[0835] The system according to claim 1, wherein the evaluation and optimization means take into account scale, mass, and strength, and further take into account the improvement of the user experience based on emotional data. [Explanation of symbols]

[0836] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting external structural data of the current equipment, Means for preprocessing the external structural data and converting it into an analyzable format, A means for training the transformed data using an artificial intelligence model, Means for generating a miniaturized novel structure based on the aforementioned learning, Means for evaluating the generated structure and optimizing it economically and technically, A system including means for outputting the optimized structure.

2. The system according to claim 1, further comprising means for forming a feedback loop based on the evaluation results of the generated new structure and using it to retrain the artificial intelligence model.

3. The system according to claim 1, wherein the evaluation and optimization means take into account the installation area, weight, and durability.

Images