System and method for requesting, processing, and managing dental structures on basis of OCR

Abstract

The present disclosure relates to a system and a method for requesting, processing, and managing dental structures on the basis of OCR. The system according to one aspect of the present disclosure comprises: a first electronic device that recognizes text on a written dental work request on the basis of OCR and transmits a digital dental work request; a server that manages the digital dental work request and transmits the digital dental work request and work information; and a second electronic device that transmits, according to the work information, work completion information with respect to the digital dental work request to the server.

Description

System and method for requesting, processing, and managing dental structures based on OCR

[0001] The present disclosure relates to an electronic device and method, and more particularly, to a system and method for converting a dental prosthesis request form between a dental hospital and / or dental clinic and a dental technician into digital data and for requesting and mediating dental prostheses using OCR technology.

[0002] During the treatment process, dental clinics recognize the need for dental prostheses and take impressions, which are then delivered to dental laboratories. During this process, desired materials and precautions are communicated via phone, notes included with mold delivery, email, or a written dental prostheses request form. After receiving the impressions, the dental laboratory manufactures the prostheses based on the accompanying instructions. These procedures typically include modeling, scanning, design, milling, porcelain buildup, firing, and polishing. Once the prostheses are complete, they are delivered to the dental clinic. After reviewing the prostheses, the dental clinic can make any necessary modifications directly or send them back to the laboratory. However, from the perspective of a dental laboratory, a single lab typically serves 20 to 100 dental clinics, receives 600 to 3,000 daily requests, and receives thousands to tens of thousands of monthly requests. Therefore, it's possible that these instructions, communicated via phone or notes, may not be accurately reflected. Furthermore, because dental prostheses are sensitive to even the slightest change in shape, it's difficult to determine who is responsible if an anomaly is discovered during the treatment process. The materials used for dental prostheses are becoming increasingly diverse, and with the development of cutting-edge equipment for manufacturing dental prostheses, production capacity is increasing. Consequently, the challenges of managing information on the vast number of dental prostheses are increasing day by day.

[0003] The purpose of the embodiment disclosed in this disclosure is to convert a dental prosthesis request form between a dental hospital and / or dental clinic and a dental technician into digital data and to build a system for requesting and mediating dental prosthetics.

[0004] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0005] A system according to one aspect of the present disclosure for achieving the above-described technical task includes a first electronic device for recognizing characters in a dental prosthesis request form based on optical character recognition (OCR) of an application program, generating a digital dental prosthesis request form by converting the dental prosthesis request form into a digital form through OCR using the application program, and transmitting the digital dental prosthesis request form using the application program, a server for managing the digital dental prosthesis request form including a hospital name, a patient name, a prosthesis type, a shade, and a tooth position number indicating the position of a tooth as a number, and a second electronic device for transmitting work completion information on the digital dental prosthesis request form to the server according to work information.

[0006] A method according to another aspect of the present disclosure includes a step of recognizing characters in a dental prosthesis request form based on optical character recognition (OCR) of an application program, a step of generating a digital dental prosthesis request form by converting the dental prosthesis request form into a digital form through OCR using the application program, a step of transmitting the digital dental prosthesis request form using the application program, a step of managing the digital dental prosthesis request form including a hospital name, a patient name, a type of prosthesis, a shade, and a tooth position number indicating the position of a tooth as a number, a step of generating work information based on the digital dental prosthesis request form, a step of transmitting the digital dental prosthesis request form and the work information, and a step of transmitting work completion information for the digital dental prosthesis request form based on the work information.

[0007] In addition, a computer program stored in a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0008] In addition, a computer-readable recording medium having recorded thereon a computer program for executing a method for implementing the present disclosure may be further provided.

[0009] According to the aforementioned problem solving means of the present disclosure, there is an effect of converting a request for dental work between a dental hospital and / or dental clinic and a dental technician into digital data and establishing a system for requesting and mediating dental work, and an effect of providing convenience to users.

[0010] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0011] FIG. 1 is a drawing illustrating an example of a system according to the present disclosure.

[0012] Figure 2 is a block diagram illustrating the server of Figure 1 as an example.

[0013] FIG. 3 is a block diagram illustrating exemplary functions of a server according to the present disclosure.

[0014] FIG. 4 is a drawing for explaining an embodiment of generating a digital air conditioning request form of the present disclosure.

[0015] FIG. 5 is a diagram for explaining OCR of an application program according to one embodiment of the present disclosure.

[0016] FIG. 6 is a diagram for explaining OCR of an application program according to another embodiment of the present disclosure.

[0017] FIG. 7 is a drawing exemplifying an embodiment of implementing the OCR of the present disclosure using a transformer.

[0018] FIG. 8a, FIG. 8b, FIG. 9, FIG. 10, and FIG. 11 are drawings exemplifying various UIs provided in the application program of the present disclosure.

[0019] Figure 12 is a flowchart for explaining a method according to the present disclosure.

[0020] FIG. 13 is a ladder flow diagram for explaining a system performing a method according to the present disclosure.

[0021] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms 'part, module, element, block' used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple 'parts, modules, elements, blocks' may be implemented as a single component, or a single 'part, module, element, block' may include multiple components.

[0022] Throughout the specification, when a part is said to be "connected" to another part, this includes not only direct connection but also indirect connection, and indirect connection includes connection via a wireless communication network.

[0023] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0024] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0025] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0026] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0027] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0028] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0029] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

[0030] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0031] A server device is a server that processes information by communicating with external devices, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0032] A portable terminal is a wireless communication device that guarantees portability and mobility, and may include all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, and smart phones.

[0033] The artificial intelligence-related functions according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a Digital Signal Processor (DSP), a graphics-only processor such as a GPU, a Vision Processing Unit (VPU), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operating rules or artificial intelligence models stored in the memory. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model. For example, the processor may include a microcontroller unit (MCU), an accelerated processing unit (APU), etc.

[0034] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rules or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0035] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0036] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that imitates human neurons (biological neurons) to enable machines to learn. Artificial intelligence methodologies can be categorized into supervised learning, in which input data and output data are provided together as training data depending on the learning method, so that the solution (output data) to the problem (input data) is determined; unsupervised learning, in which only input data is provided without output data, so that the solution (output data) to the problem (input data) is not determined; and reinforcement learning, in which a reward (Reward) is provided from an external environment whenever an action (Action) is taken in the current state (State), and learning is performed in a direction to maximize this reward. In addition, artificial intelligence methodologies can be categorized according to the architecture of the learning model. The architectures of widely used deep learning technologies can be categorized into convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs).

[0037] The present device and system may include an artificial intelligence model. The artificial intelligence model may be a single artificial intelligence model or may be implemented as multiple artificial intelligence models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model in general that has problem-solving capabilities by changing the binding strength of synapses through learning, formed by artificial neurons (nodes) that form a network by combining synapses. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a desired result (output) from an arbitrary input (input) by changing the weights of neurons through learning.

[0038] The processor can create a neural network, train (or learn) a neural network, perform a calculation based on received input data, generate an information signal based on the calculation result, or retrain the neural network. The neural network models may include, but are not limited to, various types of models such as CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, etc. The processor may include one or more processors for performing calculations according to the neural network models. For example, a neural network may include a deep neural network.

[0039] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), Generative Adversarial Network (GAN), Liquid State Machine (LSM), Extreme Learning Machine (ELM), It will be understood by those skilled in the art that any neural network may be included, including but not limited to ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), KN (Kohonen Network), and AN (Attention Network).

[0040] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms, including optimization, recommendation, and data creation, can be utilized, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0041] FIG. 1 is a drawing illustrating an example of a system according to the present disclosure.

[0042] Referring to FIG. 1, the system (100) may include a first electronic device (110), a server (120), a second electronic device (130), and a network (140). For example, the first electronic device (110) may be an electronic device used in a dental hospital and / or dental clinic, and the second electronic device (130) may be an electronic device used in a dental laboratory. However, the present invention is not limited thereto.

[0043] The first electronic device (110) can recognize characters in a construction request form by executing an application program and using the application program's optical character recognition (OCR) capabilities. The application program is executed by an operating system (OS) and can be installed on the system or memory, or can provide services to users in real time via the web. For example, the application program can be provided by a server (120).

[0044] In an exemplary embodiment, the first electronic device (110) may generate a digital dental prosthesis request form by converting the dental prosthesis request form into a digital form through OCR using an application program. The first electronic device (110) may transmit the digital dental prosthesis request form to a server (120) using the application program. The digital dental prosthesis request form may be transmitted to the server (120) via a network (140). The digital dental prosthesis request form may include a hospital name, patient name, prosthesis type, shade, and a tooth position number indicating the position of the tooth using numbers.

[0045] In one embodiment, the first electronic device (110) can recognize letters and numbers in a request for construction based on the character positions according to a standard request form provided by the application program. This may be referred to as a so-called template-based character recognition method.

[0046] In another embodiment, the first electronic device (110) can recognize letters and numbers in a construction request form based on random locations in an arbitrary request form that does not follow the standard request form format, and determine the context based on the recognized letters and numbers. This may be referred to as a so-called non-template-based character recognition method or a random location-based character recognition method.

[0047] The server (120) can manage digital construction request forms.

[0048] In one embodiment, the server (120) can classify clear and unclear characters in a digital request form using an artificial intelligence model that recognizes characters. Then, the server (120) can highlight unclear characters in the digital request form and transmit the highlighted digital request form to the first electronic device (110). The highlighted digital request form can be transmitted to the first electronic device (110) via the network (140). If the server (120) cannot recognize and classify unclear characters using the artificial intelligence model, the server (120) transmits a response thereto and information about the relevant portion to the first electronic device (110), and the user operating the first electronic device (110) can provide feedback to the server (120). That is, the user operating the first electronic device (110) can directly highlight unclear points.

[0049] In another embodiment, the first electronic device (110) may request a rework of a dental appliance from a server using an application program. In this case, the server (120) may provide a quick menu UI for terminal adjustment to the first electronic device (110) in response to the request for rework of the dental appliance. The quick menu UI may be executed by the application program and displayed on the first electronic device (110).

[0050] In another embodiment, the server (120) may calculate an OCR error rate based on the digital pore request form. Furthermore, the server (120) may provide an incentive UI based on the OCR error rate to the first electronic device (110). In an exemplary embodiment, the first OCR error rate may be the ratio of clearly recognized characters to unclearly recognized characters in the digital pore request form.

[0051] In an exemplary embodiment, the second OCR error rate may be a value obtained by dividing the difference between the ratio of clearly recognized characters to unclearly recognized characters (hereinafter, specific error rate) for a specific digital engraving request form by the average ratio of clearly recognized characters to unclearly recognized characters within the entire set of individual digital engraving request form events input to the first electronic device (110) (hereinafter, average error rate) by the average error rate. That is, the second OCR error rate is as shown in the following mathematical expression 1.

[0052] [Mathematical Formula 1] Second OCR Error Rate = {(Specific Error Rate) - (Average Error Rate)} / (Average Error Rate)

[0053] According to an exemplary embodiment, the average error rate may be equal to the average first OCR error rate of all digital pore request forms input into the first electronic device (110). According to an exemplary embodiment, the specific error rate may be equal to the first OCR error rate of any specific digital pore request form input into the first electronic device (110).

[0054] The incentive UI can be executed by the application program and displayed on the first electronic device (110). For example, as the first OCR error rate decreases, the incentive provided by the incentive UI can increase. As the first OCR error rate increases, the incentive provided by the incentive UI can decrease.

[0055] According to an exemplary embodiment, the first electronic device (110) may place greater weight on incentives based on the second OCR error rate compared to incentives based on the first OCR error rate. For example, as the second OCR error rate decreases, the incentive based on the incentive UI may increase relatively more compared to the decrease in the first OCR error rate. As the second OCR error rate increases, the incentive based on the incentive UI may decrease relatively more compared to the increase in the first OCR error rate.

[0056] Incentives can be, but are not limited to, discount rates, for example. The incentive UI will be described in more detail in Figure 10.

[0057] The server (120) can generate work information based on a digital construction request form. The server (120) can transmit the digital construction request form and work information to a second electronic device (130). The digital construction request form and work information can be transmitted to the second electronic device (130) via a network (140).

[0058] In another exemplary embodiment, the server (120) may provide an auction system to adjust the cost of dental technicians or to bid on the cost of dental technicians. For example, the server (120) may provide an auction system to allow multiple dental technicians to bid for open bidding at dental hospitals and / or dental clinics, and / or to conduct reverse auctions.

[0059] In one embodiment, a first electronic device (110) may upload data representing a request for multiple prosthetics for one patient to an application program, and transmit a digital prosthetic request form and the uploaded data to a server (120) using the application program. The server (120) may receive the digital prosthetic request form and the uploaded data via a network (140). The server (120) may display a separate display UI (User Interface) corresponding to each of the multiple prosthetics on the digital prosthetic request form, and transmit the digital prosthetic request form with the separate display UI displayed to a second electronic device (130). The separate display UI is executed by the application program, and may be distinguished by color, layer, etc.

[0060] In another embodiment, the server (120) may provide a portfolio sharing community UI to the second electronic device (130) for dental technicians to upload their work to the application program. The portfolio sharing community UI may be executed by the application program and displayed on the second electronic device (130).

[0061] In another embodiment, the server (120) may generate a dedicated chat room UI that enables communication between the first electronic device (110) and the second electronic device (130) in the application program, and provide the dedicated chat room UI to each of the first electronic device (110) and the second electronic device (130). The dedicated chat room UI may be executed by the application program and displayed on the first electronic device (110) and the second electronic device (130). The criteria for generating the dedicated chat room may be a criterion that the chat room is generated only for cases where the dental hospital, dental laboratory, and patient are the same. However, the present invention is not limited thereto.

[0062] In another embodiment, the server (120) may provide a portfolio sharing community UI to the second electronic device (130) for dental technicians to upload their work to the application program. The portfolio sharing community UI may be executed by the application program.

[0063] The second electronic device (130) can receive a digital construction request form and work information. The second electronic device (130) can transmit work completion information, which is the result of completing construction work for the digital construction request form based on the work information, to the server (120).

[0064] Figure 2 is a block diagram illustrating the server of Figure 1 as an example.

[0065] Referring to FIG. 2, the server (120) may include a communication interface (121), an API (Application Programming Interface) server (122), a web server (123), a memory (124), a processor (125), and a database server (126).

[0066] The communication interface (121) may include one or more components that enable communication with an external device. For example, the communication interface (121) may include at least one of a wired communication module, a wireless communication module, and a short-range communication module.

[0067] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0068] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0069] The wireless communication module may include a wireless communication interface including an antenna and a transmitter for transmitting signals. Furthermore, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor (110) through the wireless communication interface into an analog wireless signal under the control of the processor (110).

[0070] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0071] The API server (122) is an application programming interface. In programming, it can provide an interface specification, i.e., an API, for interaction by defining a series of sub-programs, protocols, etc. for writing a program.

[0072] A web server (123) may run a service program, web server software, that transmits HTML documents or objects (such as image files) requested by a web browser via HTTP or HTTPS. The web server (123) may include a computer program that accepts HTTP requests from a client, such as a web browser, and returns web pages, such as HTML documents, and / or a computing device that executes such a computer program.

[0073] The memory (124) can store data supporting various functions of the system (100) and programs for the operation of the processor, can store input / output data (e.g., music files, still images, moving images, etc.), and can store a plurality of application programs (or applications) running in the system (100), data for the operation of the system (100), and commands. At least some of these application programs can be downloaded from an external server via wireless communication. The memory (124) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. The memory (124) may include an OCR processing module (1241) including commands for processing OCR, a messaging processing module (1243) including commands for processing various messages, and an artificial neural network processing module (1245) including commands for executing an artificial neural network.

[0074] The processor (125) may include an artificial neural network processing unit (1251) for implementing artificial intelligence. As described above, the methodologies of artificial intelligence can be divided into supervised learning, unsupervised learning, and reinforcement learning. The architecture of deep learning technology can be divided into CNN, RNN, Transformer, GAN, etc. The artificial intelligence model may be one or more artificial intelligence models. As described above, the processor may generate a neural network, train a neural network, perform a calculation based on received input data, generate an information signal based on the result of the calculation, or retrain a neural network. The neural network may include, but is not limited to, a CNN, an RNN, a perceptron, a multilayer perceptron, and the like, and it will be understood by those skilled in the art that the neural network may include any neural network. The processor, as described above, can utilize various artificial intelligence structures and algorithms such as CNN, R-CNN, such as GoogleNet, AlexNet, VGG Network, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for natural language processing, Visual Analytics, Visual Understanding, Video Synthesis, ResNet for vision processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, Recommendation, Data Creation for data intelligence, etc., but is not limited thereto.CNNs can be structured by alternating between convolutional layers, which apply multiple filters to each region of an image to create a feature map, and pooling layers, which spatially integrate the feature maps to extract features that are invariant to changes in position or rotation. This allows for the extraction of features at various levels, from low-level features such as points, lines, and surfaces to complex and meaningful high-level features. The convolutional layer obtains a feature map by applying a nonlinear activation function to the inner product of the filter and the local receptive field for each patch of the input image. Compared to other network architectures, CNNs can have the characteristics of using filters with sparse connectivity and shared weights. This connection structure reduces the number of parameters to be learned and makes learning through the backpropagation algorithm efficient, ultimately improving prediction performance. In this way, the features finally extracted through repetition of convolutional and integration layers can be combined with classification models such as multi-layer perceptrons (MLPs) or support vector machines (SVMs) in the form of fully-connected layers, and used for compressed model learning and prediction. Meanwhile, an artificial intelligence-based problem development model can refer to an artificial intelligence model trained based on deep learning, and for example, it can refer to a model trained using a convolutional neural network (CNN).Additionally, the AI-based problem development model may include at least one algorithm among Natural Language Processing (NLP), Random Forest (RF), Support Vector Machine (SVC), eXtra Gradient Boost (XGB), Decision Tree (DC), Knearest Neighbors (KNN), Gaussian Naive Bayes (GNB), Stochastic Gradient Descent (SGD), Linear Discriminant Analysis (LDA), Ridge, Lasso, and Elastic net.

[0075] The database server (126) can manage various user information, purchase history information, etc. stored in the database.

[0076] FIG. 3 is a block diagram illustrating exemplary functions of a server according to the present disclosure.

[0077] Referring to FIG. 3, the server (310) may correspond to the server (120) of FIGS. 1 and 2. The server (310) may communicate with an electronic device (e.g., a first electronic device (110)) used in a dental clinic (320) and an electronic device (e.g., a second electronic device (130)) used in a dental laboratory (330). The server (310) may include a financial management unit (311), a community management unit (312), a chat management unit (313), and a data management unit (314).

[0078] The financial management department (311) can be linked to accounts, cards, home tax, etc. The financial management department (311) can manage expenses such as equipment rental, depreciation, labor costs, rent, utility bills, material costs, and consumables. The financial management department (311) can manage sales. The financial management department (311) can analyze revenue and / or expenses, such as revenue trends by business partner, major cost trends, and trend charts. The financial management department (311) can manage financial performance. The financial management department (311) can manage employee salaries, retirement benefits, etc.

[0079] The community management department (312) can provide a news feed of dental lab content posts, etc. The community management department (312) can operate its own chatbot system. The community management department (312) can connect dental clinics and dental labs, facilitate new transactions between dental clinics and dental labs, and operate a job search platform.

[0080] The chat management unit (313) can operate chat between electronic devices. The chat management unit (313) can create menus for each business partner and chat rooms for each request and patient.

[0081] The data management unit (314) can provide users with a login page, a membership registration page, a rate plan information page, etc. When a user logs in, the data management unit (314) may provide an application program that includes a dashboard (total sales, sales growth rate compared to the previous month, settlement status by dental clinic, OCR recognition accuracy status, provision of discount coupons when accuracy is maintained for a certain period, etc.), a calendar (indication of reception / closing dates by patient, etc.), request upload (OCR recognition of request file, etc.), order management (request chart, request electronic chart, request chart modification, Excel, etc.), client / prosthesis management (registration of basic sales prosthesis, registration of client (dental clinic / laboratory, etc.), registration of sales prosthesis by client, etc.), settlement management (verification of sales by client, verification of deposit status by client, inquiry of receivables, issuance of settlement statement by client, issuance and transmission of settlement statement by period by client, issuance of order list for the corresponding period, etc.), creation of menu by client, creation of chat rooms by request and patient, pinning of request and oral scan images to the top in an Instagram feed structure for conversation, location tags for leaving comments on photos, etc.

[0082] FIG. 4 is a diagram illustrating an embodiment of generating a digital construction request form according to the present disclosure. The term "digital construction request form" as used herein includes a digital document file in which digitally recognized characters are inserted into a predefined document format, and construction request input data, which is a collection of information extracted from a written construction request form. Therefore, generating a digital construction request form will be understood to refer to both the generation of a digitally converted document file and the generation of a digital data set.

[0083] Referring to FIG. 4, the dental prosthesis request form (410) may include characters and figures such as a hospital name, dental prosthesis type, patient name, patient age, patient gender, reception date, completion date, shade, and an image of the patient's teeth. The characters may include letters and numbers. The characters and figures of the dental prosthesis request form (410) may be recognized through OCR. An OCR-recognized digital dental prosthesis request form (420) may be generated. The digital dental prosthesis request form (420) may include a hospital name, patient name, prosthesis type, shade, reception date, completion date, and a tooth position number indicating the position of the tooth using numbers. The tooth position numbers are numbers that sequentially represent the teeth on the upper right of the target patient as shown in Fig. 4, the tooth position numbers on the upper right are numbers that sequentially represent the teeth on the lower right of the target patient, the tooth position numbers on the upper left are numbers that sequentially represent the teeth on the upper left of the target patient, and the tooth position numbers on the lower left are numbers that sequentially represent the teeth on the lower left of the target patient. Fig. 5 is a drawing for explaining OCR of an application program according to one embodiment of the present disclosure.

[0084] Referring to FIG. 5, the server (120) can organize OCR and display the customer's prosthesis type (510). For example, the server (120) can organize recognized OCR based on the "Classification-Material Name" list in the "Prosthesis Management Window" registered in the "Settlement Management Page" and display the customer's prosthesis type.

[0085] The server (120) can use multiple prosthetics per person. In this case, the types of prosthetics included in the digital prosthesis request form (420) can be displayed as two or more. The server (120) can arrange the information read by OCR according to the diagram (521) (520). The diagram (521) can be exemplarily shown as shown in FIG. 5. In the case of numbers read by OCR, the server (120) can display them in bold letters according to their positions in the diagram (521). When the user clicks on a dimmed number, the server (120) can display the corresponding number in bold letters in the diagram (521). When the user clicks on a bold number, the server (120) can display the corresponding number in a dimmed letter in the diagram (521). The server (120) can display a check mark in the case of a rework request (530). For example, 'RE', 'remake', and the like can be displayed. When a user clicks the upload menu in the application program, a photo is transmitted to the server (120) (540), and when the user clicks, the server (120) can display a 'request upload completion pop-up window' in the application program. When the user clicks, the server (120) can move the files displayed in the 'Check files to be uploaded' group to the 'request group' that the application program is organizing. The button can be activated only when there is a photo in the 'Check files to be uploaded' space. The server (120) can include an image OCR API and a GPT API. The photo is stored in the server, and the server (120) can extract text through the OCR function. The server (120) organizes the text extracted by OCR into a table of contents through GPT, converts it to CSV data, and displays it like an Excel sheet on the order management screen, so that it can be exported. The server (120) can view the data uploaded by the user.Uploaded data is converted into a sheet like Excel through OCR and GPT API, and if there are any errors in the changed content, they can be corrected through the admin account and reflected to users.

[0086] In an exemplary embodiment, the server (120) can manage the inventory (type, quantity) of materials currently managed by the second electronic device (130). For example, when a predetermined number or more of a specific dental material is requested by the first electronic device (110), the server (120) can compare the remaining inventory of the second electronic device (130) with the order quantity, and when the inventory quantity of the specific material is less than or equal to a first threshold, the server (120) can provide a notification to the second electronic device (130) that an order is required. According to an exemplary embodiment, when the server (130) receives an additional material order input by the second electronic device (130), the server (130) can transmit a command to order the corresponding material to an external device. Therefore, a dental laboratory, which is a user of the second electronic device (130), can easily manage inventory and order insufficient inventory through the server (120).

[0087] According to an exemplary embodiment, the server (120) may count and manage the average inventory of each of the plurality of second electronic devices (130), and may manage the average material ordering tendency of each of the plurality of first electronic devices (110). For example, if it is determined that the first electronic device (110) has a greater tendency to order a specific material compared to other dental clinics, the server (120) may provide a special notification to the second electronic device (130) indicating that an order is required if the inventory quantity of the specific material managed by the second electronic device (130) is lower than a second threshold that is higher than a first threshold. Accordingly, even if the expected inventory quantity managed by the second electronic device (130) is higher than the first threshold and thus determined to be normal, the server (120) may be able to prevent a stock shortage situation of the second electronic device (130) through dynamic inventory management according to the material ordering tendency of the first electronic device (110). FIG. 6 is a diagram for explaining OCR of an application program according to another embodiment of the present disclosure.

[0088] Referring to FIG. 6, a request document recognition step is performed in step S610. A step is performed to secure multiple OCR data by performing OCR multiple times on the same request document.

[0089] Step S610 may be referred to as an input data processing step. Aligned multiple OCR output characters, characters xy-coordinates, characters OCR confidence scores, Position ID (word order), etc. may be performed. Through this, the first electronic device (110) can recognize letters and numbers of a construction request form at a random position according to an arbitrary request form that does not follow the format of a standard request form, and further, comments, messages, and handwriting written in a blank space on the document, and determine a context based on the recognized letters and numbers.

[0090] In some embodiments related to character OCR confidence scores, confidence scores of OCR data are calculated, and only OCR data above a certain value can be used as input data. Confidence scores are numerical values ​​representing the quality scores of scanned images of a request document, and can be calculated based on various variables such as the ratio of parts of the request document recognized as characters to parts recognized as non-character images, resolution, and shaking. This has the effect of providing error verification and improved accuracy through multiple OCR operations.

[0091] In step S620, an error extraction step is performed in the request form. A step is performed to determine whether an error has occurred in each word order included in the OCR data and whether correction is required for each word order. The types of errors included in the request form may include at least one of a first error and a second error. The first error may be an error that occurred during the OCR recognition process. The first error may be extracted by comparing and analyzing multiple OCR data obtained by performing OCR multiple times on the same request form and extracting word orders that have differences. For example, assuming that the ground truth is 'coping imp, R10', the first OCR data is 'coplng imp, R10', and the second OCR data is 'coping imp, R1O', the first error in 'coplng imp, R10' in the first OCR data may be 'l', and the first error in the second OCR data may be 'o'. The second error may be a typo included in the original text of the request form. Secondary errors can be extracted by comparing and analyzing frequently used terms / expressions in the request with a pre-stored DB and extracting errors. At this time, the 'pre-stored DB' can include various examples of correct expressions for the terms / expressions and errors matching them. For example, the correct expression is 'R10', the first error is 'RIO' which is recognized as all English letters, the second error is 'RlO' which is a numeric and English letter mutual error, the third error is a case-similar word error 'L(l) / I(i)', and the fourth error is a shape-similar error 'p, d / 10, lO, / a, d'. It has the effect of detecting specific OCR execution errors resulting from multiple OCR executions.

[0092] In step S630, an error correction step is performed. A step of setting a correction direction for the extracted errors and performing a corresponding correction is performed. Step S630 may be referred to as an output data processing step. Types of error correction methods may include, for example, NO EDIT(remain), DELETE, INSERT, SELECT, GENERATE(replace), etc. NO EDIT(remain) may determine that a word order does not require correction when multiple pieces of OCR data are identical, and may maintain the existing data without performing a correction task that changes the recognition data. DELETE may delete an incorrect character. INSERT may insert a missing character. SELECT may select and apply the most appropriate data among the recognized data for a specific word order in multiple pieces of OCR data. GENERATE(replace) may delete an incorrect character, generate a correct character, and insert (replace) it. DELETE, INSERT, and GENERATE(replace) are applicable to the first and second errors. SELECT is applicable to the first error. An example of extracting the first error is as described above. Error correction examples may include (“c”, 'no edit'), (“o”, 'no edit'),…, (“i", 'select 2'), … (“1”, 'select 2'), … (“0”, 'select 1'). This has the effect of providing specific correction logic for OCR data according to multiple OCR executions.

[0093] FIG. 7 is a drawing exemplifying an embodiment of implementing the OCR of the present disclosure using a transformer.

[0094] Referring to FIG. 7, the embedding layer (710) can convert each character of each OCR into a high-density vector, quantize the x and y coordinates to map them into the high-density vector, quantize the OCR confidence score into the high-density vector, and concatenate all vectors and map them into a single vector using linear projection. The self-attention layer (720) can perform self-attention between vectors. The feed-forward layer (730) can be a general feed-forward layer of a transformer. The cross-attention layer (740) can perform cross-attention using image embeddings as “keys” and “values.” The cross-attention layer (740) is optional and can be omitted depending on the task and available resources. The image embedding layer (750) can be a CNN or a visual transformer that converts a document image into a series of high-density vectors. The number of visual tokens can be fixed. The character tagger (760) may be a single linear layer that maps the final hidden vector to five possible tags. Among the five possible tags, each character tag may include "no edit", which performs no action or no action, "delete", which deletes the character, "insert", which newly inserts the next character, "select", which selects one of the characters recognized by multiple OCRs, and "generate", which deletes the current character and generates a new character. The character generator (770) may be a single linear layer that maps the final hidden vector to a vector of the same size as the number of model vocabulary, and may generate a new character if the predicted tag is equal to "insert" or "generate." The addition of an action layer to the Transformer-based architecture for performing multiple OCRs has the effect of improving the accuracy of OCR recognition.

[0095] FIG. 8a, FIG. 8b, FIG. 9, FIG. 10, and FIG. 11 are drawings exemplifying various UIs provided in the application program of the present disclosure.

[0096] Referring to FIG. 8A, the application program of the present disclosure may provide an order management menu as part of various functions for users. The application program of the present disclosure may provide detailed menus, such as prosthesis management and settlement management, as a transaction management menu for transaction ledgers and work records. Furthermore, the application program of the present disclosure may provide a request upload menu, which is a menu for creating an electronic dental request form as OCR data by uploading a handwritten written dental request form. Furthermore, the application program of the present disclosure may provide an order management menu, which is a screen for easily searching transaction history between a dental laboratory and a dental clinic, work information, and cost per work by search period, dental clinic name, patient name, etc.

[0097] Referring to FIG. 8a, the application program of the present disclosure can provide various convenient menus for users, such as a serial number per order or task, date of receipt, date of completion request, whether rework is required, name of dental clinic requesting work, patient name, type of prosthesis, shade of prosthesis, tooth number per tooth, unit price per quantity, whether completed, total amount, and a menu for viewing details of a request form, through an order management menu.

[0098] Referring to FIG. 8b, when a user clicks on any one of the task lists, a pop-up request detail view menu may be provided to the user by covering a portion of the screen. According to an exemplary embodiment, a date selection function (810) may be provided on the screen of the application program of the present disclosure. When the user clicks, a calendar may appear and a date may be selected. The period selection range may be limited to a maximum of three months, but is not limited thereto. The default search period may be set to one week, but is not limited thereto. Dates may be searched based on the date of receipt. When a specific item in a group (820) is clicked, a request detail view window (830) may be displayed. When the request detail view window (830) opens, the entire page may be pushed to the left, and the request detail view window may be positioned on the right. The user may click a number in the format window (840) in the request detail view window (830). For numbers read using OCR, the numbers may be displayed in bold letters according to their position in the text input window (840). If a user clicks on a dimmed number in the text input window (840), the number may be displayed in bold. If a user clicks on a bolded number in the text input window (840), the number may be displayed in a dimmed manner.

[0099] Referring to FIG. 9, when a user clicks on the upload menu in the application program, a photo is transmitted to the server (120) (910), and when the user clicks, the server (120) can display a 'request upload completion pop-up window' in the application program. When the user clicks, the server (120) can move the files displayed in the 'Check files to be uploaded' group to the 'request group' that the application program is organizing. The button can be activated only when there is a photo in the 'Check files to be uploaded' space. A serial number can be generated based on one uploaded photo in the request detail view window (920). A regular serial number is generated like an order number is managed in a shopping mall, and there is an effect that the customer center can quickly find and respond to customer inquiries with the serial number. When a file is uploaded through the request photo upload button in the image preview (930), the photo to be uploaded can be displayed in the image preview (930). The user can click the number in the format window (940) in the request detail view window (830). For numbers read using OCR, the numbers may be displayed in bold letters according to their location in the text input window (940). If a user clicks on a dimmed number in the text input window (940), the number may be displayed in bold. If a user clicks on a bolded number in the text input window (940), the number may be displayed in a dimmed manner.

[0100] Referring to FIG. 10, the server (120) may provide an incentive UI, for example, a discount rate, based on the OCR recognition rate. As described above, the first OCR error rate may be the ratio of characters that are unclearly recognized to characters that are clearly recognized in a digital construction request form. As described above, in an exemplary embodiment, the second OCR error rate may be the difference between an average error rate, which is the average of the ratio of characters that are unclearly recognized to characters that are clearly recognized in the entire set of individual digital construction request form events input to the first electronic device (110), and a specific error rate, which is the ratio of characters that are unclearly recognized to characters that are clearly recognized for a specific digital construction request form, divided by the average error rate.

[0101] The incentive UI can be executed by the application program and displayed on the first electronic device (110). For example, as the OCR error rate decreases, the incentive according to the incentive UI can increase. As the OCR error rate increases, the incentive according to the incentive UI can decrease. The incentive may be, for example, a discount rate, but is not limited thereto. For example, as the OCR error rate decreases, the discount rate can increase.

[0102] According to an exemplary embodiment, the first electronic device (110) may place greater weight on incentives based on the second OCR error rate compared to incentives based on the first OCR error rate. For example, as the second OCR error rate decreases, the incentive based on the incentive UI may increase relatively more compared to the decrease in the first OCR error rate. As the second OCR error rate increases, the incentive based on the incentive UI may decrease relatively more compared to the increase in the first OCR error rate.

[0103] According to an exemplary embodiment, the server (120) may display a discount rate on the incentive UI (1010).

[0104] According to an exemplary embodiment, the discount rate displayed in the incentive UI (1010) may be predefined by a user, an administrator, or a platform operator, or may be fixed according to a value agreed upon in advance between users (dental clinics and dental laboratories).

[0105] According to an exemplary embodiment, the discount rate displayed on the incentive UI (1010) may be differentially displayed based on the first and / or second OCR error rates. For example, the server (120) may display the first discount rate based on the first OCR error rate being lower than the first reference value. For example, the server (120) may display the second discount rate, which is different from the first discount rate, based on the second OCR error rate being lower than the second reference value. Since the system according to the present disclosure can provide discount rates based on the first and / or second OCR error rates, the system can improve the overall OCR recognition rate by inducing the user of the first electronic device to write a handwritten dental prosthesis request form in a direction that increases the OCR recognition rate. Referring to FIG. 11, a dedicated chat room is opened between a specific dental hospital and a dental laboratory, so that the specific dental hospital and the dental laboratory can communicate smoothly through the chat room.

[0106] According to an exemplary embodiment, the criteria for creating a chat room may be set such that a hospital, a dental laboratory, and a patient are the same. The first user terminal (1110) and the second user terminal (1130) may correspond to the first electronic device (120) and the second electronic device (130) of FIG. 1. The server (120) creates a dedicated chat room UI in the application program, and the first user terminal (1110) and the second user terminal (1130) may perform a chat via the network (1120). For example, chat room 1 may be created for Hospital A, Dental Laboratory B, and Patient C, chat room 2 may be created for Hospital A, Dental Laboratory B, and Patient D, chat room 3 may be created for Hospital A, Dental Laboratory X, and Patient D, and chat room 4 may be created for Hospital B, Dental Laboratory X, and Patient D. For Patient D, who has been referred to other dental laboratories and hospitals, a "Patient Dental Information Export" menu can be created within the chat room (Chat Room 2). With the consent of the dental laboratory or hospital, this information can be shared in other chat rooms (Chat Rooms 3 and 4). Obtaining consent and authorization from the dental laboratory or hospital can be accomplished by offering discounts and incentives within the platform upon subsequent requests and acceptances, and automatically granting the dental laboratory or hospital "sharing request permission" when other patients' dental information is needed.

[0107] According to an exemplary embodiment, a first user terminal (1110) and a second user terminal (1130) can send and receive various media such as text, images, voice, and video through a chat room. For example, the first user terminal (1110) can send a first image related to a request for qigong to the second user terminal (1130) through the chat room. The second user terminal (1130) can write text in the first image related to the request for qigong, or insert an object including a context such as a memo, tagging, or free drawing, and reply to the first user terminal (1110) with a second image with inserted text or object or a related chat message.

[0108] In short, the way we communicate through chat rooms can include a variety of media, such as inserting chat, images, messages, or drawing free-form objects.

[0109] The first user terminal (1110) can reply to the second user terminal (1130) with a third image or chat message that reinserts the text or object in response to the text or object. This allows the first user terminal (1110) and the second user terminal (1130) to conduct context-based chatting including images via the network (1120), and improve the efficiency of requesting and providing feedback through more concise and clear communication via images.

[0110] Fig. 12 is a flowchart for explaining a method according to the present disclosure. Fig. 13 is a ladder flowchart for explaining a system for performing the method according to the present disclosure.

[0111] Referring to FIGS. 12 and 13, a step of recognizing characters in a dental prosthesis request form based on optical character recognition (OCR) of an application program is performed (S1210). A step of generating a digital dental prosthesis request form by converting the dental prosthesis request form into a digital format through OCR using the application program is performed (S1220). Referring to FIG. 13, for example, a first user terminal (1310) can recognize characters in a dental prosthesis request form through OCR (S1310). The first user terminal (1310) can generate a digital dental prosthesis request form by converting the OCR-recognized dental prosthesis request form into a digital format. The digital dental prosthesis request form can include a hospital name, patient name, prosthesis type, shade, and tooth position number indicating the position of the tooth as a number.

[0112] A step of transmitting a digital request for construction using an application program is performed (S1230). Referring to FIG. 13, for example, a first user terminal (1310) can transmit a digital request for construction to a server (1320) (S1320).

[0113] A step for managing a digital construction request form is performed (S1240). A step for generating work information based on the digital construction request form is performed (S1250). Referring to FIG. 13, for example, the server (120) can manage the digital construction request form by extracting unclear characters or calculating the OCR error rate (S1330).

[0114] A step of transmitting a digital construction request form and work information is performed (S1260). Referring to FIG. 13, for example, the server (120) can transmit the digital construction request form and work information to a second user terminal (1330) (S1340).

[0115] A step of transmitting work completion information, which is the result of performing work on a digital construction request form based on work information, is performed (S1270). Referring to FIG. 13, for example, a second user terminal (1330) can transmit work completion information to a server (1320) (S1350).

[0116] In some embodiments, the first user terminal (1310) may transmit a digital request form to the server (1320) (S1360). The digital request form may be data indicating a request for multiple prosthetics for a single patient. The server (120) may transmit a digital processing request form displaying a separate display UI to the second user terminal (1330) (S1370).

[0117] In some embodiments, the first user terminal (1310) may request rework from the server (120) (S1380). The server (120) may provide a quick menu UI to the first user terminal (1310) (S1390).

[0118] In some embodiments, the server (120) may provide an incentive UI to the first user terminal (1310) based on the OCR error rate (S1391).

[0119] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0120] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0121] The disclosed embodiments have been described with reference to the attached drawings as follows. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. A first electronic device that recognizes characters in a request for construction based on optical character recognition (OCR) of an application program, creates a digital request for construction by converting the request for construction into a digital form through the OCR using the application program, transmits the digital request for construction using the application program, and extracts OCR errors by comparing and analyzing whether the original text errors in the request for construction correspond to any one of the following types: a first type of error in which all errors are recognized as English characters, a second type of error in which numbers and English characters are mutually incorrect, a third type of error in which English uppercase and lowercase letters are similar words, and a fourth type of error in which English character shapes are similar; A server that manages the digital dental prosthesis request form including the hospital name, patient name, prosthesis type, shade, and tooth position number indicating the position of the tooth as a number, creates work information based on the digital dental prosthesis request form, and transmits the digital dental prosthesis request form and the work information; and A second electronic device is included that receives the digital construction request form and the work information, and transmits work completion information for the digital construction request form to the server according to the work information. The above server, Calculating an OCR error rate based on the digital blasting request form, and providing an incentive UI according to the OCR error rate to the first electronic device, wherein a first OCR error rate, which is a ratio of characters that are unclearly recognized to characters that are clearly recognized in the digital blasting request form, and a second OCR error rate, which is a value obtained by dividing a difference of a specific error rate, which is a first OCR error rate for a specific digital blasting request form, by an average error rate, which is an average of the first OCR error rates for all digital blasting request forms received from the first electronic device, are calculated, and a first incentive according to the first OCR error rate and a second incentive according to the second OCR error rate are displayed. A system characterized in that the second incentive according to the second OCR error rate has a greater weight than the first incentive according to the first OCR error rate.

2. In paragraph 1, The above first electronic device, A system characterized in that it recognizes letters and numbers of the request for construction based on the character positions according to the standard request form provided by the application program.

3. In paragraph 2, The above first electronic device, A system characterized in that it recognizes letters and numbers of the above construction request form based on a random location according to an arbitrary request form that does not follow the format of the above standard request form, and determines the context based on the recognized letters and numbers.

4. In paragraph 3, The above server, A system characterized in that it classifies clear characters and unclear characters in the digital construction request form using an artificial intelligence model that recognizes characters, highlights the unclear characters in the digital construction request form, and transmits the digital construction request form with the highlights to the first electronic device.

5. In paragraph 4, The above first electronic device, Uploading data representing a request form indicating a request for multiple prostheses for one patient to the application program, and transmitting the digital prosthesis request form and the uploaded data to the server using the application program, The above server, A system characterized in that a separation display UI (User Interface) corresponding to each of the plurality of prostheses is displayed on the digital prosthesis request form, and the digital prosthesis request form with the separation display UI displayed is transmitted to the second electronic device.

6. In paragraph 5, The above first electronic device, Request the reworking of the dental work to the server using the above application program The above server, A system characterized in that it provides a quick menu UI for terminal adjustment to the first electronic device in response to a request for reworking of the above-mentioned dental work.

7. In paragraph 1, The above server, A system characterized in that the second electronic device provides a portfolio sharing community UI for dental technicians to upload their work to the application program.

8. In paragraph 1, The above server, A system characterized in that the application program generates a dedicated chat room UI that can communicate between the first electronic device and the second electronic device, and provides the dedicated chat room UI to each of the first electronic device and the second electronic device.

9. A step of recognizing characters in a construction request form based on optical character recognition (OCR) of an application program; A step of generating a digital construction request form by converting the construction request form into a digital form through the OCR using the above application program; A step of transmitting the digital construction request form using the above application program; A step of managing the digital dental prosthesis request form including the hospital name, patient name, prosthesis type, shade, and tooth position number indicating the position of the tooth as a number; A step of creating work information based on the above digital construction request form; A step of transmitting the digital construction request form and the work information; A step of transmitting work completion information for the digital construction request form according to the above work information; and It includes a step of calculating an OCR error rate based on the above digital construction request form and displaying an incentive UI according to the OCR error rate. The step of recognizing the characters in the construction request form based on the above optical character recognition is as follows: It includes a step of extracting OCR errors by comparing and analyzing whether the original text errors in the above construction request form fall into any of the following types: the first type of error, which is recognized as English letters; the second type of error, which is an error between numbers and English letters; the third type of error, which is an error in the case of similar words in English; and the fourth type of error, which is an error in the form of similar English letters. The step of providing the above incentive UI is: It includes a step of calculating a first OCR error rate, which is the ratio of characters that are unclearly recognized to characters that are clearly recognized in the digital construction request form, and a second OCR error rate, which is the difference between the first OCR error rate for a specific digital construction request form and the average error rate, which is the average of the first OCR error rates for the entire digital construction request form, divided by the average error rate. A method, characterized in that the second incentive according to the second OCR error rate has a greater weight than the first incentive according to the first OCR error rate.

Images