Method for generating information related to product repair

Abstract

According to one embodiment of the present disclosure, a method for generating information related to the repair of a product is disclosed, which is performed by a computing device. The method may include the step of obtaining information on the temperature change of the product caused by heat in a time domain; the step of converting the temperature change information of the product obtained in the time domain into information in a frequency domain; and the step of generating information related to the repair of the product based on at least one component among a plurality of components in the frequency domain.

Description

Technology Field

[0001] The present invention relates to a method for generating information related to product repair, and more specifically, to a technology for detecting the repair history of a vehicle based on image analysis. Background Technology

[0003] Previously, verifying the repair history of industrial products or vehicles often relied solely on maintenance documentation or the visual judgment of skilled personnel. For instance, in the case of vehicles, even if there is a history of painting or putty repairs due to accidents or external damage, such facts can only be confirmed indirectly through insurance claim records, repair shop records, or user statements; consequently, technology for quantitatively analyzing physical repair traces present on the product surface is currently lacking.

[0004] To address these issues, there is a need to develop technology that automatically analyzes repair history using image data of product surfaces.

[0005] Korean Patent Publication No. 10-2024-0083904 (June 13, 2024) discloses a system for repairing a broken vehicle using a 3D measuring robot. The problem to be solved

[0007] The present disclosure aims to provide a method for generating information related to product repair by analyzing frequency domain components based on information regarding temperature changes of a product caused by heat.

[0008] Meanwhile, the technical problem that the present disclosure aims to solve is not limited to the technical problem mentioned above, and various technical problems may be included within the scope obvious to a person skilled in the art from the contents described below. means of solving the problem

[0010] According to one embodiment of the present disclosure for realizing the aforementioned objectives, a method for generating information related to the repair of a product performed by a computing device is disclosed. The method may include the steps of: obtaining information on the temperature change of the product caused by heat in a time domain; converting the temperature change information of the product obtained in the time domain into information in a frequency domain; and generating information related to the repair of the product based on at least one component among a plurality of components in the frequency domain.

[0011] In one embodiment, the step of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include the step of generating image information in which the phase component is visualized based on the phase component among the plurality of components of the frequency domain.

[0012] In one embodiment, the step of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include at least one of the steps of: displaying image information in which the phase component is visualized as information for determining whether the product is painted; or generating information related to the painting of the product based on image information in which the phase component is visualized by utilizing a machine learning model.

[0013] In one embodiment, the step of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include the step of generating image information in which the amplitude component is visualized based on the amplitude component among the plurality of components of the frequency domain.

[0014] In one embodiment, the step of generating information related to the repair of the product based on at least one component among a plurality of components in the frequency domain may include: displaying image information in which the amplitude component is visualized as information for determining whether to restore the surface of the substrate of the product; or utilizing a machine learning model to generate information related to the restoration of the surface of the substrate of the product based on the image information in which the amplitude component is visualized.

[0015] In one embodiment, the step of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include: generating image information in which the phase component is visualized based on the phase component among the plurality of components of the frequency domain; generating image information in which the amplitude component is visualized based on the amplitude component among the plurality of components of the frequency domain; and aligning and displaying together the image information in which the phase component is visualized and the image information in which the amplitude component is visualized for one or more parts of the product.

[0016] In one embodiment, for one or more parts of the product, the step of aligning and displaying together the image information in which the phase component is visualized and the image information in which the amplitude component is visualized may include the step of displaying the image information in which the phase component is visualized as information for determining whether to paint, and displaying the image information in which the amplitude component is visualized as information for determining whether to restore the surface of the substrate.

[0017] In one embodiment, for one or more parts of the product, the step of aligning and displaying together image information in which the phase component is visualized and image information in which the amplitude component is visualized may include: a step of displaying first prediction information indicating whether one or more parts of the product are painted based on image information in which the phase component is visualized, utilizing a first machine learning model; and a step of displaying second prediction information indicating whether the surface of a substrate for one or more parts of the product is restored based on image information in which the amplitude component is visualized, utilizing a second machine learning model.

[0018] In one embodiment, the first machine learning model and the second machine learning model may be implemented as separate models or implemented together as an integrated model.

[0019] In one embodiment, the step of acquiring information on the temperature change of the product caused by the heat in the time domain may include acquiring a plurality of image frames sampled in the time domain by utilizing a thermal sensing camera that captures the temperature change of the surface of the product after a heat pulse is applied to the surface of the product.

[0020] In one embodiment, the step of converting the temperature change information of the product obtained in the time domain into information in the frequency domain may include the step of converting the temperature change information of the product obtained in the time domain into information in the frequency domain by utilizing the Discrete Fourier Transform (DFT) based on the sampling interval information.

[0021] In one embodiment, at least one of the plurality of components of the frequency domain may include at least one of the phase component or amplitude component of the lowest non-zero frequency of the frequency domain.

[0022] In one embodiment, the product is a vehicle, and one of the plurality of components in the frequency domain includes at least one of a phase component or an amplitude component, and information related to the repair of the product may include at least one of information related to the paint repair of the vehicle or information related to the putty repair of the vehicle.

[0023] A computer program stored on a computer-readable storage medium is disclosed in accordance with one embodiment of the present disclosure for realizing the aforementioned objectives. When the computer program is executed on one or more processors, the one or more processors are configured to perform the following operations to generate information related to the repair of a product, wherein the operations may include: an operation of obtaining information on the temperature change of the product due to heat in a time domain; an operation of converting the temperature change information of the product obtained in the time domain into information in a frequency domain; and an operation of generating information related to the repair of the product based on at least one component among a plurality of components in the frequency domain.

[0024] In one embodiment, the operation of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include the operation of generating image information in which the phase component is visualized based on the phase component among the plurality of components of the frequency domain.

[0025] In one embodiment, the operation of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include the operation of generating image information in which the amplitude component is visualized based on an amplitude component among a plurality of components of the frequency domain.

[0026] In one embodiment, the operation of generating information related to the repair of the product based on at least one component among a plurality of components of the frequency domain may include: an operation of generating image information in which the phase component is visualized based on the phase component among the plurality of components of the frequency domain; an operation of generating image information in which the amplitude component is visualized based on the amplitude component among the plurality of components of the frequency domain; and an operation of aligning and displaying together the image information in which the phase component is visualized and the image information in which the amplitude component is visualized for one or more parts of the product.

[0027] In one embodiment, the step of acquiring information on the temperature change of the product caused by the heat in the time domain may include acquiring a plurality of image frames sampled in the time domain by utilizing a thermal sensing camera that captures the temperature change of the surface of the product after a heat pulse is applied to the surface of the product.

[0028] In one embodiment, the operation of converting the temperature change information of the product obtained in the time domain into information in the frequency domain may include the operation of converting the temperature change information of the product obtained in the time domain into information in the frequency domain by utilizing the Discrete Fourier Transform (DFT) based on the sampling interval information.

[0029] In one embodiment, at least one of the plurality of components of the frequency domain may include at least one of the phase component or amplitude component of the lowest non-zero frequency of the frequency domain.

[0030] In one embodiment, the product is a vehicle, and one of the plurality of components in the frequency domain includes at least one of a phase component or an amplitude component, and information related to the repair of the product may include at least one of information related to the paint repair of the vehicle or information related to the putty repair of the vehicle.

[0031] A computing device according to one embodiment of the present disclosure for realizing the aforementioned objectives is disclosed. The device comprises at least one processor; and a memory, wherein the at least one processor may be configured to acquire information on the temperature change of the product due to heat in a time domain; convert the temperature change information of the product acquired in the time domain into information in a frequency domain; and generate information related to the repair of the product based on at least one component among a plurality of components in the frequency domain.

[0032] In one embodiment, the at least one processor may be configured to generate image information in which the phase component is visualized, based on the phase component among a plurality of components of the frequency domain.

[0033] In one embodiment, the at least one processor may be configured to generate image information in which the amplitude component is visualized, based on the amplitude component among a plurality of components in the frequency domain.

[0034] In one embodiment, the at least one processor may be configured to generate image information in which the phase component is visualized based on the phase component among the plurality of components in the frequency domain; generate image information in which the amplitude component is visualized based on the amplitude component among the plurality of components in the frequency domain; and, for one or more parts of the product, to align and display together the image information in which the phase component is visualized and the image information in which the amplitude component is visualized.

[0035] In one embodiment, the at least one processor may be configured to acquire a plurality of image frames sampled in the time domain by utilizing a thermal sensing camera that captures a temperature change of the surface of the product after a thermal pulse is applied to the surface of the product.

[0036] In one embodiment, the at least one processor may be configured to convert the temperature change information of the product obtained in the time domain into information in the frequency domain by utilizing the Discrete Fourier Transform (DFT) based on the sampling interval information.

[0037] In one embodiment, at least one of the plurality of components of the frequency domain may include at least one of the phase component or amplitude component of the lowest non-zero frequency of the frequency domain.

[0038] In one embodiment, the product is a vehicle, and one of the plurality of components in the frequency domain includes at least one of a phase component or an amplitude component, and information related to the repair of the product may include at least one of information related to the paint repair of the vehicle or information related to the putty repair of the vehicle.

[0039] An apparatus for generating information related to the repair of a product according to one embodiment of the present disclosure for realizing the aforementioned objectives is disclosed. The apparatus may include: a physical stimulation module for applying a physical stimulation to the surface of a product; a camera module for photographing the surface of the product after the physical stimulation has been applied; and an analysis module for converting information regarding a plurality of image frames generated by the camera module into information in the frequency domain and generating information related to the repair of the product based on at least one component among a plurality of components in the frequency domain. Effects of the invention

[0041] The present disclosure allows for more precise determination of a product's repair history, such as painting history or putty history, by acquiring temperature change information in the time domain, converting it to the frequency domain, and utilizing at least one of a plurality of components (e.g., phase component, amplitude component, etc.).

[0042] Meanwhile, the effects of the present disclosure are not limited to those mentioned above, and various effects may be included within the scope obvious to a person skilled in the art from the contents described below. Brief explanation of the drawing

[0044] FIG. 1 is a block diagram of a computing device for generating information related to the repair of a product according to one embodiment of the present disclosure. FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure. FIG. 3 is a flowchart illustrating a method for generating information related to the repair of a product according to one embodiment of the present disclosure. FIG. 4 is a diagram showing image information in which phase components are visualized according to one embodiment of the present disclosure. FIG. 5 is a diagram showing the result of generating paint-related information for a product based on image information in which phase components are visualized, using a machine learning model according to one embodiment of the present disclosure. FIG. 6 is a diagram showing image information in which the amplitude component is visualized according to one embodiment of the present disclosure. FIG. 7 is a diagram showing the result of generating information related to surface restoration of a product's substrate based on image information in which amplitude components are visualized, using a machine learning model according to one embodiment of the present disclosure. FIG. 8 is a flowchart illustrating an operation to generate information related to product repair by simultaneously utilizing phase and amplitude values ​​according to one embodiment of the present disclosure. FIG. 9 is a diagram showing the result of aligning and displaying together image information with a phase component visualized and image information with an amplitude component visualized according to one embodiment of the present disclosure. FIG. 10 is a diagram showing the result of displaying the first prediction information of a first machine learning model and the second prediction information of a second machine learning model according to one embodiment of the present disclosure. FIG. 11 is a schematic diagram of a device for generating information related to the repair of a product according to one embodiment of the present disclosure. FIG. 12 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. Specific details for implementing the invention

[0045] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to provide an understanding of the present disclosure. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0046] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0047] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0048] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0049] And, the term “at least one of A or B” should be interpreted to mean “a case including only A,” “a case including only B,” or “a combination of A and B.”

[0050] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be construed as going beyond the scope of this disclosure.

[0052] FIG. 1 is a block diagram of a computing device for generating information related to the repair of a product according to one embodiment of the present disclosure.

[0053] The configuration of the computing device (100) illustrated in FIG. 1 is merely a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing the computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

[0054] The computing device (100) may include a processor (110), memory (130), and a network unit (150).

[0055] The processor (110) may be composed of one or more cores and may include processors for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. The processor (110) may read a computer program stored in memory (130) and perform data processing for machine learning according to one embodiment of the present disclosure. According to one embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. The processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process the learning of a network function. For example, a CPU and a GPGPU can work together to process the learning of a network function and data classification using the network function. Additionally, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process the learning of a network function and data classification using the network function. Furthermore, a computer program executed on a computing device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0056] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the network unit (150).

[0057] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk. The computing device (100) may operate in conjunction with web storage that performs the storage function of the memory (130) on the internet. The description of the memory described above is merely an example and the present disclosure is not limited thereto.

[0058] A network unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0059] In addition, the network unit (150) presented in this specification may use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0060] In the present disclosure, the network unit (150) can be configured regardless of the communication mode, such as wired and wireless, and can be configured as various communication networks such as a Local Area Network (LAN), a Personal Area Network (PAN), and a Wide Area Network (WAN). In addition, the network may be a known World Wide Web (WWW) and may utilize wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0061] The technologies described in this specification can be used not only in the networks mentioned above but also in other networks.

[0063] FIG. 2 illustrates an exemplary structure of an artificial intelligence-based model according to one embodiment of the present disclosure.

[0064] Throughout this specification, artificial intelligence model, artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably.

[0065] A neural network can be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node. The nodes (or neurons) constituting neural networks may be interconnected by one or more links.

[0066] In a neural network, one or more nodes connected via links can form relative input and output node relationships. The concepts of input and output nodes are relative; any node in an output node relationship with respect to one node may be in an input node relationship with respect to another node, and vice versa. As described above, the input node versus output node relationship can be generated based on links. One or more output nodes may be connected to a single input node via links, and vice versa.

[0067] In a relationship between an input node and an output node connected through a single link, the value of the output node's data can be determined based on the data input to the input node. Here, the link interconnecting the input node and the output node may have a weight. The weight can be variable and can be varied by the user or an algorithm to enable the neural network to perform the desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node's value can be determined based on the values ​​input to the input nodes connected to the output node and the weights set on the links corresponding to each input node.

[0068] As described above, a neural network consists of one or more nodes interconnected through one or more links, forming input-output node relationships within the network. The characteristics of a neural network can be determined by the number of nodes and links within the network, the relationships between the nodes and links, and the weight values ​​assigned to each link. For example, if two neural networks exist with the same number of nodes and links but different weight values ​​for the links, the two neural networks may be recognized as different from each other.

[0069] A neural network can be composed of a set of one or more nodes. A subset of nodes constituting a neural network can form a layer. Some of the nodes constituting a neural network can form a layer based on their distances from an initial input node. For example, a set of nodes with a distance of n from an initial input node can form n layers. The distance from the initial input node can be defined by the minimum number of links that must be traversed to reach that node from the initial input node. However, this definition of a layer is arbitrary for illustrative purposes, and the degree of a layer within a neural network can be defined in a way different from that described above. For example, a layer of nodes may be defined by its distance from a final output node.

[0070] In one embodiment of the present disclosure, a set of neurons or nodes may be defined by the expression a layer.

[0071] Initial input nodes may refer to one or more nodes within a neural network to which data is directly input without passing through links in their relationships with other nodes. Alternatively, in terms of link-based relationships between nodes within the neural network, they may refer to nodes that do not have other input nodes connected by links. Similarly, final output nodes may refer to one or more nodes within a neural network that do not have output nodes in their relationships with other nodes. Furthermore, hidden nodes may refer to nodes constituting the neural network that are neither initial input nodes nor final output nodes.

[0072] A neural network according to one embodiment of the present disclosure may have the number of nodes in the input layer equal to the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. Additionally, a neural network according to another embodiment of the present disclosure may have the number of nodes in the input layer less than the number of nodes in the output layer, and may be a neural network in which the number of nodes increases as it progresses from the input layer to the hidden layer. Additionally, a neural network according to yet another embodiment of the present disclosure may have the number of nodes in the input layer greater than the number of nodes in the output layer, and may be a neural network in which the number of nodes decreases as it progresses from the input layer to the hidden layer. A neural network according to yet another embodiment of the present disclosure may be a neural network in which the above-described neural networks are combined.

[0073] An artificial intelligence-based model according to one embodiment of the present disclosure may include a deep neural network (DNN). A deep neural network may refer to a neural network that includes a plurality of hidden layers in addition to an input layer and an output layer. By using a deep neural network, latent structures of data can be identified. That is, latent structures of photos, text, video, voice, protein sequence structures, gene sequence structures, peptide sequence structures, music (e.g., what objects are in the photo, what is the content and emotion of the text, what is the content and emotion of the voice, etc.), and / or binding affinity between peptides and MHCs can be identified. Deep neural networks may include convolutional neural networks (CNN), recurrent neural networks (RNN), autoencoders, restricted Boltzmann machines (RBM), deep belief networks (DBN), Q networks, U networks, Siamese networks, Generative Adversarial Networks (GAN), Transformers, etc. The description of deep neural networks described above is merely illustrative and the present disclosure is not limited thereto.

[0074] The artificial intelligence-based model of the present disclosure may be represented by a network structure of any structure described above, including an input layer, a hidden layer, and an output layer.

[0075] A neural network that can be used in an artificial intelligence-based model of the present disclosure may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, transfer learning, active learning, or reinforcement learning. Training of a neural network may be a process of applying knowledge to the neural network to perform a specific operation.

[0076] Neural networks can be trained to minimize the error in their output. The training process involves repeatedly inputting training data into the network, calculating the error between the network's output and the target for the training data, and updating the weights of each node by backpropagating the error from the output layer to the input layer in a direction that reduces the error. In supervised learning, training data is used where the correct answer is labeled for each data point (i.e., labeled training data), whereas in unsupervised learning, the correct answer may not be labeled for each training data point. For instance, in the case of supervised learning for data classification, the training data may consist of data where each training point is labeled with a category. Labeled training data is input into the neural network, and the error can be calculated by comparing the network's output (category) with the labels of the training data. As another example, in the case of unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network's output. The calculated error is backpropagated in the neural network (i.e., from the output layer to the input layer), and through backpropagation, the connection weights of each node in each layer of the neural network can be updated. The amount of change in the connection weights of each node being updated can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle. For example, a high learning rate can be used in the early stages of training to quickly achieve a certain level of performance and increase efficiency, while a low learning rate can be used in the later stages to improve accuracy.

[0077] In the training of neural networks, the training data is generally a subset of the real-world data (i.e., the data intended to be processed using the trained neural network). Consequently, a training cycle may exist where errors decrease on the training data but increase on the real-world data. Overfitting is a phenomenon where the network learns excessively on the training data, leading to increased errors on the real-world data. For example, a neural network trained on yellow cats might fail to recognize cats when seeing anything other than yellow, which can be considered a type of overfitting. Overfitting can act as a cause for increased errors in machine learning algorithms. Various optimization methods can be used to prevent this overfitting. To prevent overfitting, methods such as increasing the training data, regularization, dropout (which disables some nodes in the network during training), and the use of batch normalization layers can be applied.

[0079] FIG. 3 is a flowchart illustrating a method for generating information related to the repair of a product according to one embodiment of the present disclosure. For reference, the method for generating information related to the repair of a product described below may be performed by a computing device (100).

[0080] According to one embodiment of the present disclosure, a computing device (100) can obtain information on the temperature change of a product due to heat in the time domain (S110). For example, the product may include various structures having temperature change characteristics due to heat, such as automobiles, aircraft exteriors, ship hulls, railway vehicle exteriors, motorcycle exteriors, electric scooters, small mobility devices, electronic device housings, industrial robot covers, construction machinery exteriors, wind turbine blades, home appliance exteriors, metal structures, and high-end furniture exteriors. In addition, the product may include various products other than these examples that are available for second-hand trading or require tracking of repair history. For such various products, the computing device (100) can generate a repair history by analyzing the temperature change due to heat.

[0081] For example, a computing device (100) can obtain a change in temperature of a surface of a product, for instance, the exterior of a car (door, fender, bumper, etc.), after applying a heat pulse to the surface of the product. Here, the product is not limited to a car but may include various structures such as motorcycles, electric scooters, small mobility devices, aircraft exteriors, and electronic device housings. In the case of a car, exterior parts (door, fender, bumper, etc.) that have a history of accidents or repairs may have altered thickness of the paint film applied to the surface or physical properties of the substrate (metal plate or putty layer). Therefore, the repair status can be indirectly determined by applying a heat pulse to such car exteriors and then detecting a change in surface temperature. Meanwhile, the "time domain" refers to an area that directly expresses how a physical quantity (temperature) changes over time. According to one embodiment of the present disclosure, “temperature change information obtained in the time domain” may be the result of measuring a change curve on the time axis regarding how the temperature of the product surface rises and cools down after the application of a heat pulse. Additionally, according to one embodiment of the present disclosure, “temperature change information obtained in the time domain” may include discrete temperature change information obtained at a predetermined sampling interval in the time domain. For example, a computing device (100) may obtain information on the temperature change of a product due to heat in the form of “40°C at t=0 sec → 38°C at t=1 sec → 36°C at t=2 sec. . .” That is, the time domain data may be a set of information listing what the surface temperature was at each point in time.

[0083] According to one embodiment, a computing device (100) can acquire a plurality of image frames sampled in the time domain by utilizing a thermal sensing camera that captures temperature changes on the surface of a product after a thermal pulse is applied to the surface of the product. First, the computing device (100) can apply a thermal pulse that applies strong thermal energy to the surface of the product for a short period of time. The thermal pulse can be generated through various heat source devices such as a flash lamp, an infrared heater, a laser, or strong LED lighting. Subsequently, the computing device (100) can acquire a plurality of image frames by continuously capturing temperature changes occurring on the surface of the product for a certain period of time immediately after the application of the thermal pulse using a thermal sensing camera. For example, the thermal sensing camera may include a thermal imaging camera, an infrared (IR) camera, etc. A thermal sensing camera may refer to equipment that detects radiant energy corresponding to the infrared region rather than visible light, and measures and visualizes the surface temperature of a target object in a non-contact manner. For example, a thermal sensing camera performs the role of recording changes in temperature distribution over time by continuously capturing temperature changes occurring on the product surface immediately after the application of a heat pulse in chronological order.

[0084] For example, a computing device (100) can acquire a plurality of image frames that continuously capture the surface temperature distribution of a product at regular intervals for a certain period of time immediately after a heat pulse is applied to the surface of a product from a heat-sensing camera. Each image frame represents the temperature distribution of the product surface at a specific point in time, and consecutive frames represent changes in surface temperature along the time axis. The acquired plurality of image frames contain information on surface temperatures changing along the time axis and may be configured, for example, in an array of the form (N, H, W). Here, N may be the number of frames captured in chronological order, H may be the height (number of pixels) of the frame, and W may be the width (number of pixels) of the frame. The computing device (100) can obtain a type of "temperature-time history data" that records the temperature change over time for each pixel. For example, the acquired plurality of image frames are data that records the temperature distribution of the product surface at regular sampling intervals, and represent the pattern of change in the surface temperature of the product after the heat pulse in the time domain. For example, a single image frame represents a two-dimensional (2D) temperature distribution of a product surface and may consist of multiple pixels in the height (H) direction and the width (W) direction. Here, each pixel represents a data point indicating the temperature at a specific location on the product surface. That is, a single image frame is an array composed of H×W temperature measurements, and if these frames are arranged in chronological order, a three-dimensional time domain of the form (N, H, W) is formed.

[0085] According to one embodiment, the computing device (100) can measure the temperature change of the product surface over time after the application of a heat pulse and calculate the amount of temperature change in the time domain according to Equation 1. For example, the computing device (100) can represent the relative amount of change from the initial temperature T0 to the temperature changing over time according to Equation 1.

[0086] [Mathematical Formula 1]

[0087]

[0088] Here, ΔT(nΔt) is the amount of temperature change at time nΔt, T0 is the initial temperature, Δt is the sampling interval, and N is the total number of frames acquired from the thermal camera.

[0090] According to one embodiment of the present disclosure, a computing device (100) can convert temperature change information of a product obtained in the time domain into information in the frequency domain (S120). For example, the computing device (100) can construct temperature change data in the time domain from a plurality of image frames obtained through a thermal detection camera for a certain period of time after a heat pulse is applied to the surface of the product, and then convert this into information in the frequency domain. As an example, the computing device (100) can obtain temperature change information in the time domain for the surface of the product in the form of a plurality of image frames, and then apply a Discrete Fourier Transform (DFT) considering a constant sampling interval between each frame. Meanwhile, various methods other than DFT can be utilized for the methodology of converting information in the time domain into information in the frequency domain. In addition, the computing device (100) can extract amplitude and phase information of one or more frequency components from the converted frequency domain information and analyze characteristics related to the repair history of the product. In particular, by utilizing amplitude and phase information at the lowest non-zero frequency point (e.g., k = 1), changes in the film thickness of the product and changes in the physical properties of the substrate can be precisely evaluated.

[0091] According to one embodiment, a computing device (100) can convert temperature change information of a product obtained in the time domain into information in the frequency domain by utilizing a Discrete Fourier Transform (DFT) based on sampling interval information. For example, the sampling interval may be the time difference between two measurement points among values ​​in which temperature data is measured at regular intervals over time. For instance, if measurements are taken at 0 seconds, 0.05 seconds, 0.10 seconds, 0.15 seconds, etc. after a heat pulse is applied, the sampling interval Δt may be 0.05 seconds. Additionally, the sampling interval may be the time interval between multiple temperature measurement data in the time domain. The sampling interval information can be used to calculate the frequency value (frequency bin) corresponding to the actual time axis of the signal when performing frequency analysis through Discrete Fourier. For example, the Discrete Fourier Transform (DFT) is a mathematical method that converts a signal obtained from discrete-time samples into the frequency domain to analyze which frequency points (e.g., frequency index, frequency bin, etc.) the signal is composed of. In this disclosure, it is used to identify periodic thermal behavior characteristics (such as thermal diffusion patterns) by decomposing temperature data of a product surface that changes over time into various frequency points. For example, the operation of converting product temperature change information obtained in the time domain into information in the frequency domain using the Discrete Fourier Transform (DFT) may be expressed as Equation 2. Equation 2 is a process of converting temperature change data into the frequency domain, which allows for the analysis of periodic patterns of temperature change. X(k) may be a complex value indicating how much thermal response is included for each frequency point.

[0094] [Mathematical Formula 2]

[0095]

[0096] Here, X(k) is the converted k-th frequency point, and ΔT(nΔt) is the temperature change obtained from Equation 1, and is a Fourier basis function in complex form, and k is the frequency index.

[0098] For example, a computing device (100) can calculate multiple components in the frequency domain by performing a Discrete Fourier Transform (DFT) based on temperature change data obtained in the time domain. For example, at least one of the multiple components in the frequency domain may include at least one of the phase component or amplitude component of the lowest non-zero frequency in the frequency domain. For example, the lowest non-zero frequency among the frequency points (e.g., k = 1) can be expressed as a complex number as in Equation 3 and can be decomposed into an amplitude component and a phase component.

[0099] [Mathematical Formula 3]

[0100]

[0101] Here, X(1) is the complex component of the frequency point corresponding to the frequency index k=1, and is the real and imaginary part of the complex number, A is the amplitude, and is a phase.

[0103] Meanwhile, the computing device (100) can perform analysis by utilizing the phase component or amplitude component of the lowest non-zero low frequency (frequency) component (e.g., k=1) among the multiple components of the frequency domain, thereby minimizing the noise effect of the thermal response signal and enabling sensitive response to changes in the physical properties of the film or substrate. This provides technical effects in terms of computational efficiency, reliability of prediction, and quantitative interpretation capability.

[0105] According to one embodiment of the present disclosure, a computing device (100) can generate information related to product repair based on at least one component among a plurality of components in the frequency domain (S130). For example, the plurality of components may include amplitude, phase, power spectrum, log-magnitude spectrum, real part, imaginary part, etc. For instance, the plurality of components may refer to individual components of at least one frequency point. In one embodiment, the plurality of components may include an amplitude component and a phase component of at least one frequency point (e.g., frequency index, frequency bin, etc.). In addition, in this case, the at least one frequency point from which the amplitude component and the phase component are derived may be a frequency point corresponding to the lowest low frequency.

[0106] In one embodiment, the computing device (100) can generate information related to the repair of a product based on at least one of these plurality of components. For example, the computing device (100) can determine whether to repair the paint on the product by analyzing the phase component of at least one frequency bin, or determine whether to restore the surface of the product's substrate (e.g., whether to repair it with putty) by analyzing the amplitude component. Additionally, it is possible to input the generated phase and amplitude information into a machine learning model to automatically predict whether to repair the paint or to repair it with putty.

[0107] For example, a computing device (100) can determine whether the surface of the product's substrate has been restored based on amplitude information. Surface restoration of the substrate is a method of restoring the surface by applying putty, and may include methods such as putty painting and putty sheet metal work. Putty painting is a method in which, when minor damage occurs to the product's substrate, the surface is flattened using putty without deforming the structure, and then painting is performed. Additionally, putty sheet metal work is a method in which, when severe deformation occurs to the product's substrate, the structure is restored to a shape close to its original form, and then any remaining irregularities are filled with putty before painting is performed. Meanwhile, in repair methods using putty, the physical properties of the substrate change, making it difficult to determine based solely on phase information; however, the repair status of the area can be estimated more clearly through the visualization of amplitude information.

[0108] Meanwhile, in another embodiment, the plurality of components may include components of two or more frequency points, and the computing device (100) may analyze the components of two or more frequency points in an integrated manner at the pixel level to detect a new type of repair history. For example, the computing device (100) may (i) integrally analyze the phase component of the “lowest low frequency point” and the phase component of the “additional frequency point spaced more than a preset index from the lowest low frequency point,” (ii) integrally analyze the amplitude component of the “lowest low frequency point” and the amplitude component of the “additional frequency point spaced more than a preset index from the lowest low frequency point,” (iii) integrally analyze the phase / amplitude components of the “lowest low frequency point” and the phase / amplitude components of the “additional frequency point spaced more than a preset index from the lowest low frequency point,” (iv) integrally analyze the phase / amplitude components of the “lowest low frequency point” and the phase / amplitude components of “multiple additional frequency points spaced by preset index intervals from the lowest low frequency point,” or (v) integrally analyze the phase / amplitude information of three or more frequency points to repair paint or the surface of a substrate. It can improve the accuracy of detecting whether restoration has been performed or detect new types of repair history.

[0110] For reference, the most widely used technology currently for non-destructively detecting the repair history of a vehicle's exterior is the coating thickness measurement method. In conventional methods, repair history is identified by measuring the coating thickness at various points on the vehicle's exterior to check for anomalies. While new cars are painted to a consistent thickness using precision machinery at the factory, repairs performed at repair shops after an accident often result in uneven coating thickness due to lower precision. However, currently used coating gauges require physical contact with specific areas to measure thickness, making it difficult to inspect the entire vehicle quickly and effectively.

[0111] According to one embodiment of the present disclosure, a computing device (100) can determine the condition of a coating film without physical contact by performing pulse thermography inspection and analyzing phase components in the frequency domain. Here, pulse thermography inspection is a non-destructive inspection technique that records the temporal change of surface temperature using an infrared camera after applying a strong heat pulse for a short period of time, and can be utilized for measuring the thickness of the coating film. In addition, if the phase value of the low-frequency component is analyzed by performing a Discrete Fourier Transform (DFT) on the temperature change data measured over a specific period of time, it exhibits a characteristic proportional to the thickness of the coating film. By utilizing these characteristics, the computing device (100) can indirectly measure the thickness of the coating film without physical contact.

[0112] Meanwhile, the aforementioned phase component-based non-destructive inspection technology is based on the assumption that the physical properties of the substrate coated with the film are identical. However, in the case of sheet metal work, putty is applied over the steel structure, which alters the physical properties of the substrate. Therefore, there is a limitation in that the conventional method using only phase values ​​cannot accurately reflect not only the film thickness but also the physical changes in the substrate. Furthermore, conventional film thickness measurement methods are limited in their ability to quickly assess the condition of the entire vehicle's film because they require contact with only specific areas for measurement. Additionally, while pulse thermal imaging and DFT-based analysis techniques are useful for measuring film thickness, they suffer from reduced reliability when the physical properties of the substrate are altered (e.g., after sheet metal work and putty application).

[0113] To solve these additional technical problems, a computing device (100) according to one embodiment of the present disclosure converts thermal response data of a product surface into the frequency domain, then utilizes phase components and amplitude components together to quantitatively analyze not only the coating thickness of a product (vehicle) but also physical changes of a substrate, and provides a technology capable of automatically detecting and visualizing repair history based thereon.

[0115] Meanwhile, the present disclosure is described below with reference to an embodiment in which the product is a vehicle, and (1) information related to paint repair of the vehicle based on a phase component among a plurality of components in the frequency domain, and (2) information related to putty repair of the vehicle based on an amplitude component among a plurality of components in the frequency domain.

[0117] FIG. 4 is a diagram showing image information with phase components visualized according to one embodiment of the present disclosure, and FIG. 5 is a diagram showing the result of generating paint-related information for a product based on image information with phase components visualized by utilizing a machine learning model according to one embodiment of the present disclosure. For reference, (a) shown in FIG. 4 and FIG. 5 is the result of photographing the left side of the vehicle, (b) is the result of photographing the right side of the vehicle, (c) is the result of photographing the roof of the vehicle, and (d) is the result of photographing the rear of the vehicle. In addition, since the area of ​​the left side (a), right side (b), and roof (c) of the vehicle is large, the camera module (200) for photographing the surface of the product (vehicle) can perform photography at different locations on the product surface in a preset number of times (e.g., 7 to 9 times) while moving in the front-rear direction. The computing device (100) can precisely analyze whether the large area of ​​the vehicle is painted by converting the time domain data obtained at each location into the frequency domain and analyzing the phase by section.

[0118] According to one embodiment of the present disclosure, a computing device (100) can generate image information in which a phase component is visualized based on a phase component among a plurality of components in the frequency domain. For example, the computing device (100) can convert temperature change information of a product surface obtained in the time domain into the frequency domain through a Discrete Fourier Transform (DFT), and calculate the phase component of a frequency point corresponding to the lowest non-zero low frequency (e.g., k=1) on a pixel-by-pixel basis. The calculated phase values ​​are mapped to each location on the product surface and formed into a two-dimensional array, and subsequently, the computing device (100) can generate image information that visually represents the distribution of phase values ​​by applying a color scale. The generated image information in which a phase component is visualized can be used to determine whether the product is painted.

[0119] According to one embodiment, a computing device (100) may display image information in which phase components are visualized as information for determining whether a product has been painted. The computing device (100) may display image information in which phase components are visualized on a user terminal. The user may visually recognize the image information in which phase components are visualized displayed on the user terminal and determine whether the product has been painted. For example, the computing device (100) may generate image data in which the phase component distribution is converted into color and then output it to the screen of a user terminal (e.g., tablet, PC, mobile device, etc.). By visually identifying the imbalance in color distribution, the difference in phase values ​​of specific areas, abnormal boundaries, etc., in the displayed visualized image, the user may determine whether the area has a history of being painted. For example, referring to FIG. 4, if the left (a) door area in the image information in which phase components are visualized has a darker color than the surrounding area or has an uneven distribution, the user may presume that there has been a paint repair on that area.

[0120] According to one embodiment, a computing device (100) may generate paint-related information for a product based on image information in which topological components are visualized, by utilizing a machine learning model. For example, the machine learning model may be a model trained to receive image information in which topological components are visualized as input and to predict whether the input is a painted area (e.g., Yes / No or probability value, etc.). The machine learning model may include various artificial intelligence architectures such as CNN (Convolutional Neural Network), MLP (Multilayer Perceptron), ResNet, UNet, SegNet, etc. Additionally, the computing device (100) may provide image information in which topological components are visualized as input to a pre-trained machine learning model and receive a classification result or a predicted probability regarding whether each part included in the image has undergone paint repair. For example, the input to the machine learning model may be a topological visualization image (e.g., an RGB color map with a resolution of 256×256), and the output may be whether it is painted (e.g., 0 or 1) or a probability of painting (e.g., 84%). At this time, whether or not it has been painted can be determined at various resolutions, such as at the pixel level, object level (door, bumper, etc.), or whole image level. For example, a computing device (100) can process the paint prediction result obtained from an artificial intelligence model into visual or numerical information and output it to a display device of a user terminal. For example, the computing device (100) can generate information predicting the paint judgment result by part in a list format, such as a text overlay of “Painted (84%)” on image information in which phase components are visualized. A specific part is highlighted with a box of the first color. Based on this information, the user can immediately determine which part of the product has received paint repair.Referring to FIG. 5 for example, the machine learning model can predict that the right door portion of the vehicle has a light and evenly distributed color, while the left door portion has a dark and unevenly distributed color, so the corresponding doors can be painted. Additionally, the machine learning model can also predict that the left and right rear fender portions have a first-1 area (11) and a first-4 area (14), the front bumper portion has a first-2 area (12), a first-3 area (13), a first-5 area (15), and the left front fender portion has a first-2 area (12).

[0121] For example, a computing device (100) can use an artificial intelligence model to predict whether a product is painted on a pixel-by-pixel or object-by-object basis from image information in which phase components are visualized. Pixel-by-pixel judgment can precisely analyze even minute paint traces or boundaries by predicting whether each pixel in the image is painted in a binary or probabilistic form. For instance, the computing device (100) provides image information in which phase components are visualized as input to an artificial intelligence model, and the artificial intelligence model can generate an output mask with the same resolution as the image. The output mask may be in the form of a binary value (e.g., 0=unpainted, 1=painted) or a probability value (e.g., 0.93) indicating whether each pixel is painted. Additionally, object-by-object judgment can provide clear and intuitive repair history information to the user by dividing structural parts such as doors, fenders, and bumpers in the image and predicting whether each part is painted. For example, the computing device (100) can extract features of image information in which phase components are visualized, and then predict whether each object is painted based on a predefined object (e.g., part segmentation information of a vehicle). The computing device (100) may also extract each part through object detection or segmentation.

[0123] FIG. 6 is a diagram showing image information with visualized amplitude components according to one embodiment of the present disclosure, and FIG. 7 is a diagram showing the result of generating information related to surface restoration of a product's substrate based on image information with visualized amplitude components using a machine learning model according to one embodiment of the present disclosure. For reference, (a) shown in FIG. 6 and FIG. 7 is the result of photographing the left side of the vehicle, (b) is the result of photographing the right side of the vehicle, (c) is the result of photographing the roof of the vehicle, and (d) is the result of photographing the rear of the vehicle. In addition, since the area of ​​the left side (a), right side (b), and roof (c) of the vehicle is large, the camera module (200) for photographing the surface of the product (vehicle) can perform photography at different locations on the product surface in a preset number of times (e.g., 7 to 9 times) while moving in the front-rear direction. The computing device (100) can precisely analyze whether putty repair is required on a large area of ​​the vehicle by converting the time domain data obtained at each location into the frequency domain and analyzing the amplitude components by section.

[0124] According to one embodiment of the present disclosure, a computing device (100) can generate image information in which amplitude components are visualized based on amplitude components among a plurality of components in the frequency domain. For example, the computing device (100) can convert temperature change information of a product surface obtained in the time domain into the frequency domain through a Discrete Fourier Transform (DFT), and calculate the amplitude component of a frequency point corresponding to the lowest non-zero low frequency (e.g., k=1) on a pixel-by-pixel basis. The calculated amplitude values ​​are mapped to each location on the product surface and formed into a two-dimensional array, and then the computing device (100) can generate image information that visually represents the distribution of amplitude values ​​by applying a color scale. The generated amplitude visualization image can be used to visually identify differences in thermal response characteristics caused by whether the substrate surface of the product has been restored, for example, putty painting, putty sheet metal work, etc.

[0125] According to one embodiment, a computing device (100) may display image information in which amplitude components are visualized as information for determining whether the surface of a product's substrate has been restored. For example, the computing device (100) may display image information in which amplitude components are visualized on a user terminal. The user may visually recognize the image information in which amplitude components are visualized displayed on the user terminal and determine whether the surface of the substrate has been restored. For example, information for determining whether the surface of the product's substrate has been restored may include whether putty has been applied to the substrate, whether there is a history of the substrate's external shape being restored (deformed), and whether there is a history of the substrate's physical properties being restored (deformed). For example, generally, areas with uniform thermal diffusion properties show a smooth and continuous pattern. On the other hand, areas where putty has been applied to the substrate, or areas where the substrate's physical properties have changed, show a pattern where the amplitude values ​​change rapidly or a mottled appearance. Through these visual patterns, the user can estimate areas where the product's external shape has been damaged and restored, or areas where internal physical properties have been deformed. For example, referring to Fig. 6, the user can infer from the image of the amplitude components visualized on the user terminal that there is a mottled putty on the rear fender of the left side of the vehicle. That is, if a specific area shows a mottled or uneven color distribution in the image of the amplitude components visualized, that area may be an area where putty has been applied or an area where the physical properties of the internal substrate have changed.

[0126] According to one embodiment, information related to the surface restoration of a product's substrate may be generated based on image information in which amplitude components are visualized, by utilizing a machine learning model. A computing device (100) can automatically generate prediction information related to the surface restoration of a product's substrate by using image information in which amplitude components are visualized as input to a pre-trained machine learning-based artificial intelligence model. For example, the machine learning model may be trained using a supervised learning method that includes image information in which amplitude components are visualized and ground truth labels regarding whether the surface of the substrate in the corresponding area is restored. For example, the machine learning model may be a model trained to receive image information in which amplitude components are visualized as input and to predict whether the input is an area with a history of putty repair or an area where the physical properties of the substrate have been deformed (e.g., Yes / No or probability values). The machine learning model may include various artificial intelligence architectures such as CNN (Convolutional Neural Network), MLP (Multilayer Perceptron), ResNet, UNet, and SegNet. Additionally, the computing device (100) may provide image information in which amplitude components are visualized as input to a pre-trained machine learning model and receive a classification result or a prediction probability regarding whether each part included in the image is an area where surface restoration of the substrate has occurred. For example, the input to the machine learning model may be an amplitude visualization image (e.g., an RGB color map with a resolution of 256×256 or a normalized heat map), and the output may be whether the surface of the substrate has been restored (e.g., 0 or 1) or a surface restoration probability (e.g., 88%). At this time, whether the surface of the substrate has been restored may be determined at the pixel level, object level (door, fender, loop, etc.), or whole image level.For example, the computing device (100) can process the prediction result regarding whether the surface of the substrate is restored, obtained from an artificial intelligence model, into visual or numerical information and output it to a display device of a user terminal. For example, the computing device (100) can provide information in various ways, such as inserting a text overlay of “Surface restoration of substrate present (88%)” on image information in which the amplitude component is visualized, highlighting the predicted area with a second-colored outline or dotted box, or providing results summarizing the substrate status by area in the form of a list. Based on this information, the user can immediately identify which part of the surface or internal structure of the product has undergone mechanical deformation (e.g., putty repair, etc.) and can quantitatively determine the existence and severity of the repair history. For example, referring to FIG. 7, the artificial intelligence model can predict that there is putty in a circular shape on the rear fender part and the second area (21) at the end of the rear door of the left side of the vehicle.

[0127] For example, the computing device (100) can utilize an artificial intelligence model to predict whether the surface of a product's substrate has been restored at the pixel level or the object level from image information in which amplitude components are visualized. For example, the artificial intelligence model may be implemented based on a deep learning architecture such as a Convolutional Neural Network (CNN), UNet, ResNet, or Vision Transformer (ViT), and the pre-trained model is trained based on amplitude component images and actual putty repair history data. The artificial intelligence model recognizes abnormal patterns, non-uniformity, and abrupt boundary changes of thermal diffusion intensity in the amplitude map image provided as input based on learning, and can determine whether the area has undergone mechanical repair or physical deformation. The prediction result may be output as a mask indicating the presence or absence of deformation at the pixel level or as a label indicating the presence or absence of deformation at the object level (e.g., door, fender, roof, etc.), and the computing device (100) may display this in a visualized form on a display device of a user terminal. The computing device (100) may also extract each area through object detection or segmentation.

[0129] FIG. 8 is a flowchart illustrating an operation of generating information related to product repair by simultaneously utilizing phase and amplitude values ​​according to one embodiment of the present disclosure, FIG. 9 is a diagram illustrating the result of aligning and displaying together image information with a phase component visualized and image information with an amplitude component visualized according to one embodiment of the present disclosure, and FIG. 10 is a diagram illustrating the result of displaying the first prediction information of a first machine learning model and the second prediction information of a second machine learning model according to one embodiment of the present disclosure.

[0130] According to one embodiment of the present disclosure, a computing device (100) may generate information related to the repair of a product by “simultaneously utilizing phase and amplitude values.” For example, referring to FIG. 8, information related to the repair of a product generated by simultaneously utilizing phase and amplitude values ​​may be generated based on the result of performing steps S110 and S120 described above.

[0131] First, the computing device (100) can generate image information in which the phase component is visualized based on the phase component among multiple components in the frequency domain, in order to generate information related to product repair by “simultaneously utilizing phase and amplitude values” (S131). For example, the computing device (100) can convert information in the frequency domain by applying a Discrete Fourier Transform (DFT) according to sampling interval information based on temperature change information of the product surface obtained in the time domain. At this time, the computing device (100) can calculate the phase component of the frequency point corresponding to the lowest non-zero low frequency (e.g., k=1) on a pixel-by-pixel basis. In addition, the computing device (100) can generate image information in which the phase component is visualized by mapping the phase component value for each vehicle surface area to a color map (e.g., red-yellow-white, etc.). In the generated phase visualization images, the areas where paint repair has been performed may show different phase values ​​compared to normal areas due to changes in paint film thickness, heat diffusion paths, and material composition; as the distribution changes in a manner where phase values ​​increase or decrease, color differences contrasting with the normal area or abnormal phase patterns may be visually apparent.

[0133] Next, the computing device (100) can generate image information in which the amplitude component is visualized based on the amplitude component among multiple components in the frequency domain (S132). For example, the computing device (100) can convert the temperature change information of the product surface obtained in the time domain into information in the frequency domain by applying a Discrete Fourier Transform (DFT) according to the sampling interval information. At this time, the computing device (100) can calculate the amplitude component of the frequency point corresponding to the lowest non-zero low frequency (e.g., k=1) on a pixel-by-pixel basis. Additionally, the computing device (100) can generate image information (amplitude map) that visualizes the amplitude distribution of the product surface by configuring the amplitude component value of each pixel into a two-dimensional array, normalizing it, and mapping it to a monochrome scale (e.g., black and white). In such amplitude map images, areas where thermal diffusion characteristics have been altered due to putty repairs (e.g., putty painting, putty sheet metal work) may appear as darker or lighter colors compared to the surroundings, and this can be utilized to quantitatively determine whether there are substrate defects or a history of repairs in those areas. Since amplitude values ​​reflect the magnitude of thermal diffusion or the intensity of heat absorption in the corresponding area, significant amplitude differences may appear compared to normal areas in regions where putty has been applied or where the density or thermal conductivity characteristics of the substrate have changed.

[0135] Next, the computing device (100) can align and display together image information in which the phase component is visualized and image information in which the amplitude component is visualized for one or more parts of a product (S133). For example, the computing device (100) can spatially align the image information in which the phase component is visualized and image information in which the amplitude component is visualized for one or more parts of a product and then display them together on the same screen or on an integrated UI. For example, since the two images are generated based on the same resolution / pixel array acquired from the same camera position and time axis, the pixels (i, j) of each image represent the same actual product surface location. The computing device (100) can align the two images based on this coordinate correspondence. For example, the computing device (100) can align and display together the image information in which the phase component is visualized and image information in which the amplitude component is visualized through an image overlay method, a side-by-side parallel display, a tap method, etc. For example, the image overlay method may be a method in which the phase image is superimposed semi-transparently on the amplitude image to show the contour or classification result. Furthermore, the method of displaying side-by-side in parallel may be a method of simultaneously providing image information with phase components visualized and image information with amplitude components visualized for the same area. Additionally, the tab switching method may be a method of comparing phase and amplitude for the same location by toggling them. The foregoing is merely an example and the present disclosure is not limited thereto. Such an alignment display method supports the user in simultaneously determining the painting history and structural deformation history of the same area, and improves the accuracy and intuitiveness of repair history analysis.

[0136] According to one embodiment, a computing device (100) may display image information in which a phase component is visualized as information for determining whether painting has been done for one or more parts of a product, and may display image information in which an amplitude component is visualized as information for determining whether the surface of a substrate has been restored. The computing device (100) may output the visualized image information of the phase component and the amplitude component in a parallel manner on the screen of a user terminal. For example, the computing device (100) may display different judgment information for the same part of the product in an intuitively comparable manner through a UI configuration divided left and right or up and down, a grid arrangement method by part, etc. For example, on the screen of a user terminal, it may be displayed as shown in FIG. 9 within a single screen. The left screen may be an image in which a phase component is visualized as information for determining whether painting has been done based on film thickness, and the right screen may be an image in which an amplitude component is visualized as information for determining whether substrate deformation has occurred based on thermal diffusion. Additionally, the computing device (100) may summarize the painting status (e.g., painted / not painted) and putty repair status (e.g., deformation present / not present) for each part of the product into a text list that displays them side by side.

[0137] According to one embodiment, a computing device (100) may utilize a first machine learning model to display first prediction information indicating whether one or more parts of a product are painted, based on image information in which a phase component is visualized. For example, the first machine learning model may be a model trained through supervised learning to receive image information in which a phase component is visualized for learning as input and to predict whether one or more parts of the product are painted (e.g., Yes / No, or probability value). The first machine learning model may be composed of a deep learning-based model such as a CNN, ResNet, or UNet. Additionally, the first machine learning model may learn the spatial distribution and pattern of phase values ​​to distinguish whether or not a part is painted. Furthermore, the first machine learning model may learn the phase pattern of a part that has a history of paint repair and output a prediction result in pixel units or object units. For example, the computing device (100) may display the generated first prediction information by superimposing it on image information in which the phase component is visualized, or on a digital model that virtually represents the structure of the product (e.g., a 2D plan or a 3D product image). At this time, the first prediction information may be expressed using various visualization techniques such as color, border, transparency, and text labels, and the user can clearly verify the prediction results on an actual thermal response pattern or an intuitive product diagram. Additionally, the computing device (100) may display second prediction information indicating whether the substrate of one or more parts of the product is deformed based on image information in which the amplitude component is visualized, by utilizing a second machine learning model. The second machine learning model may be constructed based on training data including image information in which the amplitude component is visualized for a plurality of product samples and correct answer information regarding whether the surface of the substrate for each part is restored (e.g., whether putty is present, whether the physical properties of the substrate have changed, etc.).Since the amplitude value is influenced by the thermal conductivity, density, and uniformity of the substrate, the second machine learning model can learn this to identify the presence or absence of putty, traces of sheet metal, changes in structural material, etc. For example, the computing device (100) may display the generated second prediction information by superimposing it on image information in which the amplitude component is visualized, or may display it on a digital model that virtually represents the structure of the product (e.g., a 2D plan or a 3D product image). At this time, the second prediction information may be expressed using various visualization techniques such as color, border, transparency, and text label, and the user can clearly verify the prediction results on an actual thermal response pattern or an intuitive product diagram. At this time, the computing device may display the first prediction information and the second prediction information separately by setting at least one of the color, border, transparency, and text label differently.

[0138] Referring to FIG. 10 for example, the computing device (100) may apply different visualization methods (e.g., display color, line shape, border style, etc.) to clearly distinguish and provide to the user first prediction information (prediction result regarding whether the surface of the substrate is restored) obtained from a first machine learning model and first prediction information obtained from a second machine learning model in a virtual product image. For example, the first prediction information is a prediction result related to whether the substrate is painted, and if the area is determined to be painted, the first-1 prediction information (31) and the first-2 prediction information (32) can be displayed on the area in the virtual product image as a 'red dotted box'. On the other hand, the first prediction information is a prediction result related to whether the substrate is structurally deformed, and if the area is determined to have undergone putty repair, the second-1 prediction information (33) can be highlighted on the area in the virtual product image as a 'green dashed box'. Additionally, the computing device (100) may display a thicker line thickness for areas with a higher probability of prediction, or, when there is suspicion of both painting and putty repair, overlap the two borders or apply a different alpha (transparency) to the background color to further enhance user recognition.

[0140] According to one embodiment, the first machine learning model and the second machine learning model may be implemented as separate models or implemented together as an integrated model. For example, the first machine learning model and the second machine learning model may each be implemented as independent models to individually predict whether a surface is painted based on a phase component visualization image and whether the surface of the substrate is restored based on an amplitude component visualization image. Alternatively, the first machine learning model and the second machine learning model may be implemented as a single integrated model to simultaneously predict whether a surface of one or more parts of a product is painted and whether the surface of the substrate is restored by utilizing common inputs or partially integrated features. In this case, the integrated model may have a multi-task learning structure, which can improve the efficiency of system resources and the consistency of prediction results.

[0142] FIG. 11 is a schematic diagram of a device for generating information related to the repair of a product according to one embodiment of the present disclosure.

[0143] According to one embodiment of the present disclosure, a device for generating information related to the repair of a product may include a physical stimulation module, a camera module, and an analysis module. However, the device for generating information related to the repair of a product is not limited thereto.

[0144] According to one embodiment, the physical stimulation module can apply physical stimulation to the surface of a product. For example, physical stimulation may include thermal stimulation, optical stimulation, electrical stimulation, magnetic stimulation, etc. Such stimulation induces a reaction in the surface or internal material of the product, causing changes in physical properties such as thermal conductivity, reflectivity, and conductivity. For example, in the case of thermal stimulation, heat may be applied for a short period of time using a high-power flash lamp or a thermal pulse generator. In addition, in the case of optical stimulation, a localized reaction may be induced through a short-wavelength laser or strong LED lighting. In addition, in the case of electrical stimulation, the electrical response of the material may be measured by applying a minute voltage through a surface electrode. Such stimulation may be controlled according to preset conditions (intensity, time, position, etc.). For example, the physical stimulation module may be fixed (placed) at a specific location or may be coupled to a moving device (201) and move together with the camera module (200).

[0146] According to one embodiment, the camera module (200) can photograph the surface of a product after physical stimulation has been applied. The camera module (200) can photograph the state of the product after physical stimulation has been applied to the surface in multiple image frames. The captured images include information such as temperature changes or reflectance changes over time. For example, the camera module (200) may be a thermal detection camera including an infrared (IR) sensor, capable of capturing images at a speed of tens of frames per second, and thus capable of recording the reaction after stimulation in real time. According to one embodiment, the camera module (200) is coupled to a rail-based moving device (201) or a robot arm, and can scan a wide area while automatically moving in the forward and backward directions of the product. For example, the product is a vehicle (1), and while the vehicle (1) is in a fixed state, the camera module (200) coupled to the moving device (201) moves and can photograph the appearance of the vehicle (1) after physical stimulation has been applied from various directions. At this time, time-series response data for the entire surface of the product can be collected by acquiring the response after physical stimulation is applied at each shooting point in multiple frames. For reference, the rail-based moving device (201) is a mechanical structure designed to move along a fixed path (rail), and may be a device that enables precise and repeatable movement and shooting operations by equipping it with a sensor such as a camera module (200). When the camera module (200) is coupled to the rail-based moving device (201), it can move precisely and stably, and systematically scan a wide area according to the length of the rail. The camera module can not only move but also rotate or move about the horizontal axis (horizontal axis, X-axis) on the moving unit. To this end, a servo motor or a gear-driven rotating shaft is built into the moving unit, so that the camera can rotate in the up and down direction.This rotation allows the product surface to be photographed from various directions, such as the front, top, and sides.

[0148] According to one embodiment, the analysis module can convert information regarding a plurality of image frames generated by the camera module (200) into information in the frequency domain and generate information related to product repair based on at least one component among a plurality of components in the frequency domain. For example, the analysis module may be the computing device (100) described above. Therefore, even if the content described below is omitted, the description of the computing device (100) can be applied equally to the description of the analysis module. For example, the analysis module can analyze a plurality of image frames acquired by the camera module (200), convert time-domain response data recorded in each frame into the frequency domain, and generate information regarding the repair history or abnormality of the product based on the phase or amplitude component of at least one frequency point among the frequency points. For example, the analysis module can apply a Discrete Fourier Transform (DFT) algorithm to decompose time-axis temperature data into complex-number-based frequency components. Subsequently, since the phase component reflects the heat transfer delay of the coating film (whether it is painted) and the amplitude component reflects the thermal diffusion characteristics of the substrate (whether it is putty), these can be processed into heat maps, color maps, and predicted probability values ​​to be provided to the user. In addition, the analysis module may also include a machine learning-based classification model, through which it can automatically determine whether each part of the product is painted and whether the substrate surface needs restoration, and output the prediction results in a visual or numerical form.

[0150] The steps mentioned in the foregoing description may be further subdivided into additional steps or combined into fewer steps, depending on the embodiment of the present disclosure. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0152] Meanwhile, a computer-readable medium storing a data structure is disclosed according to an embodiment of the present disclosure.

[0153] A computer-readable medium storing a data structure according to one embodiment of the present disclosure is disclosed. The aforementioned data structure may be stored in memory as described in the present disclosure, executed by a processor, and transmitted and received by a network unit.

[0154] A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure can refer to the organization of data for solving specific problems (e.g., data analysis, data retrieval, data storage, data modification). A data structure may also be defined by physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements may include connections between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., a permanent storage device). Specifically, a data structure may include sets of data, relationships between data, and functions or instructions applicable to the data. Through an effectively designed data structure, a computing device can perform operations while minimizing the use of the device's resources. Specifically, through an effectively designed data structure, a computing device can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and retrieval.

[0155] Data structures can be classified into linear and non-linear data structures based on their form. A linear data structure is one where only one piece of data is connected to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a set of data that maintains an internal order. Lists can include linked lists. A linked list is a data structure where data is connected in a line, with each piece of data possessing a pointer. In a linked list, the pointer can contain information regarding the connection to the next or previous data. Depending on its form, a linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list. A stack is a data arrangement structure that allows for restricted access to data. A stack can be a linear data structure where data can be processed (e.g., insertion or deletion) only at one end. Data stored in a stack can be a Last-In, First-Out (LIFO) data structure, meaning that the later an item is entered, the sooner it is retrieved. A queue is a data sequence structure that allows for limited access to data; unlike a stack, it can be a FIFO (First in First Out) data structure where data stored later is retrieved later. A deque is a data structure that can process data at both ends.

[0156] Non-linear data structures can be structures where multiple data are connected after a single piece of data. Non-linear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge may include a line connecting two different vertices. Graph data structures may include tree data structures. A tree data structure may be a data structure where there is only one path connecting two different vertices among the multiple vertices included in the tree. In other words, it may be a data structure that does not form a loop in a graph data structure.

[0157] Throughout this specification, the terms artificial intelligence-based model, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, they will be described uniformly as neural network. A data structure may include a neural network. Furthermore, a data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. In addition to the configurations described above, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated during the computational process of the neural network, and is not limited to the foregoing. A computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0158] A data structure may include data input to a neural network. A data structure including data input to a neural network may be stored on a computer-readable medium. Data input to a neural network may include training data input during the neural network learning process and / or input data input to a neural network after training is complete. Data input to a neural network may include pre-processed data and / or data subject to pre-processing. Pre-processing may include a data processing process for inputting data into a neural network. Accordingly, a data structure may include data subject to pre-processing and data generated by pre-processing. The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0159] The data structure may include weights of the neural network. (In this specification, weights and parameters may be used interchangeably.) The data structure including the weights of the neural network may be stored on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node may determine the data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set on the links corresponding to each input node. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0160] As an example rather than a limitation, weights may include weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and / or weights that vary during the learning cycle. Weights for which neural network learning is completed may include weights for which the learning cycle is completed. Accordingly, a data structure containing the weights of a neural network may include a data structure containing weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Therefore, the weights and / or combinations of each weight described above are included in the data structure containing the weights of a neural network. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0161] Data structures containing the weights of a neural network may be stored on a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed for use. A computing device may serialize the data structure to transmit and receive data over a network. A serialized data structure containing the weights of a neural network may be reconstructed on the same or different computing devices through deserialization. Data structures containing the weights of a neural network are not limited to serialization. Furthermore, data structures containing the weights of a neural network may include data structures designed to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, R-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in non-linear data structures). The foregoing is merely an example and the present disclosure is not limited thereto.

[0162] The data structure may include hyperparameters of the neural network. The data structure including the neural network hyperparameters may be stored on a computer-readable medium. The hyperparameters may be variables that are varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weight values ​​subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0164] FIG. 12 is a brief and general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0165] Although the present disclosure has been described as generally being implementable by a computing device, a person skilled in the art will be well aware that the present disclosure may be implemented in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0166] Generally, a program module includes routines, programs, components, data structures, etc., that perform a specific task or implement a specific abstract data type. Furthermore, a person skilled in the art will be well aware that the method of the present disclosure can be implemented in other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which may be connected to and operated with one or more associated devices).

[0167] The embodiments described in this disclosure may also be implemented in a distributed computing environment in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0168] Computers typically include various computer-readable media. Any medium accessible by a computer may be a computer-readable medium, and such computer-readable media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media. By example, but not limiting, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transitory and non-transitory media, and removable and non-removable media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, DVD (digital video disk) or other optical disk storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, or any other media that can be accessed by a computer and used to store desired information.

[0169] Computer-readable transmission media typically include all information transmission media that implement computer-readable instructions, data structures, program modules, or other data, etc., on a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal in which one or more of the characteristics of the signal are set or modified to encode information within the signal. By example, not limiting, computer-readable transmission media include wired media, such as wired networks or direct-wired connections, and wireless media, such as acoustic, RF, infrared, and other wireless media. Any combination of the media described above is also considered to be within the scope of computer-readable transmission media.

[0170] An exemplary environment for implementing various aspects of the present disclosure, including a computer (1102), is shown, wherein the computer (1102) includes a processing unit (1104), system memory (1106), and a system bus (1108). The system bus (1108) connects system components, including system memory (1106) (but not limited thereto), to the processing unit (1104). The processing unit (1104) may be any processor among various commercial processors. Dual processors and other multiprocessor architectures may also be used as the processing unit (1104).

[0171] The system bus (1108) may be any of several types of bus structures that can be additionally interconnected to a local bus using any of the memory bus, peripheral bus, and various commercial bus architectures. System memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). The basic input / output system (BIOS) is stored in non-volatile memory (1110), such as ROM, EPROM, EEPROM, etc., and this BIOS includes basic routines that help transfer information between components within the computer (1102) at times such as during startup. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

[0172] The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—this internal hard disk drive (1114) may also be configured for external use within a suitable chassis (not shown)—a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from a CD-ROM disk (1122) or reading from or writing to other high-capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may each be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128). The interface (1124) for implementing an external drive includes at least one or both of USB (Universal Serial Bus) and IEEE 1394 interface technologies.

[0173] These drives and associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of a computer (1102), the drives and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, a person skilled in the art will know that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in exemplary operating environments and that any of these media may contain computer-executable instructions for performing the methods of the present disclosure.

[0174] A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or part of the operating system, application, module and / or data may also be cached in RAM (1112). It will be well known that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

[0175] The user can input commands and information into the computer (1102) through one or more wired / wireless input devices, such as a pointing device like a keyboard (1138) and a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, etc. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) connected to the system bus (1108), but may also be connected via other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

[0176] A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface such as a video adapter (1146). In addition to the monitor (1144), the computer generally includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

[0177] The computer (1102) may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer(s) (1148), via wired and / or wireless communication. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and generally include many or all of the components described for the computer (1102), but for brevity, only the memory storage device (1150) is illustrated. The illustrated logical connection includes a wired / wireless connection to a local area network (LAN) (1152) and / or a larger network, e.g., a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a global computer network, e.g., the Internet.

[0178] When used in a LAN networking environment, the computer (1102) is connected to a local network (1152) via a wired and / or wireless communication network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communication to the LAN (1152), and the LAN (1152) may also include a wireless access point installed therein to communicate with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communication computing device on the WAN (1154), or have other means to establish communication through the WAN (1154), such as through the Internet. The modem (1158), which may be an internal or external and a wired or wireless device, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, the program modules described for the computer (1102) or parts thereof may be stored in a remote memory / storage device (1150). It will be well known that the illustrated network connection is exemplary and that other means of establishing a communication link between computers may be used.

[0179] The computer (1102) operates to communicate with any wireless device or object that is deployed and operated via wireless communication, for example, a printer, scanner, desktop and / or portable computer, PDA (portable data assistant), communication satellite, any equipment or place associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or simply ad hoc communication between at least two devices.

[0180] Wi-Fi (Wireless Fidelity) enables connectivity to the Internet and other sources without wires. Wi-Fi is a wireless technology, similar to a cell phone, that allows devices, such as computers, to transmit and receive data indoors and outdoors—that is, anywhere within the coverage area of ​​a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands at data rates, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

[0181] Those skilled in the art of the present disclosure will understand that information and signals may be represented using any various different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0182] Those skilled in the art will understand that the various exemplary logical blocks, configurations, modules, logics, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented by electronic hardware, various forms of computer programs or design code (referred to herein as software for convenience), or a combination of all such. To clearly illustrate this interoperability between hardware and software, the various exemplary logical blocks, configurations, modules, logics, processors, means, circuits, and steps have been generally described above in relation to their functions. Whether such functions are implemented in hardware or software depends on the design constraints imposed on the specific application and the overall system. Those skilled in the art may implement the functions described in this disclosure in various ways for each specific application, but such implementation decisions should not be interpreted as being outside the scope of this disclosure.

[0183] The various embodiments presented herein may be implemented as methods, devices, or articles manufactured using standard programming and / or engineering techniques. The term "article manufactured" includes a computer program, a carrier, or a medium accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical discs (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information.

[0184] It should be understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of this disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but do not imply being limited to the specific order or hierarchy presented.

[0185] Description of the presented embodiments is provided so that a person skilled in the art may use or practice the present disclosure. Various modifications to these embodiments will be apparent to a person skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the embodiments presented herein, but should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

Claims

Claim 1 A method and device for generating information related to product repair.

Images