KR102274281B1 - method and analysis server that analyzes information about parts of a product - Google Patents

Abstract

Embodiments relate to a method and an analysis server for analyzing information on parts of a product.
According to embodiments, anyone can easily identify a part that needs to be replaced in a product.
According to embodiments, it is possible to provide an efficient extraction process in the process of extracting the part that needs to be replaced by the server that determines the need for replacing the part of the product.

Description

{method and analysis server that analyzes information about parts of a product}

Embodiments relate to a method and an analysis server for analyzing information on parts of a product.

Embodiments relate to a server for determining the necessity of replacing parts of a product and an operating method thereof.

Various types of products such as pumps, motors, valves, pistons and regulators are used in machinery or equipment used in factory facilities. However, these products are easily broken or damaged during the operation of the factory, and it is very difficult to repair them on the spot if they are broken or damaged. Unless you are an expert on these products, it is difficult to figure out which parts need to be repaired for a broken product, and it is difficult to determine which product the broken product belongs to. However, due to the nature of the operation of the factory, if a product breaks down, it is necessary to quickly and accurately replace parts for the broken product.

Accordingly, consumers are increasing the demand for a system that quickly and accurately informs which parts need to be replaced/repaired for a defective product.

However, in the case of most existing product description sites, in many cases, the consumer must know the name of the product and its intended use in order to check the parts included in the product.

Registered Patent Publication No. 10-2181624 (Notice Date: November 23, 2020)

In order to solve the above-described problems, the embodiments aim to provide a server that determines the need to replace parts of the product.

The technical problems to be achieved in the embodiments are not limited to those mentioned above, and other technical problems not mentioned may be considered by those of ordinary skill in the art from various embodiments to be described below. can

According to embodiments, there is provided a server for determining the need to replace parts of a product, comprising: at least one processor; and a memory for storing instructions instructing the at least one processor to perform at least one step, wherein the at least one step includes image data for a product from a user terminal receiving; identifying the product and one or more components included in the product from the received image data, wherein the identification of the product and the components is based on a product database; extracting a replacement part from among the identified one or more parts; and transmitting information on the identified product, information on one or more parts included in the identified product, and information on the extracted parts requiring replacement to the user terminal; and, wherein the image data corresponds to data obtained through a LiDAR sensor or a Time of Flight (TOF) sensor included in the user terminal, and provides a server.

According to embodiments, the product database includes product information, product pattern value information, and part information of the product, and includes a product and one or more components included in the product in the received image data. ) may include: recognizing first points in the image data and calculating a product pattern value according to the first points; identifying a product of the image data based on the product pattern value according to the calculated first points and the product pattern value information; and identifying one or more parts included in the identified product based on the identified product and part information of the product. It provides a server, including.

According to embodiments, the product database further includes part pattern value information of the product, and the step of extracting a replacement part from among the identified one or more parts may include recognizing second points in the image data. and calculating a part pattern value according to the second points; and extracting the part that needs to be replaced based on the part pattern value according to the calculated second points and the part pattern value information. It provides a server, including.

According to embodiments, the product database further includes information on a frequently broken part of the product, wherein the recognized second points correspond to points located in the frequently broken part of the identified product, server is provided.

According to embodiments, the product pattern value according to the first points includes a vector value from a center point to each of the first points, and the center point is based on coordinates indicating the positions of the first points. is determined, and the part pattern value according to the second points includes a vector value from the center point to each of the second points, and the extraction of the part requiring replacement is the part according to the calculated second points. It provides a server based on a difference value between a vector value included in the pattern value and a vector value included in the part pattern value information of the product database.

According to embodiments, it is possible to provide a server that determines the need to replace parts of a product.

According to embodiments, anyone can easily identify a part that needs to be replaced in a product.

According to embodiments, it is possible to provide an efficient extraction process in the process of extracting the part that needs to be replaced by the server that determines the need for replacing the part of the product.

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those of ordinary skill in the art based on the following detailed description. can be

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included as part of the detailed description to aid understanding of the embodiments, provide various embodiments and, together with the detailed description, explain technical features of the various embodiments.
1 illustrates an example of a method in which a server for determining the necessity of replacing parts of a product according to embodiments is driven.
2 illustrates an example of a method of acquiring image data for a product through a user terminal according to embodiments.
3 is a view for explaining product information and product part information stored in a product database according to embodiments.
4 illustrates an example of a process in which a server identifies a product from image data according to embodiments.
5 illustrates an example of a process in which a server extracts a replacement part according to an exemplary embodiment.
6 is an example of an artificial intelligence unit included in a server according to embodiments.
7 is an example of a process of extracting a part requiring replacement based on a frequently broken part according to embodiments.
FIG. 8 is a hardware configuration diagram for a server that determines the necessity of replacing parts of the product according to FIG. 1 .

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form that is not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some features or features of one embodiment may be included in another embodiment, or may be replaced with corresponding features or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood at the level of those of ordinary skill in the art are also not described. did.

Throughout the specification, when a part is said to "comprising or including" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated. do. In addition, terms such as "... unit", "... group", and "module" described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, "a or an", "one", "the" and like related terms are used herein in the context of describing various embodiments (especially in the context of the claims that follow). Unless otherwise indicated or clearly contradicted by context, it may be used in a sense including both the singular and the plural.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION The detailed description set forth below in conjunction with the appended drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent the only embodiments.

In addition, specific terms used in various embodiments are provided to help the understanding of various embodiments, and the use of these specific terms may be changed to other forms without departing from the technical spirit of various embodiments. .

1 illustrates an example of a method in which a server for determining the necessity of replacing parts of a product according to embodiments is driven.

1 illustrates an example of a method in which a server for determining the necessity of replacement of a component of a product according to embodiments is driven. 100 represents a server that determines the necessity of replacing parts of products according to embodiments. 200 represents a user terminal according to embodiments. 50 represents a product database according to embodiments. One or more elements, not shown in this figure, may be further included in order to drive a server that determines the necessity of replacing parts of a product according to embodiments.

Products according to embodiments may represent a pump, a motor, a valve, a piston, and/or a regulator used for driving a machine or device. Components according to the embodiments represent components constituting the above-described product. A component according to embodiments is a component for driving a product. That is, a product according to embodiments may include one or more components. For example, parts of a valve include a valve plate, a spacer, a set plate, a shoe plate, a shaft front, and a shaft rear. rear, block spring, piston shoe set and swash plate.

The server 100 for determining the necessity of replacing parts of a product according to embodiments may transmit/receive data to/from the user terminal 200 and/or the product database 50 . The product database according to the embodiments may be included in a server that determines the need to replace parts of a product.

The user terminal according to the embodiments refers to a terminal or device that a user has in order to use a server that determines the need to replace parts of a product. For example, the user terminal is a communicationable desktop computer (desktop computer), laptop computer (laptop computer), notebook (notebook), smart phone (smart phone), tablet PC (tablet PC), mobile phone (mobile phone), smart Watch (smart watch), smart glass (smart glass), e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital It may be a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, a personal digital assistant (PDA), or the like.

The user may photograph the product through the user terminal. That is, the user may acquire image data for the product through the user terminal. A user terminal according to embodiments may include a Light Detection And Ranging (LiDAR) camera (or LiDAR sensor) and/or a Time of Flight (TOF) camera (or TOF sensor). Accordingly, the image data for the product obtained through the user terminal may represent 3D data for the product. The 3D data for the above-described product may include depth information about the product.

A server (or server) that determines the necessity of replacing parts of a product according to embodiments may receive image data about the product from the user terminal. The server according to the embodiments may perform at least one step on the received image data. At least one step of the server according to the embodiments is a step for determining the necessity of replacing parts of a product corresponding to the image data. A server according to embodiments may receive image data and identify a product of the image data and one or more parts included in the product. The server according to embodiments may extract a replacement part from among the identified one or more parts. The server according to the embodiments may transmit information on the identified product, information on one or more parts included in the identified product, and/or information on the extracted parts requiring replacement to the user terminal. The server according to embodiments may further include one or more steps to determine a replacement part. The above-described at least one step of the server according to the embodiments may be performed based on information stored in the product database.

The server for determining the necessity of replacing parts of a product according to embodiments may analyze image data received from the user terminal and provide information on parts requiring replacement to the user. Accordingly, even if the user has no knowledge of the product, information about the product and information about the parts requiring replacement can be immediately known through photographing the product.

2 illustrates an example of a method of acquiring image data for a product through a user terminal according to embodiments.

2 illustrates an example of a method of acquiring image data for a product 201 through a user terminal 200 according to embodiments. Descriptions of user terminals and products according to embodiments are the same as those described above with reference to FIG. 1 .

As described above in FIG. 1 , a user terminal according to embodiments may include a lidar sensor and/or a TOF sensor. A user terminal including a lidar sensor and/or a TOF sensor according to embodiments may photograph a product using an inward-facing method. The inward-pacing method according to the embodiments refers to a method of photographing the target object in a manner surrounding the target object. The inward-pacing method according to embodiments may be used to acquire a 360-degree image (or 3D image) of an object to be photographed. The inward pacing method according to the embodiments may be a method opposite to the outward-facing method of photographing the surrounding environment of the user terminal.

The lidar sensor according to the embodiments may represent a device that precisely draws the shape of the target object by measuring the distance to the target object based on the reflection of a laser pulse. The lidar sensor according to embodiments may acquire depth information about the target object and attribute information (eg, color information) corresponding to the depth information.

The TOF sensor according to the embodiments may represent a device that precisely draws the shape of the target object by measuring the distance to the target object based on the reflection of infrared rays.

The user terminal according to the embodiments may acquire image data of a target object (eg, a product) using the above-described lidar sensor and/or TOF sensor. The obtained image data according to embodiments may be referred to as a 3D image and/or a 360-degree image of the target object. The image data obtained by the user terminal according to the embodiments may use the above-described LiDAR sensor and/or TOF sensor, and the server may receive precise image data for the product 201 .

3 is a view for explaining product information and product part information stored in a product database according to embodiments.

FIG. 3 is a diagram for explaining product information (or product information) stored in a product database according to embodiments, and information (or product part information) on one or more parts included in the product. Reference numeral 201 denotes a product according to the embodiments (eg, the product described in FIGS. 1 to 2 ), and 202 denotes parts (eg, the parts described in FIGS. 1 to 2 ) according to the embodiments. indicates.

A server (eg, a server that determines the necessity of replacing parts of a product) according to embodiments may identify a product of image data and one or more parts included in the product. Identification of products and parts according to embodiments may be based on a product database.

The product database according to embodiments may include product information, product pattern value information, and/or part information of a product. The product information according to embodiments may indicate information indicating the name of a product and model information in which the corresponding product can be used. Product pattern value information according to embodiments may be product-specific information for identifying a corresponding product. A process in which the server uses product pattern value information of a product database according to embodiments to identify a product will be described in detail later with reference to FIG. 4 . Part information of a product according to embodiments may indicate information (eg, a name of a corresponding part, a required quantity of a corresponding part, a corresponding part model number) on one or more parts included in the corresponding product. .

As described above, the product information stored in the product database according to the embodiments may include information indicating the name of the product and model information in which the corresponding product can be used. For example, information indicating the name of the product of 201 stored in the product database indicates the K3V180DT valve, and the available model information of product 201 is SK400-2, HD1250V2, S330, S360, S450, SE350, SE450, R360 and R420 indicates. 201 Product name information is CYL/BLOCK&VALVE PLATE RH, CYL/BLOCK&VALVE PLATE LH, BLOCK SPRING, SPACER, SET PLATE&BALL GUIDE, PISTON SHOE SET, SHOE PLATE, SWASH PLATE & SUPPORT, SHAFT FRONT (17T), SHAFT FRONT ( KB), SHAFT FRONT (17T), SHAFT REAR (12T) and SHAFT REAR (13T).

In a process of extracting a replacement part from among product parts, the server according to the embodiments may efficiently perform an extraction process using data stored in the product database described in this figure. In addition, the server may transmit the information stored in the product database described in this figure to the user terminal, so that the user can recognize information about the product and information on parts requiring replacement.

4 illustrates an example of a process in which a server identifies a product from image data according to embodiments.

4 is a view showing image data (in FIGS. 1 to 3 ) received by a server (eg, a server that determines the necessity of replacing parts of a product) according to the embodiments from a user terminal (the user terminal described with reference to FIGS. 1 to 3 ); An example of the process of identifying a product from the described image data) is shown.

The server according to embodiments may identify a product of the received image data and one or more parts included in the product. Identification of parts according to embodiments is based on the identified product. That is, identification of a product may precede identification of parts. The server according to embodiments may search for information on parts corresponding to the identified product from the product database (the product database described with reference to FIGS. 1 to 3 ) based on the identified product. The server according to the embodiments may utilize information stored in the product database to identify the product from the image data.

The process of the server identifying the product according to the embodiments may be performed through the following process.

The server according to embodiments may recognize the first points in the received image data.

As described above, the image data received from the user terminal is data including depth information of an object (eg, a product). The server according to the embodiments may display the object included in the image data as a coordinate system in a 3D space (eg, a coordinate system expressed by an x-axis, a y-axis, a z-axis, and an origin). The server according to the embodiments may recognize vertices of an object (eg, a product) expressed in a coordinate system in a three-dimensional space as first points. That is, the vertex may correspond to the vertex of the product including the image data. For example, a vertex includes a coordinate having the largest value in the x-axis direction, a coordinate having the smallest value in the x-axis direction, a coordinate having the largest value in the y-axis direction, and / or the coordinate having the smallest value in the y-axis direction may be included. 300 is a first point corresponding to a coordinate having the smallest value in the y-axis direction among coordinates indicating a product included in the image data. Reference numeral 301 denotes a first point corresponding to a coordinate having the largest value in the x-axis direction among coordinates indicating a product included in the image data. 302 is a first point corresponding to a coordinate having the largest value in the y-axis direction among coordinates indicating a product included in the image data. 303 is a first point corresponding to a coordinate having the smallest value in the x-axis direction among coordinates indicating a product included in the image data.

The server according to embodiments may calculate a product pattern value according to the first points based on the recognized first points.

As described above in FIG. 3 , the product pattern value may be a unique value of a product for identifying a corresponding product. The server according to the embodiments may express the recognized first points in a three-dimensional coordinate system and set the center point 304 based on the first points. The center point according to embodiments is used to calculate the above-described product pattern value. The center point according to embodiments may be determined based on coordinates indicating the positions of the first points. For example, the center point may correspond to an intersection of a line segment connecting 300 and 302 and a line segment connecting 301 and 303 . In addition, if the line segment connecting 300 and 302 and the line segment connecting 301 and 303 do not have an intersection point, the line segment connecting each line segment may be a midpoint of a line segment connecting the respective line segments. For example, the coordinates representing the location of 300 are (2, 2, 3), the coordinates representing the location of 301 are (6, 4, 3), the coordinates representing the location of 302 are (2, 10, 3), 303 If the coordinates representing the location of , represent (1, 3, 3), the coordinates representing the location of the center point have (2, 3.2, 3).

The server according to the embodiments may calculate a vector value from the above-described center point to each of the first points. That is, the number of calculated vector values is equal to the number of first points. The calculated vector value may have the form of a coordinate vector. For example, the coordinates indicating the position of 00 are (2, 2, 3), the coordinates indicating the position of 301 are (6, 4, 3), the coordinates indicating the position of 302 are (2, 10, 3), 303 If the coordinates indicating the position of , indicate (1, 3, 3), the vector value v1 = (0, -1.2, 0) from the center point to 300, and the vector value v2 from the center point to 301 = (4, 0.8, 0), a vector value v3 = (0, 6.8, 0) from the center point to 302, and a vector value v4 = (-1, -0.2, 0) from the center point to 303.

The product pattern value according to the first points according to the embodiments may include a vector value from the above-described center point to each of the first points. That is, the product pattern values according to the first points may include v1 to v4. Since each vector value has a magnitude and a direction, v1 to v4 may further include an angle value between the vector values. Accordingly, the vector value from the center point to each of the first points may include a distance value from the center point to each of the first points and an angle value between the vector values.

The server according to embodiments may identify a product of the image data based on a product pattern value according to the calculated first points and a product pattern value stored in the product database.

As described above, the product pattern value is a unique value for identifying a corresponding product, and may be calculated in advance and stored in a product database. That is, the product database may store product pattern value information indicating a product pattern value for a product. The server according to the embodiments may identify the product of the image data by comparing the product pattern value according to the first points calculated by the above-described process and the product pattern value information stored in the product database. That is, the server may search the product database for product pattern value information having a value closest to the calculated product pattern value, and identify the corresponding product as a product of the image data.

The server according to embodiments may identify one or more parts of the product of the image data based on part information corresponding to the product identified in the product database. Descriptions of product information and part information according to embodiments are the same as described above with reference to FIG. 3 .

A server that determines the necessity of replacing parts of a product according to embodiments may use a product pattern value described in this figure to identify a product of the image data. The product pattern value according to the embodiments includes a vector value as described above, and the vector value is a value having magnitude and direction. Accordingly, the product pattern value according to the embodiments may represent a value for identifying a corresponding product by storing minimum information. That is, the server may adjust the latency in the product identification process of image data through the product pattern value according to the embodiments, and perform an efficient product identification process.

5 illustrates an example of a process in which a server extracts a replacement part according to an exemplary embodiment.

5 illustrates an example of a process in which a server extracts (or selects) a replacement part from among one or more parts according to embodiments.

The server according to the embodiments may extract a replacement part from among the identified one or more parts as described above with reference to FIG. 4 . The server according to the embodiments may use information stored in the product database in a process of extracting a replacement part. A process in which the server extracts a part that needs to be replaced according to the embodiments may include the following process.

The server according to embodiments may recognize the second points 410 in the image data.

400 denotes the first points described above in FIG. 4 . 410 denote second points according to embodiments. The second points according to embodiments are points indicating the location of each of one or more parts included in the identified product. That is, the second points may be set according to parts included in the product. That is, the second points may be set for each product. The product database (the product database of FIGS. 1 to 4 ) according to embodiments may include information on second points corresponding to products. Information on the second points according to embodiments may include information indicating positions of parts. For example, the information on the second points may include information indicating a vector value for each of the second points from the center point of the product (the center point of FIG. 4 ). The server according to embodiments may recognize the second points in the image data based on information about the second points stored in the product database.

The server according to the embodiments may calculate a part pattern value according to the recognized second points.

The component pattern values according to the embodiments are similar to the product pattern values described with reference to FIGS. 3 to 4 . A part pattern value according to embodiments is a unique value for identifying parts of a product, and may be calculated in advance and stored in a product database. The server according to the embodiments may calculate a vector value from the above-described center point to each of the second points. The process of calculating the vector values from the center point to each of the second points is the same as or similar to the process of calculating the vector values from the center point to each of the first points described in FIG. 4 . The component pattern value according to embodiments may include a vector value from a center point to each of the second points.

The server according to the embodiments may extract a part requiring replacement based on the part pattern value according to the calculated second points and the part pattern information of the product database.

The server according to the embodiments may extract a part requiring replacement by comparing the part pattern value according to the second points calculated by the above-described process and the part pattern information of the product database with each other. The server according to the embodiments may calculate a difference value by comparing the vector value included in the part pattern value according to the calculated second points with the vector value included in the part pattern value of the product database. When the calculated difference value is greater than or equal to the preset value, the server may extract a part corresponding to the second point including the calculated vector value as a part requiring replacement. The calculated difference value according to embodiments may include a difference in magnitude values and/or a difference in angle values included in the vector values. The preset value according to embodiments may include a magnitude value and/or an angle value included in the vector value. An angle value according to embodiments may be defined as two or more vectors. That is, the server according to the embodiments selects the parts requiring replacement based on the difference value between the vector value included in the part pattern value according to the calculated second points and the vector value included in the part pattern value information of the product database. can be extracted.

If the difference between the calculated vector value according to the embodiments and the vector value included in the product database is large, it is highly likely that a part corresponding to the calculated vector value is broken. Accordingly, when the server defines a preset value and the difference between the vector values is greater than the preset value, the server may determine that a part corresponding to the calculated vector value is defective and extract it as a part requiring replacement.

6 is an example of an artificial intelligence unit included in a server according to embodiments.

6 is a neural network model of an artificial intelligence unit for predicting a part that needs to be replaced at a time when the server according to the embodiments recognizes the first points (the first points of FIGS. 3 to 5). Model, 601) is shown. A neural network model according to embodiments may be referred to as an artificial intelligence model. The artificial intelligence unit described in this figure may be included in the server for determining the need to replace parts of products according to embodiments. The model used in the artificial intelligence unit according to the embodiments is not limited to the above-described example.

The neural network model of the artificial intelligence unit according to embodiments may include one or more hidden layers 602 . For example, one or more hidden layers may be a simple linear layer, and may be a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN) and/or a Long Short-Term Memory Model (LSTM). It may be a set of configured layers.

The neural network model according to the embodiments learns product information, product pattern value information, product parts information, part pattern value information, and/or difference value information (or learning data, 600) between vector values, so as to Broken Part) may be a model that outputs information 603. Descriptions of product information, product pattern value information, product part information, and part pattern value information according to embodiments are the same as or similar to those described above. Difference value information between vector values according to embodiments is the same as or similar to the difference value described with reference to FIG. 5 . The learning data according to the embodiments include data stored in a product database and/or data about values calculated by the server. That is, the artificial intelligence unit according to the embodiments may predict a part corresponding to the second point at which a difference value between vector values for a specific product is calculated to be greater than a preset value based on the above-described learning data. As described above, the part corresponding to the second point at which the difference value between the vector values is calculated to be greater than the preset value may correspond to the part requiring replacement. Accordingly, the artificial intelligence unit may predict the parts to be extracted as replacement parts for a specific product based on the learning data. A region corresponding to the predicted part may be referred to as a failure-prone region.

The server according to the embodiments may predict information on parts that frequently fail for any product through the artificial intelligence unit described in this figure. Accordingly, the server may calculate the vector value by generating the second points (second points in FIG. 5 ) only in the area corresponding to the predicted part. That is, the server can reduce a burden in the process of determining a replacement part by performing a vector value calculation according to the second points in the limited area through the artificial intelligence unit described in this figure.

7 is an example of a process of extracting a part requiring replacement based on a frequently broken part according to embodiments.

7 illustrates an example of a process of extracting a part requiring replacement based on the frequent failure area 710 according to embodiments. The description of the frequent failure region according to the embodiments is the same as described above with reference to FIG. 6 . 700 represents first points according to embodiments. 710 indicates a frequent failure region according to embodiments. 720 indicates second points according to embodiments.

When a product is identified, the server according to the embodiments may recognize second points corresponding to the identified parts of the product from the image data. However, as described above with reference to FIG. 6 , when the frequent failure area is predicted, the server may recognize only the second points corresponding to parts in the predicted frequent failure area from the image data. That is, as shown in the drawing, the server according to the embodiments may calculate the component pattern value by recognizing only the second points 720 corresponding to the components in the frequent failure area 710 from the image data. The server according to the embodiments may calculate a part pattern value according to the second points in the frequent failure area to determine the need for replacement of a part in the frequent failure area. A process of determining the need for replacement of a part according to embodiments is the same as described above with reference to FIG. 5 .

The server for determining the need for replacement of parts of the product according to the embodiments may efficiently perform a determination process through the process of determining the need for replacement of parts based on the frequent failure area described in this drawing. That is, the server according to the embodiments does not need to recognize the second points corresponding to all parts of the product, and thus may perform a faster determination process.

FIG. 8 is a hardware configuration diagram for a server that determines the necessity of replacing parts of the product according to FIG. 1 .

Referring to FIG. 8 , the server 100 for determining the need to replace parts of a product, at least one processor 110 and/or at least one processor 110 instructs to perform at least one step It may include a memory 120 for storing instructions.

The at least one processor 110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments are performed. Each of the memory 120 and the storage device 160 may be configured as at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 120 may be configured as at least one of a read only memory (ROM) and a random access memory (RAM).

In addition, the server 100 for determining the need to replace parts of a product may include a transceiver 130 that performs communication through a wireless network. In addition, the server for determining the necessity of replacing parts of the product may further include an input interface device 140 , an output interface device 150 , a storage device 160 , and the like. Each of the components included in the server 100 operating the reptile trading platform may be connected by a bus 170 to communicate with each other.

At least one step according to embodiments may include receiving image data for a product from a user terminal, and identifying a product and one or more components included in the product from the received image data step, identification of products and parts is based on a product database, and extracting parts requiring replacement from among the identified one or more parts and/or information on the identified products, identified products It may include transmitting information on one or more parts included in the information and information on the extracted parts requiring replacement to the user terminal. Also, image data according to embodiments may correspond to data acquired through a LiDAR sensor or a Time of Flight (TOF) sensor included in the user terminal.

The product database according to embodiments may include product information, product pattern value information, and product part information. The step of identifying a product and one or more components included in the product in the received image data according to embodiments may include recognizing first points in the image data and a product pattern according to the first points. calculating a value, identifying a product in the image data based on product pattern value and product pattern value information according to the calculated first points, and/or identifying product and product identified based on parts information of the product identifying one or more components included in the .

The product database according to embodiments may further include part pattern value information of the product. The extracting of a part requiring replacement from among the identified one or more parts according to embodiments may include recognizing second points in image data and calculating and/or calculating a part pattern value according to the second points. It may include extracting a part requiring replacement based on the part pattern value and part pattern value information according to the second points.

The product database according to the embodiments may further include information (Frequently Broken Part) on the area of frequent failure of the product. Recognized second points according to embodiments may correspond to points located in a failure-prone area of the identified product.

A product pattern value according to the first points according to embodiments may include a vector value from a center point to each of the first points, and the center point may be determined based on coordinates indicating positions of the first points. The part pattern value according to the second points according to embodiments may include a vector value from a center point to each of the second points. Extraction of a part requiring replacement according to embodiments may be based on a difference value between a vector value included in the part pattern value according to the calculated second points and a vector value included in the part pattern value information of the product database.

Embodiments may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer-readable medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.

Examples of computer-readable media may include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions may include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as at least one software module to perform the operations of the present invention, and vice versa.

In addition, the above-described method or apparatus may be implemented by combining all or part of the configuration or function, or may be implemented separately.

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

Claims (1)

processor;
memory; and
including a database;
The processor is
Receive image data for a product from a user terminal,
identifying the product and one or more components included in the product from the received image data;
extracting a replacement part from among the identified one or more parts;
Transmitting information on the identified product, information on one or more parts included in the identified product, and information on the extracted parts requiring replacement to the user terminal,
The image data corresponds to data acquired through a LiDAR sensor or a Time of Flight (TOF) sensor included in the user terminal;
The database stores information about the pattern value of the product and information about the parts of the product,
The processor is
Recognize as first points corresponding to vertices of an object expressed in a coordinate system in a three-dimensional space in the image data,
Calculate a product pattern value according to the first points, wherein the product pattern value corresponds to a unique value for identifying a product,
identify the product of the image data based on the product pattern value according to the first points and information on the product pattern value,
identifying one or more parts included in the identified product based on information about the identified product and parts of the product;
The processor is
Recognizing second points in the image data and calculating a part pattern value according to the second points,
extracting the parts requiring replacement based on the part pattern value according to the calculated second points and information on the parts of the product;
The product pattern value according to the first points includes a vector value from a center point to each of the first points, wherein the center point is determined based on coordinates indicating the positions of the first points,
The part pattern value according to the second points includes a vector value from the center point to each of the second points,
The extraction of the parts requiring replacement is based on a difference value between a vector value included in the part pattern value according to the calculated second points and a vector value included in the information about the part of the product,
analysis server.

Images