KR20220071697A - An analysis system for predictive power usage by learning operation date and method thereof - Google Patents

Abstract

The present invention relates to a system and a method for providing a non-contact textile product search service. The method is executed by a server and includes the following steps in which: the server receives textile product measurement data from a user terminal; and the server compares and analyzes the textile product measurement data based on textile product standard data to generate textile product result data corresponding to the textile product measurement data. In the textile product result data generation step, the server extracts the similarity between the textile product measurement data and the textile product standard data and provides textile product information corresponding to the textile product standard data in a case where the similarity is higher than a preset similarity.

Description

A system and method for providing a non-contact textile product search service {AN ANALYSIS SYSTEM FOR PREDICTIVE POWER USAGE BY LEARNING OPERATION DATE AND METHOD THEREOF}

The present invention relates to a non-contact type textile product search service providing system and method. In particular, it is possible to provide textile product analysis results by comparing and analyzing textile products in a non-contact method using big data based on deep learning. It relates to a non-contact type textile product search service providing system and method therefor.

With the rapid development of the smart mobile environment, the mobile shopping industry is growing day by day. The need for a visual search that meets the needs of various users, especially for non-standardized objects such as clothing, is emerging.

In addition, users are aiming for a so-called user-centered information retrieval service that not only searches for various and useful information, but also finds a highly reliable search tailored to the user's preference and situation. At this time, technology related to rotational and scale invariant image classification and search technology for clothing search was studied, and with the development of machine learning along with the image clothing recognition rate or database construction, research and cases of searching for clothing or fabrics by image matching were conducted. is increasing

However, the clothing or fabric search field is a very difficult field due to the atypical characteristics of clothing, and recognition errors are still inevitable unless big data learning is performed. In addition, there is no specific study on the entire learning and recognition process to reduce errors and computations, and some related technologies still show many limitations.

In addition, in the case of the clothing or fabric search technology currently being developed, its performance is still insufficient, so it is not properly applied to the actual clothing search service.

Korean Patent Registration No. 10-1832946, 2018.02.21.

An object of the present invention is to provide a non-contact type textile product search service providing system and method.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

A method for providing a non-contact textile product search service according to an embodiment of the present invention for solving the above-described problems is a method for providing a non-contact textile product search service performed by a server, wherein the server provides a user receiving textile product measurement data from the terminal; and generating, by the server, the textile product result data corresponding to the textile product measurement data by comparing and analyzing the textile product measurement data based on the textile product standard data; including, but generating the textile product result data may provide textile product information corresponding to the textile product standard data when the server extracts the similarity between the textile product measurement data and the textile product standard data, and the similarity is higher than a preset similarity.

In one embodiment of the present invention, in the step of generating the textile product result data, the server determines the image similarity between the standard image information included in the textile product standard data and the measurement image information included in the textile product measurement data. judging; and determining, by the server, the document similarity between the standard document information included in the textile product standard data and the measurement document information included in the textile product measurement data; including, wherein the image similarity and the document similarity are each 80% In this case, it is determined that the textile product standard data and the textile product measurement data are the same, and the textile product result data can be generated.

In one embodiment of the present invention, the user terminal generates the textile product measurement data including the measurement image information and the measurement document information of the textile product in a non-contact manner; including; the textile product measurement data The generating may include: acquiring the measurement image information by photographing an image of the textile product; obtaining the measurement document information by irradiating a terahertz wave to the textile product; and generating the textile product measurement data excluding duplicate data by comparing and analyzing the measurement image information and the measurement document information.

In one embodiment of the present invention, the step of obtaining the measurement image information includes receiving image information from the surface of the textile product, and the color, label, size, thickness, fabric characteristics, fabric type, and weaving form of the textile product. , obtaining at least one of the quantity, and obtaining the measurement document information includes simultaneously receiving electromagnetic wave information on terahertz waves transmitted and reflected from the textile product to obtain color, label, size, and thickness of the textile product. , fabric characteristics, fabric type, weaving type, and at least one of quantity may be acquired.

In one embodiment of the present invention, the server uses a deep learning technique to match the textile product and the textile product information based on big data to repeat learning to generate the textile product standard data; The textile product standard data may be updated in real time in response to the textile product result data.

In addition, the non-contact type textile product search service providing system according to another embodiment of the present invention for solving the above-described problems includes the measurement image information and measurement document information obtained from the textile products using the non-contact method. a textile product measurement device for generating textile product measurement data; and a textile product management server that compares and analyzes the textile product measurement data based on the textile product standard data and generates textile product result data corresponding to the textile product measurement data; including, wherein the textile product management server includes the textile product After extracting the image similarity between the measurement image information of the measurement data and the standard image information of the textile product standard data, and after extracting the document similarity between the measurement document information of the textile product measurement data and the standard document information of the textile product standard data , when the image similarity and the document similarity are respectively 80% or more, it is determined that the textile product standard data and the textile product measurement data are the same, and the textile product result data can be generated.

In an embodiment of the present invention, a manager terminal for repeatedly learning the textile product standard data to compare and analyze the textile product measurement data to generate textile product result data corresponding to the textile product measurement data; may further include.

In addition, the program according to an embodiment of the present invention is stored in a computer-readable recording medium so as to perform the non-contact method for providing a textile product search service by being combined with a computer which is hardware.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention, it is possible to provide a textile product analysis result by comparing and analyzing textile products in a non-contact manner using big data based on deep learning.

Effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 is a conceptual diagram for explaining a non-contact type textile product search service providing system.
FIG. 2 is a view for explaining the detailed configuration of the non-contact type textile product search service providing system shown in FIG. 1 .
3 is a view for explaining a method for providing a non-contact textile product search service according to an embodiment of the present invention.
FIG. 4 is a view for explaining the step of generating the textile product measurement data shown in FIG. 3 .
FIG. 5 is a diagram for explaining a step of determining the image similarity among the similarities shown in FIG. 3 .
FIG. 6 is a diagram for explaining a step of determining the document similarity among the similarities shown in FIG. 3 .

Advantages and features of the present invention, and methods for achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

FIG. 1 is a conceptual diagram for explaining a non-contact type textile product search service providing system, and FIG. 2 is a diagram for explaining a detailed configuration of the non-contact type textile product search service providing system shown in FIG. 1 .

1 and 2, the non-contact type textile product search service providing system 1 according to an embodiment of the present invention includes a textile product measurement device 10, a textile product management server 20, and an administrator terminal 30. ) may be included. In this case, the manager terminal 30 may be omitted.

Here, the textile product measuring device 10 , the textile product management server 20 , and the manager terminal 30 may be synchronized in real time using a wireless communication network to transmit and receive data. The wireless communication network may support various long-distance communication methods, for example, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), and Wimax (World Interoperability for Microwave Access: Wimax). ), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA) , HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uplink Packet Access), IEEE 802.16, Long Term Evolution (LTE), LTEA (Long Term Evolution-Advanced), broadband wireless mobile communication service (Wireless Mobile) Broadband Service: Various communication methods such as WMBS), BLE (Bluetooth Low Energy), Zigbee, RF (Radio Frequency), LoRa (Long Range), etc. may be applied, but are not limited thereto, and various well-known wireless communication or mobility A communication method may be applied.

The textile product measuring device 10 may be a terminal for measuring at least one or more textile products 11 in a non-contact manner, but is not limited thereto, and measures various objects or substances such as food, semiconductor equipment, manufacturing equipment, and the like. results can be provided. The textile product measuring device 10 may operate by using an application program or application in the present disclosure, and this application program is downloaded from an external server or textile product management server 20 through wireless communication. can be

The textile product measuring device 10 may include a product measuring unit 100 , a signal transmitting and receiving unit 110 , a display unit 120 , a memory unit 130 , a power supply unit 140 , and a terminal control unit 150 .

The product measurement unit 100 takes an image of the textile product 11 using at least one camera 111 in a non-contact manner to generate measurement image information, and uses at least one camera 111 to generate measurement image information. 11) can generate measurement document information by irradiating terahertz waves.

Specifically, the product measurement unit 100 may acquire image information from the surface of the textile product 11 using a plurality of cameras 111 . At this time, the camera 111 is a CCD camera, CMOS camera, DVR (Digital Video Recorder), NVR (Network Video Recorder), NVS (Network Video Server), infrared camera (Infrared Camera), thermal imaging camera (Thermo-graphic Camera) , but may include, but is not limited to, a photographing device such as a camera equipped with a wide-angle lens or a fish-eye lens effective for waterproof and dust-proof.

In addition, the product measurement unit 100 irradiates the terahertz wave generated using the camera 111 to the textile product 11 disposed on the stage 112 , and the reflected terrazzo transmitted and reflected from the textile product 11 . It is possible to obtain document information including high-resolution images by simultaneously receiving electromagnetic wave information for hertz waves. In this case, the generated terahertz wave may have an intensity and a pulse width that can be transmitted or reflected by being irradiated to the textile product 11 , but is not limited thereto. For example, the product measurement unit 100 may generate and irradiate a terahertz wave composed of an electromagnetic wave having a frequency of 0.1 THz to 10 THz.

According to the embodiment, the product measurement unit 100 may be located in the same measurement space as the chamber (A) in order to minimize the influence of the external environment. That is, in order to increase the transmittance and/or reflectivity of the textile product 11 for terahertz waves, it may be located in a separate measurement space, for example, a chamber, but is not limited thereto. Accordingly, the loss of terahertz waves irradiated to the textile product 11 and the loss of terahertz waves received from the textile product 11 can be maximally reduced to obtain a high-resolution image.

The signal transmitting/receiving unit 110 may transmit textile product measurement data to the textile product management server 20 , and receive textile product result data corresponding to the textile product measurement data from the textile product management server 20 .

Here, the textile product measurement data may include measurement image information and measurement document information. The textile product result data may include textile product information corresponding to the textile product measurement data and product judgment information on the textile product information. The textile product information may include information on the type and product characteristics of the textile product 11 , and the product judgment information may include information on determining the similarity with respect to the textile product 11 . The measurement image information may be at least one image and/or a moving image of 10 seconds or more, and the measurement document information may be text information.

According to an embodiment, when the signal transmission/reception unit 110 receives the textile product standard data from the textile product management server 20 , it transmits the textile product result data corresponding to the textile product measurement data to the textile product management server 20 . can

Here, the textile product standard data may be data generated by repeatedly learning textile product information based on big data using a deep learning technique. In this case, the textile product standard data may be updated in real time in response to the textile product result data.

According to an embodiment, the signal transmitting/receiving unit 110 may receive a feedback signal for the textile product measuring device 10 from the textile product management server 20 .

The display unit 120 is a means for visually and audibly displaying the current operating state of the textile product measuring device 10, and can output symbols, characters, numbers, etc. on the screen according to the operating state. It may include a lamp for outputting, or a speaker for outputting audio.

The memory unit 130 may store data transmitted and received through the signal transmission/reception unit 100 and data supporting various functions of the textile product measuring apparatus 10 .

The memory unit 130 may store a plurality of application programs (or applications) driven by the textile product measurement device 10 , data for the operation of the textile product measurement device 10 , and commands. At least some of these application programs may be downloaded from an external server through wireless communication.

The power supply unit 140 may receive external power and internal power under the control of the terminal control unit 150 to supply power to each component included in the textile product measuring device 10 .

The power supply unit 140 includes a battery (not shown), and can visually check the remaining amount of the battery. The battery can be charged by connecting the USB to 220V commercial power or a laptop computer or computer. In addition, the battery unit uses a 3.7V lithium-ion battery, which is the most economical and efficient secondary battery for mobile phones, so that it can be charged with a mobile phone battery charger. Alternatively, the battery may be a built-in battery or a replaceable battery.

The terminal control unit 150 compares and analyzes the measurement image information and the measurement document information of the textile product 11 obtained from the product measurement unit 100 to generate textile product measurement data excluding duplicate data.

Specifically, the terminal control unit 150 receives image information from the surface of the textile product 11 and selects at least one of color, label, size, thickness, fabric characteristics, fabric type, weaving form, and quantity of the textile product 11 . Information is obtained, and electromagnetic wave information about terahertz waves transmitted and reflected from the textile product 11 is simultaneously received, and the color, label, size, thickness, fabric characteristics, fabric type, weaving form, and quantity of the textile product 11 are received. After obtaining at least one of the information, it is possible to generate optimal textile product measurement data from which overlapping data is deleted by comparing and analyzing the measurement image information and the measurement document information. Here, the terminal control unit 150 may convert the measurement document information formed of a high-resolution image into document data.

In other words, in the image data and document data for the textile product 11 , the terminal control unit 150 may generate optimal textile product measurement data by excluding overlapping data. Accordingly, the textile product measurement data may include high-resolution image data and document data for the textile product 11 .

According to an embodiment, when receiving the textile product standard data, the terminal control unit 150 may generate textile product result data using textile product measurement data obtained based on the textile product standard data. That is, the terminal control unit 150 compares and analyzes the textile product measurement data and the textile product standard data to extract the degree of similarity between each other, and when the similarity is higher than the preset similarity, the textile product measurement data corresponding to the textile product standard data can be generated. have. For example, in the present embodiment, when the degree of similarity is 80% or more, it is disclosed that it is determined that the textile product standard data and the textile product measurement data are the same, but the present invention is not limited thereto.

According to an embodiment, when receiving a feedback signal from the textile product management server 20 , the terminal controller 150 may control the operation of the textile product measurement device 10 to generate more accurate textile product measurement data. In this case, the feedback signal may be a signal for controlling the operation of the textile product measuring device 10 to be optimized to generate accurate textile product measurement data for the textile product 11 .

According to an embodiment, the terminal control unit 150 may receive the textile product result data from the manager terminal 30 when transmitting the textile product standard data and the textile product measurement data to the manager terminal 30 .

The textile product measuring apparatus 10 having such a structure may generate high-resolution measurement image information and measurement document information for the textile product 11 to generate textile product measurement data.

The textile product management server 20 may include a data communication unit ( ) 200 , a monitoring unit 220 , a database unit 240 , and a management control unit 260 .

The data communication unit 200 may receive the textile product measurement data from the textile product measurement device 10 , and transmit textile product result data corresponding to the textile product measurement data to the textile product management server 20 .

According to an embodiment, the data communication unit 200 may transmit the textile product standard data and/or the feedback signal to the textile product measuring device 10 .

The monitoring unit 220 includes an operation state of the textile product measuring device 10 by user manipulation, an operating state of the textile product management server 20 , and an operation state between the textile product measuring device 10 and the textile product management server 20 . Data transmitted and received can be monitored through the screen. That is, by checking the usage state of the textile product measuring device 10 in real time, the user can use it conveniently and give the user more confidence.

The database unit 240 may store data transmitted/received to and from the textile product measuring device 10 through a wireless communication network. In this case, the textile product standard data may be updated in real time in response to the textile product result data.

The database unit 240 may store data supporting various functions of the textile product management server 20 . The database unit 240 may store a plurality of application programs (or applications) driven by the textile product management server 20 , data for the operation of the textile product management server 20 , and commands. At least some of these application programs may be downloaded from an external server through wireless communication.

According to an embodiment, the textile product measurement data, textile product result data, and textile product standard data used in this embodiment stored in the database unit 240 may be implemented in the form of a mapping table corresponding to each other, but limiting this is not possible. not.

The management and control unit 260 matches textile products and textile product information based on big data to generate textile product standard data by repeating learning, and compares and analyzes textile product measurement data based on the generated textile product standard data to compare and analyze textile products. You can create product result data.

Specifically, the management control unit 260 may generate textile product standard data by repeatedly learning by matching textile products and textile product information using a deep learning technique. Although it has been described as using deep learning in this embodiment, it is not limited thereto, and it is disclosed as using a machine learning technique such as a random forest and a support vector machine, but the deep learning technique is not limited thereto. You can also use

In this case, the management control unit 260 may update the updated textile product standard data in real time in response to the textile product result data.

In addition, the management and control unit 260 compares and analyzes the textile product measurement data and the textile product standard data to extract the degree of similarity between each other, and provides textile product information corresponding to the textile product 11 when the degree of similarity is higher than a preset degree of similarity, When the similarity is lower than the preset similarity, the textile product measurement data is re-analyzed to detect the similarity with the new textile product standard data, and repeated execution is performed until a preset similarity is obtained, thereby generating textile product result data. At this time, for example, in the present embodiment, when the similarity is 80% or more, it is disclosed that it is determined that the textile product standard data and the textile product measurement data are the same, but the present invention is not limited thereto.

Specifically, the management control unit 260 determines the image similarity of the standard image information included in the textile product standard data and the measurement image information included in the textile product measurement data, and when the image similarity is 80% or more, the standard image of the textile product standard data By determining that the information and the measurement image information of the textile product measurement data are the same, textile product result data including textile product information and product judgment information corresponding to the product information 11 can be generated.

In addition, the management control unit 260 determines the document similarity of the standard document information included in the textile product standard data and the measurement document information included in the textile product measurement data, and if the document similarity is 80% or more, the standard document information of the textile product standard data It is determined that the measurement document information of the textile product measurement data is identical to the textile product result data including textile product information and product judgment information corresponding to the product information 11 .

In addition, when the image similarity and the document similarity are 80% or more on average, the management control unit 260 may determine that the textile product standard data and the textile product measurement data are the same and generate textile product result data.

According to an embodiment, the management control unit 260 may receive the textile product result data from the manager terminal 30 when transmitting the textile product standard data and the textile product measurement data to the manager terminal 30 .

According to an embodiment, the management control unit 260 may generate a feedback signal for the textile product measuring device 10 .

Such a textile product management server 20 may be implemented by a hardware circuit (eg, CMOS-based logic circuit), firmware, software, or a combination thereof. For example, it may be implemented using transistors, logic gates, and electronic circuits in the form of various electrical structures.

The manager terminal 30 receives the textile product standard data from the textile product management server 20, receives textile product measurement data from the textile product measurement device 10, and transmits the textile product measurement data based on the textile product standard data. It is possible to create textile product result data by comparison and analysis.

On the other hand, when the textile product result data is generated by the textile product management server 20 , the manager terminal 30 receives the textile product result data from the textile product management server 20 and transmits it to the textile product measurement device 10 . can

Also, the manager terminal 30 may generate a feedback signal for the textile product measurement device 10 and transmit it to the textile product measurement device 10 or the textile product management server 20 .

In addition, when the textile product result data is generated by the textile product measurement device 10 , the controller 360 may receive the textile product result data from the textile product measurement device 10 and transmit it to the textile product management server 20 . .

Also, the manager terminal 30 may transmit the generated textile product result data to the textile product measuring device 10 and the textile product management server 20 .

In addition, the manager terminal 30 may transmit and receive data in synchronization with the textile product measuring device 10 and the textile product management server 20 in real time using a wireless communication network. At this time, the manager terminal 30 may control the operation of the textile product measuring device 10 in the manager terminal 30 using an application program (application program or application), and this application program performs wireless communication It can be downloaded from an external server or the textile product management server 20 through the

In addition, the manager terminal 30 may monitor data transmitted and received between the textile product measuring device 10 , the textile product management server 20 , and the manager terminal 30 through the screen.

In addition, the manager terminal 30 outputs the operating state of the textile product measuring device 10 visually and audibly so that the user can easily check it. Accordingly, since the user can control the textile product measurement apparatus 10 through the manager terminal 30 without directly operating the textile product measurement apparatus 10, the convenience of use can be further improved.

Such a manager terminal 30 may include various portable electronic communication devices that support communication with the textile product measuring device 10 and the textile product management server 20 . For example, as a separate smart device, a smart phone, a personal digital assistant (PDA), a tablet, a wearable device, for example, a watch-type terminal (Smartwatch), a glass-type terminal (including Smart Glass), HMD (Head Mounted Display), etc.) and various Internet of Things (IoT) terminals, but are not limited thereto.

The operation of the method for providing a non-contact textile product search service according to an embodiment of the present invention having such a structure is as follows. FIG. 3 is a diagram for explaining a method for providing a non-contact textile product search service according to an embodiment of the present invention, FIG. 4 is a diagram for explaining a step of generating the textile product measurement data shown in FIG. 3 , and FIG. 5 FIG. 3 is a diagram for explaining the step of determining the image similarity among the similarities shown in FIG. 3 , and FIG. 6 is a diagram for explaining the step of determining the document similarity among the similarities shown in FIG. 3 .

In this embodiment, although it is disclosed that the textile product management server 20 generates textile product standard data and textile product result data, it is not limited thereto.

First, as shown in FIG. 3 , the textile product management server 20 may receive big data on textile product information ( S10 ).

Specifically, the textile product management server 20 may collect information on the type of the textile product 11 and product characteristics of the type. For example, the textile product management server 20 provides information on each fiber for natural fibers and man-made fibers classified into vegetable and animal origin by type, information on fibers classified by use, information on fibers classified by color, and thickness. Information on fibers classified by type, information on fibers classified by weaving type, information on fibers classified by dyeing, and the like can be collected.

Next, the textile product management server 20 may generate textile product standard data by repeating learning by matching textile products and textile product information based on the collected big data (S12).

Next, the textile product measuring device 10 may obtain measurement image information and measurement document information from the textile product 11 (S14).

Next, the textile product measurement apparatus 10 may generate textile submission measurement data using the obtained measurement image information and measurement document information (S16).

Specifically, referring to FIG. 4 , the textile product measuring device 10 may photograph the textile product 11 using the camera 111 ( S100 ).

Next, when the shooting technique is a moving picture (S110), the textile product measuring apparatus 10 may extract at least 10 normal images from the moving picture (S120).

Next, the textile product measuring apparatus 10 pre-processes the extracted normal image through the filtering step (S130), and may generate measurement image information consisting of a high-resolution image (S140).

On the other hand, when the photographing technique is a photograph (S110), the textile product measuring device 10 may acquire a booty image from the surface of the textile product 11 (S150).

Next, the textile product measuring apparatus 10 may pre-process the obtained image (S130), and generate measurement image information consisting of a high-resolution image (S140).

Specifically, the textile product measuring device 10 may automatically adjust the brightness and sharpness of the acquired image in consideration of the surrounding environment, shaking, and the like. In this case, the application used in the image correction method may be an application built into the textile product measuring device 10 , or an application downloaded from an application distribution server and installed in the textile product measuring device 10 .

In the present embodiment, the measurement image information may include at least one image, but is not limited thereto, and may include a moving image of 10 seconds or longer, or both an image and a moving image.

Next, the textile product measuring device 10 may generate a terahertz wave (S160).

At this time, the generated terahertz wave may have an intensity and a pulse width that can be transmitted and reflected by being irradiated to at least one sheet of textile 11, but is not limited thereto. For example, a terahertz wave composed of electromagnetic waves having a frequency of 0.1 THz to 10 THz may be generated.

Next, the textile product measuring device 10 irradiates a terahertz wave to the textile product 11 using at least one camera 111 ( S170 ), and transmits and reflects the terahertz wave from the textile product 11 . electromagnetic wave information can be simultaneously received (S180). That is, the textile product measuring apparatus 10 may acquire an image by the camera 111 moving in the x-axis direction, the y-axis direction, and the z-axis direction through the line scanning system.

At this time, the textile product measuring device 10 includes transmitted and reflected waves from transmitted and reflected terahertz waves in consideration of the thickness of the textile product 11 and the distance between the textile products 11 when there are several textile products 11 . electromagnetic wave information can be detected.

According to the embodiment, the textile product measuring device 10 considers the distance between the textile product 11 and the camera 111 in the chamber A, and electromagnetic wave information including transmitted and reflected waves from transmitted and reflected terahertz waves. can be detected.

Next, the textile product measuring device 10 may generate a high-resolution image using the detected electromagnetic wave information (S190).

Next, the textile product measuring device 10 may convert the high-resolution image into document data (S200), and generate measurement document information (S210).

Next, the textile product measurement apparatus 10 may generate textile product measurement data excluding duplicated data by comparing and analyzing the measurement image information and measurement document information of the textile product 11 ( S220 ).

Specifically, the textile product measuring device 10 receives image information from the surface of the textile product 11, and at least among the color, label, size, thickness, fabric characteristics, fabric type, weaving form, and quantity of the textile product 11 . Obtaining one piece of information and simultaneously receiving electromagnetic wave information on transmitted and reflected terahertz waves from the textile product 11, color, label, size, thickness, fabric characteristics, fabric type, weaving form of the textile product 11 , after obtaining at least one information among the quantity, it is possible to generate optimal textile product measurement data from which duplicate data is deleted by comparing and analyzing the measurement image information and the measurement document information.

Next, the textile product management server 20 matches the textile product measurement data based on the textile product standard data (S18), determines the similarity thereof (S20), and determines the textile product measurement data for the similarity determination result Textile product result data including textile product information corresponding to and product judgment information on textile product information may be generated (S22).

Specifically, the textile product management server 20 extracts the similarity including the image similarity and document similarity between the textile product measurement data and the textile product standard data, and when the similarity is higher than a preset similarity, the textile corresponding to the textile product standard data Product information can be provided. At this time, when the similarity is 80% or more, it is disclosed that it is determined that the textile product standard data and the textile product measurement data are the same, but the present invention is not limited thereto.

For example, referring to FIG. 5 , the textile product management server 20 may analyze measurement image information included in textile product measurement data ( S300 ).

Next, the textile product management server 20 may search for standard image information included in the textile product standard data matching the analyzed measurement image information (S320).

Next, the textile product management server 20 may match the standard image information of the found textile product standard data with the measurement image information of the textile product measurement data (S340) to determine the image similarity (S360).

Next, when the image similarity is 80% or more, the textile product management server 20 determines that the standard image information of the textile product standard data and the measurement image information of the textile product measurement data are the same, and the textile product information corresponding to the product information 11 and textile product result data including product judgment information can be generated (S380).

On the other hand, if the image similarity is lower than the preset similarity, the textile product management server 20 re-analyses the measurement image information of the textile product measurement data to detect the similarity with the standard image information of the new textile product standard data, and the predetermined similarity degree It can be repeated until .

And, referring to FIG. 6 , the textile product management server 20 may analyze measurement document information included in the textile product measurement data ( S500 ).

Next, the textile product management server 20 may search for standard document information included in the textile product standard data matching the analyzed measurement document information (S520).

Next, the textile product management server 20 may match the standard document information of the found textile product standard data with the measurement document information of the textile product measurement data (S540) to determine the document similarity (S560).

Next, the textile product management server 20 determines that the standard document information of the textile product standard data and the measurement document information of the textile product measurement data are the same when the document similarity is 80% or more, and the textile product information corresponding to the product information 11 and textile product result data including product judgment information may be generated (S580).

On the other hand, when the document similarity is lower than the preset similarity, the textile product management server 20 re-analyses the measurement document information of the textile product measurement data to detect the similarity of the new textile product standard data with the standard document information, and the preset similarity degree It is possible to generate the result data of the textile product by repeating it until it comes out.

Next, the textile product measuring device 10 may receive textile product result data from the textile product management server 20 (S24).

Next, the textile product management server 20 may update the textile product standard data in real time by using the textile product result data corresponding to the textile product measurement data received from the textile product measurement device 10 ( S26 ).

Finally, the manager terminal 30 may monitor the textile product measuring device 10 and the textile product management server 20 in real time, and generate a feedback signal according to the monitoring result (S28).

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or this It may reside in any type of computer-readable recording medium well known in the art.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains know that the present invention may be embodied in other specific forms without changing the technical spirit or essential features thereof. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: textile product measuring device
20: Textile product management server
30: administrator terminal

Claims (8)

A method of providing a non-contact textile product search service performed by a server, the method comprising:
receiving, by the server, textile product measurement data from a user terminal; and
Comprising, the server compares and analyzes the textile product measurement data based on the textile product standard data to generate textile product result data corresponding to the textile product measurement data;
The step of generating the textile product result data comprises:
The server extracts the similarity between the textile product measurement data and the textile product standard data, and provides textile product information corresponding to the textile product standard data when the similarity is higher than a preset similarity, a non-contact textile product search service How to provide. The method of claim 1,
The step of generating the textile product result data comprises:
determining, by the server, the image similarity between the standard image information included in the textile product standard data and the measurement image information included in the textile product measurement data; and
determining, by the server, the document similarity between the standard document information included in the textile product standard data and the measurement document information included in the textile product measurement data;
When the image similarity and the document similarity are each 80% or more, it is determined that the textile product standard data and the textile product measurement data are the same, and the textile product result data is generated. 3. The method of claim 2,
generating, by the user terminal, the textile product measurement data including the measurement image information and the measurement document information of the textile product in a non-contact manner;
The step of generating the textile product measurement data,
acquiring the measurement image information by taking an image of the textile product;
obtaining the measurement document information by irradiating the textile product with terahertz waves; and
Comparing and analyzing the measurement image information and the measurement document information to generate the textile product measurement data excluding duplicate data; Containing, a method for providing a non-contact textile product search service. 4. The method of claim 3,
The step of obtaining the measurement image information includes receiving image information from the surface of the textile product to obtain at least one information of color, label, size, thickness, fabric characteristics, fabric type, weaving form, and quantity of the textile product. and obtaining the measurement document information includes simultaneously receiving electromagnetic wave information on terahertz waves transmitted and reflected from the textile product, and the color, label, size, thickness, fabric characteristics, fabric type, and weaving form of the textile product. , a method of providing a non-contact textile product search service for acquiring at least one information among the quantity. The method of claim 1,
The server uses a deep learning technique to repeatedly learn by matching the textile product and the textile product information based on big data to generate the textile product standard data;
The textile product standard data is updated in real time in response to the textile product result data, a method of providing a non-contact textile product search service. a textile product measurement device for generating the textile product measurement data including measurement image information and measurement document information obtained from textile products using a non-contact method; and
A textile product management server that compares and analyzes the textile product measurement data based on the textile product standard data and generates textile product result data corresponding to the textile product measurement data; including,
The textile product management server extracts the image similarity between the measurement image information of the textile product measurement data and the standard image information of the textile product standard data, and the measurement document information of the textile product measurement data and the standard of the textile product standard data After extracting the document similarity with document information, if the image similarity and the document similarity are respectively 80% or more, it is determined that the textile product standard data and the textile product measurement data are the same, and the textile product result data is generated. of textile product search service provision system. According to claim 6,
a manager terminal for repeatedly learning the textile product standard data to compare and analyze the textile product measurement data to generate textile product result data corresponding to the textile product measurement data; Further comprising, a non-contact type textile product search service providing system. A computer program stored in a computer-readable recording medium in combination with a computer, which is hardware, to perform the method of claim 1.

Images