KR102265043B1 - Online and offline integrated brand product big data information provision system - Google Patents

Abstract

The present invention relates to an online and offline integrated brand product big data information provision system, and more specifically, to an online and offline integrated brand product big data information provision system, which promotes the convenience of buyers and sellers by providing information based on artificial intelligence while systematically managing big data-based brand product information to further inspire brand product awareness and product quality to the buyers.

Description

Online and offline integrated brand product big data information provision system

The present invention relates to an online and offline integrated brand product big data information providing system, and more specifically, to systematically manage big data-based brand product information to further enhance brand product awareness and product quality to buyers. It relates to an online and offline integrated brand product big data information providing system to promote convenience for buyers and sellers by providing information based on artificial intelligence

In order to provide online and offline branded products, when a merchant corresponding to a seller registers a branded product to be newly sold, or when a buyer searches for a branded product to purchase online or visits offline, accurate identification information is provided for branded products unless they are experts. In order to select brand products because it is unknown, it is necessary to collect a lot of information individually in order to purchase correctly and at the right price.

However, learning for such information is almost impossible for busy modern people, so technology development is required.

Republic of Korea Patent Application No. 10-2019-0034470 (2019.03.26) "Upload method for farmer's scenario video product information using augmented reality"

The present invention is to solve the above problems, and by systematically managing big data-based brand product information to further inspire brand product awareness and product quality to buyers, while providing information based on artificial intelligence to buyers It is to provide an online and offline integrated brand product big data information providing system for the convenience of and sellers.

In addition, the present invention provides online and offline integrated brand product big data information for preventing accidents on health equipment in advance and strengthening food safety when the brand product is health equipment as the target of the information provided to provide a system.

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

In order to achieve the above object, the online and offline integrated brand product big data information providing system according to an embodiment of the present invention includes a merchant terminal group 100g comprising a plurality of merchant terminals 100, a network 200, and a brand product. In the online and offline integrated brand product big data information providing system 1 including the information providing server 300 and the big data server 400, the brand product information providing server 300 is provided to the affiliated store terminal group 100g. When the registration of each brand product unit information from each included affiliated store terminal 100 is completed, for each brand product unit information, it is analyzed whether it is an offline-only product and an online-only product corresponding to a large category in the brand product category information. Primary information is collected through the secondary information, and if the primary information is an offline-only product, subdivided product classification information including heavy food, large exercise equipment, hazardous chemicals (very toxic petrochemical products), large home appliances, and expensive cosmetics is secondary It can be collected as information, and when the primary information is an online-only product, the subdivided product classification information including small exercise equipment, small and medium-sized home appliances, household appliances, and small and medium-sized cosmetics is used as secondary information for each affiliated store through the network 200. Controls the transceiver 310 to collect according to data transmission and reception with the terminal 100, and through the network 200 for each product name and manufacturing year included in the "brand product unit information" and with each secondary information. Through a request to the data server 400, "composition information" (including food, dangerous chemicals, high-priced and small-to-medium price cosmetics) that corresponds to whether a product contains a composition and "parts information" that corresponds to whether a product includes parts An information generating module 322 that collects primary to tertiary information for each of one brand product by collecting tertiary information corresponding to at least one of "(large and small-sized exercise equipment, including large and small-sized home appliances) ; And the transceiver 310 to transmit the composition image request including the part number of each composition information corresponding to the composition information among the composition information and the part information in the tertiary information to the big data server 400 connected to the network 200 controls the transceiver 310 to receive the "3D rendering image (exterior image of the 3D composition)" corresponding to the part number through the network 200 by controlling the transceiver 310 to receive the part external image information collected for the 3D rendering image, respectively. At least one or more is extracted as "final image information" for a representative image whose shape is matched through a comparison according to a 360° rotation process for each representative image extracted by the big data server 400, but the extracted final image an information generating module 322 that designates the part number of each composition information in the information and stores it in the database 330, and forms information on the composition actually used based on big data through a set of "final image information"; It may be characterized in that it includes.

In this case, the 3D rendering image may be characterized as a representative image registered around one brand product information for each composition provided by the manufacturer terminal 300 operated by the manufacturer of each brand product.

The online and offline integrated brand product big data information providing system according to an embodiment of the present invention systematically manages big data-based brand product information to further enhance brand product awareness and product quality to buyers, while It has the effect of promoting the convenience of buyers and sellers by providing information based on intelligence.

In addition, the online and offline integrated brand product big data information providing system according to another embodiment of the present invention can prevent accidents on fitness equipment in advance when the brand product is health equipment as the target of the information provided, There is an effect that can also enhance safety.

1 is a diagram illustrating a system 1 for providing online and offline integrated brand product big data information according to an embodiment of the present invention.
2 is a block diagram showing the components of the brand product information providing server 300 of the online and offline integrated brand product big data information providing system 1 according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, detailed description of preferred embodiments of the present invention will be described with reference to the accompanying drawings. In the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

In the present specification, when one component 'transmits' data or signal to another component, the component may directly transmit the data or signal to another component, and through at least one other component This means that data or signals can be transmitted to other components.

1 is a diagram illustrating a system 1 for providing online and offline integrated brand product big data information according to an embodiment of the present invention. Referring to FIG. 1 , the online and offline integrated brand product big data information providing system 1 includes a franchise terminal group 100g including a plurality of affiliated store terminals 100 , a network 200 , and a brand product information providing server 300 . , Big data server 400, SNS server 500, and a buyer terminal group (600g) consisting of a plurality of purchaser terminals (600), and a manufacturer terminal group (700g) consisting of a plurality of manufacturer terminals (700). can

2 is a block diagram showing the components of the brand product information providing server 300 of the online and offline integrated brand product big data information providing system 1 according to an embodiment of the present invention. 2, the brand product information providing server 300 includes a transceiver 310, a control unit 320, and a database 330, and the control unit 320 includes an information collection module 321, an information generation module ( 322 ), an information providing module 323 , and an information utilization module 324 may be included.

The information collection module 321 transmits and receives the transceiver 310 to receive from the affiliated store terminal 100 through the network 200 as one encrypted "brand product unit information" including brand product category information, product name and manufacturing year information. can be controlled

Thereafter, the information collection module 321 may store the brand product unit information in the database 330 as metadata of the member ID of the market request terminal 100 .

When the registration of each brand product unit information from each affiliate store terminal 100 included in the affiliate store terminal group 100g is completed, the information generation module 322 is configured for each brand product unit information from the brand product category information to the large category. Primary information is collected through analysis of whether it is an offline-only product or an online-only product, and if the primary information is an offline-only product, heavy food, large exercise equipment, hazardous chemicals (venomous petrochemical products), large home appliances , high-priced cosmetics, etc. can be collected as secondary information, and if the primary information is an online-only product, it is possible to collect product classification information subdivided into small exercise equipment, small and medium-sized appliances, household appliances, and small and medium-priced cosmetics. As secondary information, the transceiver 310 may be controlled to collect data according to data transmission/reception with each affiliated store terminal 100 through the network 200 .

On the other hand, the information generation module 322 generates a composition through a request to the big data server 400 through the network 200 for each product name and manufacturing year included in the "brand product unit information" and with each secondary information. “Composition information” (food, dangerous chemicals, high-priced and small-to-medium-priced cosmetics, etc.) that corresponds to whether a product contains and “parts information” that corresponds to whether a product contains parts (large and small-sized exercise equipment, large and small-sized home appliances) etc.), by collecting the tertiary information corresponding to at least one of the first to tertiary information for each one brand product, respectively.

Meanwhile, hereinafter, the present invention is mainly described as a brand product based on an offline-only product and an online-only product, but may be modified and applied to other brand products, such as online and offline mixed products.

The information generation module 322 is configured to, when parts information is extracted as tertiary information for both the offline-only product and the online-only product among the secondary information, each part of the part information matching each product name and manufacturing year for brand product unit information After requesting the external image information to the big data server 400 through the network 200 , the transceiver 310 may be controlled to receive the part external image information from the big data server 400 .

In addition, when composition information is extracted as tertiary information for both offline-only products and online-only products among secondary information, external image information of each composition of composition information matching each product name and year of manufacture for brand product unit information (composition) After requesting the external image of the composition, or chemical formula in the case of a chemical composition) to the big data server 400 through the network 200, the transceiver 310 is controlled to receive the composition external image information from the big data server 400. can

To this end, it is preferable that the big data server 400 manages the DB divided according to the product name and manufacturing year of each brand product based on artificial intelligence.

To this end, the big data server 400 provides one of the product name, year of manufacture, and part name and composition name of each brand product as metadata by a distributed file program for one of part external image information and composition external image information. DCS DB divided by collecting information through image information that each user provides publicly from various web servers (not shown), SNS server 500, etc., and classifying one of the product name, year of manufacture, and part name and composition name as a category It is possible to analyze the collected data distributed and stored in the machine learning algorithm and issue state management commands. More specifically, the machine learning algorithm used in the big data server 400 may be one of a decision tree (DT) classification algorithm, a random forest classification algorithm, and a support vector machine (SVM) classification algorithm.

The big data server 400 analyzes the collected data distributed and stored in the DCS DB by the distributed file program, extracts a plurality of feature information as a result of the analysis, and uses at least one of a plurality of machine learning algorithms for the extracted feature information As a result of learning and learning, it is possible to determine whether an abnormal state exists on an image, exclude an image corresponding to an abnormal state or not, and provide at least one image having the most characteristic information as a representative image.

That is, the big data server 400 may apply an ensemble structure composed of a plurality of complementary machine learning algorithms to improve the accuracy of the status determination result.

The decision tree classification algorithm is a method of deriving results by learning in a tree structure, which makes it easy to interpret and understand the results, and the data processing speed is fast, and rules can be derived based on the search tree. RF can be applied as a method to improve the low classification accuracy of DT. The random forest classification algorithm is a method of slaughtering the results of learning multiple DTs as an ensemble, and it is difficult to understand the results than DT, but the accuracy of the results may be higher than that of DT. SVM can be applied as a method to improve overfitting that may occur through DT or RF learning. The SVM classification algorithm classifies data belonging to different classifications on a plane-based basis, and generally has high accuracy and may have low sensitivity to structural overfitting.

In addition, the information generation module 322 is a big data server 400 connected to the network 200 for a part image request including a part number of each part information corresponding to part information among each composition information and part information in the tertiary information. It is possible to control the transceiver 310 to transmit the transceiver 310 to receive the “3D rendering image” corresponding to the part number through the network 200 . Here, the 3D rendering image may be a representative image registered around one brand product information for each part provided by the manufacturer terminal 300 operated by the manufacturer of each brand product.

After that, the information generation module 322 is configured to match the shape through a 360° rotation process for each representative image extracted by the big data server 400 among the parts external image information collected for the 3D rendering image, respectively. At least one or more is extracted as "final image information" for the representative image, and 3D coordinate information on the 3D rendering image may be extracted from the extracted final image information.

Also, the information generating module 322 may generate the extracted final image information as a 3D stereoscopic image.

More specifically, the information generating module 322 generates a plurality of decoded images by performing decoding on the final image information, generates a set of polygons, which is a basic unit for expressing in a three-dimensional shape, and then decodes the image 3D final image information corresponding to a 3D stereoscopic image can be generated by performing texture mapping by attaching each on the set of polygons, and 3D coordinates matching the 3D rendering image with respect to the 3D final image information generated on the 3D rendering image It is also desirable to perform the operation of inserting the 3D final image information on the information.

That is, the information generation module 322 performs an edit in which the generated 3D final image information is replaced with coordinate information for a 3D rendering image that changes according to an angle, and then the database 330 for the edited “3D part image information” ), you can set the serial number, product name, and manufacturing year of “brand product unit information” as a plurality of metadata and store it as “3D part image information”, and by performing this process for each coordinate of each 3D part image, Information on actually used parts can be formed based on big data through the set of "3D part image information".

In addition, for the same process, the information generation module 322 may generate information formed mainly on the actual inspection provided by each user based on big data through the set of "3D brand image information" for brand products.

The information providing module 323 not only sets the serial number, product name, and manufacturing year of "brand product unit information" as a plurality of metadata, but also "3D brand image information" and "3D part image information corresponding to the parts attached thereto" Publishing on the online web server operated by the brand product information providing server 300, but according to the selection request according to the access through the network 200 by the purchaser smart terminal 500, each product name and By controlling the transceiver 310 to provide "3D brand image information" and "3D part image information" to the purchaser smart terminal 500 along with "brand product unit information" classified according to the manufacturing year, detailed information is provided to the purchaser By providing an innovative method of providing the smart terminal 500 based on big data, it is possible to provide an effect that can be trusted and purchased for both offline and online products.

In addition, in another embodiment of the present invention, the information generating module 322 is the network 200 for a composition image request including the part number of each composition information corresponding to the composition information among each composition information and part information in the tertiary information. The transceiver 310 controls the transceiver 310 to transmit it to the big data server 400 connected to the transceiver unit 310 to receive the "3D rendering image (exterior image of the 3D composition)" corresponding to the part number through the network 200. can control Here, the 3D rendering image may be a representative image registered around one brand product information for each composition provided by the manufacturer terminal 300 operated by the manufacturer of each brand product.

After that, the information generation module 322 is configured to match the shape through a 360° rotation process for each representative image extracted by the big data server 400 among the parts external image information collected for the 3D rendering image, respectively. At least one of the representative images is extracted as "final image information", but the extracted final image information may be designated as the part number of each composition information and stored in the database 330 .

Through this process, the information generating module 322 may form information about the composition actually used based on big data through a set of "final image information".

Also, for the same process, the information generation module 322 may generate "image information of 3D brand products" based on big data through a set of image information provided by the user for brand products.

The information providing module 323 not only sets the serial number, product name, and year of manufacture of "brand product unit information" as a plurality of metadata, but also sets "image information of 3D brand product" and the "final image corresponding to the composition attached thereto" Information is posted on the online web server operated by the brand product information providing server 300 for "information", but according to a selection request according to access through the network 200 by the purchaser smart terminal 500, each product name By controlling the transceiver 310 to provide "image information of 3D brand product" and "final image information" to the purchaser smart terminal 500 along with "brand product unit information" separated by manufacturing year and "brand product unit information", detailed information By providing an innovative method of providing the buyer smart terminal 500 based on big data, it is possible to provide an effect that can be trusted and purchased for both offline and online products.

The information utilization module 324 includes "3D brand image information" and "3D part image information" along with "brand product unit information" for brand products corresponding to parts information among each composition information and parts information in the tertiary information. When providing to the purchaser smart terminal 500, the change parameters (information about changes that occur over time for each part) generated over time for the parts corresponding to each part number are transferred to the big data server 400 ), after controlling the transceiver 310 to receive through a request for each period (week, month, year unit, seasonal unit, etc.) By controlling the transceiver 310 to transmit the generated image information for each period to the purchaser smart terminal 500 through the network 200 after each generation, for example, corrosion of each part that occurs over time, parts Not only can it be used to realistically experience changes in wear, etc., but it can also be used for A/S applications by providing the state of parts that cannot be directly checked with the naked eye in branded products based on AI.

In addition, the information utilization module 324 includes "image information of 3D brand products" and "final image" along with "brand product unit information" for brand products corresponding to composition information among each composition information and part information in the tertiary information. When providing "information" to the purchaser's smart terminal 500, the change parameters (information about changes occurring over time for each part) and the composition of the composition corresponding to each part number are generated over time. After controlling the transceiver 310 to receive the change parameter at the time of mixing (chemical action DB for each component of the composition) through a request to the big data server 400, in time through the machine learning algorithm for the provided change parameter After generating the image information generated according to each period (week, month, year unit, season unit, etc.), the transceiver unit to transmit the generated image information to the purchaser smart terminal 500 through the network 200 for each period By controlling the 310, for example, it is possible not only to realistically feel changes in oxidation and bubble generation of each composition that occur over time, but also to chemical action of the composition that cannot be directly observed in branded products with the naked eye. By providing it based on AI, it can be used for A/S application within the warranty period.

Here, the machine learning algorithm provided by the big data server 400 may also be one of a decision tree (DT) classification algorithm, a random forest classification algorithm, and a support vector machine (SVM) classification algorithm.

In another embodiment, the big data server 400 extracts a plurality of feature information between two or more parts and two or more compositions to provide each change parameter, and uses the extracted feature information to at least one or more of a plurality of machine learning algorithms. It is possible to derive additional verification result data as a result of learning by using .

That is, the big data server 400 has an ensemble structure composed of a plurality of complementary machine learning algorithms to improve the accuracy of results such as shape, shape, color, etc. for each plurality of change parameter information generated by the machine learning algorithm. can be applied.

After machine learning, the big data server 400 may perform deep learning by using additional verification result data, which is purified data distributed and stored for a plurality of change parameter information. Here, the deep learning method is the cycle time, which is the time required for one entire process during repetitive work to which each landscape parameter information formed by analyzing the change parameters by the big data server 400 is applied, and the maximum time It can be upgraded and performed according to the conversion and application of the program in a way that minimizes the reduction of the tact time.

Accordingly, the present invention can provide the effect of being able to prevent accidents on the fitness equipment in advance, and strengthening the safety of food, especially when the brand product is fitness equipment through the above-described technology.

The present invention can also be implemented as computer-readable codes on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording devices in which data readable by a computer system is stored.

Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., and may also be implemented in the form of a carrier wave (eg, transmission through the Internet). also includes

In addition, the computer-readable recording medium is distributed in a computer system connected through a network, so that the computer-readable code can be stored and executed in a distributed manner. And functional programs, codes, and code segments for implementing the present invention can be easily inferred by programmers in the technical field to which the present invention pertains.

As described above, preferred embodiments of the present invention have been disclosed in the present specification and drawings, and although specific terms are used, these are only used in a general sense to easily explain the technical content of the present invention and help the understanding of the present invention. , it is not intended to limit the scope of the present invention. It will be apparent to those of ordinary skill in the art to which the present invention pertains that other modifications based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein.

1: Online and offline integrated brand product big data information provision system
100: Merchant terminal
100g: Merchant terminal group
200: network
300: brand product information providing server
310: transceiver
320: control unit
321: information collection module
322: information generation module
323: information providing module
324: feedback providing module
330: database
400: big data server
500: SNS server
600: buyer terminal
600g: Buyer terminal group
700: manufacturer terminal
700g: manufacturer terminal group

Claims (2)

An affiliated store terminal group 100g consisting of a plurality of affiliated store terminals 100, a network 200, a brand product information providing server 300, a big data server 400, an SNS server 500, and a plurality of purchaser terminals 600 In the online and offline integrated brand product big data information providing system (1) including a buyer terminal group (600g) consisting of ), and a manufacturer terminal group (700g) consisting of a plurality of manufacturer terminals (700),
The brand product information providing server 300,
It includes a transceiver unit 310, a control unit 320 and a database 330, and the control unit 320 includes an information collection module 321, an information generation module 322, an information provision module 323, and an information utilization module 324. ), including
The information collection module 321,
Controls the transceiver 310 to receive from the affiliated store terminal 100 through the network 200 as one encrypted "brand product unit information" including brand product category information, product name and manufacturing year information, and brand product unit information stores the member ID of the market request terminal 100 as metadata in the database 330,
The information generation module 322,
When the registration of each brand product unit information from each affiliate store terminal 100 included in the affiliate store terminal group 100g is completed, for each brand product unit information, an offline-only product corresponding to a large category in the brand product category information and online Primary information is collected through analysis of whether the product is an exclusive product, and if the primary information is an offline-only product, it includes heavy food, large exercise equipment, hazardous chemicals (including highly toxic petrochemical products), large home appliances, and expensive cosmetics. The subdivided product classification information can be collected as secondary information, and if the primary information is an online-only product, the segmented product classification information, including small exercise equipment, small and medium-sized appliances, household appliances, and small and medium-sized cosmetics, is used as secondary information. Controls the transceiver 310 to collect data according to data transmission and reception with each affiliated store terminal 100 through the network 200,
With each secondary information and through a request to the big data server 400 through the network 200 for each product name and manufacturing year included in the "brand product unit information", the "composition corresponding to whether the product contains the composition" 3 that corresponds to at least one of “information” (including food, hazardous chemicals, high-priced and small-to-medium-priced cosmetics) and “parts information” (including large and small-sized sports equipment, large and small-sized household appliances) that corresponds to whether a product contains parts By collecting primary information, primary to tertiary information is collected for each of one brand product,
Among the secondary information, when parts information is extracted as tertiary information for both offline-only products and online-only products, network (200) network (200) ), after making a request to the big data server 400, controls the transceiver 310 to receive external image information of parts from the big data server 400,
When composition information is extracted as tertiary information for both offline-only products and online-only products among secondary information, external image information of each composition of composition information matching each product name and manufacturing year for brand product unit information (appearance of composition) After requesting an image or chemical formula in the case of a chemical composition) to the big data server 400 through the network 200, the transceiver 310 is controlled to receive the composition external image information from the big data server 400,
In the tertiary information, the transceiver 310 is sent to the big data server 400 connected to the network 200 for a part image request including the part number of each part information corresponding to the part information among each composition information and part information. Controls the transceiver 310 to receive the "3D rendering image" corresponding to the part number through the network 200, and the 3D rendering image is provided by the manufacturer terminal 300 operated by the manufacturer of each brand product. For each part, we use the registered representative image centered on one brand product information,
"Final image information" for a representative image whose shape is matched through a comparison according to a 360° rotation process for each representative image extracted by the big data server 400 among the external image information of parts collected for each 3D rendering image extracting at least one or more, extracting 3D coordinate information on a 3D rendering image from the extracted final image information, and generating the extracted final image information as a 3D stereoscopic image,
Decoding is performed on the final image information to generate a plurality of decoded images, a set of polygons, which are basic units for expressing a three-dimensional shape, are generated, and texture mapping is performed by attaching each decoded image on the set of polygons. 3D final image information corresponding to a 3D stereoscopic image can be generated by performing the 3D final image information generated on the 3D rendering image, and the 3D final image information is inserted into the 3D coordinate information matching the 3D rendering image. Also, after editing is performed by replacing the generated 3D final image information with the coordinate information for the 3D rendering image that changes according to the angle, the edited “3D part image information” is listed on the database 330 as “brand By performing the process of setting the serial number, product name, and manufacturing year of “product unit information” as a plurality of metadata and saving it as “3D part image information” for each coordinate of each 3D part image, information on the actually used parts is stored. It is formed based on big data through the set of "3D part image information", and for brand products, information formed mainly on the actual action provided by each user is generated based on big data through the set of "3D brand image information". ,
Information providing module 323,
In addition to setting the serial number, product name, and manufacturing year of “brand product unit information” as multiple metadata, the brand product information providing server ( 300) is posted on the online web server operated by the company, but according to the selection request according to the access through the network 200 by the purchaser smart terminal 500, the "branded products" classified according to each product name and year of manufacture Controls the transceiver 310 to provide "3D brand image information" and "3D part image information" to the purchaser smart terminal 500 along with "unit information",
The information generation module 322,
In the tertiary information, the transceiver 310 transmits the composition image request including the part number of each composition information corresponding to the composition information among the composition information and the part information to the big data server 400 connected to the network 200. Controls the transceiver 310 to receive the "3D rendering image (exterior image of the 3D composition)" corresponding to the part number through the network 200 by controlling, and the 3D rendering image is a manufacturer operated by the manufacturer of each brand product. For each composition provided by the terminal 300, a representative image registered around one brand product information is used,
"Final image information" for a representative image whose shape is matched through a comparison according to a 360° rotation process for each representative image extracted by the big data server 400 among the external image information of parts collected for each 3D rendering image By extracting at least one or more with the, but storing in the database 330 by specifying the part number of each composition information in the extracted final image information, information about the actually used composition is stored in the database 330 through a set of "final image information". It is formed based on data, and for brand products, “image information of 3D brand products” is created based on big data through the set of image information provided by users.
Information providing module 323,
In addition to setting the serial number, product name, and manufacturing year of “brand product unit information” as multiple metadata, it also provides brand product information about “image information of 3D brand products” and “final image information” corresponding to the composition attached thereto. Posting is performed on the online web server operated by the server 300, but according to the selection request according to the access through the network 200 by the purchaser smart terminal 500, " Controls the transceiver 310 to provide "image information of 3D brand product" and "final image information" to the purchaser smart terminal 500 together with "brand product unit information",
The information utilization module 324,
For brand products corresponding to parts information among each composition information and parts information in the tertiary information, "3D brand image information" and "3D parts image information" along with "brand product unit information" are provided to the buyer's smart terminal (500) When provided as , change parameters generated over time for parts corresponding to each part number (including information about changes over time for each part) through a request to the big data server 400 After controlling the transceiver 310 to receive, image information generated over time through a machine learning algorithm for the provided change parameters is generated for each period (including weekly, monthly, yearly, and seasonal units), and then generated By controlling the transceiver 310 to transmit the image information to the purchaser smart terminal 500 through the network 200 for each period, in reality, changes in corrosion of each part and wear of parts that occur over time Not only can it be felt realistically, but also the state of parts that cannot be directly checked with the naked eye in branded products is provided based on AI, so that it can be used for A/S applications,
For brand products corresponding to composition information among each composition information and parts information in the tertiary information, "image information of 3D brand products" and "final image information" along with "brand product unit information" are provided to the purchaser's smart terminal (500). When provided as , change parameters generated over time for the composition corresponding to each part number (including information on changes over time for each part) and change parameters when mixing each composition (composition of the composition) After controlling the transceiver 310 to receive the parameter extracted from the chemical action DB for each component through a request to the big data server 400, an image generated over time through a machine learning algorithm for the provided change parameter After generating information for each period (including weekly, monthly, yearly, and seasonal units), the transceiver 310 transmits the generated image information to the purchaser smart terminal 500 through the network 200 for each period. By controlling, not only can you realistically feel the changes including oxidation and bubble generation of each composition that occur over time, but also the chemical action of the composition that cannot be directly checked with the naked eye in branded products based on AI. An online and offline integrated brand product big data information providing system that can be used for A/S applications within the warranty period by providing it.
delete

Images