KR102284165B1 - Method for providing product information, server for provding product information and system for providing product information - Google Patents

Abstract

Receive a plurality of product information including unit information of a product name and at least one product attribute from at least one terminal, and parse a unit of a product name and product attribute from the received plurality of product information, and the parsed product name and at least one Build a database about products based on the unit of product attributes, analyze the units parsed from a plurality of product information based on the frequency, or train the AI model using the training data, and the analyzed units or the learned AI model Determining a representative unit of at least one product attribute based on , receiving a product information search request from at least one terminal, A method for providing product information in a server is disclosed, which includes converting to a representative unit and transmitting a response to a product information search request including a plurality of company product information based on the converted representative unit.

Description

Product information provision method, product information provision server and product information provision system

It relates to a method for providing product information, a server for providing product information, and a system for providing product information. In detail, it relates to a product information providing method, a product information providing server, and a product information providing system for receiving product information so that product consumers can easily understand and compare product information of various companies.

In order to promote their products, each company created information about the product they wanted to upload in various forms and uploaded it to the product information providing server.

However, when interested product consumers search for product information of various companies through the product information providing server, they are provided with information of each company's products in various uploaded formats. There was a problem in that it was difficult to easily understand the information of the manufactured products, and it was difficult to compare them with each other. In particular, when the units of product attributes are uploaded differently from each other, it is difficult for a product consumer to easily understand the attributes of the product and it is difficult to compare them with each other.

According to various embodiments, the product information providing server analyzes the product information provided from the user terminal or uses it as learning data of the product through artificial intelligence (hereinafter referred to as 'AI') model training. By determining the representative unit of the attribute and unifying the unit of product attribute as the representative unit and providing it to the user terminal, users (product consumers) can easily understand the attributes of products of various companies and make comparisons between products easy. This allows users to choose the product they want.

In addition, according to various embodiments, when the product information providing server receives a change request for the display unit of the unit of product attribute from the user terminal, the unit of product attribute is unified into the display unit included in the change request and provided to the user terminal By doing so, it is possible to easily understand the properties of products of various companies based on the display unit desired by the product consumer, and to facilitate comparison between products, so that the product consumer can select the desired product.

In addition, according to various embodiments, the product information providing server analyzes the product information provided from the user terminal and the product name included in the product information search request, or determines a product search keyword candidate through AI model learning using this as training data, , by constructing a database for products corresponding to product search keyword candidates, when a product consumer searches for a product, even if the product name is input in various forms, product information corresponding to the product information can be properly provided.

In addition, according to various embodiments, the product information providing server analyzes product information provided from the user terminal or determines a representative test method of product attributes through AI model learning using this as learning data, and responds to the representative test method By providing product information so that the product information to be displayed in the user terminal can be preferentially displayed in the user terminal, product consumers can easily understand the properties of products of various companies measured by the same product test method and facilitate comparison between products. This allows consumers to choose the product they want.

In addition, according to various embodiments, when the product information providing server receives a selection request for a product attribute test method from a user terminal, it preferentially displays product information corresponding to the product attribute test method included in the selection request or , by providing product information to the user terminal so that it can be displayed exclusively, the product consumer can easily understand the properties of various companies' products measured by the product test method desired by the product consumer, and also facilitate comparison between products. You can choose the product you want.

Of course, the technical problems of the various embodiments are not limited to the above-mentioned features, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

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

A method for providing product information according to various embodiments of the present disclosure includes: receiving a plurality of product information including a product name and unit information of at least one product attribute from at least one terminal; parsing a unit of product name and product attribute from the received plurality of product information; building a product database based on the parsed product name and units of at least one product attribute; Analyzing units parsed from a plurality of product information based on the frequency, or learning an AI model as training data, and determining a representative unit of at least one product attribute based on the analyzed units or the learned AI model ; Receiving a product information search request from at least one terminal; and converting a unit of at least one product attribute included in the information of a plurality of company products in the database about the product into a representative unit, and for a product information search request including a plurality of company product information based on the converted representative unit sending a response.

A method of providing product information according to various embodiments of the present disclosure includes: receiving a change request for a display unit of the at least one product attribute from the at least one terminal; and converting the unit of at least one product attribute included in information of a plurality of corporate products in the database about the product from the at least one terminal into a display unit included in the change request, and a plurality of units based on the converted display unit. The method may further include transmitting a response to the change request including corporate product information.

The product information providing method according to various embodiments analyzes a plurality of product information and a product name included in a product information search request, or learns an AI model using the training data, and based on the analyzed plurality of product information or the learned AI model The method may further include determining at least one product search keyword candidate corresponding to the raw product.

The step of constructing the product database based on the parsed product name and the unit of at least one product attribute may include building a product database corresponding to the at least one product search keyword candidate.

Transmitting a response to the product information search request comprises:

determining a product corresponding to a product keyword included in the product information search request based on the at least one product search keyword candidate; and

Product information including a plurality of corporate product information based on the converted representative unit by converting a unit of at least one product attribute included in the information of a plurality of corporate products in the database regarding the product corresponding to the product keyword into a representative unit It may include transmitting a response to the search request.

The plurality of product information includes information about a product test method,

Parsing the product name and the unit corresponding to the product comprises:

Parsing the product name, a unit corresponding to the product, and a product test method,

Analyze the product test methods parsed from the plurality of product information, or train an AI model as training data, classify at least one product test method based on the analyzed test methods or the learned AI model, and the Further comprising the step of determining a representative product testing method among the at least one product testing method,

Transmitting a response to the product information search request comprises:

and transmitting a response to a product information search request including information on the representative product test method among the at least one product test method.

The at least one terminal may receive a response to the product information search request, and preferentially display corporate product information of a company corresponding to the representative product test method based on the received information on the representative product test method. .

Transmitting a response to the product information search request including information on the representative product test method comprises:

Transmitting a response to a product information search request including the plurality of company product information based on the classified at least one product test method,

The at least one terminal receives a user input for selecting one product test method from among the classified at least one product test method,

Based on the received user input, the company product information corresponding to one product test method is preferentially displayed, or the company product information other than the company product information of the company corresponding to one product test method is not displayed. , may display corporate product information of the company corresponding to the one product test method. The response to the information search request may include download link information of classified data of at least one product test method.

Product information providing server according to various embodiments,

at least one processor, wherein the at least one processor receives a plurality of product information including a product name and at least one product attribute unit information from at least one terminal, and a product name from the received plurality of product information and parsing the unit of product attribute, building a database about the product based on the parsed product name and the unit of at least one product attribute, and analyzing the parsed units from a plurality of product information based on frequency, or learning data to learn the AI model, determine the representative unit of at least one product attribute based on the analyzed units or the learned AI model, receive a product information search request from at least one terminal, and a database about the product It is possible to convert a unit of at least one product attribute included in the information of a plurality of corporate products to a representative unit, and transmit a response to a product information search request including a plurality of corporate product information based on the converted representative unit.

A product information providing system according to various embodiments may include a server providing product information; and

At least one terminal receiving the product information,

The at least one user terminal transmits a plurality of product information including a product name and unit information of at least one product attribute,

The server receives the plurality of product information from the at least one terminal,

Parsing a product name and a unit corresponding to the product from the received plurality of product information,

Build a database about products based on the parsed product name and units of at least one product attribute,

Analyze units parsed from a plurality of product information based on the frequency, or train an AI model as training data, and determine a representative unit of at least one product attribute based on the analyzed units or the learned AI model,

The at least one terminal transmits a product information search request,

The server receives a product information search request from the at least one terminal,

The server converts the unit of at least one product attribute included in the information of a plurality of corporate products in the database about the product into a representative unit, and a product information search request including a plurality of corporate product information based on the converted representative unit You can send a response to

It may include a computer-readable recording medium in which a program for implementing the method according to various embodiments is recorded.

FIG. 1 is a diagram illustrating a process in which a server determines a representative unit of a product attribute through big data analysis or AI model learning for product information in order to provide product information, according to various embodiments of the present disclosure.
2 is a view for explaining providing product information to a user terminal in consideration of user convenience, such as unifying the unit of product attribute into a representative unit after the server determines the representative unit of product attribute, etc., according to various embodiments; show
3 is a block diagram illustrating a product information providing server according to various embodiments.
4 is a flowchart illustrating a method of providing product information according to various embodiments of the present disclosure;
5 is a server receives product information from a user terminal to determine a representative unit of a database construction and product attributes related to a product, and when receiving a product information search request from a user terminal, the unit of product attributes in the database according to an embodiment Converts to a representative unit, transmits a plurality of company product information based on the converted representative unit to a user terminal, and is a diagram for explaining a process of displaying a plurality of company product information on the user terminal.
6 is a diagram for explaining a process in which a company requests a server to upload product information using a terminal.
7 is a diagram for explaining a database related to a product built in a server according to an embodiment.
8 is a diagram for explaining a process in which a product consumer transmits a product search request using a user terminal and displays desired search results to the product consumer on the user terminal based on various user inputs.

Terms such as “…unit” described in the specification mean a unit for processing at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.

Terms used in this document are only used to describe specific embodiments, and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, may have the same meanings as commonly understood by one of ordinary skill in the art described in this document. Among the terms used in this document, terms defined in a general dictionary may be interpreted with the same or similar meaning as the meaning in the context of the related art, and unless explicitly defined in this document, have an ideal or excessively formal meaning. not interpreted In some cases, even terms defined in this document cannot be construed to exclude embodiments of this document.

Functions related to artificial intelligence according to the present disclosure are operated through a processor and a memory. The processor may consist of one or a plurality of processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a digital signal processor (DSP), or the like, a graphics-only processor such as a GPU, or an artificial intelligence-only processor such as an NPU. One or more processors control to process input data according to the AI model stored in the memory. Alternatively, when one or a plurality of processors are AI-only processors, the AI-only processor may be designed with a hardware structure specialized for processing a specific AI model. AI models are characterized by being created through learning. Here, being made through learning means that an artificial intelligence model set to perform a desired characteristic (or purpose) is created by learning a basic artificial intelligence model using a plurality of learning data by a learning algorithm. Such learning may be performed in the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and/or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

The artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and a neural network operation is performed through an operation between an operation result of a previous layer and a plurality of weight values. The plurality of weights of the plurality of neural network layers may be optimized by the learning result of the artificial intelligence model. For example, a plurality of weights may be updated so that a loss value or a cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a deep neural network (DNN), for example, a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a Restricted Boltzmann Machine (RBM), There may be a Deep Belief Network (DBN), a Bidirectional Recurrent Deep Neural Network (BRDNN), or a Deep Q-Networks, but is not limited to the above-described example.

Big data analysis according to the present disclosure is a technique of extracting valuable information to perform a desired characteristic (or purpose) from data including a large amount of structured or even unstructured data sets that are not in the form of a database, and analyzing the extracted information am.

FIG. 1 is a diagram illustrating a process in which a server determines a representative unit of a product attribute through big data analysis or AI model learning for product information in order to provide product information, according to various embodiments of the present disclosure.

Referring to FIG. 1 , in step S105 , the server 100 may receive a product information upload request or a product information search request from at least one user terminal 150 . For example, a company that wants to promote a product may transmit a product information upload request to the server 100 by using the user terminal 150 for product promotion. In addition, a product consumer who wants to purchase a product may transmit a product information search request to the server 100 by using the user terminal 150 to purchase the product.

In step S110, the server 100 learns an AI model by using big data analysis or product information for product information included in the product information upload request or product information search request as learning data, and big data analyzed product information or learning The representative unit of product attributes can be determined based on the AI model.

For example, the server 100 analyzes the units of at least one product attribute included in the product information upload requests based on the frequency, or learns the AI model by using the units of at least one product attribute as training data, A representative unit of at least one product attribute may be determined based on the analyzed unit or the learned AI model.

Alternatively, the server 100 analyzes the test methods of at least one attribute included in the product information upload requests, or at least one attribute of the at least one attribute based on the learned AI model using the test methods of the at least one attribute as training data. Classify product testing methods and determine representative product testing methods. In this case, a product database may be built based on the classified product test method.

Alternatively, the server 100 analyzes the product names included in the product information upload request and the product names included in the product information search request, or learns the AI model using the product names as learning data, and the analyzed product names or the learned AI model At least one product search keyword candidate corresponding to the product may be determined based on the . For example, if the product is chlorinated polyethylene (CPE) 135A, the product keyword input through the user terminal 150 may be CPE-135A, CPE 135A, CPE 135 A, CPE135A, CPE_135A, and the like. Analyze various product keywords input through the user terminal 150, or use this as learning data to learn an AI model, and based on the learned AI model, product search keyword candidates corresponding to chlorinated polyethylene (CPE) 135A can be decided For example, candidate product search keywords corresponding to chlorinated polyethylene (CPE) 135A might be CPE-135A, CPE 135A, CPE 135 A, CPE135A, CPE 135-A, CPE-135-A, CPE_135A, and CPE_135_A. there is. That is, a user's product search keyword input pattern is analyzed by big data based on the collected product information upload request data or product search request data to determine various product search keyword candidates, or to analyze product information upload request data or product search request data. Various product search keyword candidates can be determined based on the trained AI model as the training data. That is, positions for inputting spaces for each user may vary, and positions of special symbols such as hyphens may also vary. In this case, by analyzing the input data, it is possible to determine various product search keyword candidates in consideration of the user's input form. The server 100 builds a database of products corresponding to various product search keyword candidates, and when a user makes a product information search request with one product search keyword among various product search keyword candidates using the user terminal 150, Product information corresponding to the product search keyword may be provided. At this time, since the server 100 knows the correspondence between the product search keyword candidate and the product, it does not simply search for information on the same product as the product search keyword, but searches all product information according to various product search keyword candidates. Therefore, product information for all possible product search keyword candidates for one product may be provided. Accordingly, even if the user inputs the product search keyword without worrying about it, information on the corresponding product can be accurately provided.

2 is a view for explaining providing product information to a user terminal in consideration of user convenience, such as unifying the unit of product attribute into a representative unit after the server determines the representative unit of product attribute, etc., according to various embodiments; show

Referring to FIG. 2 , in step S205 , the user terminal 250 may transmit a product information search request to the server 100 .

In step S210 , the server 200 may convert a unit of at least one attribute of a product included in product information of a plurality of companies into a representative unit in response to the product information search request of the user terminal 250 . That is, the server 200 builds a database corresponding to the product based on the product information upload requests, and at this time, does not store the unit in a unified way, but considers the unit included in the product information upload request. You can build a database. Accordingly, the server 200 may convert a unit of at least one attribute of a product included in product information of a plurality of companies in a database corresponding to the product into a representative unit. The correspondence between the units of the attribute and the representative unit may be predefined, and the server 200 may convert the unit of at least one attribute of the product into the representative unit based on the correspondence between the units. In this case, the correspondence may be expressed in the form of a table and stored in the server 200 .

However, the server 200 is not limited thereto, and may construct a new database by converting the unit of at least one attribute into a representative unit. In this case, the server 200 may provide product information of a plurality of companies in which the unit of at least one attribute of the product is a representative unit to the user terminal 250 in response to the product information search request.

In step S215 , the server 200 may provide a plurality of pieces of product information in which at least one attribute unit is converted into a representative unit to the user terminal 250 .

In step S220 , the user terminal 250 may display a plurality of product information by unifying the unit of at least one attribute of the product as a representative unit.

3 is a block diagram illustrating a product information providing server according to various embodiments.

Referring to FIG. 3 , the product information providing server 300 according to various embodiments includes a control unit 310 , a communication unit 320 , and a database storage unit 330 . However, not all illustrated components are essential components. The product information providing server 300 may be implemented by more components than the illustrated components, and the product information providing server 300 may be implemented by fewer components.

The control unit 310 controls the communication unit 320 as a whole. In addition, the control unit 310 may control the database storage unit 330 as a whole. In addition, the control unit 310 may control various components as a whole.

The control unit 310 may be implemented by a processor. The processor is a dedicated processor (eg, an embedded processor) for performing an operation, or a generic-purpose processor (eg, a CPU or an application processor), and may include one or more of a communication processor (CP). For example, the processor may include operation or data related to at least one control and/or communication of the product information providing server 300 . processing can be executed.

The processor may generally control various components by executing at least one program stored in a memory or a database of an intermediary server. The processor may perform a function or operation of the product information providing server 300 by executing at least one program stored in a memory or a database of an intermediary server. In this case, the memory is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg, SD or XD memory, etc.), RAM ( RAM, Random Access Memory, SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, It may include at least one type of storage medium among optical disks.

The control unit 310 may include a representative unit determining unit 315 .

The controller 310 may control the communication unit 320 to receive a plurality of product information including a product name and unit information of at least one product attribute from at least one terminal.

The controller 310 may parse the unit of the product name and product attribute from the received plurality of product information. The control unit 310 may control the database storage unit 330 to build a database about products based on the parsed product name and units of at least one product attribute.

The controller 310 may additionally parse the product name and the unit of product attribute corresponding to the product, as well as the product test method for the product attribute. Here, the product testing method for product properties may be based on standards prescribed by various countries, national associations, or international standardization organizations. For example, product testing methods for product properties may be based on ISO, ASTM, DIN, JIS, KS and EN standards.

The control unit 310 analyzes product test methods parsed from a plurality of product information, or learns an AI model as training data, and at least one product test method based on the analyzed product test methods or the learned AI model. classify and determine a representative product testing method among at least one product testing method.

The controller 310 may transmit a response to a product information search request including information on a representative product test method among at least one product test method.

The at least one terminal may receive a response to the product information search request, and may preferentially display corporate product information of a company corresponding to the representative product test method based on the received information on the representative product test method.

The control unit 310 may control the communication unit 320 to transmit a response to a product information search request including a plurality of company product information based on the classified at least one product test method. The response to the information retrieval request may include download link information of the classified at least one product test method material.

The at least one terminal receives a user input for selecting a partial product test method from among the classified at least one product test method, and preferentially displays corporate product information of the company corresponding to the partial product test method based on the received user input Alternatively, the company's product information corresponding to some product test methods may be displayed without displaying the remaining company product information except for the company's company product information corresponding to some product test methods.

The representative unit determining unit 315 analyzes the units of at least one product attribute parsed from a plurality of product information based on the frequency, or learns the AI model as training data, and selects the analyzed units or the learned AI model. A representative unit of at least one product attribute may be determined on the basis.

The controller 310 may control the communication unit 320 to receive a product information search request from at least one terminal. The control unit 310 may convert the unit of at least one product attribute included in information on a plurality of company products in the product database into a representative unit. The control unit 310 may control the communication unit 320 to transmit a response to a product information search request including a plurality of company product information based on the converted representative unit.

The control unit 310 may control the communication unit 320 to receive a change request of a display unit for at least one product attribute from at least one terminal.

The control unit 310 may convert the unit of at least one product attribute included in information on a plurality of corporate products in the database about products from at least one terminal into a display unit included in the change request. The control unit 310 may transmit a response to the change request including a plurality of company product information based on the converted display unit.

The control unit 310 analyzes a plurality of product information and a product name included in a product information search request, or learns an AI model as learning data, and corresponds to a product based on the analyzed plurality of product information or the learned AI model. At least one product search keyword candidate may be determined.

The control unit 310 may control the database storage unit 330 to build a database about products corresponding to at least one product search keyword candidate.

The controller 310 may determine a product corresponding to a product keyword included in the product information search request based on at least one product search keyword candidate.

The control unit 310 converts the unit of at least one product attribute included in the information of a plurality of corporate products in the database regarding the product corresponding to the product keyword into a representative unit, and converts a plurality of corporate product information based on the converted representative unit. It is possible to transmit a response to a request for retrieval of product information including.

The communication unit 320 may transmit data to or receive data from an external device.

The communication unit 320 may receive a plurality of product information including a product name and unit information of at least one product attribute from at least one terminal.

The communication unit 320 may receive a product information search request from at least one terminal. When the unit of at least one product attribute included in the plurality of corporate products in the product-related database is converted, the communication unit 320 responds to a product information search request including a plurality of corporate product information based on the converted representative unit. It can be transmitted to at least one terminal.

The communication unit 320 may receive a change request for the display unit of at least one product attribute from at least one terminal.

When the communication unit 320 converts the unit of at least one product attribute included in the information of a plurality of company products in the database about the product from at least one terminal to the display unit included in the change request, A response to the change request including a plurality of company product information based on the converted display unit may be transmitted to at least one terminal.

The communication unit 320 may transmit a response to a product information search request including information on a representative product test method among at least one product test method to at least one terminal.

The communication unit 320 may transmit a response to the product information search request including a plurality of company product information based on the classified at least one product test method.

The database storage unit 330 may store a database related to a product built based on a product name, a unit of at least one product attribute, and a value of the product attribute.

The database storage unit 330 may store various information related to operations or functions of various components other than the control unit 310 and the communication unit 320 .

The database storage unit 330 may be included in the product information providing server 300 , but is not limited thereto, and may be included in an external device connected to the product information providing server 300 through various networks. Alternatively, some information may be stored in the database storage unit 330 , and the remaining information may be stored in a database storage unit included in an external device. When information stored in the database storage unit included in the external device is required, the product information providing server 300 transmits a request for providing necessary information to the external device, and may receive the necessary information from the external device in response to the provision request. there is.

4 is a flowchart illustrating a method of providing product information according to various embodiments of the present disclosure;

Referring to FIG. 4 , in step S405 , the product information providing server 300 may receive a plurality of product information including a product name and unit information of at least one product attribute from at least one terminal.

In step S410 , the product information providing server 300 may parse a product name and a unit corresponding to the product from the received plurality of product information.

In step S415, the product information providing server 300 may build a database about the product based on the unit of the product name and at least one product attribute.

In step S420, the product information providing server 300 analyzes the units parsed from a plurality of product information based on the frequency, or learns the AI model as training data, and based on the analyzed units or the learned AI model A representative unit of at least one product attribute may be determined.

In step S430 , the product information providing server 300 may receive a product information search request from at least one terminal.

In step S440, the product information providing server 300 converts the unit of at least one product attribute included in the information of the plurality of corporate products in the product-related database into a representative unit, and a plurality of corporate products based on the converted representative unit. A response to the product information search request including the information may be transmitted to at least one terminal.

5 is a server receives product information from a user terminal to determine a representative unit of a database construction and product attributes related to a product, and when receiving a product information search request from a user terminal, the unit of product attributes in the database according to an embodiment Converts to a representative unit, transmits a plurality of company product information based on the converted representative unit to a user terminal, and is a diagram for explaining a process of displaying a plurality of company product information on the user terminal.

Referring to FIG. 5 , in operation S505 , product information including a product name and unit information of at least one product attribute may be transmitted to the server 510 from at least one of the user terminals 505 . The server 510 may receive a plurality of pieces of product information from at least one user terminal among the user terminals 505 in order to determine the representative unit of the product attribute. In this case, the product information may be information about an upload request for registering the product in the server.

In step S510 , the server 510 may parse the unit of the product name and product attribute from the received product information. Additionally, the server 510 may parse information about a test method of product attributes from the received product information. Also, the server 510 may parse the value of the product attribute from the received product.

In step S515 , the server 510 may build a product database based on the parsed product name, product attribute unit, and product attribute value. Additionally, the server 510 may build a product-related database further based on the parsed information on the test method of product attributes.

In step S520, the server 510 may determine a representative unit of the product attribute. For example, the server 510 analyzes units parsed from a plurality of product information based on the frequency, or learns an AI model using the training data, and at least one or more units based on the analyzed units or the learned AI model. A representative unit of product attributes can be determined.

In step S525 , one of the user terminals 505 may transmit a product information search request to the server 510 .

In step S530 , the server 510 may convert the unit of product attribute into a representative unit in response to the received product information search request.

In step S535 , the server 510 may transmit a response to the product information search request including a plurality of company product information based on the converted representative unit to the user terminal 505 .

In step S540, the user terminal 505 may receive a response to the search request, and display company product information based on the received response.

6 is a diagram for explaining a process in which a company requests a server to upload product information using a terminal.

Referring to FIG. 6 , the company uses a terminal to request the upload of product information to the server, and the product name, attribute, attribute value, attribute unit and attribute test (measure) method for their product in the product description field 610 etc. can be entered according to the input method recommended by the server. That is, the server may parse the product name, attribute, attribute value, attribute unit, and test method from the content of the input product description field 610 according to a predetermined parsing rule.

However, without being limited thereto, the company uses a terminal to request upload of product information to the server in various forms, such as product name, attribute, attribute value, attribute unit, test method, etc. for its product in the product description field 610 in various forms. can be entered. The server receives various types of upload requests, analyzes them, or uses them as training data to train an AI model, and based on the analyzed upload request or trained AI model, product name, attribute, attribute value, attribute unit, and test method can be parsed. That is, the server can analyze the input pattern or the characteristics of each parameter and the parameter classification method based on various types of upload request data, and thus, the server can analyze the product inputted in the product description field 610 from various types of upload requests. You can parse the product name, attribute, attribute value, attribute unit and attribute test method for .

7 is a diagram for explaining a database related to a product built in a server according to an embodiment.

Referring to FIG. 7 , the company transmits various types of upload requests using the terminal as described with reference to FIG. 6 , and the server determines the product name, attribute, attribute value, attribute unit, and test method for the product from the upload request. By parsing, you can build a database for products based on the parsed data.

For example, the server receives the upload request for the CPE 135A of company A, parses the product name, attribute, unit, attribute value, and measurement method therefrom, and based on the parsed data, data 705 for the CPE 135A of company A ) to build a database containing

Or, for example, the server receives the upload request for the CPE 135A of company B, parses the product name, attribute, unit, attribute value, and measurement method therefrom, and based on the parsed data, data on the CPE 135A of company B ( 710) may be constructed.

Referring to FIG. 7 , in the data 705 for CPE 135A of company A and the data 710 for CPE 135A of company B, product names, attributes, measurement methods, and the like may have different forms. This is because, as described with reference to FIG. 6 , the server can input the product name, attribute, attribute value, attribute unit, test method, etc. for its product in the product description field 610 in various forms. This is because, in the process of parsing, data can be parsed as it is without processing. However, the server may determine that the data is substantially the same even if the data is of different types. For example, it may be determined that “Bulk density” among the properties of the data 705 for CPE 135A and “Density” among the properties of the data 710 for CPE 135A are substantially the same. That is, the server receives various types of upload requests, analyzes them, or trains an AI model using it as training data, You can decide if they are the same. The server may classify the data as one data if it is determined that slightly different types of data are substantially identical.

Meanwhile, in the data 705 for CPE 135A of company A and the data 710 for CPE 135A of company B, the units for attributes may be different. As described above, the server may determine the representative unit of the attribute, and may convert the unit of the attribute into the representative unit based on the representative unit of the attribute. For example, the server may determine the representative unit of "Heat of fusion" among the attributes of CPE 135A as "J/g", and in the data 705 for CPE 135A, the unit of "Heat of fusion" (cal/g) ) can be converted to the representative unit "J/g".

8 is a diagram for explaining a process in which a product consumer transmits a product search request using a user terminal and displays desired search results to the product consumer on the user terminal based on various user inputs.

Referring to FIG. 8 , a product consumer may input a product keyword to be searched in the search window 805 using a user terminal. The user terminal may transmit a product search request including the input product keyword to the server.

The server may convert the unit of the product attribute into a representative unit in response to the product search request, and transmit a response including product information in which the unit of the product attribute is converted into the representative unit to the user terminal.

The product consumer may receive product information in which a unit of product attribute is converted into a representative unit, and the user terminal may display a product search result based on the received product information.

In this case, the product consumer may change the displayed search result by using the attribute button 810 , the display unit button 815 , and the measurement method button 820 .

For example, the attribute button 810 may be a button for selecting one attribute among various attributes of a product. The product consumer may select "Heat of fusion" using the attribute button 810 .

The display unit button 815 may be a button for selecting a unit desired to be displayed in the search result among various units of the attribute selected through the attribute button 810 . For example, the product consumer may select “cal/g” using the display unit button 815 . The server converts the unit of "Heat of fusion" to "cal/g" and retransmits the product search result to the user terminal, and the user terminal converts the unit of "Heat of fusion" to "cal/g" can be displayed.

The measurement method button 820 is a button for selecting a measurement method for which a search result is to be displayed among various measurement methods (standards) of the attribute selected through the attribute button 810, and the product consumer can select multiple measurement methods. there is. However, the present invention is not limited thereto, and the product consumer may select only one measurement method or may further select a priority of a plurality of measurement methods. In this case, product information corresponding to a plurality of selected measurement methods may be sequentially displayed according to their priorities, and product information corresponding to an unselected measurement method is not displayed or has a lower priority than product information corresponding to the selected measurement method. can be displayed as

According to various embodiments, the product information providing server analyzes the product information provided from the user terminal or determines the representative unit of the product attribute through AI model training using this as training data, and determines the unit of the product attribute. By unifying the representative unit and providing it to the user terminal, the user (product consumer) can easily understand the properties of the products of various companies, as well as facilitate the comparison between products, so that the user can select the desired product.

In addition, according to various embodiments, when the product information providing server receives a change request for the display unit of the unit of product attribute from the user terminal, the unit of product attribute is unified into the display unit included in the change request and provided to the user terminal By doing so, the user (product consumer) can easily understand the properties of the products of various companies based on the desired display unit, and it is possible to easily compare the products, so that the user can select the desired product.

In addition, according to various embodiments, the product information providing server analyzes product information provided from the user terminal or determines a representative test method of product attributes through AI model learning using this as learning data, and responds to the representative test method By providing product information so that the product information to be displayed in the user terminal can be preferentially displayed, the user (product consumer) can easily understand the properties of products of various companies measured by the same product test method, and compare the products This makes it easy for users to choose the product they want.

In addition, according to various embodiments, when the product information providing server receives a selection request for a product attribute test method from a user terminal, it preferentially displays product information corresponding to the product attribute test method included in the selection request or , by providing product information to the user terminal so that it can be displayed exclusively, the user (product consumer) can easily understand the properties of various companies' products measured by the desired product test method, and also facilitate comparison between products. So users can choose the product they want.

So far, various embodiments have been mainly looked at. Those of ordinary skill in the art to which the present disclosure pertains will understand that the present disclosure may be implemented in a modified form without departing from the essential characteristics of the present disclosure. Therefore, the disclosed embodiments are to be considered in an illustrative rather than a restrictive sense. The scope of the present disclosure is indicated in the claims rather than the foregoing description, and all differences within an equivalent scope should be construed as being included in the present disclosure.

Meanwhile, the above-described embodiments of the present disclosure can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. The computer-readable recording medium includes a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optically readable medium (eg, a CD-ROM, a DVD, etc.).

Claims (12)

Receiving a plurality of product information including a product name, unit information of at least one product attribute, and product test method information from at least one terminal;
parsing a product name, a unit of at least one product attribute, and a product test method from the received plurality of product information;
building a product database based on the parsed product name, unit of at least one product attribute, and a product test method;
Analyze the units parsed from the plurality of product information based on the frequency, or learn the first AI model using the plurality of product information as training data, and at least one determining a representative unit of a product attribute;
Analyze the product test method parsed from the plurality of product information, or learn a second AI model using the plurality of product information as training data, and at least one based on the analyzed test method or the learned second AI model classifying a product test method of the , and determining a representative product test method from among the at least one product test method;
Receiving a product information search request from at least one terminal; and
Converts a unit of at least one product attribute included in information of a plurality of company products in the database about the product into a representative unit, and includes a plurality of pieces of company product information based on the converted representative unit, and tests the at least one product Transmitting a response to a product information search request including information on the representative product test method among methods;
The at least one terminal receives a response to the product information search request, and based on the received information on the representative product test method, preferentially displaying the company product information of the company corresponding to the representative product test method A method of providing product information of the server characterized by it.
The method of claim 1,
receiving a change request for a display unit of the at least one product attribute from the at least one terminal; and
Converting the unit of at least one product attribute included in the information of a plurality of company products in the database regarding the product from the at least one terminal to the display unit included in the change request, and a plurality of companies based on the converted display unit Product information providing method of the server, characterized in that it further comprises the step of transmitting a response to the change request including the product information.
The method of claim 1,
Analyze a product name included in at least one of a plurality of product information and product information search request, or learn a third AI model as training data, The method for providing product information by a server, further comprising the step of determining a corresponding at least one product search keyword candidate.
4. The method of claim 3,
The step of constructing a database about a product based on the parsed product name and the unit of at least one product attribute,
and constructing a database on products corresponding to the at least one product search keyword candidate.
5. The method of claim 4,
Transmitting a response to the product information search request comprises:
determining a product corresponding to a product keyword included in the product information search request based on the at least one product search keyword candidate; and
Product information including a plurality of corporate product information based on the converted representative unit by converting a unit of at least one product attribute included in the information of a plurality of corporate products in the database regarding the product corresponding to the product keyword into a representative unit A method of providing product information on a server, comprising the step of transmitting a response to the search request.
delete delete The method of claim 1,
Transmitting a response to the product information search request including information on the representative product test method comprises:
Transmitting a response to a product information search request including the plurality of corporate product information based on the classified at least one product test method,
The at least one terminal receives a user input for selecting one product test method from among the classified at least one product test method,
Based on the received user input, the company product information corresponding to one product test method is preferentially displayed, or the company product information other than the company product information of the company corresponding to one product test method is not displayed. , A method for providing product information on a server, characterized in that displaying company product information of a company corresponding to the one product test method.
The method of claim 1,
The method for providing product information of a server, characterized in that the response to the information retrieval request includes download link information of the classified at least one product test method material.
at least one processor;
The at least one processor receives a plurality of product information including a product name, unit information of at least one product attribute, and product test method information from at least one terminal, and a product name, at least one from the received plurality of product information Parsing the unit of product attribute and product test method of Analyze based on or learn a first AI model as training data, and determine a representative unit of at least one product attribute based on the analyzed units or the learned first AI model,
Analyze the product test method parsed from the plurality of product information, or learn a second AI model using the plurality of product information as training data, and at least one based on the analyzed test method or the learned second AI model classify the product test method of the, and determine a representative product test method among the at least one product test method
Receive a product information search request from at least one terminal, convert the unit of at least one product attribute included in information of a plurality of corporate products in the database about the product into a representative unit, and convert a plurality of units based on the converted representative unit Transmitting a response to a product information search request that includes corporate product information and includes information on the representative product test method among the at least one product test method;
The at least one terminal receives a response to the product information search request, and based on the received information on the representative product test method, preferentially displays the company product information corresponding to the representative product test method Characterized product information providing server.
servers that provide product information; and
At least one terminal receiving the product information,
The at least one terminal transmits a plurality of product information including a product name, unit information of at least one product attribute, and product test method information,
The server receives the plurality of product information from the at least one terminal,
Parsing a product name, a unit of at least one product attribute, and a product test method from the received plurality of product information,
Build a database about products based on the parsed product name, unit of at least one product attribute, and product test method,
Analyze the units parsed from the plurality of product information based on the frequency, or learn the first AI model using the plurality of product information as training data, and at least one Determining the representative unit of product attributes,
Analyze the product test method parsed from the plurality of product information, or learn a second AI model using the plurality of product information as training data, and at least one based on the analyzed test method or the learned second AI model classify a product test method of the at least one product test method, and determine a representative product test method among the at least one product test method;
The at least one terminal transmits a product information search request,
The server receives a product information search request from the at least one terminal,
The server converts the unit of at least one product attribute included in the information of the plurality of enterprise products in the database about the product into a representative unit, and includes a plurality of pieces of enterprise product information based on the converted representative unit, wherein the at least one transmits a response to a product information search request including information on the representative product test method among the product test methods of
The at least one terminal receives a response to the product information search request, and based on the received information on the representative product test method, preferentially displays the company product information corresponding to the representative product test method A system for providing product information.

In the computer program stored in the recording medium to execute the product information providing method of the server,
The method of providing product information of the server,
Receiving a plurality of product information including a product name, at least one product attribute unit information and product test method information from at least one terminal in the server;
parsing a product name, a unit of at least one product attribute, and a product test method from the received plurality of product information;
building a product database based on the parsed product name, unit of at least one product attribute, and a product test method;
Analyze the units parsed from the plurality of product information based on the frequency, or learn the first AI model using the plurality of product information as training data, and at least one determining a representative unit of a product attribute;
Analyze the product test method parsed from the plurality of product information, or learn a second AI model using the plurality of product information as training data, and at least one based on the analyzed test method or the learned second AI model classifying a product test method of the , and determining a representative product test method from among the at least one product test method;
Receiving a product information search request from at least one terminal; and
Converts a unit of at least one product attribute included in information of a plurality of company products in the database about the product into a representative unit, and includes a plurality of pieces of company product information based on the converted representative unit, and tests the at least one product Transmitting a response to a product information search request including information on the representative product test method among methods;
The at least one terminal receives a response to the product information search request, and based on the received information on the representative product test method, preferentially displaying the company product information of the company corresponding to the representative product test method A computer program stored in a recording medium, characterized in that it.

Images