KR102587038B1 - Method, device and system for monitoring product price of competitors in artificial intelligence-based online commerce and discovering promising products for sale - Google Patents

Abstract

The device according to one embodiment acquires product information including the name of the product to perform price monitoring, the product category, the image of the product, and the manufacturer of the product from the seller's seller terminal, and based on the product information, the product Obtain information on competitors who sell, obtain the seller's selling price of products sold by the seller at preset cycles based on the product information, and obtain information on the products sold by the competitor at each cycle based on the information on the competitors. Obtain the selling price, compare the seller selling price with the competitor selling price, and based on the seller selling price being higher than the competitor selling price, generate a recommended seller price corresponding to the product, and use the seller terminal to compare the competitor selling price and the recommended seller. Send the sales price.

Description

Methods, devices and systems for monitoring prices of products sold by competitors in artificial intelligence-based online commerce and discovering promising products for sale {METHOD, DEVICE AND SYSTEM FOR MONITORING PRODUCT PRICE OF COMPETITORS IN ARTIFICIAL INTELLIGENCE-BASED ONLINE COMMERCE AND DISCOVERING PROMISING PRODUCTS FOR SALE}

The examples below relate to methods, devices, and systems for monitoring prices of products sold by competitors and discovering promising products for sale in artificial intelligence-based online commerce.

As the Internet became more widespread, product sellers or sales agents began to build virtual markets on the Internet called Internet shopping malls. As a result, product buyers were able to purchase specific products or goods they wanted to purchase through the virtual market without having to visit the store in person, and thanks to this, the number of sellers and sales agents operating online shopping malls also increased.

However, the selling price at these internet shopping malls varies from internet shopping mall to internet shopping mall even if the products are the same. Accordingly, buyers have developed a desire to purchase products from Internet shopping malls that offer the lowest prices, and since they compare prices in multiple markets to make purchase decisions, any price differences between products have a direct impact on sales performance. In order to satisfy the needs of buyers, many sellers on the Internet are competitively adjusting prices and selling in the open market.

In order to competitively control prices, business operators who run online shopping malls have accessed multiple open markets or social commerce sites and continuously looked at the product information and price information of competitors registered to sell the product. There was the inconvenience of having to monitor the extent of the price difference with the product being sold and directly modify or change the selling price of my product based on the monitoring results.

In addition, in many cases, repeated monitoring was carried out by deploying separate personnel to monitor the price of the product, which not only required labor costs and effort, but also required people to visit the relevant sales sites one by one and visually compare them. , it was not possible to identify price changes at competitors in real time, and had the fundamental limitation of being delayed for a certain period of time.

Therefore, research is required on technology that automatically monitors the prices of products sold by competitors in online commerce based on artificial intelligence and discovers promising products for sale when the product is judged to be uncompetitive.

Korean Patent No. 10-2243554 Korean Patent No. 10-1753481 Korean Patent No. 10-1431803 Korean Patent No. 10-1336151

Embodiments seek to compare a competitor's sales price and the seller's sales price at preset intervals for products sold by the seller.

Embodiments attempt to confirm sales price trends of products and generate recommended seller sales prices in response to the sales price trends.

In the embodiments, the lower limit of the seller's sales price corresponding to the product is obtained from the seller, and when there are more competitors selling lower than the seller's lower limit of the sales price, the product is excluded and a promising product is selected to recommend sales of the promising product. do.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned can be clearly understood from the description below.

In artificial intelligence-based online commerce, the method of monitoring the price of products sold by competitors and discovering promising products for sale is to obtain product information including the name of the product to be price monitored, product category, product image, and product manufacturer from the seller's seller terminal. acquiring; Obtaining information about competitors selling the product based on information about the product; Obtaining a seller's selling price of the product sold by the seller at preset intervals based on the product information; Obtaining a competitor's sales price of the product sold by the competitor in each cycle based on the competitor's information; Comparing the seller's selling price with the competitor's selling price; And based on the fact that the seller's sales price is higher than the competitor's sales price, generating a recommended seller's sales price corresponding to the product, and transmitting the competitor's sales price and the recommended seller's sales price to the seller terminal. .

The step of generating a recommended seller sale price corresponding to the product includes obtaining a trend of the seller sale price during a first preset period from the history of the seller sale price, when it is confirmed that the trend of the seller sale price is increasing. , maintaining the recommended seller sales price at the seller sales price, when it is confirmed that the trend of the seller sales price is maintained within a preset range, the recommended seller sales price is subtracted from the competitor sales price by a first standard value. A step of generating a price, if it is confirmed that the trend of the seller's sales price is decreasing, generating a recommended seller's sales price corresponding to the product as a price subtracted from the competitor's sales price by a second standard value, and the competitor's sales price Comparing the number of sales reviews and sales ratings according to sales of the product with the number of sales reviews and sales ratings according to sales of the product by the seller, and changing the first reference value or the second reference value, the second reference value is set to be greater than the first standard value, and the competitor is a competitor that is exposed at a higher level than the seller on the sales platform where the product is sold.

A method of monitoring prices of products sold by competitors and discovering promising products for sale in artificial intelligence-based online commerce includes the steps of obtaining a lower limit of the seller's selling price from the seller's terminal; Comparing the competitor's selling price with a lower limit of the seller's selling price, based on the seller's selling price being higher than the competitor's selling price; Obtaining the number of competitors whose sales price is lower than the lower limit of the seller's sales price; If it is confirmed that the number of competitors is greater than the threshold, transmitting a message recommending to sell a promising product instead of the product to the seller terminal; and, if it is confirmed that the number of competitors is not greater than the threshold, transmitting the recommended seller sales price to the seller terminal.

The promising product acquires information on the product to be sold, including the category, color, function, and sales price of the product to be sold from the seller terminal, and is sold more than a preset target value from the seller's sales database. Classify sales items into a first group, obtain categories of products classified into the first group, generate recommended category information, obtain prices of products classified into the first group, and generate recommended price information. and obtain keywords of products searched for a preset second period from the sales platform, generate trend information, and based on the recommended category information, the recommended price information, the trend information, and the information on the product to be sold, 1 Generate an input signal, apply the first input signal to a first artificial neural network to generate a first output signal, and generate a recommendation score corresponding to the product to be sold based on the first output signal, Using the recommendation score, the product scheduled for sale with the highest recommendation score is selected.

A method of monitoring prices of products sold by competitors and discovering promising products for sale in artificial intelligence-based online commerce includes the steps of obtaining price information of other companies selling the promising products; setting at least one of the average value, median value, and mode value of the price information of the other companies as the recommended price of the promising product; setting a recommended price range for the promising product using the variance value of the price information of the other company; and transmitting the recommended price of the promising product and the recommended price range of the promising product to the seller terminal; setting the recommended price range of the promising product using the variance value of the price information of the other company. The step of checking whether the variance value is greater than the reference value, and if the variance value is greater than the reference value, setting a first reference percentage as a reference value for setting a recommended price range of the promising product, When the variance value is not greater than the reference value, setting a second reference percentage smaller than the first reference percent as a reference value for setting the recommended price range of the promising product.

The method of monitoring prices of products sold by competitors and discovering promising products for sale in artificial intelligence-based online commerce further includes the step of transmitting an information message about the product to the seller terminal based on reviews of the product, The step of transmitting an information message about the product to the seller terminal based on the step of extracting text information of the review of the product and extracting keywords, and selecting keywords mentioned more than a preset standard number of times from the extracted keywords as main Setting a keyword, classifying the main keyword as a positive keyword or negative keyword, calculating a positive ratio, which is the ratio of the positive keyword among the keywords, and calculating a negative ratio, which is the ratio of the negative keyword among the keywords. Calculating, comparing the fraud rate with a preset first and second standard ratio, if the fraud rate is lower than the first standard rate, sending a guidance message recommending continued sales of the product to the seller Transmitting to the terminal, when the negative keyword is higher than the first reference rate and lower than the second reference rate, sorting the negative keywords in the order in which the negative keywords are extracted most, and based on the sorted negative keywords Generating improvements in the product and transmitting a guidance message about the fraudulent keywords and the improvements to the seller terminal; and, if the fraud rate is higher than the second standard rate, changing the product to the promising product. It includes transmitting a recommended information message to the seller terminal.

The device according to one embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the above-described methods.

Embodiments may compare a competitor's sales price and the seller's sales price at preset intervals for products sold by the seller.

Embodiments may check the sales price trend of a product and generate a recommended seller sales price in response to the sales price trend.

In embodiments, the lower limit of the seller's sales price corresponding to the product is obtained from the seller, and if there are more competitors selling below the seller's lower limit of the sales price than the standard value, the sales of the promising product are recommended by excluding the product. You can.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
Figure 2 is a flow chart to explain the process of monitoring the price at which a seller sells a product and the price at which a competitor sells a product every cycle according to an embodiment.
FIG. 3 is a flowchart illustrating a process for generating a recommended seller sales price based on a trend of a sales price corresponding to a product according to an embodiment.
Figure 4 is a diagram illustrating a process for determining whether to continue selling a product or selecting another promising product based on the lower limit of the seller's selling price according to one embodiment.
Figure 5 is a flow chart to explain the process of selecting a promising product through artificial intelligence according to an embodiment.
Figure 6 is a flowchart illustrating a process for providing a recommended price and recommended price range of a promising product according to an embodiment.
Figure 7 is a flowchart illustrating a process for setting a recommended price range for a promising product according to an embodiment.
Figure 8 is a flowchart illustrating a process for transmitting a product information message to a seller terminal based on a product review according to an embodiment.
Figure 9 is an exemplary diagram of the configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1, a system according to an embodiment may include a seller terminal 100 and a device 200 that can communicate with each other through a communication network.

First, a communication network can be configured regardless of the communication mode, such as wired or wireless, and can be implemented in various forms to enable communication between servers and between servers and terminals.

The seller terminal 100 is a terminal used by a seller who sells a product through online commerce and monitors the prices sold by competitors for price competitiveness of the product, and may be a desktop computer, laptop, tablet, smartphone, etc. For example, as shown in FIG. 1, the user's terminal 100 may be a smartphone, and may be employed differently depending on the embodiment.

Each of the seller terminals 100 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. A plurality of seller terminals 100 may be configured to communicate with the device 200 in a wired or wireless manner.

Each of the seller terminals 100 is connected to a website operated by a person or organization providing services using the device 200, or an application developed and distributed by a person or organization providing services using the device 200. This can be installed. Each seller terminal 100 may be linked to the device 200 through a website or application.

In Figure 1 and the following description, for convenience of explanation, only one seller terminal 100 is shown, but the number of terminals may vary depending on the embodiment. As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

The device 200 may be its own server owned by a person or organization that provides services using the device 200, a cloud server, or a p2p (peer-to-peer) set of distributed nodes. It may be possible. The device 200 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The device 200 may include at least one artificial neural network that performs an inference function. The device 200 may be configured to communicate with the seller terminal 100 in a wired or wireless manner.

The device 200 can communicate and connect with a website wired or wirelessly, where the website includes online commerce that sells products and SNS - a social network service that includes articles, blogs, cafes, Instagram, etc. As an Internet site, the device 200 can communicate and connect with the website wired or wirelessly to obtain seller information, information related to products being sold, information about competitors, and information about products sold by competitors.

Additionally, the device 200 can operate a sales platform, and the device 200 can obtain information related to products sold by a seller from the sales platform, obtain information related to competitors, and obtain information from users. You can obtain keywords for products searched on the sales platform.

The device 200 obtains product information including the name of the product to perform price monitoring, the product category, the image of the product, and the manufacturer of the product from the seller's seller terminal 100, and based on the product information, Obtain information on competitors selling the product, obtain the seller's selling price of the product sold by the seller at preset cycles based on the product information, and obtain the seller's selling price of the product sold by the competitor every cycle based on the competitor's information. Obtain the competitor's selling price, compare the seller's selling price with the competitor's selling price, generate a recommended seller's price corresponding to the product based on the seller's selling price being higher than the competitor's selling price, and recommend the competitor's selling price and recommendation to the seller's terminal The seller can transmit the selling price.

Figure 2 is a flow chart to explain the process of monitoring the price at which a seller sells a product and the price at which a competitor sells a product every cycle according to an embodiment.

Referring to FIG. 2, first, in step S201, the device 200 receives product information including the name of the product to perform price monitoring, the product category, the image of the product, and the manufacturer of the product from the seller's seller terminal 100. can be obtained. Here, product categories may include clothing, beauty, food, furniture, digital, books, stationery, household goods, kitchenware, etc.

Specifically, the device 200 receives product information including the name of the product to perform price monitoring, the product category, the image of the product, and the manufacturer of the product from the seller terminal 100 of the seller selling the product in online commerce. It can be obtained.

In addition, the device 200 may additionally obtain information on a sales platform or online commerce, including information on which site or platform the seller sells the product, and seller information related to the seller, from the seller terminal 100. You can.

For example, if the seller wants to monitor the price of the first product, the device 200 receives the name of the first product, the category of the first product, the image of the first product, and the manufacturer of the first product from the seller terminal 100. Information on the first product including can be obtained.

In step S202, the device 200 may obtain information about competitors selling the product based on product information. Here, the competitor's information may include the competitor's name, price information on products sold by the competitor, and information on the online commerce or sales platform sold by the competitor.

Specifically, the device 200 can determine whether there are other competitors selling the product through online commerce or a sales platform, based on information on the product to perform price monitoring obtained from the seller, and determine whether there is a competitor selling the product. If there are other competitors, information on the competitor can be obtained, including the name of the competitor, price information for products sold by the competitor, and information on the online commerce or sales platform where the competitor sells the product.

In step S203, the device 200 may obtain the seller's selling price of the product sold by the seller at preset intervals, based on product information. Here, the preset period is a preset value and may vary depending on the embodiment.

Specifically, the device 200 may obtain the seller's selling price of the product sold by the seller at preset intervals based on product information.

At this time, in order to obtain the seller's sales price of the product every cycle, the device 200 requests the seller's current selling price for the product from the seller terminal 100 every cycle and sends the product to the seller terminal 100 every cycle. You can also get the price. In addition, the device 200 can access the online commerce or sales platform where the seller sells the product, based on the information on the sales platform or online commerce where the seller sells the product, obtained from the seller terminal 100. Based on the seller information and product information through the online commerce or sales platform you access, you can obtain the seller's sales price of the product every cycle.

In step S204, the device 200 may obtain the competitor's sales price of the product sold by the competitor every cycle, based on the competitor's information.

Specifically, the device 200 may obtain the competitor's sales price of the product sold by the competitor every cycle based on the competitor's information and product information. At this time, in order to obtain the competitor's sales price of the product every cycle, the device 200 uses the online commerce or sales platform where the competitor sells the product based on the information of the online commerce or sales platform where the competitor sells the product included in the competitor's information. You can access a commerce or sales platform, and obtain the competitor's sales price of the product every cycle based on product information and competitor information through the accessed online commerce or sales platform.

In step S205, the device 200 may compare the seller's selling price with the competitor's selling price.

Specifically, the device 200 can obtain the seller's sales price of the product and the competitor's sales price of the product at each preset cycle, and compare the acquired seller's sales price of the product and the competitor's sales price of the product at each cycle.

In step S206, the device 200 may generate a recommended seller price corresponding to the product based on the fact that the seller sale price is higher than the competitor sale price, and transmit the competitor sale price and the recommended seller sale price to the seller terminal 100. .

Specifically, the device 200 may compare a seller's selling price of a product with a competitor's selling price of the product, and generate a recommended seller's price corresponding to the product based on the seller's selling price being higher than the competitor's selling price as a result of the comparison. , Competitor sales prices and recommended seller sales prices can be transmitted to the seller terminal 100. Here, a detailed description of generating the recommended seller sales price will be referred to FIG. 3.

That is, the device 200 can obtain the seller's sales price of the product and the competitor's sales price of the product every cycle, and compare the seller's sales price of the obtained product with the competitor's sales price of the product every cycle, and as a result of the comparison, the seller If the selling price is higher than the competitor's selling price, a recommended seller's price corresponding to the product can be generated and the competitor's selling price and the recommended seller's selling price can be transmitted to the seller terminal 100.

In addition, the device 200 compares the seller selling price of the product with the competitor selling price of the product, and if the seller selling price is not higher than the competitor selling price, the device 200 does not generate a recommended seller price and sends a message to the seller terminal 100. It may not be transmitted.

FIG. 3 is a flowchart illustrating a process for generating a recommended seller sales price based on a trend of a sales price corresponding to a product according to an embodiment.

Referring to FIG. 3, first, in step S301, the device 200 may obtain a trend of the seller's sales price during a preset first period from the history of the seller's sales price. Here, the first period is a preset value and may vary depending on the embodiment.

Specifically, the device 200 may communicate wired or wirelessly with the seller's sales database, and the seller's sales database stores a history of the seller's sales price, which includes information on when and how much the seller sold the product. It may be. The device 200 may obtain a history of the seller's sales price from the seller's sales database, and check how much the product was sold for during a preset first period from the history of the seller's sales price. As a result of the confirmation, the product The trend of the corresponding seller's sales price can be obtained.

In addition, the device 200 checks the trend of the seller sales price corresponding to the product obtained from the history of the seller sales price to determine whether the trend of the seller sales price is rising, maintained within a preset range, or falling. You can.

In step S302, if the device 200 confirms that the trend of the seller's sale price is increasing, the device 200 may maintain the recommended seller's sale price as the seller's sale price.

Specifically, the device 200 checks the trend of the seller sale price corresponding to the product obtained from the history of the seller sale price, and if it is confirmed that the trend of the seller sale price is increasing, the device 200 determines the recommended seller sale. The price can be maintained at the seller's selling price.

In other words, the device 200 checks the trend of the seller's sales price corresponding to the corresponding product, and if it is confirmed that the trend of the seller's sales price is increasing, the device 200 determines that the seller is competitive without lowering the seller's sales price to match the competitor's sales price. A message may be sent to the terminal 100 to continue selling the product at the seller's existing selling price.

In step S303, if it is confirmed that the trend of the seller's sales price is maintained within the range, the device 200 may generate the recommended seller's sales price as a price subtracted from the competitor's sales price by a first standard value. Here, the range is a preset range based on the seller's sales price and may vary depending on the embodiment. Additionally, the first reference value is a preset value and may vary depending on the embodiment, and may be changed through step S305.

Specifically, the device 200 checks the trend of the seller sales price corresponding to the product obtained from the history of the seller sales price, and if it is confirmed that the trend of the seller sales price remains within the range, the device 200 makes a recommendation. The seller's sales price can be created as a price subtracted from the competitor's sales price by a first standard value.

That is, the device 200 checks the trend of the seller's sales price corresponding to the product, and if it is confirmed that the trend of the seller's sales price is maintained within a preset range, the device 200 lowers the seller's sales price to match the competitor's sales price. It is determined that it is competitive even if it is slightly lower than the recommended seller's sales price, and the recommended seller's sales price can be created as a price subtracted from the competitor's sales price by a first standard value, and the device 200 is a seller terminal 100 that is lower than the competitor's sales price by the first standard value. You can transmit the recommended seller sales price and competitor sales price generated from the deducted price.

In step S304, if it is confirmed that the trend of the seller's sales price is decreasing, the device 200 may generate the recommended seller's sales price as a price subtracted from the competitor's sales price by a second standard value. Here, the second reference value is a preset value greater than the first reference value and may vary depending on the embodiment, and may be changed through step S305.

Specifically, the device 200 checks the trend of the seller sales price corresponding to the product obtained from the history of the seller sales price, and if it is confirmed that the trend of the seller sales price is decreasing, the device 200 determines the recommended seller sales. The price can be created as a price subtracted from the competitor's sales price by a second standard value.

That is, the device 200 checks the trend of the seller's sales price corresponding to the product, and if it is confirmed that the trend of the seller's sales price is maintained within a preset range, the device 200 lowers the seller's sales price to match the competitor's sales price. It is determined that the recommended seller's sales price must be lowered to be competitive, so the recommended seller's sales price can be generated as a price subtracted from the competitor's sales price by a second standard value, and the device 200 uses the seller terminal 100 to subtract the competitor's sales price by a second standard value. You can transmit the recommended seller sales price and competitor sales price generated at the given price.

In step S305, the device 200 may change the first reference value or the second reference value by comparing the number of sales reviews and sales rating according to the sales of a competitor's product with the number of sales reviews and sales rating according to the seller's product sales.

Specifically, the device 200 accesses the online commerce or sales platform where the competitor sells the product, based on information on the online commerce or sales platform where the competitor sells the product, and provides a sales review of the product sold by the competitor. You can obtain the quantity and sales rating, and based on the information of the online commerce or sales platform where the seller sells the product, you can access the online commerce or sales platform where the seller sells the product to purchase the product sold by the seller. You can obtain the number of sales reviews and sales rating. The device 200 compares the number of sales reviews and sales ratings of the product sold by a competitor with the number of sales reviews and sales ratings of the product sold by the seller, and determines that the competitor has a higher number of sales reviews for the product than the seller. If the sales rating is higher, the first and second standard values can be changed to be larger than before, and if the seller has more sales reviews for the product than competitors and the sales rating is higher, the first and second standard values can be changed to be larger than before. The standard can be changed to be lower than before. In addition, the device 200 compares the number of sales reviews and sales ratings of the product sold by a competitor with the number of sales reviews and sales ratings of the product sold by the seller, and as a result, the number of sales reviews and sales ratings for the product sold by the competitor and the seller are calculated. If the sales rating is the same, the first standard value and the second standard value can be maintained.

Figure 4 is a diagram illustrating a process for determining whether to continue selling a product or selecting another promising product based on the lower limit of the seller's selling price according to one embodiment.

Referring to FIG. 4, first, in step S401, the device 200 may obtain the lower limit of the seller's sales price from the seller terminal 100. Here, the lower limit of the seller's selling price is the minimum amount that the seller can allow to sell the product when selling it at a price acceptable to the seller. In other words, when determining the lower limit of the seller's sales price, the seller can set it by considering the margin of the product.

For example, if the current price of the first product is 10,000 and the seller determines that the product cannot be sold for less than 7,000 won considering the margin, the device 200 sends the seller corresponding to the first product from the seller terminal. You can get 7,000 won as the lower limit of the selling price.

In step S402, the device 200 may compare the lower limit of the competitor's selling price and the seller's selling price based on whether the seller's selling price is higher than the competitor's selling price.

Specifically, the device 200 obtains the seller's sales price and competitor's sales price corresponding to the product at a preset cycle and compares the seller's sales price with the competitor's sales price. If the seller's sales price is higher than the competitor's sales price, You can compare the lower limit of a competitor's selling price with the seller's selling price.

That is, the device 200 compares the seller's sales price with the competitor's sales price at a preset cycle, and when the seller's sales price is higher than the competitor's sales price, the device 200 compares the lower limit of the competitor's sales price and the seller's sales price, and the seller If the selling price is not higher than the competitor's selling price, the seller can continue to sell the product at the seller's selling price without comparing the competitor's selling price with the lower limit of the seller's selling price.

In step S403, the device 200 may obtain the number of competitors whose selling price is lower than the lower limit of the seller's selling price.

Specifically, the device 200 compares the seller's sales price and the competitor's sales price in a preset cycle, and when the seller's sales price is higher than the competitor's sales price, the device 200 can compare the lower limit of the competitor's sales price and the seller's sales price, and the device ( 200), if a competitor's selling price exists that is lower than the seller's selling price as a result of comparison, the number of competitors whose selling price is lower than the lower limit of the seller's selling price can be obtained.

In step S404, the device 200 may check whether the number of competitors is greater than the threshold value. Here, the threshold value is a preset value and may vary depending on the embodiment.

If it is determined in step S404 that the number of competitors is greater than the threshold, in step S405, the device 200 may transmit a message recommending that the seller terminal 100 sell a promising product instead of the product.

Specifically, the device 200 obtains the number of competitors whose selling price is lower than the lower limit of the seller's selling price, checks whether the number of competitors is greater than a preset threshold value, and determines whether the number of competitors is greater than the threshold value. If confirmed, it is determined that the product is not competitive and a message recommending that the seller sell a promising product instead of the product can be sent to the seller terminal 100. Here, the promising product is a product selected through artificial intelligence among products scheduled to be sold by the seller, and a detailed description regarding the promising product will be made with reference to FIG. 5.

If it is determined in step S404 that the number of competitors is not greater than the threshold, the device 200 may transmit the recommended seller sales price to the seller terminal 100 in step S406.

Specifically, the device 200 obtains the number of competitors whose selling price is lower than the lower limit of the seller's selling price, checks whether the number of competitors is greater than a preset threshold, and determines whether the number of competitors is greater than the threshold. If it is confirmed that the product is still competitive, the recommended seller selling price can be transmitted to the seller terminal 100.

Figure 5 is a flow chart to explain the process of selecting a promising product through artificial intelligence according to an embodiment.

Referring to FIG. 5 , first, in step S501, the device 200 may obtain information on the product to be sold including the category, color, and sales price of the product to be sold from the seller terminal 100.

Specifically, the device 200 may obtain information from the seller terminal 100 on a product scheduled for sale that the seller intends to sell through online commerce in the future. At this time, the information on the product to be sold may include the category of the product to be sold, the color of the product to be sold, and the selling price of the product to be sold. The selling price of the product to be sold may be determined by whether the product to be sold is sold through another company. It may include at least one of the price or the price at which the seller of the product to be sold will sell it.

In step S502, the device 200 may classify sales items sold above a preset target value from the seller's sales database into a first group. Here, the target value is a preset value and may vary depending on the embodiment.

Specifically, the device 200 may communicate wired or wirelessly with the seller's sales database, and the seller's sales database may store information about products sold by the seller through online commerce. Information about sold products may include product information about sold products and history information about which products were sold, when they were sold, how much they were sold for, and at what price they were sold. The device 200 can obtain information about products sold by the seller through online commerce from the seller's sales database, and check information about products sold by the seller through online commerce to determine sales that are sold above the target value. Items can be classified into a first group.

In step S503, the device 200 may obtain categories of products classified into the first group and generate recommended category information.

Specifically, the device 200 can obtain product information about products classified into the first group from the seller's sales database, confirm the categories of products classified into the first group, and provide recommended category information according to the confirmation result. can be created.

In step S504, the device 200 may obtain prices of products classified into the first group and generate recommended price information.

Specifically, the device 200 can obtain product information about products classified into the first group from the seller's sales database, check the prices of the products classified into the first group, and provide recommended price information according to the confirmation result. can be created.

In step S505, the device 200 may generate trend information by obtaining keywords of products searched during a preset second period from the sales platform.

Specifically, the device 200 may communicate with the sales platform wired or wirelessly, obtain keywords of products searched during a preset second period from the sales platform, and generate trend information based on the keywords of the obtained products. can do.

In step S506, the device 200 may generate a first input signal based on recommended category information, recommended price information, trend information, and information on products scheduled for sale.

Specifically, the device 200 may perform a process of preprocessing recommended category information, recommended price information, trend information, and information on products scheduled for sale. The preprocessed recommended category information, recommended price information, trend information, and information on products scheduled for sale can be used as input to the first artificial neural network, or the first input signal can be generated through normal processing to remove unnecessary information. there is.

In step S507, the device 200 may generate a first output signal by applying the first input signal to the first artificial neural network.

The first artificial neural network is an artificial intelligence model that outputs recommendation scores corresponding to products to be sold according to the input recommendation category information, recommendation price information, trend information, and information of products to be sold. Training recommendation category information, training recommendation It can be learned in advance based on price information, training trend information, information on products scheduled for training sale, first output signals, and training scores. Here, the training scores are scores corresponding to training recommendation category information, training recommendation price information, training trend information, and information on products scheduled to be sold for training, and the first output signals are training recommendation category information and training recommendation price. Information, training trend information, and information on products scheduled to be sold for training are output signals generated by applying them to the first artificial neural network, and the first artificial neural network is the training generated based on the differences between the first output signals and the training scores. It is learned by minimizing errors. Additionally, the recommendation score may be a real number between 0 and 1.

The first artificial neural network may be an artificial neural network learned according to reinforcement learning. The first artificial neural network may be a Q-Network, Depp Q-Network (DQN), or relational network (RL) structure suitable for outputting abstract inference through reinforcement learning. The first artificial neural network learned according to reinforcement learning can be updated and optimized by reflecting the evaluation of various rewards. For example, the first reward may have a higher reward value as the recommendation score of the product to be sold is selected based on recommended category information, recommended price information, trend information, and information of the product to be sold, and the second reward is recommended category information. , Depending on the recommended price information, trend information, and information on the product to be sold, the reward value may increase as the recommendation score of the unsuitable product to be sold is not selected.

In step S508, the device 200 may select the product scheduled for sale with the highest recommendation score as a promising product based on the first output signal.

For example, when the recommendation scores of products to be sold are 0.8, 0.1, 0.7, and 0.3, the device 200 may select the product to be sold corresponding to a score of 0.8 as a promising product.

Figure 6 is a flowchart illustrating a process for providing a recommended price and recommended price range of a promising product according to an embodiment.

Referring to FIG. 6, first, in step S601, the device 200 may obtain price information of another company selling a promising product. Here, the other company may be one or multiple companies.

Specifically, the device 200 communicates wired and wirelessly with online commerce including a sales platform to obtain information about other companies selling promising products through online commerce including a sales platform, and can obtain information about other companies selling promising products through online commerce including a sales platform. You can obtain price information from other companies, which is price information on promising products sold by the company.

For example, if the promising product is a second product, the device 200 can obtain information about company 'A', which is another company selling the second product through the sales platform, and the information of company 'A' obtained. Through the information, it is possible to obtain the price information of company 'A', which is the price information of the second product sold by company 'A'.

In step S602, the device 200 may set at least one of the average value, median value, and mode value of the price information of other companies as the recommended price of a promising product.

In step S603, the device 200 may set a recommended price range for a promising product using the variance value of other companies' price information.

Specifically, the device 200 can generate a dispersion of the price of a promising product based on the price of a promising product sold by another company, and generate a price dispersion value of the promising product through the dispersion. .

That is, the device 200 can determine whether the price of a promising product is similar or different for each company through the variance value, and can set the recommended price range to be wide or narrow depending on the variance value.

In step S604, the device 200 may transmit the recommended price of the promising product and the recommended price range of the promising product to the seller terminal 100.

Figure 7 is a flowchart illustrating a process for setting a recommended price range for a promising product according to an embodiment.

Referring to FIG. 7, first, in step S701, the device 200 may generate a variance value based on price information of another company.

In step S702, the device 200 may check whether the variance value is greater than the reference value. Here, the reference value is a preset value and may vary depending on the embodiment.

If it is determined in step S702 that the variance value is greater than the reference value, in step S703, the device 200 may set the first standard percentage as a reference value for setting the price range of a promising product. Here, the first reference percentage is a preset value and may vary depending on the embodiment.

For example, if the recommended price of a promising product is 100,000 won, the variance value is 40,000, and the reference value is 25,000, the device 200 determines that the variance value is greater than the reference value and sets the price range of the promising product. 20% can be set as the standard, and the recommended price range for promising products can be set from 80,000 won to 120,000 won.

If it is determined in step S702 that the variance value is not greater than the reference value, in step S704, the device 200 may set a second standard percentage as a reference value for setting the price range of a promising product. Here, the second reference percentage is a preset value that is smaller than the first reference percentage and may vary depending on the embodiment.

For example, if the recommended price of a promising product is 100,000 won, the variance value is 10,000, and the reference value is 25,000, the device 200 determines that the variance value is smaller than the reference value and sets the price range of the promising product. 10% can be set as the standard, and the recommended price range for promising products can be set from 90,000 won to 110,000 won.

Figure 8 is a flowchart illustrating a process for transmitting a product information message to a seller terminal based on a product review according to an embodiment.

If the device 200 determines that the product is not competitive through price monitoring, it can transmit a message recommending the sale of a promising product to the seller terminal 100. Additionally, the device 200 can check the reviews of the product and determine that the negative review rate is the standard rate. If there are more, a message recommending the sale of a promising product may be transmitted to the seller terminal 100.

Referring to FIG. 8, first, in step S801, the device 200 may extract text information of a product review and extract keywords. At this time, product reviews are written by buyers who have experience purchasing the product, and include the number and length of reviews registered related to the product, images included in the review, text included in the review, and video included in the review. It can be done and may be stored in the seller's sales database. The device 200 can communicate wired or wirelessly with the seller's sales database, obtain product reviews from the seller's sales database, and extract keywords by extracting text information from the product reviews.

In step S802, the device 200 may set keywords mentioned more than a preset standard number of extracted keywords as main keywords. At this time, the reference number of times may be set differently depending on the embodiment.

In step S803, the device 200 may classify the main keyword as a positive keyword or a negative keyword.

In step S804, the device 200 may calculate the positive rate and negative rate. At this time, the positive ratio may refer to the ratio of positive keywords among keywords, and the negative ratio may refer to the ratio of negative keywords among keywords.

In step S805, the device 200 may compare the denial rate with a preset first reference rate. At this time, the first reference ratio may be set differently depending on the embodiment.

As a result of comparing the fraud rate with the preset first standard rate in step S805, if the fraud rate is lower than the first standard rate, in step S806, the device 200 sends a guidance message recommending continued sales of the product to the seller terminal ( 100).

As a result of comparing the fraud rate with the preset first reference rate in step S805, if the fraud rate is not lower than the first reference rate, in step S807, the device 200 may compare the fraud rate with the preset second reference rate. there is. At this time, the second reference ratio may be set differently depending on the embodiment.

As a result of comparing the negative rate with the preset second standard rate in step S807, if the negative rate is higher than the first standard rate and lower than the second standard rate, in step S808, the device 200 provides guidance on negative keywords and improvement points. A message can be transmitted to the seller terminal 100.

According to one embodiment, the device 200 may sort the negative keywords in the order in which the most negative keywords are extracted, and create improvements to the product based on the sorted negative keywords.

For example, if the negative keywords are 'weak durability' and 'not good color', the device 200 sorts the negative keywords in the order in which they are extracted the most, and selects 'improved durability' and 'improved color' based on the negative keywords. Improvements to the product can be created.

As a result of comparing the fraud rate with the preset second standard rate in step S807, if the fraud rate is higher than the second standard rate, in step S809, the device 200 sends a guidance message recommending that the seller change the product to a promising product. It can be transmitted to the terminal 100.

Figure 9 is an exemplary diagram of the configuration of a device according to an embodiment.

Device 200 according to one embodiment includes a processor 210 and memory 220. The processor 210 may include at least one device described above with reference to FIGS. 1 to 8 or may perform at least one method described above with reference to FIGS. 1 to 8 . An individual or organization using device 200 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 8 .

The memory 220 may store information related to the methods described above or store a program in which methods described later are implemented. Memory 220 may be volatile memory or non-volatile memory.

The processor 210 can execute programs and control the device 200. The code of the program executed by the processor 210 may be stored in the memory 220. The device 200 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and can exchange data through wired or wireless communication.

The device 200 can be used to train an artificial neural network or use a trained artificial neural network. Memory 220 may include an artificial neural network that is being trained or has been trained. The processor 210 may learn or execute the artificial neural network algorithm stored in the memory 220. The device 200 for training an artificial neural network and the device 200 for using the learned artificial neural network may be the same or may be separate.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

Claims (3)

In the method of monitoring prices of products sold by competitors and discovering promising products for sale in artificial intelligence-based online commerce, which is performed by a device,
Obtaining product information including the name of the product to perform price monitoring, the product category, the image of the product, and the manufacturer of the product from the seller's seller terminal;
Obtaining information about competitors selling the product based on information about the product;
Obtaining a seller's selling price of the product sold by the seller at preset intervals based on the product information;
Obtaining a competitor's sales price of the product sold by the competitor in each cycle based on the competitor's information;
Comparing the seller's selling price with the competitor's selling price; and
Based on the fact that the seller's sales price is higher than the competitor's sales price, generating a recommended seller's sales price corresponding to the product, and transmitting the competitor's sales price and the recommended seller's sales price to the seller terminal,
Obtaining a lower limit of the seller's selling price from the seller's terminal;
Comparing the competitor's selling price with a lower limit of the seller's selling price, based on the seller's selling price being higher than the competitor's selling price;
Obtaining the number of competitors whose sales price is lower than the lower limit of the seller's sales price;
If it is confirmed that the number of competitors is greater than the threshold, transmitting a message recommending to sell a promising product instead of the product to the seller terminal; and
If it is confirmed that the number of competitors is not greater than the threshold, transmitting the recommended seller sales price to the seller terminal; further comprising;
The step of generating a recommended seller sales price corresponding to the product is
Obtaining a trend of the seller's sales price during a first preset period from the history of the seller's sales price;
If it is confirmed that the trend of the seller's sales price is increasing, maintaining the recommended seller's sales price at the seller's sales price,
If it is confirmed that the trend of the seller's sales price is maintained within a preset range, generating the recommended seller's sales price as a price subtracted from the competitor's sales price by a first standard value;
If it is confirmed that the trend of the seller's sales price is decreasing, generating a recommended seller's sales price corresponding to the product at a price subtracted from the competitor's sales price by a second standard value, and
Comprising the step of changing the first reference value or the second reference value by comparing the number of sales reviews and sales rating according to the sales of the product by the competitor with the number of sales reviews and sales rating according to the sales of the product by the seller,
The second reference value is set to be greater than the first reference value,
The competitors are:
It is a competitor that is exposed higher than the seller on the sales platform where the product is sold,
The promising products are:
Obtain information on the product to be sold from the seller terminal, including the category, color, function, and sales price of the product to be sold,
Classifying sales products sold above a preset target value from the seller's sales database into a first group,
Obtaining categories of products classified into the first group and generating recommended category information,
Obtaining prices of products classified into the first group and generating recommended price information,
Generate trend information by obtaining keywords of products searched during a preset second period from the sales platform,
Generate a first input signal based on the recommended category information, the recommended price information, the trend information, and the information on the product scheduled for sale,
Applying the first input signal to a first artificial neural network to generate a first output signal,
Based on the first output signal, the product scheduled for sale with the highest recommendation score is selected,
When it is confirmed that the number of competitors is greater than the threshold, transmitting a message recommending to sell a promising product instead of the product to the seller terminal;
Further comprising transmitting the recommended price of the promising product and the recommended price range of the promising product to the seller's terminal,
The step of transmitting the recommended price of the promising product and the recommended price range of the promising product to the seller's terminal,
Obtaining price information of other companies selling the promising product,
Setting at least one of the average value, median value, and mode value of the price information of the other companies as the recommended price of the promising product;
Setting a recommended price range for the promising product using the variance value of the price information of the other company, and
Further comprising transmitting the recommended price of the promising product and the recommended price range of the promising product to the seller terminal,
The step of setting the recommended price range for the promising product using the variance value of the price information of the other company is,
checking whether the variance value is greater than a reference value, and
If it is confirmed that the variance value is greater than the reference value, a first standard percentage is set as a reference value for setting the recommended price range of the promising product, and if it is confirmed that the variance value is not greater than the reference value, recommendation of the promising product is made. Comprising the step of setting a second reference percentage that is smaller than the first reference percent as a reference value for setting the price range,
How to monitor prices of products sold by competitors and discover promising products for sale in artificial intelligence-based online commerce. delete delete