KR20200027071A - Artificial Intelligent Shopping System for Open Market - Google Patents

Abstract

An objective of the present invention is to provide an artificial intelligence shopping system applied to an open market which can determine and select a product most suitable for a purchase condition of a customer. The artificial intelligence shopping system applied to an open market comprises: an input unit to receive order information including one or more types of products which a customer wants to purchase and quantities by the products from the customer on an open market; a search unit to search for all sellers selling the products on the open market; a sale information storage unit to store seller information including delivery charges by the sellers and a free delivery reference amount and product information including sale prices of the products by the sellers; a comparative price calculation unit to convert the sale prices of the different sellers into comparative prices which can be directly compared by the products based on the order information, the seller information, and the product information; an optimal combination selection unit to generate at least one combination of the comparative prices selected one at a time by all the products, align comparative price totals obtained by summing the comparative prices by the combination in an ascending order to generate optimal ranks and select the combination up to a specific high rank from the optimal ranks as an optimal combination; a recommended combination selection unit to calculate delivery charges by the optimal combination based on the seller information, sum the comparative price totals to generate recommended ranks aligned in an ascending order, and select up to a specific high rank from the recommended ranks as a recommended combination; and a display unit to display the comparative price totals, the sale price totals, and the delivery charges by the recommended combination to the customer.

Description

Artificial intelligence shopping system for open market {Artificial Intelligent Shopping System for Open Market}

The present invention (Disclosure) relates to an artificial intelligence shopping system applied to an open market, and specifically, a product capable of maximizing customer satisfaction at a minimum cost and using artificial intelligence to best suit the customer's purchasing conditions. It relates to an artificial intelligence shopping system applied to an open market that recommends products.

Here, the background arts of the present invention are provided, and they do not necessarily mean the prior art.

The general online market has an advantage in that customers can check various products provided by a large number of sellers without moving the location. However, there is a limit to the quality of the product. This is because it is confirmed through a 2D or 3D image prepared in advance, not the product itself.

In addition, instead of unnecessary physical movement of the customer, physical movement of the product in the long and medium distance is essential. This is the movement of goods using logistics systems such as courier or cargo delivery.

However, the online market has an advantage in that information about customer complaints or factors causing complaints can be disclosed or confirmed relatively transparently. In general, it is common for online sellers to post reviews of their products. Therefore, the satisfaction can be quantified by specifying the corresponding seller.

On the other hand, when purchasing a product in an online market, it is extremely rare to purchase only one product from one seller. In particular, when the product price is less than 10,000 won, the shipping cost may occupy a significant portion of the product price. Therefore, the general buyer of the online market often purchases the total amount to be purchased in accordance with the free shipping threshold for free shipping of the corresponding market.

In addition, in the online market, various products are displayed online by various sellers. Even for the same product, the price and quality of the product vary depending on the seller, and there are various indicators of factors that evaluate the seller, such as delivery and complaints.

No matter how good a quality product can be purchased at an affordable price, if the delivery time is more than a week or if there is a high probability of misdelivery, there is a difficulty in determining the customer's purchase.

Offline stores can check the real thing and immediately purchase it, and the process of returning or filing complaints can be clearly done offline.

However, in the online market, even if a delivery delay occurs, complaints about the delivery delay are forced to use online or wired or wireless calls. When making a purchase decision without confirming the real thing, factors other than the product price should be considered and applied to various products provided by various sellers.

In a conventional online market, a comparison function may be provided for the same product, the same function product, and the same product for product comparison. However, in this case, as a comparison structure that simply lists the performance and resources of the product, the customer has to compare a lot of information himself. In addition, the price information is the price of the product set by the seller, and unless it is a comparison between completely identical products, there is a problem that it is difficult to directly compare in reality.

1. Korea Patent Publication No. 10-2001-0035483

Disclosure of the Invention The present invention (Disclosure) aims to provide an artificial intelligence shopping system applied to an open market, by which artificial intelligence (artificial intelligent) can select and select the most suitable product for the customer's purchasing conditions.

Disclosure of the Invention The present invention (Disclosure) aims to provide an artificial intelligence shopping system applied to an open market that enables maximum customer satisfaction at a minimum cost.

Here, an overall summary of the present invention is provided, which should not be understood as limiting the periphery of the present invention (This section provides a general summary of the disclosure and is not a comprehensive disclosure of its full scope or all of its features).

In order to solve the above problems, an artificial intelligence shopping system applied to an open market according to an aspect of any of several aspects describing the present invention, in an open market, one or more products that a customer wants to purchase An input unit that receives order information including the quantity of each product from a customer; A search unit for searching all sellers selling the product in the open market; A seller information-storage unit in which seller information including the shipping cost for each seller and a free shipping threshold, and product information including the selling price of the product for each seller are stored; A comparison price-calculating unit that converts the selling price of the different sellers into a comparison price that can be directly compared for each product based on the order information, the seller information, and the product information; At least one combination of the comparison prices selected one by one for each product is generated, and an optimal ranking is generated by arranging the comparison price sums summing the comparison prices for each combination in a small order, and from the optimum ranking to a specific higher ranking. An optimal combination-selecting unit for selecting the combination as an optimal combination; A recommendation combination based on the seller information, calculating a delivery cost for each optimal combination, generating a recommendation ranking sorted in small order by summing the comparison price sums, and selecting a specific higher rank from the recommendation ranking as a recommendation combination- Sorting unit; And a display unit that displays the total price of the comparison, the total sales price, and the delivery cost for each of the recommended combinations to the customer.

In an artificial intelligence shopping system applied to an open market according to one aspect of several aspects describing the present invention, the recommendation combination-selecting unit calculates a sales price sum of the merchandise prices of the products for each recommendation combination And, the display unit may display the sum of the selling price to the customer by matching the recommendation ranking.

In an artificial intelligence shopping system applied to an open market according to an aspect of any of several aspects describing the present invention, the product information is a quality state and a weight for each quality state set by the seller for each product. Further comprising a quality status index, the seller information includes: a purchase satisfaction rate evaluated by all customers who have dealt with the seller with respect to the seller, a display state satisfaction rate with which the accuracy of the quality condition is evaluated, and an average delivery date of the seller , The return rate, the sales cancellation rate, and the number of return disputes.

In an artificial intelligence shopping system applied to an open market according to any one of several aspects describing the present invention, the comparison index may be defined by the following Equations 1 to 3.

[Calculation formula 1]

Comparative price = (Selling price x Commodity status index) + (Selling price x (100-company credit index) x 2/100)

[Calculation formula 2]

Product Status Index = 100 / Quality Status Index

[Calculation formula 3]

Company Credit Index = (Purchase Satisfaction + Notation Status + (100-Average Delivery Date) -Return Rate × 4-Sales Cancellation Rate × 4- (Number of Return Disputes × 10)) / 400

In order to solve the above problems, a method of operating an AI shopping system applied to an open market according to an aspect of any of several aspects describing the present invention, in an open market, a customer purchases through an input unit An order step of inputting order information including one or more types of products desired and quantities per product; A search step in which a search unit searches for all sellers selling the product in the open market; A sales information-storage unit, an information storage step of storing the seller information including the shipping cost for each seller and the free shipping threshold, and product information including the selling price of the product for each seller; A comparison price-calculating step of converting the selling price of the different sellers into a comparison price that can be directly compared for each product based on the order information, the seller information, and the product information; Optimal Combination-Selecting price, generating at least one combination of the comparison prices selected one by one for all the products, and arranging the comparison price sums summing the comparison prices for each combination in small order to generate an optimal ranking, and from the optimal ranking. An optimal combination-selection step of selecting the combinations up to a specific upper rank as an optimal combination; The recommended combination-selecting unit calculates the delivery cost for each optimal combination based on the seller information, generates the recommended rankings arranged in small order by summing the comparison price sums, and recommends the combination from the recommended ranking to a specific higher rank. Recommendation combination to select-selection step; And a display unit for displaying the comparison price sum and the delivery cost for each of the recommended combinations to the customer.

The operation method of the AI shopping system applied to the open market according to an aspect of any of several aspects describing the present invention may include, in the recommendation combination-selection step, the recommendation combination-selection unit for each recommendation combination. The method may further include a step of calculating a sales price sum of the merchandise prices, and in the display step, the display unit matches the sales price sum to the recommendation order and displays the sum to the customer.

In an operation method of an artificial intelligence shopping system applied to an open market according to an aspect of one of several aspects describing the present invention, the product information includes the quality state and the quality state established by the seller for each product. It further includes a quality status index that is a weight for each item, and the seller information includes a purchase satisfaction rate evaluated for the seller by all customers who have traded with the seller, a display state satisfaction rate for evaluating the accuracy of the quality state, and the seller. It may further include the average delivery date, return rate, sales cancellation rate, and the number of return disputes.

In the method of operating an AI shopping system applied to an open market according to any one of several aspects describing the present invention, the comparison index may be defined by the following Equations 1 to 3.

[Calculation formula 1]

Comparative price = (Selling price × Commodity status index) + (Sales price × (100-company credit index) * 2/100)

[Calculation formula 2]

Product Status Index = 100 / Quality Status Index

[Calculation formula 3]

Company Credit Index = (Purchase Satisfaction + Notation Status + (100-Average Delivery Date)-Return Rate * 4-Sales Cancellation Rate * 4-(Number of Return Disputes * 10)) / 400

According to the present invention, by using a comparative price capable of direct comparison calculated based on seller information and product information, it is possible to determine and select the product that is most suitable for the customer's purchasing condition by artificial intelligence.

According to the present invention, it is possible to maximize customer satisfaction at a minimum cost by selecting a product combination optimized for customer needs and determining whether free shipping conditions are satisfied by using the total amount of comparative prices.

1 is a block diagram showing an embodiment of an artificial intelligence shopping system applied to an open market according to the present invention.
Figure 2 is a flow chart of one embodiment of the operation method of the artificial intelligence shopping system applied to the open market according to the present invention.

Hereinafter, embodiments of implementing an artificial intelligence shopping system applied to an open market according to the present invention will be described in detail with reference to the drawings.

However, the intrinsic technical spirit of the present invention is not limited to the embodiments described below by the embodiments described below, and based on the intrinsic technical spirit of the present invention by the person skilled in the art It turns out that the embodiments described in the present invention encompass the range that can be easily proposed by the method of substitution or modification.

In addition, the terms used below are selected for convenience of description, and thus, in grasping the intrinsic technical spirit of the present invention, the terminology used herein is not limited to a dictionary meaning, and is properly interpreted in a meaning consistent with the technical spirit of the present invention. Should be.

Table 1 is an example of product information by seller of a product that a customer wants to purchase.

As shown in Table 1, sellers of a, b, c, d, e, and f sell at least one of nine products that the customer wants to purchase.

The list price is the price when each product is new, and when the product sold by each seller is a used product, the quality status of the product is expressed as one of the best, upper, and lower.

In general, the selling price of used goods is determined by the seller on an arbitrary basis. The quality of used products can be applied to various criteria compared to new products.

Physical damage or deterioration of the product surface or corners can be the primary product selection criteria. Alternatively, the function or contents of the product may be the main criterion for product selection.

Therefore, since the customer cannot confirm the actual product, the quality of the product published online cannot be completely trusted. Assuming that the quality status of the same products sold by different sellers is different, additional information is needed for the customer to select which seller's product to buy.

When comparing the same product, the customer generally selects and purchases the product corresponding to the minimum value for each product. However, as described above, since the selling price of the used product sets the quality condition on the basis of the seller's discretion, the quality of the actual product delivered may greatly deviate from the customer's expectations. When this situation occurs, the minimum value, which is the selection criterion at the time of purchase, does not become the actual minimum value.

As a result, the seller's price and quality alone do not guarantee the customer's satisfaction with the product after receiving the product, or the customer cannot decide which product to buy.

Table 2 is an example of seller information for each seller.

As shown in Table 2, seller information includes various evaluation factors that can provide a criterion for a customer to select a seller.

The purchase satisfaction is the satisfaction level of the customer with respect to the seller's overall sales behavior, and is preferably set in the range of 0% to 100%.

The satisfaction level of the display state evaluates the accuracy of the quality state. Among customers who have already dealt with the seller, it is the degree of agreement between the quality status determined by the seller and the quality status determined by the customer after receiving the actual product. Preferably, it is set in the range of 0 to 200%, and if the quality state determined by the customer and the quality state announced by the seller are the same, it is set to 100%. However, if it does not meet the customer's expectations, it will be set to less than 100%, while if it is in a good quality condition that exceeds the customer's expectation, it will be set to exceed 100%.

The average delivery date is calculated on a daily basis and is the average delivery date of all products sold by the seller.

The return rate is the ratio of the number of returns to the total number of transactions.

The sales cancellation rate is the ratio of the number of orders canceled by the customer due to a situation where the customer cancels the order or the seller cannot sell the product, such as out of stock.

The number of returns disputes is the total number of cases that have developed into disputes with the seller when the customer requests a return.

Such seller information may be a major criterion for a customer to select a seller in an online market where the product cannot be checked in real life.

In the general online market, products that have been ordered before a certain time period are processed based on the same day shipment as the order, and are notified to the customer. However, if you place an order beyond business hours, or if the order exceeds the number of shipments, or if the order and shipment are different, a delivery period of about 1 day or 2 days may be added.

For customers who need to receive goods urgently, delivery or delay of delivery can be a very important purchase standard.

When the return rate is high, it may be determined that the product of the corresponding seller causes the customer to have a high complaint rate. Returning a product from an online market can be more cumbersome compared to an offline market. Upon receipt of the courier, you can either return it or apply for courier delivery, but the customer must deliver the product.

Depending on the seller, a specific courier is requested to return. In this case, it is not possible to use an always-on collection system such as a convenience store. The return of products purchased in the online market also causes hassle for customers, and the return processing period may be longer. Therefore, the return rate may also serve as a customer's purchase criterion.

As described above, the price of the product disclosed in the online market through the Internet is arbitrarily set by the seller. In particular, in the case of used goods, it is not possible to expect the consistency of pricing to different sellers. Therefore, it is impossible for customers to compare products of different sellers.

Therefore, in general, the customer selects and orders the product with the lowest selling price. However, until the product is received and confirmed, the actual value of the product is not guaranteed to be the same as that of other sellers. Therefore, the product at the price selected by the customer does not substantially guarantee the value of the price. In addition, if a delay in delivery or a reason for return occurs, the actual product value may further decrease.

The factors that affect the product value of the open market on the online market can be quantified, but it is difficult to find a correlation between them as evaluation elements in different units or forms. Therefore, there is no evaluation element including all of these elements, and therefore objective evaluation is difficult. Since the objective evaluation factor cannot be introduced in this way, even in online purchases in which all purchasing activities are composed of digital information, the selection process of the most important product is inevitably dependent on the customer.

As can be seen from Tables 1 to 2, in the current general online shopping mall, the selling price capable of numerical comparison of products has a limitation in performing a practical comparison function. In addition, due to the uniqueness of the online open market, the seller or product information included in the purchasing decision factor together with the selling price cannot be quantified, and thus, it cannot function as a product selection element.

1 is a block diagram showing an embodiment of an artificial intelligence shopping system applied to an open market according to the present invention.

Referring to FIG. 1, the AI shopping system applied to the open market according to the present invention includes an input unit 100, a search unit 200, a sales information-storage unit 300, a comparison price, and an optimal combination with a calculation unit- It includes a selection unit 400 and a recommended combination-selection unit 500 and display unit 600.

The input unit 100 receives, from the customer, order information including one or more types of products and quantities for each product that a customer wants to purchase in an open market.

The search unit 200 searches for all sellers selling products in the open market.

The sales information-storage unit 300 stores seller information including a shipping cost for each seller and a free shipping threshold, and product information including a selling price of products for each seller.

The comparison price-calculation unit converts the selling price of different sellers into a comparison price that can be directly compared for each product based on order information, seller information, and product information.

The optimal combination-selecting unit 400 generates at least one combination of the comparison prices selected one by one for every product. In addition, the optimal rankings are generated by sorting the comparative price sums, which are the sum of the comparative prices for each combination, in a small order, and selecting the combinations from the optimal ranking to a specific higher ranking as the optimal combination.

Recommended Combination-Selecting unit 500, calculates the shipping cost for each optimal combination based on seller information, generates the recommended rankings sorted in small order by adding up the comparison price sums, and recommends the specific ranking to the highest ranking. Screening recommendation combination-selection unit 500;

The display unit 600 displays a comparison price sum, a sales price sum, and a delivery cost for each recommendation combination to the customer.

In addition, in the artificial intelligence shopping system applied to the open market according to the present invention, the recommendation combination-selecting unit 500 calculates the sum of the selling price of the merchandise selling price for each recommendation combination. At this time, the display unit 600 displays the sum of the selling price to the recommendation ranking and displays it to the customer.

In addition, in the artificial intelligence shopping system applied to the open market according to the present invention, the product information may further include a quality status index, which is preferably a quality status set by each seller and a weight for each quality status. In addition, the seller information, preferably, the purchase satisfaction evaluated by all customers who have dealt with the seller, the display status satisfaction evaluated by evaluating the accuracy of the quality condition, the average delivery date of the seller, the return rate, the sales cancellation rate and the return The number of disputes may be further included.

In addition, in the artificial intelligence shopping system applied to the open market according to the present invention, the comparative price is preferably defined by the following equations 1 to 3.

[Calculation formula 1]

Comparative price = (Selling price x Commodity status index) + (Selling price x (100-company credit index) x 2/100)

[Calculation formula 2]

Product Status Index = 100 / Quality Status Index

[Calculation formula 3]

Company Credit Index = (Purchase Satisfaction + Notation Status + (100-Average Delivery Date) -Return Rate × 4-Sales Cancellation Rate × 4- (Number of Return Disputes × 10)) / 400

The quality status index is determined according to the quality status shown in Table 1, and when the new status is 100%, when the quality status is lowered, the quality status index is also set to a small value.

That is, if the quality status of the product that the customer intends to purchase is applied as the main product selection criterion, the difference in the quality status index value according to the quality status can be increased. On the other hand, if the quality status of the product is not to be applied as a main product selection criterion, the difference in the value of the quality status stock according to the quality status can be reduced.

Table 3 is an example of the comparative price calculated by the artificial intelligence shopping system applied to the open market according to the present invention using the selling price of Table 1, and Table 4 is the optimal combination selected based on the comparative price of Table 3 It is the corresponding selling price. In addition, Table 5 is a recommended combination selected based on the optimal combination of Table 4, the free shipping standard of Table 2 and the comparative price of Table 3. Table 6 shows the shipping cost and free shipping standard for each seller.

The comparative price of Table 3, the comparative price calculated by the artificial intelligence shopping system applied to the open market according to the present invention, can be directly compared between the same products sold by different sellers.

The comparative price according to the present invention combines various factors affecting the value of a product purchased by a customer in an online market, and enables mutual direct comparison with numerical information. By converting the virtual “price” information that quantifies the selling price, it is possible to directly compare even small differences. In addition, by using quantitative information, it is possible to judge and select by artificial intelligence, and it is easy to verify or confirm after the purchasing act.

That is, it can be determined that the comparative price shown in Table 3 is closer to the product desired by the customer as the value is smaller.

For example, product 1 has a product of seller a 5470 and seller d has a product 3647. At this time, it can be determined that the seller's product 1 having a comparative price of 3647 is more suitable for the customer's purchasing conditions.

On the other hand, in Product 2, the comparison price 5002 of the product 2 of the seller b is lower than the comparison price 5010 of the product 2 of the seller a. Therefore, even if the quality condition is high, it can be determined that product 2 of seller b is a product more suitable for the customer's purchasing condition.

Referring to Table 4, based on the comparative price selected in Table 3, the selected-seller and the seller including at least one of the selected-price and the selected-price are shown as a seller.

Referring to Table 4, the selling price corresponding to the comparative price selected in Table 3 is selected as the selection price. Sellers that include at least one sorting-price are selected as sorting-sellers. That is, the selected sort-seller is sellers a, b, d, e, f. If the sum of the selected sorting-seller-selecting prices is 30,500 won, the total shipping cost is 11,500 won. Therefore, the total amount that the customer has to pay for purchasing nine products is 42,000 won.

Referring to Table 6, the free shipping threshold varies by seller. The free shipping standard of Seller a and Seller b is the lowest with 20,000 won.

Referring to Table 4, it is possible to calculate the difference between the total selling price of the product for each seller included in the optimal combination and the free shipping threshold. Among the products of seller a, the products included in the optimal combination are products 4, 6, and 7, and the total selling price of these products is 16,000 won. Since the free shipping standard is 20,000 won, if you add a product of 4,000 won, you can receive free shipping benefits from seller a.

Referring to Table 5, in the optimal combination of Table 4, Product 2 and Product 5 were changed from Seller b and Seller d to Seller a, respectively, and selected as a recommended combination.

If this happens, you will have to pay 1,500 more for the sale price. Since the shipping cost of seller a is reduced by 2,500 won, 1,000 won can be reduced from the total purchase cost.

In conclusion, the AI shopping system applied to the open market according to the present invention selects products capable of maximizing customer satisfaction as objective numerical information, and minimizes changes to products optimized for the customer's purchasing requirements, Purchase costs, including shipping costs, can be minimized.

In addition, referring to Table 5, product 1 of seller d may be changed to product 1 of seller a. The delivery cost of seller d is reduced, and since seller a is already free shipping, the distribution of product 1 is increased by 1,000 won, but the delivery cost of seller d is reduced by 3,000. Therefore, in this case, the purchase cost becomes 2,000 won cheaper.

However, when creating the recommended combination of Table 5 by changing the seller of each product of the optimal combination of Tables 3 to 4, the sum of the comparison prices of products by seller included in the changed recommended combination is the product of each seller included in the optimal combination The comparison price of is increased than the sum. That is, a product that does not meet the customer's purchasing conditions may be selected as a purchase target.

Therefore, the artificial intelligence shopping system applied to the open market according to the present invention according to the present invention sorts the sum of the comparative price and the sum of the shipping cost in consideration of the free shipping threshold condition, in order of small value, and information up to a specific upper rank By disclosing to the customer, the customer can select the product quality and actual payment cost.

Figure 2 is a flow chart of one embodiment of the operation method of the artificial intelligence shopping system applied to the open market according to the present invention.

Referring to FIG. 2, according to the present invention, an operation method of an artificial intelligence shopping system applied to an open market, first, in an ordering step, inputs order information including one or more types of products that the customer wants to purchase and quantity per product.

In the search step, based on the entered order information, the search unit 200 searches for all sellers selling products in the open market.

Next, in the information storage step, the sales information-storage unit 300 stores seller information including a shipping cost for each seller and a free shipping standard, and product information including a selling price of a product for each seller.

Next, in the comparison price-calculation step, the comparison price-calculation unit converts the selling prices of different sellers into comparison prices that can be directly compared for each product based on order information, seller information, and product information.

Next, in the optimal combination-selection step, at least one combination of the optimal combination-selector price and the comparison price selected one by one for all products is generated, and the optimal price is generated by sorting the comparison price sums that combine the comparison prices for each combination in a small order. Then, the combination from the optimal rank to a specific upper rank is selected as the optimal combination.

In the recommendation combination-selection step, the recommendation combination-selection unit 500 calculates the shipping cost for each optimal combination based on seller information, generates the recommendation rankings arranged in small order by adding up the comparison price sums, and selects the recommendation rankings. The top ranking is selected as a recommended combination.

In the display step, the display unit 600 displays a comparison price sum, a sales price sum, and a delivery cost for each recommendation combination to the customer.

In addition, according to the present invention, in the method of operating the AI shopping system applied to the open market, in the recommendation combination-selection step, the recommendation combination-selection unit 500 calculates the sum of the sales price of the products for each recommendation combination. The method may further include a step of displaying, and in the display step, the display unit 600 may further include displaying the sum of sales prices in a recommendation order and displaying the sum to the customer.

The customer may check the comparison price total, shipping cost, and sales price total for each recommended combination displayed on the display unit 600, select one of the recommended combinations, make a purchase decision, and perform payment.

On the other hand, the customer can start the order phase again without selecting any of the recommended combinations. At this time, the order condition can be changed by changing the quality state without changing the product.

Claims (8)

In an open market, an input unit that receives order information including one or more types of products that a customer wants to purchase and quantities per product;
A search unit for searching all sellers selling the product in the open market;
A seller information-storage unit in which seller information including the shipping cost for each seller and a free shipping threshold, and product information including the selling price of the product for each seller are stored;
A comparison price-calculating unit that converts the selling price of the different sellers into a comparison price that can be directly compared for each product based on the order information, the seller information, and the product information;
At least one combination of the comparison prices selected one by one for each of the products is generated, and an optimal ranking is generated by arranging the comparison price sum of the comparison prices for each combination in a small order, and from the optimum ranking to a specific higher ranking. An optimal combination-selecting unit for selecting the combination as an optimal combination;
Based on the seller information, calculate the shipping cost for each optimal combination, generate the recommended rankings sorted in small order by summing the comparison price sums, and select the recommended combination from the recommended ranking to a specific higher ranking as the recommended combination- Sorting unit; And
And a display unit for displaying the sum of the comparison price, the sum of the selling price, and the shipping cost for each of the recommended combinations to the customer, the artificial intelligence shopping system applied to an open market. The method according to claim 1,
The recommended combination-selection unit,
The sum of the selling prices of the products for each of the recommended combinations is calculated,
The display unit is the artificial intelligence shopping system applied to the open market, characterized in that to display to the customer by matching the total sales price to the recommendation ranking. The method according to claim 1,
The product information,
Further comprising a quality status index, which is the weight of the quality status and the quality status established by the seller for each product,
The above seller information,
It further includes the purchase satisfaction assessed for the seller by all customers who have dealt with the seller, the display status satisfaction assessed for the accuracy of the quality status, the average delivery date of the seller, the return rate, the sales cancellation rate, and the number of returns disputes. Characterized in that, the artificial intelligence shopping system applied to the open market. The method according to claim 3,
The comparison index, AI shopping system applied to the open market, characterized in that defined by the following equation 1 to equation 3:
[Calculation formula 1]
Comparative price = (Selling price x Commodity status index) + (Selling price x (100-company credit index) x 2/100)
[Calculation formula 2]
Product Status Index = 100 / Quality Status Index
[Calculation formula 3]
Company Credit Index = (Purchase Satisfaction + Notation Status + (100-Average Delivery Date) -Return Rate × 4-Sales Cancellation Rate × 4- (Number of Return Disputes × 10)) / 400 In an open market, an ordering step of inputting order information including one or more types of products desired by the customer to purchase and quantities for each product through an input unit;
A search step in which a search unit searches for all sellers selling the product in the open market;
A sales information-storing unit, an information storage step of storing the seller information including the shipping cost for each seller and the free shipping threshold, and product information including the selling price of the product for each seller;
A comparison price-calculating step of converting the selling price of the different sellers into a comparison price that can be directly compared for each product based on the order information, the seller information, and the product information;
Optimal Combination-Selection price, at least one combination of the comparison prices selected one by one for all the products is generated, and an optimal ranking is generated by arranging the comparison price sum of the comparison prices for each combination in a small order, and in the optimal ranking An optimal combination-selection step of selecting the combinations up to a specific upper rank as an optimal combination;
The recommended combination-selecting unit calculates the delivery cost for each optimal combination based on the seller information, generates the recommended rankings arranged in small order by summing the totals of the comparative prices, and recommends the combination from the recommended ranking to a specific higher rank Recommendation combination-selection step to select by; And
And a display unit displaying the comparison price sum and the delivery cost for each of the recommended combinations to the customer. A method of operating an artificial intelligence shopping system applied to an open market, comprising: The method according to claim 5,
In the recommended combination-selection step,
Further comprising the step of calculating the sum of the selling price of the product by the recommended combination-selecting unit by the recommended combination;
In the display step,
And displaying, by the display unit, the total sales price matching the recommendation ranking and displaying the sum to the customer, further comprising the method of operating an artificial intelligence shopping system applied to an open market. The method according to claim 5,
The product information,
Further comprising a quality status index, which is the weight of the quality status and the quality status established by the seller for each product,
The above seller information,
All customers who have dealt with the seller further include the purchase satisfaction rating for the seller, the display state satisfaction rating for evaluating the accuracy of the quality status, the average delivery date of the seller, the return rate, the sales cancellation rate and the number of returns disputes. A method of operating an artificial intelligence shopping system applied to an open market, characterized by including The method according to claim 7,
The comparison index, characterized in that defined by the following equations 1 to 3, the operation method of the artificial intelligence shopping system applied to the open market
[Calculation formula 1]
Comparative price = (Selling price x Commodity status index) + (Selling price x (100-company credit index) x 2/100)
[Calculation formula 2]
Product Status Index = 100 / Quality Status Index
[Calculation formula 3]
Company Credit Index = (Purchase Satisfaction + Notation Status + (100-Average Delivery Date) -Return Rate × 4-Sales Cancellation Rate × 4- (Number of Return Disputes × 10)) / 400

Images