Product recommendation methods and systems

Abstract

This invention provides a product recommendation method and system for recommending appropriate products that reflect user needs. [Solution] In order to solve the above problems, the product recommendation method according to the present invention may include the steps of: identifying target story information including at least one of target subject information and target intent information; obtaining a recommended product category corresponding to the target story information based on sample story information including at least one of sample subject information and sample intent information, and sample product categories corresponding to each of the sample story information; and extracting at least one recommended product from among the products belonging to the recommended product category that matches the target story information.

Claims

1. In a product recommendation method using a chatbot, The steps include receiving a message from the user's terminal via the chatbot, The steps include inputting the message received from the user terminal into a large language model, The steps include: obtaining recommended product information corresponding to the message from the aforementioned large language model; The steps include: extracting recommended products corresponding to the recommended product information obtained from the large language model via the product recommendation engine; The steps include providing the recommended products to the user terminal via the chatbot, and A product recommendation method using a chatbot, characterized by including the following features.

2. A product recommendation method using a chatbot according to claim 1, further comprising the step of identifying story information related to the recommended product based on the message received from the user terminal.

3. The process further includes the step of providing a question message to the user's terminal via the chatbot, The product recommendation method using a chatbot according to claim 2, characterized in that, in the step of providing the question message to the user terminal, a message is configured to guide the user terminal to provide additional information in order to obtain the information necessary to construct the story information.

4. The product recommendation method using a chatbot according to claim 3, characterized in that, in the step of providing the question message to the user terminal, the question message is provided to the user terminal multiple times in order to induce the additional information.

5. The product recommendation method using a chatbot according to claim 4, characterized in that the question messages provided to the user terminal multiple times in order to induce the additional information include questions related to at least one of the target recipients who will receive the recommended product as a gift and target intent information that corresponds to the purpose of giving the recommended product as a gift.

6. The steps include providing a specific page for the shopping service to the user terminal, A method for recommending products using a chatbot according to claim 1, further comprising the step of identifying story information related to the recommended product based on information entered into an information input area included in the specific page.

7. The steps include providing the user terminal with a specific page for the product recommendation service, A method for recommending products using a chatbot according to claim 1, further comprising the step of identifying story information related to the recommended product based on information entered into an information input area included in the specific page.

8. A product recommendation method using a chatbot according to claim 1, further comprising the step of processing user information of a user account logged into the user terminal as input to the large language model so that it can be used in the large language model to extract the recommended products.

9. The product recommendation method using a chatbot according to claim 8, characterized in that the user information includes at least one of the user's gender, age, residential area, and occupation corresponding to the user account.

10. The aforementioned recommended products are available for purchase on at least one product sales website accessible via the internet. The product recommendation method according to claim 1, further comprising the step of providing the user terminal with product sales information linked to the sales page of the recommended product when the recommended product is extracted.

11. The product recommendation method according to claim 10, further comprising the step of generating a message related to the recommended product using at least a portion of the message and information relating to the recommended product when the recommended product is purchased.

12. The product recommendation method according to claim 11, characterized in that the step of generating a message related to the recommended product generates a message that includes at least one of information about a recipient who will receive the recommended product as a gift and information about the intention behind giving the recommended product as a gift.

13. In a product recommendation system using a chatbot, The aforementioned system, The chatbot receives messages from the user's terminal. The message received from the user terminal is input into the large language model. The recommended product information corresponding to the message is obtained from the aforementioned large language model. The recommended products corresponding to the recommended product information obtained from the large language model are extracted via the product recommendation engine. The recommended products are provided to the user terminal via the chatbot. A product recommendation system using a chatbot, characterized by the following features.

14. The steps include receiving a message from the user's device via a chatbot, The steps include inputting the message received from the user terminal into a large language model, The steps include: obtaining recommended product information corresponding to the message from the aforementioned large language model; The steps include: extracting recommended products corresponding to the recommended product information obtained from the large language model via the product recommendation engine; The steps include providing the recommended products to the user terminal via the chatbot, and A program stored on a computer-readable recording medium, characterized by containing instructions to execute a program.

Images