Commodity recommendation method and system

Abstract

To provide a commodity recommendation method and a system for recommending an appropriate commodity by reflecting the needs of a user.SOLUTION: A commodity recommendation method may include the steps of: identifying target story information including at least one of target object information and target intention information; acquiring a recommendation commodity category corresponding to the target story information, on the basis of sample story information including at least one of sample object information and sample intention information, and sample commodity categories corresponding to the sample story information; and extracting at least one recommendation commodity matched with the target story information, out of commodities belonging to the recommendation commodity category.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a product recommendation method and system for recommending appropriate products that reflect the needs of a user. [Background technology]

[0002] The dictionary definition of artificial intelligence is a technology that realizes human learning abilities, reasoning abilities, perception abilities, natural language understanding abilities, etc. through computer programs. This type of artificial intelligence has made great strides thanks to deep learning.

[0003] In particular, with the advancement of artificial intelligence, various language models have been developed, and these language models have reached a level where they can not only recognize text and understand its meaning, but also extract and classify information from data containing huge amounts of text such as documents, and even directly generate text.

[0004] Such language models are actively used in a variety of fields, such as search engines, document creation (e.g., resume writing, report writing, bulletin board writing, etc.), free dialogue on various topics, data parsing in a given text (e.g., data summarization, classification, etc.), providing expert knowledge, programming, converting a given text into a text of an appropriate style, and many other fields where text can be based.

[0005] Based on such language models, it is possible to automate various tasks that have traditionally been performed directly by humans. In particular, it is possible to automate text-based tasks that have been directly generated or edited by humans in various service fields (e.g., shopping services, news services, etc.). In doing so, however, research is required on methods of utilizing language models while taking into account the characteristics of the service. Summary of the Invention [Problem to be solved by the invention]

[0006] The present invention provides a product recommendation method and system that can be utilized for shopping services.

[0007] In particular, the present invention provides a product recommendation method and system capable of recommending an appropriate product according to the target and intention of the gift when a user purchases a product to give as a gift to another person.

[0008] Furthermore, the present invention provides a product recommendation method and system capable of recommending appropriate products according to the user's situation or the situation for giving a gift, using a language model. [Means for solving the problem]

[0009] In order to solve the above problem, the product recommendation method according to the present invention may include a step of identifying target story information including at least one of target subject information and target intention information, a step of acquiring 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 intention information and sample product categories corresponding to the sample story information, and a step of extracting at least one recommended product that matches the target story information from among products belonging to the recommended product category.

[0010] The product recommendation method according to the present invention may include the steps of receiving target story information from a user terminal, the target story information including information regarding at least one of a gift target and a gift intention; constructing a first prompt to be input to a pre-specified large language model using at least one dataset including sample story information and theme information of a sample product category, and the target story information; obtaining a plurality of theme keywords corresponding to the target story information as an output of the large language model based on the first prompt; providing the plurality of theme keywords to the user terminal, and at least one of the plurality of theme keywords is selected in the user terminal; constructing a second prompt including a specific theme keyword selected in the user terminal; and obtaining a recommended gift category corresponding to the target story information from the large language model by processing the second prompt including the specific theme keyword as an input to the large language model.

[0011] The product recommendation system according to the present invention may include a storage unit that stores sample story information including at least one of sample subject information and sample intention information, and sample product categories corresponding to the sample story information, and a control unit that performs a process of acquiring a recommended product category corresponding to target story information based on the sample story information and the sample product categories corresponding to the sample story information, using a pre-specified large language model, and a process of extracting at least one recommended product that matches the target story information from among products belonging to the recommended product category.

[0012] A program executed by one or more processes in an electronic device according to the present invention and stored on a computer-readable recording medium may include commands to perform the steps of identifying target story information including at least one of target subject information and target intention 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 intention information, and sample product categories corresponding to the sample story information respectively, and extracting at least one recommended product that matches the target story information from among products belonging to the recommended product category. Effect of the Invention

[0013] As described above, the product recommendation method and system according to the present invention can extract recommended products using a large language model that receives as input a prompt containing story information.

[0014] Here, the story information is configured to include information regarding the recipient of the recommended product and the intention of the purchaser to purchase the recommended product, so that in the present invention, a product that reflects the intention of the user to purchase the recommended product can be recommended.

[0015] In this way, the product recommendation method and system according to the present invention can recommend products according to the story of the user who will give the recommended product as a gift from a large language model by constructing a prompt using story information that reflects the recipient of the recommended product and the intention of giving the recommended product. Therefore, according to the present invention, it is possible to reduce the time required to select a product to give as a gift, and to purchase a product that is optimized according to the recipient and the intention of the gift. [Brief description of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram for explaining an example of application of a product recommendation method and system according to the present invention. [Diagram 2] 1 is a conceptual diagram for explaining a product recommendation system according to the present invention. [Diagram 3] 2 is a flowchart illustrating a product recommendation method according to the present invention. [Figure 4] 1 is a conceptual diagram for explaining a prompt utilized in a product recommendation method and system according to the present invention; [Diagram 5] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 6] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 7A] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 7B] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 8] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 9A] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 9B] 1 is a conceptual diagram for explaining a method of inputting story information in a product recommendation method and system according to the present invention. [Figure 10A] 1 is a conceptual diagram for explaining an example of a prompt utilized in the product recommendation method and system according to the present invention; [Figure 10B] 1 is a conceptual diagram for explaining an example of a prompt utilized in the product recommendation method and system according to the present invention; [Figure 11] 1 is a conceptual diagram for explaining an example of a prompt utilized in the product recommendation method and system according to the present invention; [Figure 12A] 1 is a conceptual diagram for explaining an example of a prompt utilized in the product recommendation method and system according to the present invention; [Figure 12B] 1 is a conceptual diagram for explaining an example of a prompt utilized in the product recommendation method and system according to the present invention; [Figure 13A] FIG. 2 is a conceptual diagram for explaining product categories and a product recommendation method. [Figure 13B] FIG. 2 is a conceptual diagram for explaining product categories and a product recommendation method. [Figure 13C] FIG. 2 is a conceptual diagram for explaining product categories and a product recommendation method. [Figure 14] FIG. 2 is a conceptual diagram for explaining a method of extracting recommended products in the product recommendation method and system according to the present invention. [Figure 15] FIG. 2 is a conceptual diagram for explaining a method of extracting recommended products in the product recommendation method and system according to the present invention. [Figure 16A] 1 is a conceptual diagram for explaining a message generating method in a product recommendation method and system according to the present invention; [Figure 16B] 1 is a conceptual diagram for explaining a message generating method in a product recommendation method and system according to the present invention; [Figure 17A] 1 is a conceptual diagram for explaining a message generating method in a product recommendation method and system according to the present invention; [Figure 17B] 1 is a conceptual diagram for explaining a message generating method in a product recommendation method and system according to the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the attached drawings. The same or similar components are denoted by the same or similar reference numerals regardless of the drawing numbers, and the description thereof will be omitted. The suffixes "module" and "part" of components used in the following description are given or mixed to facilitate the preparation of the specification, and do not have any significance or usefulness in themselves. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of related publicly known technology may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof will be omitted. Note that the attached drawings are merely for the purpose of making the embodiments disclosed in this specification easily understandable, and the technical ideas disclosed in this specification are not limited by the attached drawings, and it should be understood that any modifications, equivalents, or alternatives included in the idea and technical scope of the present invention are included in the present invention.

[0018] Terms including ordinal numbers such as first, second, etc. are used to describe various components, but the components are not limited to the terms. The terms are used only to distinguish one component from another.

[0019] When a component is said to be "coupled" or "connected" to another component, it should be understood that the component may be directly coupled or connected to the other component, and that there may be additional components in between. In contrast, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no additional components in between.

[0020] Singular expressions include plural expressions unless otherwise specified.

[0021] As used herein, terms such as "comprise" and "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof set forth in the specification, but should not be understood to preclude the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0022] As described above, various language models have been developed with the advancement of artificial intelligence, and based on these, it has become possible to automate various tasks that were previously performed directly by humans. In particular, it has become possible to automate various tasks that were previously selected or generated directly by humans in various service fields (e.g., shopping services, news services, etc.). In particular, the present invention provides a product recommendation method and system that can recommend products suitable for a user by taking into account various situations of the user who purchases the product.

[0023] A user purchases products on the Internet for himself or herself or for others, and particularly when purchasing a product for another person, there may be a recipient and an intention to give the purchased product.

[0024] For example, purchasing a product for someone else may result in giving it as a gift to that person. In this case, the user can search for and purchase the product to give on the Internet, keeping in mind the intention and the recipient of the gift.

[0025] The present invention provides a method and system for recommending products to facilitate the convenience of users who purchase products for others. The present invention can provide a method and system for recommending products that can reduce the time a user spends selecting products to purchase for others and can recommend products according to the user's intention to purchase the product and the recipient of the product.

[0026] In the present invention, for the sake of convenience, the terms "purchase of a product" and "purchase of a present" are used interchangeably, and the present invention is not necessarily limited to purchasing a present. In other words, it goes without saying that the present invention can be used when a user purchases a product for himself or herself, or when purchasing a product for someone else who is not intended to be a present. Therefore, the "purchase of a present" in the present invention may be replaced with "purchase of a product" or may be interpreted as "purchase of a product". However, in the case of purchasing a present, there is a difference in that the purchaser of the product and the user of the product are different, and therefore the product cannot be recommended by directly reflecting the purchaser's behavioral characteristics and preferences. The present invention provides a method for solving such a problem. The term "product" in this case may be used not only for tangible goods but also for intangible services.

[0027] More specifically, as shown in Fig. 1, the product recommendation method and system according to the present invention may recommend products to a user using story information, where the products recommended to the user may be products that the user can purchase on the Internet.

[0028] The story information in the present invention may include information on at least one of a target and an intention. Here, the "target" may be understood as a party who receives a product recommended in the product recommendation system according to the present invention. For example, when a user uses the product recommendation system according to the present invention for a gift, the "target" may be a person (the party or the other person) who receives the gift. Here, the information on the target (or target information) included in the story information may be composed of at least one of various pieces of information that can describe a specific person corresponding to the target, such as gender, age, occupation, relationship with the user, hobbies, preferences, and place of residence.

[0029] Furthermore, the "intention" may be interpreted as the reason or purpose of a user who purchases a product recommended in the product recommendation system according to the present invention. For example, when a user purchases a product as a gift, the "intention" may be interpreted as at least one of various pieces of information that may explain the intention of the gift (e.g., a housewarming gift, a moving gift, a wedding anniversary gift, etc.).

[0030] Meanwhile, in the product recommendation method and system according to the present invention, the story information can be input by the user in various ways. For example, the story information can be input by the user on a service page 110 provided by the product recommendation system according to the present invention, or can be selected from a story information list 112 provided as shown in FIG. 1(a).

[0031] Meanwhile, in the product recommendation system according to the present invention, a recommended product category corresponding to the story information may be acquired using a language model (LM) or a large language model 10. Furthermore, in the product recommendation system according to the present invention, based on that, as shown in Fig. 1(b), recommended products corresponding to the story information may be extracted and provided to the user. Also, at least one keyword related to the recommended products or keywords that can classify them may be extracted and provided to the user.

[0032] Meanwhile, the language model utilized in the present invention is not limited in type, and may be any language model that has been trained on various information. Meanwhile, a large-scale language model or a hyperscale language model that has been actively researched in recent years is a model trained with a large amount of data using a model having parameters (or variables) (e.g., more than 100 billion parameters) that are 10 times larger than conventional general language models, and can be inferred without fine-tuning the model using a method such as few-shot learning. In such a large-scale language model, a pre-trained model can understand patterns in the prompt by inputting a prompt including a small amount of example data, and can generate and output a probability distribution of a word sequence or a word (or sentence) based on the distribution.

[0033] Here, the recommended product category may be interpreted as a category or type to which the recommended product belongs. Product categories may be classified based on various criteria such as product use, product color, product price range, etc. For example, product categories may include categories such as accessories, stationery, and automotive supplies depending on the product use. Here, the recommended product in the present invention may mean a product that belongs to a specific category and can actually be purchased on the Internet. In other words, the product recommendation system according to the present invention may recommend products to a user and even support the user in purchasing the recommended product.

[0034] Here, the recommended product may be made available for purchase on a shopping service page 120 (e.g., a web page or an application page) provided by a shopping service linked to the product recommendation system according to the present invention, as shown in (b) of FIG. 1.

[0035] Hereinafter, the product recommendation method and system according to the present invention will be described in more detail with reference to the accompanying drawings. FIG. 2 is a conceptual diagram for explaining the product recommendation system according to the present invention, and FIG. 3 is a flow chart for explaining the product recommendation method according to the present invention. FIG. 4 is a conceptual diagram for explaining a prompt used in the product recommendation method and system according to the present invention, and FIGS. 5, 6, 7A, 7B, 8, 9A, and 9B are conceptual diagrams for explaining a method of inputting story information in the product recommendation method and system according to the present invention. Also, FIGS. 10A, 10B, 11, 12A, and 12B are conceptual diagrams for explaining examples of prompts used in the product recommendation method and system according to the present invention, and FIGS. 13A, 13B, and 13C are conceptual diagrams for explaining a product category and a product recommendation method. FIGS. 14 and 15 are conceptual diagrams for explaining a method of extracting recommended products in the product recommendation method and system according to the present invention, and FIGS. 16A, 16B, 17A, and 17B are conceptual diagrams for explaining a method of generating a message in the product recommendation method and system according to the present invention.

[0036] 2, a product recommendation system 200 according to the present invention may include at least one of an input unit 210, a storage unit 220, and a control unit 230. Although not shown, the product recommendation system 200 may further include a communication unit, which may be configured to communicate with at least one server or electronic device (or user terminal).

[0037] Furthermore, the product recommendation system 200 may be configured to include at least one of the large language model 10 and the product recommendation engine 20, and may be configured to operate in conjunction with at least one of them.

[0038] The product recommendation system 200 according to the present invention may acquire a recommended product category from the large language model 10 based on story information input to the large language model 10, and extract recommended products corresponding to the recommended product category by the product recommendation engine 20. At least a part of the configuration of the product recommendation system 200 may play a role in processing information input to at least one of the large language model 10 and the product recommendation engine 20, or in processing information output from at least one of the large language model 10 and the product recommendation engine 20.

[0039] Regarding the input unit 210, the input unit 210 may serve to input information constituting a prompt to be input to the large language model 10.

[0040] The input unit 210 may include i) an interface that connects a user (or a user terminal) and the product recommendation system 200 according to the present invention, or ii) an interface that connects the product recommendation system 200 according to the present invention and at least one other system. Furthermore, the input unit 210 may include an interface that connects between components included in the product recommendation system 200 according to the present invention.

[0041] In the present invention, a prompt may be input to the large language model 10 to obtain recommended product categories and corresponding recommended products as a result.

[0042] Here, the recommended product category may be acquired from the large language model 10, and the recommended products belonging to the recommended product category may be acquired from the product recommendation engine 20. The control unit 230 may control a series of processes for acquiring recommended products from the product recommendation engine 20 by inputting information related to the recommended product category acquired from the large language model 10 to the product recommendation engine 20.

[0043] A prompt input to the large language model 10 is data input to the large language model 10, as shown in (a) of Figure 4, and may include datasets 411, 412, 413 (hereinafter referred to as "sample datasets") that are referenced in the large language model 10, and a dataset 414 (hereinafter referred to as "target dataset") that corresponds to the information to be obtained from the large language model 10.

[0044] Such data sets 411, 412, 413, 414 may include the story information described above.

[0045] The sample data set may be configured with a pair of sample story information and information on a sample product category corresponding to the sample story information. Here, the sample story information may be generated using information created or produced by a user, or may be generated by extracting a target and an intention from a product purchase history of the user. In addition, the sample story information may be generated by inputting a prompt including the above-mentioned information (e.g., information created or produced by a user, a product purchase history of the user, etc.) into a trained language model or a large language model.

[0046] The target story information included in the target dataset may be data input by the user in text format or data selected from a story information list, as described with reference to (a) of Fig. 1. In addition, the target story information may be generated by combining at least one of various pieces of information such as basic information of the user (e.g., age, gender, etc.) and information input by the user (e.g., target, intent, etc.).

[0047] The target dataset does not include a target product category corresponding to the target story information, i.e., a recommended product category, which may be configured to be obtained from the large language model 10 .

[0048] The prompt 410 may be configured to include at least one sample data set 411, 412, 413 and / or a target data set 414. The configuration of the prompt is described in more detail below. The configuration of the information and the method of obtaining the corresponding product category are also described in more detail below.

[0049] Meanwhile, according to another embodiment of the present invention, the prompt input to the large language model 10 may be an embedding vector generated using a trained embedding model instead of a text format. Here, the prompt embedding model may be trained using sample story information created or generated by a user, or sample story information generated by extracting targets and intentions from a user's product purchase details.

[0050] Next, various information may be stored in the storage unit 220. The storage unit 220 may be present inside or outside the product recommendation system according to the present invention. It goes without saying that the storage unit 220 may be configured as a server or as a cloud-based storage.

[0051] The storage unit 220 may store data relating to at least one of a plurality of sample data sets and a target data set.

[0052] The plurality of sample data sets may be configured to include at least one of story information, product category information, theme information, keyword information, and tag information.

[0053] At least a portion of the various information contained in the sample data sets listed above may be comprised of information collected at various pages accessible via the Internet.

[0054] The collected information may be composed of information created or produced by any user on the Internet. Such data may be called UGC (User Generated Contents). Furthermore, at least a portion of the various information included in the sample dataset may be composed of information generated by the large language model 10.

[0055] In this manner, the storage unit 220 may store at least one of story information, product category information, theme information, keyword information, and tag information collected through various routes, which may be paired together to form a data set to be input to the prompt.

[0056] Next, the control unit 230 may perform general control required to obtain the recommended product category and the recommended product. As an example, the control unit 230 may be linked with the large language model 10 so that the prompt 410 is processed as an input to the large language model 10. Furthermore, the product recommendation system 200 according to the present invention may include the large language model 10 as one component, and then the control unit 230 can perform appropriate control over the large language model 10.

[0057] As another example, the control unit 230 may be configured to work in conjunction with the product recommendation engine 20 such that information regarding recommended product categories obtained from the large language model 10 is processed as input to the product recommendation engine 20 .

[0058] Meanwhile, the information generated by the large language model 10 may be stored in the storage unit 220, or may be configured to be output from an output unit (not shown) so that the user can check it, and may be appropriately processed according to the situation. The control unit 230 may process the information generated by the large language model 10, and may provide the information to a user terminal when information on a recommended category needs to be visually output to the user, for example.

[0059] In the product recommendation method and system according to the present invention, as shown in Figures 1 and 2, a data set including at least one of story information and information related to the corresponding product category may be input to a large language model 10 to obtain a recommended product category.

[0060] As described with reference to FIG. 4, the large language model 10 is input with a prompt 410 consisting of sample data sets 411, 412, 413 and a target data set 414, and each data set may consist of data fields corresponding to a type of data (category, or data type, data attribute) and corresponding data values.

[0061] A data field may be interpreted as defining the meaning of a data value or the type of the data value, such as "story information" or "product category," as shown in (a) of Figure 4. Such a data field may also be interpreted as "category name," "data type," "data attribute," etc.

[0062] Alternatively, data fields may follow predefined rules so that they can be recognized by the large language model 10. For example, the large language model 10 may recognize that data entered after "Story Info:" is data that falls into the data field "Story Info."

[0063] In the large language model 10, data pairs contained in the dataset may be referenced to generate data corresponding to a specific data field (eg, "product category:") contained in the target dataset.

[0064] In the present invention, as shown by reference numeral 414b in Fig. 4(a), the end of the prompt 410 may be configured with only a data field, so that the corresponding data value can be obtained as the output of the large language model 10. As a result, as shown by reference numeral 424b in Fig. 4(b), a data value (picture frame, potted plant, vase, diffuser, candle warmer, lighting, etc.) for the "product category" data field can be obtained.

[0065] It goes without saying that the names of the data fields may be changed to appropriate terms depending on the situation.

[0066] Next, the product recommendation engine 20 is an engine that recommends products that belong to a recommended product category obtained from the large language model 10, and may be configured to recommend at least one appropriate product based on the similarity between at least two of the story information, the product category, and the product name. In the present invention, the product recommendation engine 20 may be of any type.

[0067] Hereinafter, a method for generating product recommendation information will be described in more detail with reference to the above-described product recommendation system 200 according to the present invention.

[0068] As shown in FIG. 3, in the present invention, a step of identifying target story information may be performed (S310).

[0069] As described above, the target story information may refer to a product category and story information that is the subject of product recommendations.

[0070] The target story information may include information on at least one of a target subject and a target intention. Here, the target subject may be understood as a party who receives a product recommended in the product recommendation system according to the present invention. For example, when a user uses the product recommendation system according to the present invention for a gift, the "target subject" is a person (party or other party) who receives the gift. Here, the information on the target subject (or subject information) included in the target story information may be composed of at least one of various pieces of information that can describe a specific person corresponding to the target subject, such as gender, age, occupation, relationship with the user, hobbies, preferences, and place of residence.

[0071] Furthermore, the "target intent" may be interpreted as the reason or purpose of a user who purchases a product recommended in the product recommendation system according to the present invention to purchase the product. For example, when a user purchases a product as a gift, the "target intent" may be interpreted as at least one of various pieces of information that may explain the intent of the gift (e.g., a housewarming gift, a moving gift, a wedding anniversary gift, etc.).

[0072] On the other hand, the above-mentioned “target story information,” “target object,” and “target intention” have the same or similar meanings as the above-defined “story information,” “object,” and “intent,” but for the sake of convenience, the term “target” has been added to distinguish them from “sample story information,” “sample object information,” and “sample intention information.”

[0073] The control unit 230 may identify (or generate) target story information based on at least one of information input from a user terminal (eg, user input information) and user information linked to a user account.

[0074] The control unit 230 may specify (or generate) the target story information by further including user information related to the user in the target story information.

[0075] The control unit 230 may extract specific user information to be included in the target story information from user information linked to the user account related to the user, or may request the user to input the specific user information. Here, the specific user information may include information regarding at least one of the user's age and gender.

[0076] Here, the user's age may be used to infer the generation of the person receiving the product (e.g., the person receiving a gift), and the user's gender may be used to infer the product purchasing popularity of users who purchase the product (e.g., a gift).

[0077] For example, when the target story information includes information on age (e.g., a teenage user) as user information, the friends of the teenage user may be inferred to be teenagers of the same age as the user, and the parents of the teenage user may be inferred to be in their 40s to 50s. In this way, when the target story information includes age as user information, the age of the person who will receive the gift may be estimated.

[0078] Furthermore, the gender of the user may be used to consider the popularity of gifts for users of that gender. For example, women in their twenties tend to give accessories as birthday presents to their younger sisters, while men in their twenties tend to give digital devices as birthday presents to their younger brothers.

[0079] In the present invention, by including user information in the target story information, the age of the person receiving the gift may be inferred, and product categories and products may be recommended taking into account the popularity of gifts among the user giving the gift.

[0080] Meanwhile, the target story information may be included in the prompt 410 so as to be processed as an input to the large language model 10 described above. The control unit 230 may generate the target story information using at least one of the user input information and the user information based on natural language processing (NLP). The control unit 230 may generate the target story information in a sentence format so as to include at least one of the user input information and the user information. Therefore, the user input information and the user information are not necessarily limited to a sentence format configuration, and may be processed by the control unit 230 to have a data structure in a form that can be processed in the large language model 10.

[0081] However, the present invention may include various methods of user input that may be used to identify target story information.

[0082] As an example, as shown in FIG. 5, in the present invention, target story information may be identified based on information entered into an information input area 510 included in a specific page 500 provided by a product recommendation service or shopping service.

[0083] The information input area 510 may be composed of various information input areas such as a product search area or a story information input area.

[0084] The control unit 230 may identify target story information using user input information (e.g., "My best friend moved last week. What should I buy for her? Something expensive is fine.") entered from a user terminal (or user account) in the information input area 510.

[0085] In this manner, the control unit 230 may identify target story information based on a product recommendation request received in the information input area 510 from a user account.

[0086] The control unit 230 may extract information on at least one of a target object and a target intention from the user input information. The control unit 230 may analyze the user input information based on natural language processing and extract information on at least one of a target object (e.g., a best friend) and a target intention (e.g., a housewarming gift) required to identify the target story information. Then, the extracted information may be used to generate the target story information.

[0087] As another example, the control unit 230 may specify the target story information using a chatbot, as shown in (a) and (b) of Figure 6. The control unit 230 may provide messages 611, 612, and 616 for specifying the target story information to the user terminal. The control unit 230 may also specify the target story information based on the message 616 received from the user terminal.

[0088] The dialogue messages 611, 612, 616 for identifying the target story information may be provided to the user terminal multiple times, and the content of the next message may be appropriately selected according to the content of the message 616 received from the user terminal and provided to the user terminal. Here, the control unit 230 may grasp information that is lacking in the configuration of the target story information, and may configure a message to be provided to the user in a form that further guides that information.

[0089] Meanwhile, in the product recommendation system 200 according to the present invention, a chatbot may be used to provide information (e.g., a question message) for identifying the target story information to the user terminal, and at least one of the extracted information on the recommended product category and the information on the recommended product 614, 616, 623 may be provided to the user terminal based on the target story information by the chatbot. This will be described in detail later.

[0090] As yet another example, in the product recommendation system 200 according to the present invention, as shown in Figures 7A and 7B, the control unit 230 may receive user input information for identifying target story information on a specific page provided to a user terminal.

[0091] As shown in FIG. 7A, a specific page 710 may be configured to include at least one of a first input area 711 for receiving target information corresponding to a recipient (or other party, e.g., a person receiving a gift) who will receive the product recommended in the product recommendation system 200 according to the present invention, and a second input area 712 for receiving target intention information corresponding to an intention to give the recommended product to the recipient.

[0092] That is, the specific page 710 may include a plurality of input areas 711, 712 for receiving from the user a recipient (target) who will receive the recommended product and an intention to give (present) the product. The control unit 230 may specify story information based on user input information received in the plurality of input areas 711, 712.

[0093] On the other hand, as shown in FIGS. 7A and 7B, information 713 and 715 constituting a specific page 710 may be changed in accordance with user input information input on the specific page 710. In the example shown in FIG.

[0094] For example, as shown in FIG. 7A, in the specific page 710, the target and the intention may be input in order by the user. Thus, information on a plurality of different targets (friends, parents, baby, mother, sister, etc.) may be provided in one area 713 of the specific page 710. Here, the information on the target provided to the user may be appropriately determined in consideration of the user information (e.g., gender, age, other family relationship information, etc.). For example, if the user is a woman in her 40s, the targets may include her husband, parents-in-law, children, etc., and if the user is a male in his teens, the targets may include friends, teachers, parents, etc.

[0095] Such information about a target may be represented by a graphic object (or icon) as shown in FIG. 7A, and when one of the graphic objects (e.g., graphic object 713a corresponding to “friends”) is selected, the control unit 230 may identify information matching the selected graphic object (e.g., “friends”) as the target.

[0096] Information about a specific target may be input into a first input area 711 as shown in Fig. 7B. Furthermore, it goes without saying that a user may directly input information about the target into the first input area 711. That is, the first input area 711 may be configured to directly input information received from a user terminal.

[0097] Next, as shown in FIG. 7B, information on a plurality of different intentions (satisfaction, gratitude, birthday, friendship, housewarming, etc.) may be provided in one area 715 of a specific page 710. Here, the intention provided to the user may be determined taking into consideration information on a preselected target and user information. For example, when the target is different, such as when the target is a "friend" and when the target is a "teacher," the information on the intention provided may also be different.

[0098] Such information regarding the intention may be represented by a graphic object (or icon) as shown in FIG. 7A, and when one of the graphic objects (e.g., graphic object 715a corresponding to “housewarming gift”) is selected, the control unit 230 may identify the information matching the selected graphic object (e.g., “housewarming gift”) as the intention.

[0099] Note that information regarding a specific intention may be input in the second input area 712. The second input area may be configured to display intentions having the same characteristics among a plurality of intentions together, and one of the intentions provided together may be selected by the user. Furthermore, it goes without saying that the user may directly input information regarding the intention into the second input area 712.

[0100] In this way, in the present invention, information on the target and intent may be received based on user input information. When the control unit 230 receives the information on the target and intent, the control unit 230 may use the received information to identify story information. That is, the target target and target intent may be identified by the above-mentioned method, and target story information may be identified based on the identified target.

[0101] The control unit 230 may use a natural language processing algorithm to generate sentences containing information about the object (or target object) and the intent (or target intent) received in the first input area 711 and the second input area 712, as shown in Figures 7A and 7B. Such sentences may be processed into a form for inclusion in a prompt in the large language model 10, as described above.

[0102] As yet another example, the control unit 230 may use a specific page 800, as shown in FIG. 8, to provide a list 810 including various story information to the user terminal, and the user may identify story information by selecting one of the provided story information.

[0103] As shown in the figure, a specific page 800 may include a list 810 consisting of multiple different pieces of story information. When any item 820 in the list 810 is selected on the user terminal, the control unit 230 may specify the story information corresponding to the selected item (e.g., "Please recommend a gift for the meeting with my mother-in-law-to-be.") as the target story information.

[0104] As yet another example, as shown in Fig. 9A, the control unit 230 may allow the user to input story information using a specific page 910. As shown in the figure, the specific page 910 may be provided with guide information 911 for guiding the user to input the story information.

[0105] Furthermore, guide information 912 for guiding the input of information that must be included in the story information (e.g., information about the target and the intention) may be provided on the specific page 910. By referring to the guide information, the user can input the story information including the target and the intention.

[0106] Additionally, the specific page 910 may be provided with sample story information 913 including information regarding the target and intent, allowing the user to intuitively recognize what story information should be entered.

[0107] Alternatively, the sample story information may be configured to be selected by a user terminal, whereby the user can input story information by selecting the sample story information.

[0108] Additionally, as shown in FIG. 9B, the specific page 920 may provide an additional information entry area 922 for more specifically specifying the story information.

[0109] The control unit 230 may provide an information input (or selection) area 922a on the specific page 920 for more specifically specifying at least one of the subject and intent that must be included in the story information.

[0110] Furthermore, the specific page 920 may be provided with an area 922b in which various information required for product recommendation, such as the price range of the product, can be input.

[0111] The control unit 230 may identify story information based on user input information received from a user terminal on such a page.

[0112] In this way, in the product recommendation system 200 according to the present invention, story information (target story information) may be identified based on user input information received by various methods.

[0113] As mentioned above, the user input information does not have to be in the form of a sentence, in which case the control unit 230 may use the user input information to generate sentence 1014a in a form that can be included in prompt 1010, as shown in (a) of FIG. 10A.

[0114] For example, if the user input information consists of multiple words, the control unit 230 may combine the multiple words to generate a sentence and include it in a prompt that is processed as an input to the large language model 10.

[0115] On the other hand, the control unit 230 may specify story information using user information stored in a specific server in association with the user account in order to recommend a product more suitable for the user. In this case, the control unit 230 may specify story information 1045 as shown in FIG. 10B (b) by further utilizing user information 1032 (e.g., male, in his teens) in addition to story information 1031 based on information input by the user (user input information) as shown in FIG. 10B (a). The story information may include first information 1045a based on the user information (e.g., "I am a male student in his teens") and second information 1045b based on the user input information ("I am a woman in my 30s who likes interior design. Please recommend a present for a housewarming."). The control unit 230 may generate at least one sentence to include the user input information and the user information, and include it in the prompt 1040 to be processed as an input to the large language model 10.

[0116] Meanwhile, the user information may include at least one of the gender, age, residential area, and occupation of a specific user corresponding to a specific user account, and may also include various other information stored in the storage unit 220 regarding the specific user.

[0117] In the present invention, when recommending products, the product category and products may be recommended according to the situation of each user by taking user information into consideration. For example, when age is input as user information, the price range of products that can be purchased by a user in his / her teens and a user in his / her thirties may be different.

[0118] Furthermore, in the present invention, when recommending a product, by taking user information into consideration, information about the recipient of the product (e.g., the recipient of a gift corresponding to the product) may be inferred, and at least one of a product category and a product suitable for the recipient may be recommended using the inferred information about the recipient. For example, age (e.g., a teenage user) may be input as user information, and user input information (e.g., "I'm thinking of giving a gift to a friend") may be received. In this case, the teenage user's friends are inferred to be teenagers of the same age as the user, and as a result, the recipient of the gift is inferred (or estimated) to be a teenage user. In this way, in the present invention, a product category or product suitable for the recipient can be recommended by inferring information about the recipient based on user information.

[0119] As yet another example, the user's age (e.g., a teenage user) may be input as user information, and user input information (e.g., "I'm thinking of giving a present to my parents") may be received. In this case, the parents of a teenage user are statistically inferred to be in their 40s to 50s, and as a result, the recipient of the present is inferred (or estimated) to be a user in their 40s to 50s. In this way, in the present invention, by inferring information about the recipient based on the user information, it is possible to recommend a product category or product suitable for the recipient (e.g., a user in their 40s to 50s).

[0120] In this way, in the present invention, story information can be specified that reflects user information so that product categories and products suitable for each user's situation are recommended.

[0121] As a result, in the present invention, the types of recommended product categories obtained as the output of the large language model 10 may vary depending on the user information. Similarly, the types of recommended products obtained as the output of the product recommendation engine 20 may vary depending on the user information.

[0122] As described above, in the present invention, information including at least one of a target and an intent is input by a user in various ways, and story information can be identified based on the information.

[0123] When story information is identified in this manner, i.e., when target story information is identified, in the present invention, a process of obtaining a recommended product category corresponding to the target story information based on the sample story information and the sample product category may be performed (S320).

[0124] The control unit 230 may configure a prompt including the target story information to obtain a recommended product category. The control unit 230 may configure a prompt including the sample story information, a sample product category corresponding to the sample story information, and the target story information. Furthermore, the control unit 230 may process the prompt as an input to the large language model 10.

[0125] Furthermore, in the large language model 10, based on an input prompt, a product recommendation category may be generated as an output (or response) to the prompt.

[0126] As described with reference to FIG. 4, the prompt may include sample data sets 411, 412, 413 that are referenced in the large language model 10, and a target data set 414 that corresponds to information to be obtained from the large language model 10.

[0127] The types of data fields included in the sample data sets 411, 412, 413 may be varied in various ways.

[0128] As an example, the sample data sets 411, 412, and 413 may include a data field corresponding to story information and a data field corresponding to a product category, as described with reference to FIG.

[0129] As another example, the sample data set may include a data field corresponding to story information, a data field corresponding to tags, and a data field corresponding to product categories, where the tags may be referred to as images, topics, keywords, etc.

[0130] In the large language model 10, the recommended product category may be output by referring to the data constituting the sample data set included in the prompt and the data constituting the target data set.

[0131] Meanwhile, the control unit 230 may select information to be input in the prompt, such as data constituting a sample data set, for example, sample story information, sample tag information, sample product category, etc. This information may be stored in the storage unit 220.

[0132] The information may also be based on UGC collected on the Internet. Furthermore, the information may be generated from a large language model 10.

[0133] The control unit 230 may configure a prompt 1110 to obtain sample story information and input it to the large language model, as shown in (a) of Fig. 11. Here, as shown in (a) of Fig. 11, a data field corresponding to story information of a target data set 1111 included in the prompt 1110 may be left empty.

[0134] In the large language model 10, at least one piece of story information 1120 may be acquired based on a prompt in which a data set (or a sample data set) consisting of a gift category and a story information data field is input, as shown in (b) of FIG. 11. Various pieces of story information acquired in this manner may be utilized as information included in the sample data set, as described with reference to FIG. 4. Meanwhile, information in the data fields corresponding to the gift category and story information included in the sample data set shown in (a) of FIG. 11 may be information collected on the Internet. Such information may be UGC generated by a user.

[0135] In this way, the control unit 230 may acquire a recommended product category from the large language model 10 based on a prompt input to the large language model 10 as an output (response) to the prompt.

[0136] On the other hand, when a recommended product category is acquired from the large language model 10, the control unit 230 may provide information on the recommended product category to the user terminal. For example, as shown in FIG. 13A, information on the recommended product category acquired from the large language model 10 (e.g., kitchen supplies, cleaning supplies, interior goods, bedding) may be provided in an area 1330 of a specific page 1310 where story information is input. The user can select a product category he or she wishes to purchase by viewing the recommended product categories and selecting a specific recommended product category (e.g., "interior goods").

[0137] In this way, the product category obtained from the large language model 10 may be provided to the user terminal as a response to the user input information on a page where story information (user input information) is input from the user terminal. Thus, the user can predict for himself what products will be recommended for the input information, and can specify the range of recommended products by selecting a specific product category.

[0138] As an example, as shown in FIG. 5, information 530 relating to recommended product categories may be provided in response to information entered in an input area 510.

[0139] As another example, as shown in FIG. 6(a), the chatbot may provide information 615 about recommended product categories in response to a message 613 entered by the user.

[0140] So far, a method has been described in which information on recommended product categories is immediately acquired from the large language model 10 in response to story information based on user input information input by a user.

[0141] Furthermore, in order to reflect the user's intention when recommending a product, the control unit 230 may primarily acquire tags corresponding to the story information from the large language model 10. Then, when at least one of the acquired tags is selected by the user, a recommended product category reflecting information related to the selected tag may secondarily be acquired from the large language model 10. In this way, the control unit 230 can recommend products reflecting the story information based on the user input information and the user's intention.

[0142] More specifically, the control unit 230 may receive target story information including information on at least one of a target target (e.g., a gift target) and a target intention (e.g., a gift intention) from the user terminal. Also, at least one data set (or sample data set) including sample story information and a theme keyword (or tag) of a sample product category, and the target story information may be used to configure a first prompt to be input to a pre-specified large language model. As shown in FIG. 12A, a prompt 1210 including a sample data set including sample story information and sample tags, and a target data set 1220 including target story information and a tag data field may be input to the large language model 10. The control unit 230 may obtain a plurality of tags (or theme keywords) corresponding to the target story information as an output 1210 of the large language model based on the prompt 1210.

[0143] As shown in FIGS. 6 and 13B, the acquired tags (e.g., luxury, health essentials, stylish, great atmosphere, Instagram-worthy, home cafe, etc.) may be provided in an area 615, 1360 on a particular page 610, 1350 in response to user input information.

[0144] Furthermore, in the present invention, a plurality of tags (or theme keywords) may be provided to the user terminal, and at least one of the plurality of tags may be selected on the user terminal. Furthermore, the control unit 230 may configure the prompt (or the second prompt) to include the selected tag, and may obtain a recommended product category from the second prompt.

[0145] The control unit 230 may obtain a recommended gift category corresponding to the target story information from the large language model 10 by processing the second prompt including the specific tag selected by the user as an input to the large language model 10.

[0146] In this way, the control unit 230 may acquire a recommended product category that reflects the user's intention by sequentially inputting a plurality of prompts to the large language model 10. On the other hand, at least one data field constituting the first prompt and one data field constituting the second prompt may be different.

[0147] For example, the first prompt may include a data field corresponding to story information and a data field corresponding to tags, and the second prompt may include a data field corresponding to story information, a data field corresponding to tags, and a data field corresponding to a product category.

[0148] Here, the second prompt may be composed of at least one first data set including sample story information, tag information (e.g., theme information of a sample product category) and a sample product category, and a second data set including target story information and specific tags, where the specific tags constituting the second data set may be composed of tags selected on the user terminal.

[0149] Meanwhile, when the recommended product category is obtained by the various methods described above, the product recommendation system and method according to the present invention may then perform a process of obtaining recommended products corresponding to the recommended product category (S330) and providing recommended product information (S340).

[0150] When the recommended product category is acquired from the large language model 10, the control unit 230 may extract, from the product recommendation engine 20, at least one recommended product that corresponds to the acquired recommended product category.

[0151] The extracted recommended products may consist of products available for purchase on the Internet, and information regarding the recommended products 540, 550, 616, 623, 714, 716 may be provided on the page receiving the user input information, as shown in Figures 5, 6, 7A and 7B.

[0152] More specifically, the recommended products may be configured to be available for purchase at at least one product sales site accessible via the Internet, and when the recommended products are extracted, product sales information linked to the sales pages of the recommended products may be provided to the user terminal.

[0153] Meanwhile, the control unit 230 may provide information about products belonging to a recommended product category obtained from a user based on at least one of the user input information and the user selected tag in a certain area 1340 of a specific page 1310, as shown in FIG. 13A.

[0154] 13A, when a user selects one of a plurality of recommended product categories (e.g., "interior goods"), the control unit 230 may provide the user terminal with product information 1340 belonging to the selected recommended product category. The control unit 230 may control the product recommendation engine 20 so that products corresponding to the recommended product category are extracted from the product recommendation engine 20.

[0155] 13C, when any tag (e.g., "Great atmosphere" or "Instagrammable") is selected from the multiple tags acquired from the user, the control unit 230 may provide the product information 1395 belonging to the selected tag to the user terminal. The control unit 230 may control the product recommendation engine 20 so that products corresponding to the selected tag are extracted from the product recommendation engine 20.

[0156] On the other hand, the control unit 230 may extract at least one of the multiple products as a recommended product in descending order of similarity based on the similarity between the target story information and multiple products belonging to a recommended product category.

[0157] As shown in FIG. 14, the control unit 230 may determine the similarity 1410 between the user input information (or story information 1421) and the product name 1431 extracted from the product recommendation engine based on the embedded model structure, and extract the top n products with the highest similarity as recommended products as shown in (a), (b), and (c) of FIG. 15, and provide the user terminal with product information (e.g., thumbnails) linked to the sales pages of the recommended products.

[0158] As shown in FIG. 14, the embedding model may use hidden layer values ​​of a large language model (eg, Hyperclova) 1422, 1432 to embed the user input information and the product name.

[0159] Furthermore, in the present invention, a message (for example, a gift message) creation service corresponding to the story information based on the user input information may be further provided.

[0160] For example, a recommended product may be provided to the user, and the user may purchase the recommended product at the user terminal. Thus, the user may purchase the recommended product as a present corresponding to the story information input as described above. In addition, there may be a need for the user to create a present message according to the story information and the recommended product that has been purchased.

[0161] When a recommended product is purchased, for example when a product is purchased on a product sales page included in product information regarding the recommended product, the control unit 230 may generate a message regarding at least one of the story information and the recommended product using the story information and information regarding the recommended product.

[0162] Here, the control unit 230 may generate a message so that the target information included in the story information is included as information regarding the recipient to whom the recommended product is to be gifted, and the intention information included in the story information is included as information regarding the intention to gift the recommended product.

[0163] Furthermore, the control unit 230 may use the large language model 10 to generate a present message 1600 as shown in FIGS. 16A and 16B.

[0164] As an example, as shown in FIG. 16A, the large language model 10 may receive a prompt including a story (or story information) 1610 and an ordered item (or purchased item) 1620, and in response thereto, a gift message (e.g., a sample message for a card) 1630.

[0165] The control unit 230 may identify a sample data set including data fields and corresponding data values ​​corresponding to the story information, the ordered items, and the gift message to obtain the gift message from the large language model 10. The control unit 230 may also configure a prompt to include the sample data set.

[0166] The prompt may further include a target data set including a data field corresponding to the target present message to be generated, the target data set may include target story information, data fields corresponding to the target order product and corresponding data values, and data fields corresponding to the target present message, wherein the data values ​​of the data fields corresponding to the target present message may exist as empty fields.

[0167] In this manner, the control unit 230 may configure a prompt so that a gift message is generated based on user input information input by the user and the user's product purchase history, and input the prompt to the large language model 10. The control unit 230 may also obtain the gift message from the large language model 10.

[0168] As another example, as shown in FIG. 16B, a prompt 1640 input to the large language model may include data fields corresponding to the intent (e.g., an intent to give a gift or an intent to purchase a product), the giver (e.g., the person purchasing the product or the person giving the gift), the recipient (e.g., the person receiving the product or the person receiving the gift), the date (e.g., the date of purchase of the product or the date of giving the gift), the gift (e.g., the type of product purchased, the product name, etc.), and the card (e.g., the gift message).

[0169] As shown in the figure, the prompt 1640 may include a sample data set including the data fields and corresponding data values ​​described above. The control unit 230 may obtain a gift message (e.g., corresponding to the “card” data field) included in the target data set 1650 using the large language model 10.

[0170] In this manner, the control unit 230 may identify a sample data set that includes data fields and corresponding data values ​​for the intent, giver, recipient, date, gift, and card, and may configure a prompt to include the sample data set.

[0171] 16B, the prompt 1640 may further include a target data set 1650 including data fields corresponding to the target present message (e.g., a card) to be generated, the target data set may include data fields corresponding to intent, giver, recipient, date, and present, and corresponding data values, and a data field corresponding to the target present message (e.g., a card), where the data value of the data field corresponding to the target present message may be an empty field.

[0172] In this manner, the control unit 230 may configure a prompt to generate a present message and input the prompt to the large language model 10. The control unit 230 may also obtain the present message from the large language model 10.

[0173] On the other hand, present messages 1731, 1732 obtained based on a large language model or obtained by other methods may be provided in a message input area 1730 of a present message creation page 1700, as shown in Figures 17A and 17B.

[0174] The control unit 230 may create a gift message based on at least one of the story information, the purchased product, and the user information.

[0175] The content and tone of the gift message may be determined based on at least one of the story information, the purchased product, and the user information.

[0176] The control unit 230 may generate a present message in consideration of the target (the person to whom the present is to be given), user information, the user's tone of voice, the frequency of stamp use, and the like. For example, the control unit 230 may generate a present message in polite language when the target is a superior (e.g., parents, teachers, bosses, etc.) in consideration of the relationship between the user and the target, and in a frank tone of voice when the target is a friend. The control unit 230 may also generate a present message using a tone of voice or buzzwords that are often used by the same group in consideration of the age and sex of the user. Furthermore, the control unit 230 may analyze UGC created by the user, identify the habits (tone of voice, frequency of stamp use, etc.) that the user uses when creating text, and generate a present message that reflects the habits. In this way, the control unit 230 can generate a present message that sounds like one created directly by the user.

[0177] Furthermore, the present message creation page 1700 may include an input area 1720 for selecting a message recipient, a message mood, etc. As shown in Fig. 17B, when the user selects message recipient information (e.g., a colleague) and mood information (e.g., a humorous message) in the input area, the control unit 230 may generate and provide a message 1732 based on the selected information.

[0178] Additionally, the gift message creation page 1700 may allow an image 1710 to be selected for inclusion in the gift message.

[0179] Meanwhile, although not shown, the control unit 230 may provide a message list of a plurality of sample present messages corresponding to various targets and situations to the user terminal. The control unit 230 may specify the present message by selecting at least one of the message lists in the user terminal.

[0180] As described above, the product recommendation method and system according to the present invention can improve the convenience of gift purchasing for users by providing services ranging from product recommendation, purchase, and gift message generation based on user story information.

[0181] Furthermore, the product recommendation method and system according to the present invention can extract recommended products using a large language model that receives as input a prompt containing story information.

[0182] Here, the story information is configured to include information regarding the recipient of the recommended product and the intention of the purchaser to purchase the recommended product, so that in the present invention, a product that reflects the intention of the user to purchase the recommended product can be recommended.

[0183] In this way, the product recommendation method and system according to the present invention can recommend products according to the story of the user who will give the recommended product as a gift from a large language model by constructing a prompt using story information that reflects the recipient of the recommended product and the intention of giving the recommended product. Therefore, according to the present invention, it is possible to reduce the time required to select a product to give as a gift, and to purchase a product that is optimized according to the recipient and the intention of the gift.

[0184] Meanwhile, the present invention described above may be realized as a program that is executed by one or more processes in a computer and can be stored in a computer-readable medium (or a recording medium).

[0185] Furthermore, the present invention described above may be realized as computer readable codes or commands on a medium on which a program is recorded. That is, the present invention may be provided in the form of a program.

[0186] The computer-readable medium includes any kind of recording device in which data read by a computer system is stored. Examples of the computer-readable medium include a hard disk drive (HDD), a solid state disk (SSD), a silicon disk drive (SDD), a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.

[0187] Furthermore, the computer-readable medium includes storage, and includes a server or cloud storage that the electronic device can access via communication. In this case, the computer can download the program according to the present invention from the server or cloud storage via wired or wireless communication.

[0188] Furthermore, in the present invention, the above-mentioned computer includes a processor, i.e., a CPU (Central Processing Unit). A processor is an electronic device that has a central processing unit (CPU) of any type.

[0189] However, the above detailed description should not be interpreted as limiting in any respect, but should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the claims, and all modifications within the equivalent scope of the present invention are included in the present invention.

[0190] (Appendix 1) In the product recommendation method, identifying target story information including at least one of target audience information and target intent information; obtaining a recommended product category corresponding to the target story information according to sample story information including at least one of sample subject information and sample intention information, and a sample product category corresponding to each of the sample story information; and extracting at least one recommended product that matches the target story information from among the products that belong to the recommended product category. (Appendix 2) The step of acquiring a recommended product category includes: constructing a prompt using the sample story information and the sample product category corresponding to the sample story information, and the target story information; and processing the prompt as an input to a pre-specified large language model; The recommended product categories are: The product recommendation method according to claim 1, characterized in that the product is generated as an output of the large language model. (Appendix 3) The product recommendation method described in Appendix 1, characterized in that at least one of the sample story information and the sample product category is obtained as output of the large language model by inputting into the large language model a prompt constructed based on UGC (User Generated Contents) created by multiple users on a page accessible via the Internet. (Appendix 4) The target story information is identified based on a product recommendation request received from a specific user account; In the step of identifying target story information, The product recommendation method described in Appendix 1, characterized in that the target story information is identified using user input information received from the specific user account and user information stored on a specific server in association with the specific user account. (Appendix 5) The user input information is The specific user account is received on a specific page provided to a user terminal logged in, The specific page is The product recommendation method according to claim 4, further comprising: a first input area for receiving input of the target information corresponding to a recipient to whom the recommended product is to be presented; and a second input area for receiving input of the target intention information corresponding to an intention to present the recommended product to the recipient. (Appendix 6) The step of identifying target story information includes: generating, as the target story information, a sentence including the target subject information and the target intention information received in the first input area and the second input area, using a natural language processing algorithm; The product recommendation method according to claim 5, wherein the sentence is included in the prompt. (Appendix 7) The user information includes at least one of the gender, age, residential area, and occupation of the specific user corresponding to the specific user account; In the step of generating the sentence, The product recommendation method described in Appendix 6, characterized in that the sentence is generated so that the user information is included in the target story information. (Appendix 8) In the step of extracting the recommended products, A product recommendation method as described in Appendix 1, characterized in that at least one of the multiple products belonging to the recommended product category is extracted as the recommended product based on the similarity between the target story information and the multiple products belonging to the recommended product category in order of highest similarity. (Appendix 9) The plurality of products are configured to be available for purchase at at least one product sales site accessible via the Internet; The product recommendation method described in Appendix 8, further comprising a step of providing product sales information linked to a sales page of the recommended product to a user terminal when the recommended product is extracted. (Appendix 10) The product recommendation method described in Appendix 9, further comprising a step of generating a message regarding the recommended product using the target story information and information regarding the recommended product when the recommended product is purchased on the sales page. (Appendix 11) In the step of generating the message, The product recommendation method described in Appendix 10, characterized in that the message is generated so that the target information is included as information regarding a recipient to whom the recommended product will be given as a gift, and the target intention information is included as information regarding an intention to give the recommended product as a gift. (Appendix 12) In the product recommendation method, receiving target story information from a user terminal, the target story information including information regarding at least one of a subject of a gift and an intention of the gift; constructing a first prompt using at least one dataset including sample story information and sample product category theme information and the target story information to be input to a pre-specified large language model; obtaining, based on the first prompt, a plurality of theme keywords corresponding to the target story information as an output of the large language model; providing the user terminal with the plurality of theme keywords, and selecting at least one of the plurality of theme keywords at the user terminal; constructing a second prompt at the user terminal, the second prompt including the selected theme keyword; and obtaining a recommended gift category corresponding to the target story information from the large language model by processing the second prompt including the specific theme keyword as an input to the large language model. (Appendix 13) The second prompt: at least one first data set including the sample story information, the theme information of the sample product category, and the sample product category; The product recommendation method according to claim 12, characterized in that the product recommendation method is composed of the target story information and a second data set including the specific theme keyword. (Appendix 14) The product recommendation method described in Appendix 13, further comprising a step of extracting at least one recommended product that corresponds to the target story information from among the products that belong to the recommended product category. (Appendix 15) In product recommendation systems, a storage unit for storing sample story information including at least one of sample subject information and sample intention information, and sample product categories corresponding to the sample story information; A product recommendation system comprising: a control unit that performs a process of acquiring a recommended product category corresponding to target story information based on the sample story information and the sample product categories corresponding to the sample story information, using a pre-specified large language model; and a process of extracting at least one recommended product that matches the target story information from among products belonging to the recommended product categories. (Appendix 16) A program executed by one or more processes in an electronic device, identifying target story information including at least one of target audience information and target intent information; obtaining a recommended product category corresponding to the target story information according to sample story information including at least one of sample subject information and sample intention information, and a sample product category corresponding to each of the sample story information; and extracting at least one recommended product that matches the target story information from among the products that belong to the recommended product category. [Explanation of symbols]

[0191] 10 Large Language Models 200 Product Recommendation System 220 Preservation Department 230 Control Unit 411,412,413 Sample Data Set 414,1111,1220,1650 Target Data Set 410,1010,1040,1110,1210,1640 prompt 500,610,710,800,910,920,1310,1350 Specific page 611,612,613,616,1732 Messages 711 First input area 712 Second input area 913 Sample Story Information 1014a Sentence 1032 User Information

Claims

1. In a product recommendation method using a chatbot, providing a question message to a user terminal by the chatbot to identify target story information; determining the target story information, including at least one of target subject information and target intent information, based on a user message received from the user terminal; obtaining a recommended product category that matches the target story information in response to the user message from a large language model; Extracting recommended products corresponding to the recommended product categories obtained from the large language model by a product recommendation engine; and providing the recommended products to the user terminal by the chatbot.

2. In the step of providing the query message to a user terminal, The product recommendation method using a chatbot as described in claim 1, characterized in that a message is constructed to guide the user terminal to obtain additional information necessary for constructing the target story information.

3. In the step of providing the query message to a user terminal, The method for recommending products using a chatbot according to claim 2, wherein the question message is provided to the user terminal multiple times in order to induce the additional information.

4. The query message provided to the user terminal multiple times to induce the additional information includes: The method for recommending a product using a chatbot according to claim 3, further comprising a question related to at least one of a target object that receives the recommended product as a gift and a purpose for gifting the recommended product.

5. The step of acquiring a recommended product category includes: obtaining a plurality of theme keywords corresponding to the target story information and related to a theme of a product category from the large language model; providing the plurality of theme keywords to the user terminal by the chatbot; A step of selecting any one of the plurality of theme keywords from the user terminal; The method for recommending products using a chatbot according to claim 1, further comprising a step of obtaining the recommended product category from the large language model, the recommended product category reflecting information related to any of the selected theme keywords.

6. The first prompt input to the large language model comprises: The target story information is included, The method for recommending products using a chatbot according to claim 5, further comprising obtaining the plurality of theme keywords from the large language model as an output in response to the first prompt.

7. The second prompt input to the large language model is The target story information and the selected one of the plurality of theme keywords are included, The method for recommending products using a chatbot according to claim 6, further comprising obtaining the recommended product category from the large language model as an output for the second prompt.

8. In the step of providing the recommended product to the user terminal by the chatbot, The method for recommending a product using a chatbot according to claim 7, wherein product sales information linked to a sales page of the recommended product is also provided to the user terminal.

9. In a product recommendation system using a chatbot, The chatbot provides a question message to a user terminal for identifying target story information; Identifying the target story information, including at least one of target subject information and target intent information, based on a user message received from the user terminal; Obtaining a recommended product category that matches the target story information in response to the user message from a large language model; A product recommendation engine extracts recommended products corresponding to the recommended product categories obtained from the large language model; A product recommendation system using a chatbot, in which the chatbot provides the recommended products to the user terminal.

10. Providing a question message for identifying target story information to a user terminal by a chatbot; determining the target story information, including at least one of target subject information and target intent information, based on a user message received from the user terminal; obtaining a recommended product category that matches the target story information in response to the user message from a large language model; Extracting recommended products corresponding to the recommended product categories obtained from the large language model by a product recommendation engine; and a step of providing the recommended products to the user terminal by the chatbot.

Images