System for product purchase service through ai based multi payment and method thereof

Abstract

The present invention relates to an AI-based multi-payment product purchase service system and method, wherein when a user selects and registers a desired product, a service provider requests crowdfunding of the product from the user's acquaintances via the SNS or messenger desired by the user, delivers the product to the user based on multi-payments by acquaintances participating in the crowdfunding, and provides a service that recommends a higher quality product to the user through AI and a verification service that determines the authenticity of the product, thereby increasing user satisfaction and reducing the price burden on acquaintances who wish to gift the product.

Description

Technology Field

[0001] The present invention relates to an AI-based multi-payment product purchase service system and method, wherein when a user selects and registers a desired product, a service provider requests crowdfunding of the product from the user's acquaintances via the SNS or messenger desired by the user, delivers the product to the user based on multi-payments by acquaintances participating in the crowdfunding, and provides a service that recommends a higher quality product to the user through AI and a verification service that determines the authenticity of the product, thereby increasing user satisfaction and reducing the price burden on acquaintances who wish to gift the product. Background Technology

[0002] Recently, due to the rapid development of communication devices such as smartphones and the internet environment, social network services such as SNS and messengers are being actively used by general users.

[0003] Accordingly, operators of social network services are introducing various additional services to support user influx and activity beyond basic networking functions; a representative example of this is a service that allows users to exchange gifts on birthdays or anniversaries (e.g., Gifticons).

[0004] The market for such gift-giving services is growing in size due to their convenience, but products are currently being distributed only within the servers or platforms operated by each service provider.

[0005] In other words, the existing gift-giving service market is limited to products within the server or platform that users wish to purchase, and since it is an environment where users cannot specify a particular shopping mall or product to receive a gift, there is a need to introduce a service that allows users to select and receive desired products from external online markets rather than specific platforms.

[0006] In addition, since the purchasing burden on acquaintances is significant when the desired product is expensive, it is necessary to introduce a service that allows multiple acquaintances to jointly purchase the product the user wants. Prior art literature

[0007] Korean Published Patent No. 10-2023-0016078 (Published Feb. 01, 2023) Korean Published Patent No. 10-2012-0117072 (Published Oct. 24, 2012) The problem to be solved

[0008] The present invention was created to solve the above-mentioned problems and aims to provide a system and a method for providing a product purchasing service that combines crowdfunding and social networks, in which acquaintances of a user jointly make a payment for a single product selected by the user.

[0009] In addition, the present invention has another objective of providing a system and method for providing a service in which, when a user selects a product they wish to receive as a gift from acquaintances, the server side recommends and registers a high-quality product that is better than the selected product through AI.

[0010] In addition, another objective of the present invention is to provide a system and a method for providing a verification service in which, when a user selects a product they wish to receive as a gift from acquaintances, the server side determines the authenticity of the product through AI.

[0011] However, the technical problems that this embodiment aims to solve are not limited to the technical problems described above, and other technical problems may exist. means of solving the problem

[0012] A product purchase service system through AI-based multi-payment according to one embodiment of the present invention is characterized by comprising: a product selection unit that confirms a user's selection of a product to be purchased through crowdfunding; a funding registration unit that registers crowdfunding by generating funding information including a period, amount, and description of the product; a funding progress unit that conducts crowdfunding for the product targeting the user's acquaintances; and a product purchase processing unit that performs the purchase and delivery of the product when crowdfunding for the product is completed.

[0013] In addition, the system further comprises a product recommendation unit that, when a product to be purchased through crowdfunding is selected, collects product information including price, name, brand, category, manufacturer, material, and ingredients of the product, and user information including user gender, age, and region, and inputs the collected product information and user information into an AI model for product recommendation to recommend other products similar to or of a higher grade than the product, thereby allowing the user to keep the product selected as is or select one of the recommended products.

[0014] In addition, the AI ​​model for product recommendation is characterized by being a deep learning model trained to classify user groups using product information including price, name, brand, category, manufacturer, material, and ingredients, and user information including user gender, age, and region as training data, and to recommend products that match the characteristics of each classified group.

[0015] In addition, the system further comprises a product verification unit that, when a product to be purchased through crowdfunding is selected, collects text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product, and image-based information including photos, unique numbers, and certificate information, and inputs the collected text-based information and image-based information into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit.

[0016] In addition, the AI ​​model for verifying the authenticity of the product is characterized as a deep learning model trained to determine authenticity by using text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product, and image-based information including photos, unique numbers, and certificate information as training data, and measuring accuracy, which is the ratio of products accurately identified as genuine among all products, precision, which is the ratio of actual genuine products among products identified as genuine, recall, which is the ratio of actual genuine products identified as genuine among actual genuine products, and F1 score, which is the harmonic mean of precision and recall.

[0017] In addition, the funding process unit is characterized by identifying a server or platform that supports at least one social network service designated by the user, and providing information related to the crowdfunding to an acquaintance of the user who uses the identified server or platform, so that they may participate in the crowdfunding for the product.

[0018] In addition, the funding process unit is characterized by accumulating funds in the user's name or refunding them to the user's acquaintances who participated in the crowdfunding, if the funding amount to purchase the product falls short of the target amount as a result of crowdfunding for the product targeting the user's acquaintances.

[0019] In addition, a product purchase service method through AI-based multi-payment according to one embodiment of the present invention is performed in an AI-based multi-payment product purchase service system and is characterized by comprising: a product selection step of confirming a user's selection of a product to be purchased through crowdfunding; a funding registration step of registering crowdfunding by generating funding information including a period, amount, and description of the product; a funding progress step of conducting crowdfunding targeting the user's acquaintances for the product; and a product purchase processing step of purchasing and delivering the product when crowdfunding for the product is completed.

[0020] In addition, the method further comprises a product recommendation step in which, when a product to be purchased through crowdfunding is selected, product information including price, name, brand, category, manufacturer, material, and ingredients of the product and user information including user gender, age, and region are collected, and the collected product information and user information are input into an AI model for product recommendation to recommend other products similar to or of a higher grade than the product, thereby allowing the user to keep the product selected as is or select one of the recommended products.

[0021] In addition, the above method is characterized by further including a product verification step in which, when a product to be purchased through crowdfunding is selected, text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product, and image-based information including photos, unique numbers, and certificate information are collected, and the collected text-based information and image-based information are input into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit. Effects of the invention

[0022] As described above, according to the AI-based multi-payment product purchase service system and method of the present invention, instead of a user purchasing or gifting a desired product through a single closed platform (server), a new type of service combining crowdfunding and social networks is provided in which a user selects various products in an open space and purchases them through payment by multiple people (user acquaintances), thereby increasing user satisfaction and reducing the price burden on the buyer.

[0023] In addition, the present invention has the effect of improving the reliability of server operators by recommending high-quality products that are better than the product in question to users through AI and providing a verification service that determines the authenticity of the product.

[0024] However, the effects of the present invention are not limited to the effects described above, and unmentioned effects will be clearly understood by those skilled in the art from this specification and the attached drawings. Brief explanation of the drawing

[0025] FIG. 1 is a schematic diagram showing the overall configuration including a product purchase service system through AI-based multi-payment according to one embodiment of the present invention. FIG. 2 is a diagram showing in more detail the configuration of a product purchase service system through AI-based multi-payment according to one embodiment of the present invention. FIG. 3 is a diagram showing the hardware structure of a product purchase service system through AI-based multi-payment according to an embodiment of the present invention. FIG. 4 is a flowchart illustrating in detail the operation process of a product purchase service method through AI-based multi-payment according to an embodiment of the present invention. Specific details for implementing the invention

[0026] Specific embodiments of the present invention will be described in detail below with reference to the drawings. However, the concept of the present invention is not limited to the presented embodiments. Those skilled in the art who understand the concept of the present invention may easily propose other inventions that are inferior or other embodiments included within the scope of the concept of the present invention by adding, changing, or deleting other components within the same scope of the concept, and such are also to be considered to be included within the scope of the concept of the present invention.

[0027] Additionally, components with the same function within the scope of the same concept appearing in the drawings of each embodiment are described using the same reference numeral.

[0028] FIG. 1 is a schematic diagram showing the overall configuration including a product purchase service system through AI-based multi-payment according to one embodiment of the present invention.

[0029] As illustrated in FIG. 1, the present invention comprises a product purchase service system (100) through AI-based multi-payment, a user terminal (200), an external server (300), a social network service server (platform) (400), a user acquaintance terminal (500), a database (600), etc.

[0030] The above AI-based multi-payment product purchase service system (100) is a server or platform that provides a product purchase service combining crowdfunding and social networks so that acquaintances of the user can jointly make a payment for one product selected by the user.

[0031] That is, when a user selects a product they want from various unspecified shopping malls rather than a specific shopping mall, the AI-based multi-payment product purchase service system (100) conducts crowdfunding for the purchase of the product targeting the user's acquaintances through the social network used by the user, and when the crowdfunding is successful and the target amount is reached through multi-payments by acquaintances, a certain fee is deducted from the raised amount, and then the product is purchased from the external server (300) and delivered to the user.

[0032] Accordingly, users can significantly enhance their satisfaction by receiving specific products they desire on birthdays or anniversaries through group purchasing by acquaintances. Additionally, the acquaintances providing the gifts can also reduce their financial burden by purchasing the products via group buying.

[0033] Meanwhile, the product purchase service system (100) based on AI-based multi-payment can, during the service provision process, recommend a higher quality product than the product by utilizing an artificial intelligence model when the user selects a specific product they wish to receive as a gift from acquaintances, thereby allowing the user to make a selection.

[0034] In addition, the product purchase service system (100) using the AI-based multi-payment mentioned above can increase the reliability of the system operator by additionally providing a service that verifies the authenticity of a specific product selected by the user through an artificial intelligence model.

[0035] The above user terminal (200) is a wired or wireless communication device, such as a smartphone or tablet PC, owned by a user who wishes to receive a specific product as a gift through a service combining crowdfunding and a social network, and after logging in as a member to the AI-based multi-payment product purchase service system (100) through the network, registers a specific product sold on the external server (300) and requests crowdfunding targeting the user's acquaintances who use the specific social network service.

[0036] In addition, the user terminal (200) receives result information of the crowdfunding (whether funding is successful, extension in case of funding failure, accumulation and refund of raised amount, etc.) from the AI-based multi-payment product purchase service system (100). If the crowdfunding is successful, the user receives the product from the system.

[0037] The above external server (300) is a shopping mall server or platform that sells various products that a user who has logged in as a member to the AI-based multi-payment product purchase service system (100) wants to receive as a gift through crowdfunding.

[0038] The above social network service server (platform) (400) provides various social network services used by the user and their acquaintances (e.g., SNS or messenger services such as Instagram, Facebook, KakaoTalk, etc.).

[0039] The above user acquaintance terminal (500) is a wired or wireless communication device, such as a smartphone or tablet PC, used by an acquaintance of a user who uses a social network service used by a user who wants to receive a specific product as a gift, and receives crowdfunding information (e.g., user information, product, period, amount, etc.) requested by a user registered as a network from the above AI-based multi-payment product purchase service system (100).

[0040] Additionally, when the user's acquaintance terminal (500) chooses to participate in crowdfunding, it accesses a payment page provided by the AI-based multi-payment product purchase service system (100) and performs multi-payment for a specific product.

[0041] At this time, the user's acquaintance can freely determine the amount to pay or pay a fixed amount in advance.

[0042] The above database (600) stores and manages various programs (e.g., applications, artificial intelligence models, etc.) used in the AI-based multi-payment product purchase service system (100), and stores and manages user information registered as a member, service usage information combining crowdfunding and social networks for each user, etc.

[0043] FIG. 2 is a diagram showing in more detail the configuration of a product purchase service system through AI-based multi-payment according to one embodiment of the present invention.

[0044] As illustrated in FIG. 2, the AI-based multi-payment product purchase service system (100) is configured to include a product selection unit (110), a funding registration unit (120), a funding progress unit (130), a product purchase processing unit (140), a product recommendation unit (150), a product verification unit (160), an artificial intelligence model generation unit (170), etc.

[0045] The product selection unit (110) confirms the selection of a product to be purchased through crowdfunding from the user terminal (200) that has performed member login (e.g., a product to be received as a gift from acquaintances on a birthday or anniversary).

[0046] At this time, the product that the user intends to purchase through crowdfunding selected by the user may be a product sold within the system or a product sold on the external server (300). That is, it may be a product sold at various unspecified shopping malls rather than a specific shopping mall.

[0047] The above funding registration unit (120) registers crowdfunding by generating funding information including the period for crowdfunding for a specific product selected by the user through the above product selection unit (110), the amount to be raised including fees, user requests or product descriptions, etc.

[0048] The funding promotion unit (130) conducts crowdfunding targeting user acquaintances for a specific product registered through the funding registration unit (120).

[0049] For example, the funding progress unit (130) identifies a user's acquaintance who uses a server or platform that supports at least one social network service designated in advance by the user to receive a specific product as a gift, and provides information related to the crowdfunding registered through the funding registration unit (120) to the user's acquaintance who uses the identified server or platform, and allows the user's acquaintance who has identified this to participate in the crowdfunding for the product so that multiple payments can be made.

[0050] At this time, if the crowdfunding conducted by the funding department (130) results in a failure to meet the target amount set to purchase the product (i.e., the amount including the product price and fees), the crowdfunding period may be extended further, the amount raised in the user's name may be accumulated, or a refund may be given to the user's acquaintances who participated in the crowdfunding.

[0051] When crowdfunding targeting the user's acquaintances is completed through the funding progress unit (130), the above product purchase processing unit (140) purchases the product the user wants and delivers it to the delivery address designated by the user.

[0052] When a user selects a specific product they wish to receive as a gift through the product selection unit (110), the product recommendation unit (150) utilizes an artificial intelligence model to recommend other products similar to the product and higher-quality products.

[0053] For example, when a user selects a product they wish to purchase through crowdfunding, the product recommendation unit (150) collects product information including the price, name, brand, category, manufacturer, material and ingredients of the product, and user information including the user's gender, age and region. Then, the collected product information and user information are input into an AI model for product recommendation to recommend other products that are similar to or of a higher grade than the product, so that the user can keep the product they selected or choose one of the recommended products.

[0054] At this time, the AI ​​model for product recommendation is a deep learning model trained to classify user groups using product information including price, name, brand, category, manufacturer, material, and ingredients, and user information including user gender, age, and region as training data, and to recommend products that match the characteristics of each classified group.

[0055] When a user selects a specific product they wish to receive as a gift through the product selection unit (110), the product verification unit (160) verifies whether the product is genuine or counterfeit by utilizing an artificial intelligence model.

[0056] For example, when a user selects a product they wish to purchase through crowdfunding, text-based information including the price, name, brand, category, manufacturer, material, and ingredients of the product, and image-based information including photos, unique numbers, and certificate information are collected. Then, the collected text-based and image-based information is input into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit.

[0057] At this time, the AI ​​model for verifying the authenticity of the product is a deep learning model trained to determine authenticity by measuring the accuracy of authenticity, using text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product, and image-based information including photos, unique numbers, and certificate information as training data.

[0058] Here, the measurement of authenticity accuracy may utilize accuracy, which is the ratio of products correctly identified as genuine out of the total products; precision, which is the ratio of actual genuine products among those identified as genuine; recall, which is the ratio of actual genuine products identified as genuine; and the F1 score, which is the harmonic mean of precision and recall.

[0059] The artificial intelligence model generation unit (170) generates the AI ​​model for product recommendation and the AI ​​model for product authenticity verification and stores them in the database (600).

[0060] At this time, the artificial intelligence model generation unit (170) is composed of a preprocessing unit, a training data generation unit, a training unit, and an update unit.

[0061] The above preprocessing unit can perform data cleaning to improve the quality of data by removing or correcting errors, outliers, etc., in the information for each product in order to improve model performance during the creation process of the AI ​​model for product recommendation and the AI ​​model for product authenticity verification.

[0062] In addition, to make each collected product information into a form that is easy for the model to learn, data transformation can be performed by converting text data into numeric vectors or adjusting the size or normalizing image data, and data standardization can be performed to stabilize model training by adjusting the range of all features equally.

[0063] The above training data generation unit generates training data through the division, sampling, and augmentation of data preprocessed through the above preprocessing unit.

[0064] Here, the training data generation unit can divide the training data into training data used for model training and test data used for model performance evaluation. In addition, the training data generation unit can balance the dataset using sampling techniques such as oversampling or undersampling, and can increase the number of training data through data augmentation.

[0065] The above-mentioned learning unit learns the training data generated by the above-mentioned training data generation unit to generate the above-mentioned AI model for product recommendation and AI model for product authenticity verification. In other words, it learns the patterns of the training data and performs predictions on the data.

[0066] Additionally, the learning unit evaluates the model performance using test data after the AI ​​model for product recommendation and the AI ​​model for product authenticity verification have completed training. Based on the evaluation results, if the evaluation result is unsatisfactory, the preprocessing and training process is performed again, and if the evaluation result is satisfactory, the AI ​​model for product recommendation and the AI ​​model for product authenticity verification are stored in the database (600).

[0067] The above update unit updates the product recommendation AI model and the product authenticity verification AI model when the number of continuously collected products satisfies a preset standard (i.e., the number serving as the standard for performing updates).

[0068] For example, the AI ​​model for product recommendation and the AI ​​model for product authenticity verification can be updated through fine-tuning, which improves the learning performance on additional training data while maintaining the performance of the existing model, or through retraining, which initializes the existing model and trains the model from scratch using additional training data.

[0069] FIG. 3 is a diagram showing the hardware structure of a product purchase service system through AI-based multi-payment according to an embodiment of the present invention.

[0070] As illustrated in FIG. 3, the hardware structure of the AI-based multi-payment product purchase service system (100) is configured to include a central processing unit (1000), memory (2000), user interface (3000), database interface (4000), network interface (5000), web server (6000), etc.

[0071] The above user interface (3000) provides an input and output interface to the user by using a graphical user interface (GUI).

[0072] The above database interface (4000) provides an interface between the database and the hardware structure. The above network interface (5000) provides a network connection between devices owned by the user.

[0073] The above web server (6000) provides a means for a user to access a hardware structure through a network. Most users can access the web server remotely to use the AI-based multi-payment product purchase service system (100), and by supporting a responsive web, it can provide a screen interface optimized for various user terminals such as PCs, mobile devices, and smart devices.

[0074] Each step of the configuration or method described above may be implemented as computer-readable code on a computer-readable recording medium or transmitted through a transmission medium. A computer-readable recording medium is a data storage device capable of storing data that can be read by a computer system.

[0075] Examples of computer-readable recording media include, but are not limited to, databases, ROM, RAM, CD-ROM, DVD, magnetic tape, floppy disk, and optical data storage devices. Transmission media may include carrier waves transmitted via the Internet or various types of communication channels. Additionally, computer-readable recording media may be distributed through networked computer systems so that computer-readable code is stored and executed in a distributed manner.

[0076] In addition, at least one component applied in the present invention may include or be implemented by a processor, such as a central processing unit (CPU) or a microprocessor, that performs a respective function, and two or more of said components may be combined into a single component to perform all operations or functions of the combined two or more components. Furthermore, a part of the at least one component applied in the present invention may be performed by another of these components. Additionally, communication between said components may be performed via a bus (not shown).

[0077] Next, an embodiment of a product purchase service method using AI-based multi-payment according to the present invention configured as described above will be explained in detail with reference to FIG. 4. At this time, the order of each step according to the method of the present invention may be changed depending on the usage environment or a person skilled in the art.

[0078] FIG. 4 is a flowchart illustrating in detail the operation process of a product purchase service method through AI-based multi-payment according to an embodiment of the present invention.

[0079] As illustrated in FIG. 4, the AI-based multi-payment product purchase service system (100) performs member login of the user terminal (200) connected via a network (S100).

[0080] And the AI-based multi-payment product purchase service system (100) confirms the user's selection of a product to be purchased through crowdfunding (S200). Here, the product selected by the user is a product sold within the system as well as a product sold on various multiple external servers (300).

[0081] Here, the AI-based multi-payment product purchase service system (100) collects product information (e.g., price, name, brand, category, manufacturer, material, ingredients, etc.) and user information (e.g., user gender, age, region, etc.) for a specific product selected by a user, and then inputs the collected product information and user information into an AI model for product recommendation to recommend other products that are similar to or of a higher grade than the product.

[0082] In addition, the AI-based multi-payment product purchase service system (100) can collect text-based information (e.g., price, name, brand, category, manufacturer, material, ingredients, etc.) and image-based information (e.g., photo, unique number, certificate, etc.) about a specific product selected by a user, and input the collected text-based information and image-based information into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit (S210).

[0083] After the user makes a final decision on a specific product that they have directly selected or been recommended through steps S200 and S210 and the authenticity of the product is verified, the AI-based multi-payment product purchase service system (100) generates funding information including a period, amount, and description for the product and registers crowdfunding (S300).

[0084] Next, the AI-based multi-payment product purchase service system (100) transmits the crowdfunding information registered through step S300 to the user's acquaintance terminal (500) via a social network service server (platform) (400) used by the user's acquaintance (S400).

[0085] Subsequently, the AI-based product purchase service system (100) determines whether the crowdfunding registered through step S300 is successful through multiple payments by the user's acquaintance terminal (500) participating in the crowdfunding (S500). That is, it determines whether the target amount, including the price of the product selected by the user who wants to receive the gift and the fees of the system side performing crowdfunding and purchase / delivery, has been reached through multiple payments by multiple user acquaintances.

[0086] If the crowdfunding for the product determined in step S500 above is successful, the AI-based multi-payment product purchase service system (100) processes the purchase and delivery of the product (S600).

[0087] However, if the crowdfunding for the product fails as determined in step S500 above, the AI-based multi-payment product purchase service system (100) may extend the crowdfunding period further, accumulate the amount raised in the user's name, or refund the amount to the user's acquaintances who participated in the crowdfunding (S700).

[0088] As such, the present invention provides a new type of service that combines crowdfunding and social networks, in which a user selects various products in an open space rather than purchasing or gifting desired products through a single closed platform (server), and multiple people (user acquaintances) make payments to purchase them. Furthermore, by using AI to recommend high-quality products that are better than the product to the user and providing a verification service to determine the authenticity of the product, it is possible to increase user satisfaction, reduce the price burden on the buyer, and enhance the credibility of the server operator.

[0089] In order to more clearly express the technical concept of the present invention, the attached drawings briefly depict or omit configurations that are unrelated to or have little relevance to the technical concept of the present invention.

[0090] Although the structure and features of the present invention have been described above based on embodiments according to the present invention, the present invention is not limited thereto, and it is obvious to those skilled in the art that various changes or modifications can be made within the spirit and scope of the present invention; therefore, it is noted that such changes or modifications fall within the scope of the appended claims. Explanation of the symbols

[0091] 100: AI-based multi-payment product purchase service system 110 : Product Selection Section 120 : Funding Register 130 : Funding Process Department 140 : Product Purchase Processing Unit 150 : Product Recommendation Section 160 : Product Verification Department 170 : Artificial Intelligence Model Generation Unit 200 : User terminal 300 : External server 400 : Social network service server (platform) 500 : User's acquaintance's device 600 : Database

Claims

Claim 1 A product purchase service system through AI-based multi-payment, characterized by comprising: a product selection unit that confirms a user's selection of a product to be purchased through crowdfunding; a funding registration unit that registers crowdfunding by generating funding information including a period, amount, and description of the product; a funding progress unit that conducts crowdfunding for the product targeting the user's acquaintances; and a product purchase processing unit that performs the purchase and delivery of the product when crowdfunding for the product is completed. Claim 2 The AI-based multi-payment product purchase service system according to claim 1, further comprising: a product recommendation unit that, when a product to be purchased through crowdfunding is selected, collects product information including price, name, brand, category, manufacturer, material, and ingredients of said product and user information including user gender, age, and region, and inputs said collected product information and user information into an AI model for product recommendation to recommend other products similar to or of a higher grade than said product, thereby allowing the user to keep the product selected as is or select one of said recommended products. Claim 3 A product purchase service system through AI-based multi-payment according to claim 2, wherein the AI ​​model for product recommendation is a deep learning model trained to classify user groups using product information including price, name, brand, category, manufacturer, material, and ingredients, and user information including user gender, age, and region as training data, and to recommend products suitable for the characteristics of each classified group. Claim 4 The AI-based multi-payment product purchase service system according to claim 1, further comprising: a product verification unit that, when a product to be purchased through crowdfunding is selected, collects text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product and image-based information including photos, unique numbers, and certificate information, and inputs the collected text-based information and image-based information into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit. Claim 5 A product purchase service system through AI-based multi-payment according to claim 4, wherein the AI ​​model for verifying product authenticity is a deep learning model trained to determine authenticity by using text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product and image-based information including photos, unique numbers, and certificate information as training data, and measuring accuracy, which is the ratio of products accurately identified as genuine among all products, precision, which is the ratio of actual genuine products among products identified as genuine, recall, which is the ratio of actual genuine products identified as genuine among genuine products, and authenticity accuracy, which is the harmonic mean of precision and recall. Claim 6 A product purchase service system through AI-based multi-payment according to claim 1, wherein the funding progress unit identifies a server or platform supporting at least one social network service designated by the user, and provides information related to the crowdfunding to an acquaintance of the user using the identified server or platform to enable them to participate in the crowdfunding for the product. Claim 7 A product purchase service system through AI-based multi-payment according to claim 1, wherein the funding progress unit, as a result of crowdfunding for the product targeting the user's acquaintances, accumulates the funds in the user's name or refunds them to the user's acquaintances who participated in the crowdfunding if the funding amount to purchase the product falls short of the target amount. Claim 8 A product purchase service method through AI-based multi-payment, performed in a product purchase service system through AI-based multi-payment described in claim 1, comprising: a product selection step of confirming a user's selection of a product to be purchased through crowdfunding; a funding registration step of registering crowdfunding by generating funding information including a period, amount, and description of the product; a funding progress step of conducting crowdfunding for the product targeting the user's acquaintances; and a product purchase processing step of purchasing and delivering the product when crowdfunding for the product is completed. Claim 9 The method of claim 8 further comprises a product recommendation step, wherein when a product to be purchased through crowdfunding is selected, the method collects product information including price, name, brand, category, manufacturer, material, and ingredients of the product and user information including user gender, age, and region, and inputs the collected product information and user information into an AI model for product recommendation to recommend other products similar to or of a higher grade than the product, thereby allowing the user to keep the product selected as is or select one of the recommended products. Claim 10 The method of claim 8 further comprises a product verification step, wherein when a product to be purchased through crowdfunding is selected, the method collects text-based information including price, name, brand, category, manufacturer, material, and ingredients of the product and image-based information including photos, unique numbers, and certificate information, and inputs the collected text-based information and image-based information into an AI model for product authenticity verification to verify whether the product is genuine or counterfeit.

Images