Electronic device and information providing method thereof

Abstract

Provided is an information providing method of an electronic device. The information providing method may comprise the steps of: checking one or more pieces of post-purchase review data created for a first item; generating representative post-purchase review data for the first item on the basis of the one or more pieces of post-purchase review data; and providing, to a user terminal, a detailed information page for the first item including the representative post-purchase review data.

Description

Electronic devices and their methods of providing information

[0001] The present disclosure relates to an electronic device and a method for providing information thereon. More specifically, the present disclosure relates to an electronic device and a method thereof that verifies one or more purchase reviews written for an item and, based on the one or more purchase reviews, provides information that allows a user to view the content of the one or more purchase reviews at a glance.

[0002] As internet use becomes more widespread, the e-commerce market is expanding. While the proportion of customers visiting offline stores to purchase products is declining, the proportion of customers purchasing products through e-commerce using computers or smartphones is rapidly increasing. Users who purchase products through e-commerce may tend to refer to product review data when making purchasing decisions. However, the greater the number of reviews, the more cumbersome it can be for users to review them all. Therefore, enabling users to quickly and conveniently access reviews can significantly increase product sales.

[0003] The disclosed embodiments aim to provide an electronic device and an information provision method thereof. More specifically, the technical challenge is to provide an electronic device and an information provision method thereof that enable a user to view purchase review data for an item at a glance.

[0004] The technical tasks to be achieved by this embodiment are not limited to the technical tasks described above, and other technical tasks can be inferred from the following embodiments.

[0005] A method for providing information performed by an electronic device according to one embodiment may include: a step of checking one or more purchase review data written for a first item; a step of generating representative purchase review data for the first item based on the one or more purchase review data; and a step of providing a detailed information page for the first item including the representative purchase review data to a user terminal.

[0006] According to one embodiment, the step of generating representative purchase review data for a first item based on one or more purchase review data includes the steps of: inputting the one or more purchase review data into an artificial intelligence-based model; and obtaining representative purchase review data output from the artificial intelligence-based model, wherein the artificial intelligence-based model may be a generative artificial intelligence model trained based on a purchase review data set including purchase review data written for each of a plurality of items and a summary review data set including a plurality of summary review data summarizing the purchase review data for each of the plurality of items.

[0007] According to one embodiment, the purchase review data may be text data including words within a first reference range, and the summary review data may be text data including words within a second reference range.

[0008] According to one embodiment, the plurality of items may include one or more items in which the number of purchase review data written for the items is greater than or equal to a first threshold value and the sum of the number of words included in the purchase review data is greater than or equal to a second threshold value, and the purchase review data set may include a plurality of first purchase review data randomly extracted from among the plurality of purchase review data written for the plurality of items and a plurality of second purchase review data extracted based on information about the writer from among the plurality of purchase review data.

[0009] According to one embodiment, the plurality of second purchase review data extracted based on information about the writer may be purchase review data written by one or more preset writers.

[0010] According to one embodiment, the purchase review data set may further include a plurality of third purchase review data having a rating equal to or greater than a first threshold score among the plurality of purchase review data written for a plurality of items, and a plurality of fourth purchase review data having a rating equal to or less than a second threshold score among the plurality of purchase review data.

[0011] According to one embodiment, the one or more purchase review data may be preprocessed purchase review data by deleting, from one or more purchase reviews written for the first item, information about the price of the first item, information about the seller of the first item, information about the delivery of the first item, and information about the writer of each of the plurality of purchase reviews confirmed for the first item.

[0012] According to one embodiment, the step of inputting to the artificial intelligence-based model may include the step of inputting a prompt requesting representative purchase review data that summarizes text data included in one or more purchase review data to include words within a second reference range, but from which information about the price of the item, information about the seller of the item, information about the delivery of the item, and information about the writer of each of the plurality of purchase reviews are deleted from the text data included in the one or more purchase review data.

[0013] According to one embodiment, the step of generating representative purchase review data for the first item based on one or more purchase review data may include the step of generating representative purchase review data based on at least one of information on the date each of the one or more purchase review data was written, information on a rating included in each of the one or more purchase review data, information on evaluation information for each of the one or more purchase review data, and information indicating whether each of the one or more purchase review data includes an image.

[0014] According to one embodiment, the representative purchase review data includes first representative purchase review data and second representative purchase review data, and the step of generating representative purchase review data for a first item based on one or more purchase review data may include: checking purchase review data written within a preset period among the one or more purchase review data; checking first type purchase review data having a rating equal to or higher than a first threshold score among the checked purchase review data; sorting the first type purchase review data in descending order of the number of evaluations included in the evaluation information of each of the first type purchase review data; and determining purchase review data including an image among the sorted first type purchase review data as the first representative purchase review data.

[0015] According to one embodiment, the step of generating each of the first representative purchase review data and the second representative purchase review data may include the steps of: checking purchase review data written within a preset period among one or more purchase review data; checking first type purchase review data having a rating equal to or higher than a first threshold score among the checked purchase review data; sorting the first type purchase review data in descending order of the number of evaluations included in the evaluation information of each of the first type purchase review data; and determining purchase review data including an image among the sorted first type purchase review data as the first representative purchase review data.

[0016] According to one embodiment, the step of generating each of the first representative purchase review data and the second representative purchase review data may include: a step of checking purchase review data written within a preset period among one or more purchase review data; a step of checking second type purchase review data having a rating lower than a second threshold score among the checked purchase review data; a step of sorting the second type purchase review data in descending order of the number of evaluations included in the evaluation information of each of the second type purchase review data; and a step of determining purchase review data including an image among the sorted second type purchase review data as the second representative purchase review data.

[0017] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of checking whether the sum total of the number of words included in the first representative purchase review data is less than a third threshold; and, if the sum total of the number of words included in the first representative purchase review data is less than the third threshold, the step of providing a detailed information page excluding the first representative purchase review text to the user terminal.

[0018] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of checking whether the sum total of the number of words included in the second representative purchase review data is less than a third threshold; and, if the sum total of the number of words included in the second representative purchase review data is less than the third threshold, the step of providing a detailed information page excluding the second representative purchase review text to the user terminal.

[0019] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of confirming first average rating information of a plurality of purchase review data based on rating information included in each of the plurality of purchase review data; and the step of providing a detailed information page including first representative purchase review data to the user terminal when the first average rating information is equal to or greater than a first threshold score.

[0020] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of checking whether the sum total of the number of words included in the second representative purchase review data is less than a third threshold; and, if the sum total of the number of words included in the second representative purchase review data is less than the third threshold, the step of providing a detailed information page excluding the second representative purchase review text to the user terminal.

[0021] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of confirming first average rating information of a plurality of purchase review data based on rating information included in each of the plurality of purchase review data; and the step of providing a detailed information page including first representative purchase review data to the user terminal when the first average rating information is equal to or greater than a first threshold score.

[0022] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include the step of confirming first average rating information of a plurality of purchase review data based on rating information included in each of the plurality of purchase review data; and the step of providing a detailed information page including second representative purchase review data to the user terminal when the first average rating information is less than a second threshold score.

[0023] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include: a step of confirming a plurality of purchase review data corresponding to a user input based on user input history for a plurality of purchase review data written for each of a plurality of items; a step of confirming second average rating information of the plurality of purchase review data based on rating information included in each of the confirmed plurality of purchase review data; and a step of providing a detailed information page including the first representative purchase review data to the user terminal when the second average rating information is equal to or greater than a first threshold score.

[0024] According to one embodiment, the step of providing a detailed information page for a first item including representative purchase review data to a user terminal may include: a step of confirming a plurality of purchase review data corresponding to a user input based on user input history for a plurality of purchase review data written for each of a plurality of items; a step of confirming second average rating information of the plurality of purchase review data based on rating information included in each of the confirmed plurality of purchase review data; and a step of providing a detailed information page including second representative purchase review data to the user terminal when the second average rating information is less than a second threshold score.

[0025] A non-transitory recording medium according to one embodiment may be a computer-readable non-transitory recording medium having recorded thereon a program for implementing a method performed by an electronic device.

[0026] An electronic device according to one embodiment includes a transceiver; a memory; and a processor, wherein the processor is configured to check one or more purchase review data written for a first item, generate representative purchase review data for the first item based on the one or more purchase review data, and provide a detailed information page for the first item including the representative purchase review data to a user terminal.

[0027] Specific details of the embodiments are included in the detailed description and drawings.

[0028] According to the proposed embodiment, one or more of the following effects can be expected.

[0029] According to an embodiment of this specification, a user can check the contents of purchase reviews written about an item at a glance.

[0030] Additionally, it can ultimately increase product sales.

[0031] The effects of the invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

[0032] FIG. 1 is a drawing for explaining a system according to one embodiment.

[0033] FIG. 2 illustrates a flowchart of a method for providing information in an electronic device according to one embodiment.

[0034] FIG. 3 is a diagram illustrating a process in which an electronic device provides a detailed information page for a first item according to one embodiment.

[0035] FIGS. 4A and 4B are diagrams illustrating a process in which an electronic device provides a detailed information page for a first item according to various embodiments.

[0036] FIG. 5 illustrates a block diagram of an electronic device according to one embodiment.

[0037] The terms used in the examples have been selected from widely used, current terms, taking into account the functions of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should not be defined simply as names, but rather based on the meanings of the terms and the overall content of the present disclosure.

[0038] When a part of a specification is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise stated.

[0039] The expression "at least one of a, b, and c" described throughout the specification may encompass 'a alone', 'b alone', 'c alone', 'a and b', 'a and c', 'b and c', or 'all of a, b, and c'.

[0040] The "terminal" mentioned below may be implemented as a computer or portable terminal that can connect to a server or other terminal via a network. Here, the computer includes, for example, a notebook, desktop, laptop, etc. equipped with a web browser, and the portable terminal may include, for example, a wireless communication device that guarantees portability and mobility, and may include all types of handheld-based wireless communication devices such as communication-based terminals such as IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), LTE (Long Term Evolution), smartphones, tablet PCs, etc.

[0041] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein.

[0042] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings.

[0043] Figure 1 illustrates a system according to one embodiment.

[0044] Referring to FIG. 1, the system may be implemented by various types of devices. For example, the system may be implemented in an electronic device (100) and a user terminal (110). Operations according to various embodiments of the present disclosure may be performed based on a system including the electronic device (100) and the user terminal (110). Meanwhile, the information provision system according to various embodiments is not limited to that illustrated in FIG. 1 and may be implemented in a wider variety of devices and servers.

[0045] Each of the electronic device (100) and the user terminal (110) may include a transceiver, a memory, and a processor. In addition, each of the electronic device (100) and the user terminal (110) refers to a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. Meanwhile, throughout the embodiments, each of the electronic device (100) and the user terminal (110) is referred to as a separate device or server, but this may be a logically divided structure, and at least some of them may be implemented by a separate function in one device or server.

[0046] According to one embodiment, the electronic device (100) and the user terminal (110) may include a plurality of computer systems or computer software implemented as network servers. For example, at least some of the electronic device (100) and the user terminal (110) may refer to a computer system and computer software that are connected to a lower device that can communicate with other network servers through a computer network such as an intranet or the Internet, receive a task execution request, perform the task in response, and provide the execution result. In addition, at least some of the electronic device (100) and the user terminal (110) may be understood as a broad concept that includes a series of application programs that can operate on a network server, and various databases built on other internal or connected nodes. For example, at least some of the electronic device (100) and the user terminal (110) may be implemented using a network server program that is provided in various ways according to an operating system such as DOS, Windows, Linux, UNIX, or MacOS.

[0047] The electronic device (100) and the user terminal (110) can communicate with each other through a network (not shown). The network includes a local area network (LAN), a wide area network (WAN), a value-added network (VAN), a mobile radio communication network, a satellite communication network, and a combination thereof, and is a comprehensive data communication network that allows each network component shown in FIG. 1 to communicate smoothly with each other, and may include wired Internet, wireless Internet, and mobile radio communication networks. Wireless communication may include, but is not limited to, wireless LAN (Wi-Fi), Bluetooth, Bluetooth low energy, Zigbee, Wi-Fi Direct (WFD), ultra wideband (UWB), infrared communication (IrDA, infrared Data Association), NFC (Near Field Communication), etc., for example.

[0048] An electronic device (100) is a device that configures and provides various types of information. The electronic device (100) may provide the configured information as a web page or application screen, or may provide the information in a form that can be displayed as a web page or application screen on a receiving terminal.

[0049] According to one embodiment, the electronic device (100) may obtain information from a user terminal (110) and provide the information to the user terminal (110). For example, the electronic device (100) may obtain purchase review data written for an item from the user terminal (110). The user terminal (110) may include a plurality of user terminals, and thus, the electronic device (100) may obtain one or more purchase review data written for a plurality of items from the plurality of user terminals. In addition, the electronic device (100) may check one or more purchase review data written for a first item among the obtained purchase review data, generate representative purchase review data for the first item based on the one or more purchase review data, and provide a detailed information page for the first item including the representative purchase review data to the user terminal (110).

[0050] The user terminal (110) is, for example, a terminal used by a user, and the user can access services provided by a network (not shown) using the terminal. For example, the electronic device (100) can provide an e-commerce service via a network. As a specific example, the electronic device (100) can provide various pages related to the e-commerce service via the network, and the user can use the e-commerce service by receiving various pages related to the e-commerce service using the user terminal (110). That is, a system including the electronic device (100) and the user terminal (110) can be, for example, an e-commerce system.

[0051] Meanwhile, although not illustrated in FIG. 1, the electronic device (100) may include a database. A database is a data structure implemented in a predetermined storage space, in which functions such as storing, searching, deleting, editing, or adding data can be freely performed. For example, the database may include fields or components for processing functions such as storing, searching, deleting, editing, or adding data.

[0052]

[0053] FIG. 2 illustrates a flowchart of a method for providing information in an electronic device according to one embodiment.

[0054] It can be clearly understood that some of the operations of the electronic device (100) shown in FIG. 2 providing information may be changed or substituted or some of the order between operations may be changed within a range clearly understandable to a person having ordinary skill in the art to which the present invention pertains.

[0055] In step S210, the electronic device (100) may verify one or more purchase review data written for the first item. That is, there may be one or more purchase reviews written for the first item. The first item may be an item sold in the aforementioned e-commerce system. Meanwhile, the purchase review data is text data written by users who purchased the item and may further include rating information for the item. Furthermore, according to one embodiment, the purchase review data may further include image data regarding the item.

[0056] In step S220, the electronic device (100) may generate representative purchase review data for the first item based on one or more purchase review data. The representative purchase review data for the first item may be, for example, purchase review data that summarizes text included in one or more purchase review data identified in step S210 (hereinafter, referred to as "summarized purchase review data" for convenience). A more specific embodiment of how the electronic device (100) generates the summarized purchase review data will be described in detail with reference to FIG. 3 below.

[0057] In another example, the representative purchase review data for the first item may include first representative purchase review data and second representative purchase review data determined from one or more purchase review data identified in step S210. The first representative purchase review data is purchase review data that summarizes the advantages of the first item and may be referred to as Pros representative purchase review data. The second representative purchase review data is purchase review data that summarizes the disadvantages of the first item and may be referred to as Cons representative purchase review data. The Pros representative purchase review data may be purchase review data of a type that includes a rating higher than a first threshold score (for convenience, referred to as the "Pros type" hereinafter) and positively evaluates the item, and the Cons representative purchase review data may be purchase review data of a type that includes a rating lower than a second threshold score (for convenience, referred to as the "Cons type" hereinafter) and negatively evaluates the item. Here, the first threshold score may be a value greater than the second threshold score. For example, if the rating included in the purchase review data is out of 5 points, the first threshold score may be preset as 4 points and the second threshold score as 3 points. A more specific embodiment in which the electronic device (100) generates representative purchase review data for the first item including the Pros representative purchase review data and the Cons representative purchase review data will be described in detail with reference to FIGS. 4A and 4B below.

[0058] In step S230, the electronic device (100) may provide a detailed information page for the first item including representative purchase review data to the user terminal (110). The detailed information page for the first item is a page that provides detailed information about the first item and may include a list of purchase reviews written for the first item. Specifically, the detailed information page for the first item may include an area where a list of purchase reviews is displayed and an area where representative purchase review data is displayed. The representative purchase review data may be located at the top of the area where the list of purchase reviews is displayed. A more specific embodiment in which the electronic device (100) provides a detailed information page for the first item including an area where a list of purchase reviews is displayed and an area where representative purchase review data is displayed will be described in detail with reference to FIGS. 3 to 4B below.

[0059]

[0060] FIG. 3 is a diagram illustrating a process in which an electronic device provides a detailed information page for a first item according to one embodiment.

[0061] According to one embodiment, the electronic device (100) may input one or more purchase review data into an artificial intelligence-based model to generate the summarized purchase review data described above, and obtain representative purchase review data (summarized purchase review data) output from the artificial intelligence-based model. Here, the artificial intelligence-based model may be, for example, a generative artificial intelligence model trained based on a purchase review data set including purchase review data written for each of a plurality of items and a summary review data set including a plurality of summary review data summarizing the purchase review data for each of a plurality of items.

[0062] In this disclosure, deep learning refers to the process of training a neural network model using experience processing a data set, and through deep learning, software can improve its own data processing capabilities. An AI-based model is a model created by modeling correlations between data sets, and these correlations can be expressed by multiple parameters. An AI-based model can derive correlations between data sets by extracting and analyzing features from a given data set, and deep learning refers to the process of optimizing the parameters of an AI-based model by repeating this process. Specifically, an AI-based model can learn correlations between inputs and outputs for a data set given as input-output pairs. Alternatively, an AI-based model can learn relationships by deriving regularities between data even when only input data is given.

[0063] Specifically, a purchase review data set including purchase review data written for each of a plurality of items may be used as an input data set for training an artificial intelligence-based model, and a summary review data set including a plurality of summary review data summarizing purchase review data for each of a plurality of items may be used as an output data set for training. The electronic device (100) may build a generative artificial intelligence model by modeling the correlation between the aforementioned training input data set and the training output data set according to a deep learning algorithm. That is, the electronic device (100) may input one or more purchase review data into the built model and obtain representative purchase review data output from the model. The deep learning algorithm may be one of a deep neural network, a recurrent neural network, a convolutional neural network, a machine learning model for classification-regression analysis, or a reinforcement learning model.

[0064] Since the summary review data for a specific product is data generated by summarizing multiple purchase review data for a specific product, an artificial intelligence-based model may be trained to extract at least one feature from each purchase review data in the purchase review data set and to derive a correlation between the purchase review data set and the summary review data set using the extracted at least one feature. The artificial intelligence-based model may be a generative artificial intelligence model trained based on a purchase review data set including purchase review data written for each of a plurality of items and a summary review data set including multiple summary review data summarizing purchase review data for each of a plurality of items.

[0065] In another example, the electronic device (100) may fine-tune a large language model (LLM) based on the aforementioned training input data set and training output data set, input one or more purchase review data into the tuned model, and obtain representative purchase review data output from the tuned model.

[0066] According to one embodiment, each of the purchase review data included in the training input data set may be text data including words within a first reference range, and each of the summary review data included in the training output data set may be text data within a second reference range. The first reference range may be, for example, a range of 30 words or more and 2000 words or less. As a more specific example, the A purchase review data written for item A included in the purchase review data set may be a portion of the entire text included in a plurality of purchase review data written for item A, and may be text data of up to 2000 words. The portion of the entire text may be a text of up to 2000 words included in the purchase reviews each including 30 words or more among the plurality of purchase reviews written for item A. Since the fewer words included in each purchase review, the less influence it may have on a user's purchase decision for an item, some of the text used as training input data may be set to text included in purchase reviews that contain a preset number of words or more.

[0067] Meanwhile, the second standard range may be, for example, a range of 150 words or more and 300 words or less. In other words, each of the summarized review data may be text data that summarizes the purchase review data, which is text data within the corresponding first standard range, to include a word count within the second standard range. The second standard range may be a range set to concisely summarize the content of the purchase reviews so that users can check the content of the written purchase reviews at a glance, while still allowing the overall content of the purchase reviews to be revealed.

[0068] According to one embodiment, the plurality of items corresponding to the plurality of purchase review data utilized in the purchase review data set may include one or more items for which the number of purchase review data written for the item is greater than or equal to a first threshold value and the sum of the number of words included in the purchase review data is greater than or equal to a second threshold value. The first threshold value may be, for example, 10, and the second threshold value may be, for example, 3000. In other words, the plurality of items may include one or more items for which 10 or more purchase reviews have been written, and for which the sum of the number of words in the entire text included in the written purchase reviews is greater than or equal to 3000.

[0069] In addition, the purchase review data set may include a plurality of first purchase review data randomly extracted from among a plurality of purchase review data written for a plurality of items, and a plurality of second purchase review data extracted based on information about the writers from among the plurality of purchase review data. Since the first purchase review data is randomly extracted, it may be data that randomly reflects the contents of a plurality of purchase reviews written for a specific item. Meanwhile, the second purchase review data may be, for example, purchase review data written by one or more preset writers. The one or more preset writers may be one or more writers set based on ratings for each writer, etc. As a specific example, the one or more preset writers may be the top 1,000 writers listed in descending order of their ratings, and the second purchase review data may be purchase review data written by one or more writers included in the top 1,000.

[0070] According to one embodiment, the purchase review data set, which is the input data set for training, may further include a plurality of third purchase review data having a rating equal to or higher than a first threshold score among the plurality of purchase review data written for a plurality of items, and a plurality of fourth purchase review data having a rating equal to or lower than a second threshold score among the plurality of purchase review data. That is, the input data set for training may further include a plurality of third purchase review data corresponding to the Pros type and a plurality of fourth purchase review data corresponding to the Cons type among the plurality of purchase review data written for a plurality of items. Specifically, the number of words included in the third purchase review data corresponding to the Pros type and the fourth purchase review data corresponding to the Cons type, which are further included in the input data set for training, may be the same or similar. Accordingly, in training an artificial intelligence-based model, input data that evenly includes purchase review data positively evaluating an item and purchase review data negatively evaluating the item can be utilized.

[0071] In another example, if the total number of words in the second purchase review data written for a specific item by one or more preset authors is less than 2,000, the second purchase review data may further include text from the third purchase review data corresponding to the Pros type and text from the fourth purchase review data corresponding to the Cons type until the total number of words reaches 2,000. In this case, the number of words in the additionally included third purchase review data may be set to be the same as or similar to the number of words in the fourth purchase review data. Considering that the purchase review data written by one or more preset authors generally mentions both the pros and cons of an item, the AI-based model can also be trained with a purchase review data set that includes more objective evaluations in the above example.

[0072] According to one embodiment, the one or more purchase review data may be preprocessed purchase review data by deleting, from one or more purchase reviews written for the first item, information regarding the price of the first item, information regarding the seller of the first item, information regarding the delivery of the first item, and information regarding the writer of each of the multiple purchase reviews confirmed for the first item. In other words, the one or more purchase review data may be data from which information regarding the price of the target item, information regarding the seller of the target item, information regarding the delivery of the target item, and personal information regarding the writer of the purchase review are deleted. In order to generate representative purchase review data for the first item, the electronic device (100) may input the data that has undergone such preprocessing into a trained artificial intelligence-based model. Similarly, each of the multiple purchase review data included in the training input data set may be preprocessed purchase review data by deleting information regarding the price of the corresponding item, information regarding the seller of the corresponding item, information regarding the delivery of the corresponding item, and information regarding the writer of the purchase review. The electronic device (100) can generate representative purchase review data that more appropriately summarizes purchase reviews by excluding information that does not indicate an evaluation of an item by utilizing purchase review data that has gone through the above-described preprocessing process for training an artificial intelligence-based model or by inputting the data into a trained model.

[0073] In one embodiment, the electronic device (100) may input a prompt to an artificial intelligence-based model to generate representative purchase review data for a first item. The electronic device (100) may input the prompt along with one or more purchase review data for the first item to the trained artificial intelligence-based model. For example, the prompt may be a prompt requesting representative purchase review data that summarizes text data included in one or more purchase review data to include words within a second reference range, but removes information regarding the price of the item, information regarding the seller of the item, information regarding the delivery of the item, and information regarding the authors of each of the multiple purchase reviews from the text data included in the one or more purchase review data. As a specific example, the prompt may be, "Please summarize the following customers' comments in 150 to 300 characters. When summarizing, please use a tone suitable for official and formal documents. Additionally, please do not include information regarding the prompt, price, seller, delivery, packaging, or personal information during the summarization process and the summary result."

[0074] Referring to FIG. 3, a detailed information page (300) for an item called Capsule A, which includes an area (301) in which summarized purchase review data is displayed, may be provided to a user terminal (110). The electronic device (100) may input a prompt requesting one or more purchase review data included in a purchase review list for Capsule A and representative purchase review data (summarized purchase review data) for Capsule A into a trained artificial intelligence-based model, and transmit a detailed information page (300) including the summarized purchase review data output from the trained model to the user terminal (110). The user terminal (110) may display the summarized purchase review data in an area (301) of the detailed information page (300). The summarized purchase review data may be text data that summarizes one or more purchase review data included in the purchase review list into 150 to 300 words. Meanwhile, the area (301) in which the summarized purchase review data is displayed may be located at the top of the area in which the purchase review list for Capsule A is displayed.

[0075]

[0076] FIGS. 4A and 4B are diagrams illustrating a process in which an electronic device provides a detailed information page for a first item according to various embodiments.

[0077] According to one embodiment, the representative purchase review data for the first item may include first representative purchase review data and second representative purchase review data, and the electronic device (100) may generate the first representative purchase review data and the second representative purchase review data based on at least one of the date information on which each of the one or more purchase review data was written, rating information included in each of the one or more purchase review data, evaluation information for each of the one or more purchase review data, and information indicating whether each of the one or more purchase review data includes an image. Here, the evaluation information for each of the one or more purchase review data may be, for example, information regarding an evaluation of each of the purchase review data obtained based on a user input. Specifically, the evaluation information may include the number of recommendations obtained based on an evaluation user input for the purchase review data, and thus may serve as an indicator of whether the purchase review data is useful to other users. Referring to FIGS. 4A and 4B , the evaluation information may be, for example, information such as "This was helpful to 9 people" included in each of the areas 402, 403, and 411.

[0078] Specifically, in order to generate the first representative purchase review data, the electronic device (100) may check purchase review data written within a preset period among one or more purchase review data, and check the first type of purchase review data having a rating higher than a first threshold score among the checked purchase review data. For example, if the preset period is set to a period of one year prior to the date of checking the one or more purchase review data, the electronic device (100) may check purchase review data written within the past year. In addition, since the first type having a rating higher than the first threshold score is the aforementioned Pros type, the electronic device (100) may check purchase review data of the Pros type among the purchase review data written within the past year.

[0079] Next, the electronic device (100) may sort the Pros type purchase review data in the order of the number of evaluations included in the evaluation information of each of the Pros type purchase review data, and determine the purchase review data including an image among the sorted Pros type purchase review data as the first representative purchase review data (i.e., Pros representative purchase review data). In other words, the electronic device (100) may determine the purchase review data including a large number of evaluations and an image as the Pros representative purchase review data. If the Pros representative purchase review data extracted by the electronic device (100) according to the above process includes a plurality of purchase review data having the same evaluation information and including the same image, the electronic device (100) may determine the most recently written purchase review data among the extracted plurality of purchase review data as the final Pros representative purchase review data. Furthermore, according to an embodiment, if the extracted Pros representative purchase review data includes a plurality of purchase review data having the same evaluation information and including the same image, the electronic device (100) may determine the purchase review data including an image or the purchase review data having the largest number of included images as the final Pros representative purchase review data.

[0080] Meanwhile, in order to generate the second representative purchase review data, the electronic device (100) may check purchase review data written within a preset period among one or more purchase review data, and check the second type of purchase review data having a rating lower than the second threshold score among the checked purchase review data. For example, if the preset period is set to a period of one year prior to the date of checking the one or more purchase review data, the electronic device (100) may check purchase review data written within the past year. In addition, since the second type having a rating higher than the second threshold score is the aforementioned Cons type, the electronic device (100) may check purchase review data of the Cons type among the purchase review data written within the past year.

[0081] Next, the electronic device (100) may sort the Cons type purchase review data in the order of the number of evaluations included in the evaluation information of each Cons type purchase review data, and determine the purchase review data including an image among the sorted Cons type purchase review data as the second representative purchase review data (i.e., Cons representative purchase review data). In other words, the electronic device (100) may determine the purchase review data including a large number of evaluations and an image as the Cons representative purchase review data. If the Cons representative purchase review data extracted by the electronic device (100) according to the above process includes a plurality of purchase review data having the same evaluation information and including an image, the electronic device (100) may determine the most recently written purchase review data among the extracted plurality of purchase review data as the final Cons representative purchase review data. Furthermore, according to an embodiment, if the extracted Cons representative purchase review data includes a plurality of purchase review data having the same evaluation information and including an image, the electronic device (100) may determine the purchase review data including an image or the purchase review data having the largest number of included images as the final Cons representative purchase review data.

[0082] Referring to FIG. 4A, a detailed information page (400) for a kitchen detergent including Pros representative purchase review data and Cons representative purchase review data determined according to the above-described embodiments may be provided to a user terminal (110). The detailed information page (400) for the kitchen detergent may include an area (401) where representative purchase review data for the kitchen detergent is displayed. Specifically, the area (401) where representative purchase review data for the kitchen detergent is displayed may include an area (402) where Pros representative purchase review data is displayed and an area (403) where Cons representative purchase review data is displayed. The Pros representative purchase review data displayed on the detailed information page (400) may be purchase review data that is written during a preset period, includes a rating of 4.5 points (a rating of 4 points or higher), includes the number of 9 recommendations (evaluation information) obtained from other users, and includes an image. On the other hand, the representative purchase review data for Cons may be purchase reviews written during a preset period, including a rating of 2 points (a rating of less than 3 points), and including 9 recommendations (evaluation information) obtained from other users, as well as purchase review data including an image.

[0083] According to one embodiment, in order to provide a detailed information page for a first item including representative purchase review data to a user terminal (110), the electronic device (100) may check whether the sum of the number of words included in the Pros representative purchase review data is less than a third threshold, and if the sum of the number of words included in the Pros representative purchase review data is less than the third threshold, the electronic device (100) may provide a detailed information page excluding text of the Pros representative purchase review data to the user terminal (110). The third threshold may be, for example, 100. That is, if the Pros representative purchase review data determined by the electronic device (100) is text data of less than 100 words, the electronic device (100) may provide a detailed information page for the first item excluding the determined Pros representative purchase review data to the user terminal (110). In another example, even if the evaluation information of the Pros representative review data determined by the electronic device (100) indicates that the number of recommendations obtained from other users is 0, the electronic device (100) may provide the user terminal (110) with a detailed information page for the first item excluding the determined Pros representative purchase review data.

[0084] Referring to FIG. 4A, the area (401) where representative purchase review data for a kitchen detergent is displayed includes both an area (402) where representative purchase review data for Pros is displayed and an area (403) where representative purchase review data for Cons is displayed. However, if the Pros representative purchase review data determined by the electronic device (100) includes text of less than 100 words or the number of recommendations obtained from other users is 0, the electronic device (100) may provide a detailed information page (400) to the user terminal (110) that excludes the area (402) where representative purchase review data for Pros is displayed from the area (401) where representative purchase review data for a kitchen detergent is displayed.

[0085] According to one embodiment, in order to provide a detailed information page for a first item including representative purchase review data to a user terminal (110), the electronic device (100) may check whether the sum of the number of words included in the Cons representative purchase review data is less than a third threshold, and if the sum of the number of words included in the Cons representative purchase review data is less than the third threshold, the electronic device (100) may provide a detailed information page excluding text of the Cons representative purchase review data to the user terminal (110). In an example where the third threshold is 100, if the Cons representative purchase review data determined by the electronic device (100) is text data of less than 100 words, the electronic device (100) may provide a detailed information page for the first item excluding the determined Cons representative purchase review data to the user terminal (110). In another example, even if the evaluation information of the Cons representative review data determined by the electronic device (100) indicates that the number of recommendations obtained from other users is 0, the electronic device (100) may provide the user terminal (110) with a detailed information page for the first item excluding the determined Cons representative purchase review data.

[0086] Referring to FIG. 4A, the area (401) where representative purchase review data for a kitchen detergent is displayed includes both an area (402) where representative purchase review data for Pros is displayed and an area (403) where representative purchase review data for Cons is displayed. However, if the representative purchase review data for Cons determined by the electronic device (100) includes text of less than 100 words or the number of recommendations obtained from other users is 0, the electronic device (100) may provide a detailed information page (400) to the user terminal (110) that excludes the area (403) where representative purchase review data for Cons is displayed from the area (401) where representative purchase review data for a kitchen detergent is displayed.

[0087] Meanwhile, referring to FIG. 4B, unlike FIG. 4A, a detailed information page (410) for a kitchen detergent including an area (411) in which one representative purchase review data is displayed may be provided to the user terminal (110). At the top of the area (411), a tab-shaped area (412) corresponding to the Pros representative purchase review data and a tab-shaped area (413) corresponding to the Cons representative purchase review data may be displayed together. At this time, one of the two tab-shaped areas (412, 413) may be selected by the electronic device (100) and the representative purchase review data corresponding to the selected area may be set as the main area on the detailed information page (410) by default. For example, the representative purchase review data provided as the main area may be the Pros representative purchase review data. However, according to various embodiments including the embodiments described below, the representative purchase review data provided as the main area may be set as the Cons representative purchase review data or may be set differently for each item.

[0088] According to one embodiment, the electronic device (100) may, in order to provide a detailed information page for a first item including representative purchase review data to a user terminal (110), determine first average rating information of the plurality of purchase review data based on rating information included in each of the plurality of purchase review data. Subsequently, the electronic device (100) may provide a detailed information page including the first representative purchase review data to the user terminal (110) if the first average rating information is equal to or greater than a first threshold score. In other words, if the average rating of the plurality of purchase review data is equal to or greater than the first threshold score and primarily indicates positive evaluations, the electronic device (100) may provide a detailed information page including Pros representative purchase review data to the user terminal (110). Accordingly, a user who receives a detailed information page for the first item through the user terminal (110) may recognize at a glance that overall purchase reviews for the first item include positive evaluations. According to an embodiment, the electronic device (100) may provide the Pros representative purchase review data as the main representative purchase review to the user terminal (110), and may also provide a tab-shaped area (e.g., 413 of FIG. 4b) where the Cons representative purchase review data can be checked. That is, when a user input corresponding to the tab-shaped area is obtained, the electronic device (100) may provide the Cons representative purchase review data to the user terminal (110).

[0089] According to one embodiment, the electronic device (100) may check first average rating information of the plurality of purchase review data based on rating information included in each of the plurality of purchase review data to provide a detailed information page for a first item including representative purchase review data to the user terminal (110). Then, if the first average rating information is less than a second threshold score, the electronic device (100) may provide a detailed information page including the first representative purchase review data to the user terminal (110). In other words, if the average rating of the plurality of purchase review data is less than the second threshold score, the electronic device (100) may provide a detailed information page including Cons representative purchase review data to the user terminal (110). According to an embodiment, the electronic device (100) may provide the Cons representative purchase review data as the main representative purchase review data to the user terminal (110), and may also provide a tab-type area (for example, 412 of FIG. 4B) for checking the Pros representative purchase review data. That is, when a user input corresponding to a tab-shaped area is obtained, the electronic device (100) can provide Cons representative purchase review data to the user terminal (110).

[0090] According to one embodiment, the electronic device (100) may verify a plurality of purchase review data corresponding to a user input based on a user input history for a plurality of purchase review data written for each of a plurality of items, in order to provide a detailed information page for a first item including representative purchase review data to the user terminal (110). Here, the user input history for the plurality of purchase review data may include, for example, a history of one or more user inputs for each of one or more purchase review data included in a purchase review list for item A obtained on a detailed information page for item A provided to the user terminal (110), one or more user inputs for each of one or more purchase review data included in a purchase review list for item B obtained on a detailed information page for item B, and the like. In other words, the user input history for the plurality of purchase review data may include information regarding purchase review data corresponding to a user input among various purchase review data. Accordingly, by checking multiple purchase review data corresponding to user input based on user input history, it is possible to determine the tendencies of purchase review data that a specific user wants to check and the types of purchase review data that a specific user prefers.

[0091] Next, the electronic device (100) can check the second average rating information of the plurality of purchase review data based on the rating information included in each of the plurality of purchase review data confirmed among the plurality of purchase review data written for each of the plurality of items. Specifically, the electronic device (100) can calculate the average rating information of the entire plurality of purchase review data corresponding to the user input. Accordingly, the electronic device (100) can check whether the purchase review data that a specific user wants to check is information that mainly includes positive ratings (e.g., ratings of purchase review data of the Pros type) or information that mainly includes negative ratings (e.g., ratings of purchase review data of the Cons type).

[0092] If the second average score information is equal to or greater than the first threshold score, the electronic device (100) may provide a detailed information page including the first representative purchase review data to the user terminal (110). In other words, if the average rating of a plurality of purchase review data is equal to or greater than the first threshold score and primarily indicates positive evaluations, the electronic device (100) may provide a detailed information page including the Pros representative purchase review data to the user terminal (110). Accordingly, a user who receives the detailed information page for the first item through the terminal may recognize at a glance that the overall purchase reviews for the first item include positive evaluations. According to an embodiment, the electronic device (100) may provide the Pros representative purchase review data to the user terminal (110) as the main representative purchase review data, and may also provide a tab-type area for checking the Cons representative purchase review data.

[0093] According to one embodiment, the electronic device (100) may verify a plurality of purchase review data corresponding to a user input based on a user input history for a plurality of purchase review data written for each of a plurality of items, in order to provide a detailed information page for a first item including representative purchase review data to the user terminal (110). Accordingly, by verifying a plurality of purchase review data corresponding to a user input based on the user input history, it is possible to identify a tendency of purchase review data that a specific user wishes to verify, a type of purchase review data preferred by a specific user, etc.

[0094] Next, the electronic device (100) can check the second average rating information of the plurality of purchase review data based on the rating information included in each of the plurality of purchase review data confirmed among the plurality of purchase review data written for each of the plurality of items. Specifically, the electronic device (100) can calculate the average rating information of the entire plurality of purchase review data corresponding to the user input. Accordingly, the electronic device (100) can check whether the purchase review data that a specific user wants to check is information that mainly includes positive ratings (e.g., ratings of purchase review data of the Pros type) or information that mainly includes negative ratings (e.g., ratings of purchase review data of the Cons type).

[0095] If the second average score information is less than the second threshold score, the electronic device (100) may provide a detailed information page including the second representative purchase review data to the user terminal (110). In other words, if the average rating of the plurality of purchase review data is less than the second threshold score and thus primarily indicates negative evaluations, the electronic device (100) may provide a detailed information page including the Cons representative purchase review data to the user terminal (110). According to an embodiment, the electronic device (100) may provide the Cons representative purchase review data as the main representative purchase review data to the user terminal (110), and may also provide a tab-type area where the Pros representative purchase review data can be checked.

[0096] According to another embodiment, the electronic device (100) may sort the plurality of purchase review data in order of the number of recommendations obtained based on the evaluation information included in the plurality of purchase review data, check the top 10 purchase review data among them, and check the average rating information of the top 10 confirmed purchase review data to set the main representative purchase review data as Pros representative purchase review data or Cons representative purchase review data. Specifically, the electronic device (100) may provide the Pros representative purchase review data as the main when the average rating information is equal to or greater than a first threshold score, and may provide the Cons representative purchase review data as the main when the average rating information is equal to or less than a second threshold score, and may provide other representative purchase review data other than the main in the form of tabs.

[0097] According to another embodiment, the electronic device (100) may sort the plurality of purchase review data in the order of the most recently written data based on information about the date on which the plurality of purchase review data were written, check the 10 most recently written purchase review data among them, and check the average rating information of the 10 confirmed purchase review data to set the main representative purchase review data as Pros representative purchase review data or Cons representative purchase review data. As in the above-described embodiment, specifically, if the average rating information is equal to or greater than a first threshold score, the electronic device (100) may provide the Pros representative purchase review data as the main, and if the average rating information is less than a second threshold score, the Cons representative purchase review data may be provided as the main, to the user terminal (110), and other representative purchase review data other than the main may be provided in the form of tabs.

[0098] According to one embodiment, the Pros representative purchase review data and the Cons representative purchase review data may be generated based on an artificial intelligence-based model. The artificial intelligence-based model may be a generative artificial intelligence model trained to output summary purchase review data summarizing one or more purchase review data when one or more purchase review data are input. Accordingly, in order to generate the Pros representative purchase review data, the electronic device (100) may check purchase review data of a type (Pros type) that includes a rating equal to or higher than a first threshold score among one or more purchase review data for a first item. The electronic device (100) may input the Pros type purchase review data into the trained artificial intelligence-based model, and determine the summary purchase review data output from the artificial intelligence-based model as the Pros representative purchase review data.

[0099] In a similar manner, the electronic device (100) may identify purchase review data of a type (Cons type) that includes a rating lower than the second threshold score among one or more purchase review data for the first item, in order to generate Cros representative purchase review data. The electronic device (100) may input the purchase review data of the Cons type into a trained artificial intelligence-based model, and determine the summary purchase review data output from the artificial intelligence-based model as the Cons representative purchase review data.

[0100] FIG. 5 shows a block diagram of an electronic device (100) according to one embodiment.

[0101] The electronic device (100) may include, according to one embodiment, a processor (510), a memory (520), and a transceiver (530). The electronic device (100) illustrated in FIG. 5 only illustrates components related to the present embodiment. Therefore, those skilled in the art will understand that, in addition to the components illustrated in FIG. 5, other general-purpose components may be included. Descriptions of content overlapping with FIGS. 1 to 4A and 4B will be omitted.

[0102] The processor (510) can control the overall operation of the electronic device (100) and process data and signals. The processor (510) can be composed of at least one hardware unit. In addition, the processor (510) can operate by one or more software modules generated by executing program codes stored in the memory (520). The processor (510) can include a memory, and the processor (510) can control the overall operation of the electronic device (100) and process data and signals by executing the program codes stored in the memory.

[0103] The processor (510) may be implemented as a computer or similar device based on hardware, software, or a combination thereof. In terms of hardware, the processor (510) may be implemented in the form of an electronic circuit that processes electrical signals to perform control functions, and in terms of software, the processor (510) may be implemented in the form of a program that drives the hardware processor (510). Meanwhile, unless otherwise specified in the above description, the operation of the electronic device may be interpreted as being performed under the control of the processor (510). That is, when the modules implemented in the system for analyzing the above-described data are executed, the modules may be interpreted as controlling the processor (510) to perform the above-described operations of the electronic device.

[0104] For example, the processor (510) may obtain one or more purchase review data written for a first item from a plurality of user terminals via a communication unit. In addition, the processor (510) may verify one or more purchase review data written for the first item, generate representative purchase review data for the first item based on the one or more purchase review data, and provide a detailed information page for the first item including the representative purchase review data to the user terminal (110). For example, the processor (510) may display the detailed information page for the first item via a display included in the electronic device (100) or a separate display connected to the electronic device (100).

[0105] The memory (520) can store various types of information. The memory (520) can store data temporarily or semi-permanently. For example, the memory (520) of the electronic device (100) can store an operating system (OS) for operating the electronic device (100), data for hosting a website, a program for generating Braille, or data related to an application (e.g., a web application). In addition, the memory (520) can store modules in the form of computer code, as described above.

[0106] Examples of memory (520) may include a hard disk drive (HDD), a solid state drive (SSD), flash memory, read-only memory (ROM), random access memory (RAM), etc. Such memory (520) may be provided as a built-in type or a detachable type.

[0107] The transceiver (530) is a device for performing wired / wireless communication and can communicate with an external electronic device. The external electronic device may be a terminal or a server. The communication technologies used by the transceiver (530) may include GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), LTE (Long Term Evolution), 5G, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Bluetooth (Bluetooth), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, NFC (Near Field Communication), etc.

[0108] In summary, the various embodiments may be implemented through various means. For example, the various embodiments may be implemented through hardware, firmware, software, or a combination thereof.

[0109] In the case of hardware implementation, the methods according to various embodiments may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, etc.

[0110] When implemented via firmware or software, the methods according to various embodiments may be implemented in the form of modules, procedures, or functions that perform the functions or operations described above. For example, software code may be stored in memory and executed by a processor. The memory may be located within or outside the processor and may exchange data with the processor via various known means.

[0111] The electronic device according to the above-described embodiments may include a processor, a memory for storing and executing program data, permanent storage such as a disk drive, a communication port for communicating with an external device, a user interface device such as a touch panel, a key, a button, etc. The methods implemented as software modules or algorithms may be stored on a computer-readable recording medium as computer-readable codes or program instructions executable on the processor. Here, the computer-readable recording medium includes a magnetic storage medium (e.g., read-only memory (ROM), random-access memory (RAM), floppy disk, hard disk, etc.) and an optical reading medium (e.g., CD-ROM, DVD: Digital Versatile Disc)). The computer-readable recording medium may be distributed to computer systems connected to a network, so that the computer-readable code may be stored and executed in a distributed manner. The medium may be readable by a computer, stored in a memory, and executed by a processor.

[0112] The present embodiment may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various hardware and / or software configurations that perform specific functions. For example, the embodiment may employ direct circuit configurations such as memory, processing, logic, look-up tables, etc., which may perform various functions under the control of one or more microprocessors or other control devices. Similarly, the present embodiment may be implemented in a programming or scripting language such as C, C++, Java, assembler, etc., including various algorithms implemented as a combination of data structures, processes, routines, or other programming configurations. Functional aspects may be implemented as algorithms that execute on one or more processors. Furthermore, the present embodiment may employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as "mechanism," "element," "means," and "composition" can be used broadly and are not limited to mechanical or physical structures. These terms can also encompass a series of software routines, such as those associated with a processor.

[0113] The above-described embodiments are merely examples, and other embodiments may be implemented within the scope of the claims set forth below.

Claims

1. In a method of providing information performed by an electronic device, A step of checking one or more purchase review data written for the first item; A step of generating representative purchase review data for the first item based on the one or more purchase review data; and An information providing method comprising the step of providing a detailed information page for a first item including the representative purchase review data to a user terminal.

2. In paragraph 1, The step of generating representative purchase review data for the first item based on the one or more purchase review data is as follows: A step of inputting one or more of the above purchase review data into an artificial intelligence-based model; and Including a step of obtaining the representative purchase review data output from the artificial intelligence-based model, The above artificial intelligence-based model is, An information providing method, comprising a generative artificial intelligence model trained on the basis of a purchase review data set including purchase review data written for each of a plurality of items and a summary review data set including a plurality of summary review data summarizing the purchase review data for each of the plurality of items.

3. In paragraph 2, The above purchase review data is text data that includes words within the first standard range, A method for providing information, wherein the above summary review data is text data containing words within a second reference range.

4. In paragraph 2, The above multiple items are, Including one or more items in which the number of purchase review data written for the item is greater than or equal to a first threshold, and the sum of the number of words included in the purchase review data is greater than or equal to a second threshold, The above purchase review data set is, An information providing method, comprising: a plurality of first purchase review data randomly extracted from among a plurality of purchase review data written for the plurality of items; and a plurality of second purchase review data extracted based on information about the writer from among the plurality of purchase review data.

5. In paragraph 4, A method for providing information, wherein the plurality of second purchase review data extracted based on information about the above-mentioned writer are purchase review data written by one or more preset writers.

6. In paragraph 4, The above purchase review data set is, An information providing method further comprising: a plurality of third purchase review data having a rating equal to or higher than a first threshold score among the plurality of purchase review data written for the plurality of items; and a plurality of fourth purchase review data having a rating equal to or lower than a second threshold score among the plurality of purchase review data.

7. In paragraph 1, One or more of the above purchase review data, A method for providing information, wherein the purchase review data is preprocessed by deleting information about the price of the first item, information about the seller of the first item, information about the delivery of the first item, and information about the writer of each of the plurality of purchase reviews confirmed for the first item from one or more purchase reviews written for the first item.

8. In paragraph 3, The steps to input into the above artificial intelligence-based model are: A method for providing information, comprising the step of inputting a prompt requesting representative purchase review data that summarizes text data included in the one or more purchase review data to include words within the second reference range, but from which information regarding the price of the item, information regarding the seller of the item, information regarding the delivery of the item, and information regarding the writer of each of the plurality of purchase reviews are deleted from the text data included in the one or more purchase review data.

9. In paragraph 1, The representative purchase review data for the above first item includes the first representative purchase review data and the second representative purchase review data, The step of generating representative purchase review data for the first item based on the one or more purchase review data is as follows: An information providing method, comprising a step of generating each of the first representative purchase review data and the second representative purchase review data based on at least one of information on the date each of the one or more purchase review data was written, rating information included in each of the one or more purchase review data, evaluation information for each of the one or more purchase review data, and information indicating whether each of the one or more purchase review data includes an image.

10. In paragraph 9, The step of generating the first representative purchase review data and the second representative purchase review data, respectively, is as follows: A step of checking purchase review data written within a preset period among the above one or more purchase review data; A step of checking the first type of purchase review data having a rating higher than the first threshold score among the above-confirmed purchase review data; For the first type of purchase review data, a step of sorting the first type of purchase review data in the order of the number of evaluations included in the evaluation information of each of the first type of purchase review data; and An information providing method, comprising a step of determining purchase review data including an image among the sorted first type of purchase review data as the first representative purchase review data.

11. In paragraph 9, The step of generating the first representative purchase review data and the second representative purchase review data, respectively, is as follows: A step of checking purchase review data written within a preset period among the above one or more purchase review data; A step of checking the second type of purchase review data having a rating lower than the second threshold score among the above-mentioned purchase review data; For the second type of purchase review data, a step of sorting the number of evaluations included in the evaluation information of each of the second type of purchase review data in ascending order; and An information providing method, comprising a step of determining purchase review data including an image among the second type of purchase review data sorted above as the second representative purchase review data.

12. In paragraph 9, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of checking whether the total number of words included in the first representative purchase review data is less than a third threshold; and An information providing method comprising the step of providing the detailed information page excluding the first representative purchase review data to a user terminal when the total number of words included in the first representative purchase review data is less than the third threshold value.

13. In paragraph 9, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of checking whether the total number of words included in the second representative purchase review data is less than a third threshold; and An information providing method comprising the step of providing the detailed information page excluding the second representative purchase review data to a user terminal when the total number of words included in the second representative purchase review data is less than the third threshold value.

14. In paragraph 10, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of confirming first average rating information of the plurality of purchase review data based on rating information included in each of the plurality of purchase review data; and An information providing method comprising the step of providing the detailed information page including the first representative purchase review data to a user terminal when the first average rating information is equal to or greater than the first threshold score.

15. In paragraph 11, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of confirming first average rating information of the plurality of purchase review data based on rating information included in each of the plurality of purchase review data; and An information providing method comprising the step of providing the detailed information page including the second representative purchase review data to a user terminal when the first average rating information is less than the second threshold score.

16. In paragraph 10, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of confirming multiple purchase review data corresponding to user input based on user input history for multiple purchase review data written for each of multiple items; A step of confirming second average rating information of the plurality of purchase review data based on rating information included in each of the plurality of confirmed purchase review data; and An information providing method comprising the step of providing the detailed information page including the first representative purchase review data to a user terminal when the second average score information is equal to or greater than the first threshold score.

17. In paragraph 11, The step of providing a detailed information page for the first item including the representative purchase review data to the user terminal is as follows: A step of confirming multiple purchase review data corresponding to user input based on user input history for multiple purchase review data written for each of multiple items; A step of confirming second average rating information of the plurality of purchase review data based on rating information included in each of the plurality of confirmed purchase review data; and An information providing method comprising the step of providing the detailed information page including the second representative purchase review data to a user terminal when the second average rating information is less than the second threshold score.

18. A non-transitory computer-readable recording medium having recorded thereon a program for executing the method of paragraph 1 on a computer.

19. As an electronic device, transceiver; memory; and comprising a processor, said processor comprising: Check one or more purchase review data written for the first item, Generating representative purchase review data for the first item based on the one or more purchase review data, and An electronic device that provides a detailed information page for a first item including the representative purchase review data to a user terminal.

Images