Commodity providing apparatus and commodity providing method

Abstract

To provide a commodity providing apparatus and a commodity providing method capable of reducing a feeling of inconsistency between a commodity viewed on the web and a commodity actually received.SOLUTION: A commodity providing apparatus for presenting a commodity on a user terminal via the Internet includes: an input unit which receives a user input for information on a desired article desired by a user via the user terminal; a retrieval extraction unit which retrieves and extracts a candidate article for the desired article from among commodities on sale in a virtual store; a three-dimensional image generation unit which generates a three-dimensional image of the candidate article on the basis of multi-viewpoint images of the candidate article; and an output unit which displays the three-dimensional image of the candidate article in an image display region on the user terminal.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The technology of the present disclosure relates to a product providing device and a product providing method. [Background technology]

[0002] With the spread of the Internet, electronic commerce, in which consumers purchase products and the like using EC (Electronic Commerce) sites on the Internet, is expanding. The general method is to look at products displayed as two-dimensional images, select the desired product, and purchase it. In recent years, a method has been provided in which products are displayed three-dimensionally in a virtual space to stimulate consumers' desire to purchase them (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2001-344474 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, even now, in small retail stores or online flea markets where ordinary people sell goods, people look at the two-dimensional images of the goods provided by the sellers, select the goods they want, and purchase them. Therefore, it is often the case that the goods that are actually delivered are different from what they imagined from the two-dimensional images. The present disclosure aims to provide a product provision device and a product provision method that can reduce the sense of discrepancy between a product viewed online and the product that actually arrives. [Means for solving the problem]

[0005] A first aspect of the technology disclosed herein is a product provision device that presents products to a user terminal via the Internet, the product provision device including: an input unit that accepts user input regarding information of a desired product desired by a user via the user terminal; a search and extraction unit that searches for and extracts candidate products for the desired product from products listed in a virtual store based on the user input; a three-dimensional image generation unit that generates a three-dimensional image of the candidate product based on images of the candidate product from multiple viewpoints; and an output unit that displays the three-dimensional image of the candidate product in an image display area of ​​the user terminal.

[0006] According to a second aspect of the technology disclosed herein, when one of the candidate items extracted by the search and extraction unit is selected on the user terminal, the three-dimensional image generation unit generates the three-dimensional image of the selected candidate item.

[0007] According to a third aspect of the technology disclosed herein, the three-dimensional image generation unit generates the three-dimensional image based on the multiple viewpoint images as well as text provided in association with the candidate item.

[0008] According to a fourth aspect of the technology disclosed herein, the three-dimensional image generation unit searches a website on the Internet for an image of the candidate item based on the model number of the candidate item, and uses the searched image as one of the multiple viewpoint images to generate the three-dimensional image.

[0009] According to a fifth aspect of the technology disclosed herein, the search and extraction unit generates a response corresponding to the user input using a data generation model that generates sentences in response to the user input, and displays the response corresponding to the user input on the user terminal.

[0010] According to a sixth aspect of the technology disclosed herein, the device further includes a call processing unit that calls the seller of the candidate item when the input unit receives a message regarding the candidate item from the user, and a dialogue processing unit that enables the user and the seller to dialogue in the virtual store.

[0011] According to a seventh aspect of the technique of the present disclosure, the dialogue processing unit enables an avatar representing the user and an avatar representing the seller to dialogue with each other in the virtual store.

[0012] An eighth aspect of the technology disclosed herein is a product provision method including the steps of accepting user input regarding information of a desired product desired by a user via a user terminal, searching for and extracting candidate products for the desired product from products listed in a virtual store based on the user input, generating a three-dimensional image of the candidate product based on multiple-view images of the candidate product, and displaying the three-dimensional image of the candidate product in an image display area of ​​the user terminal. [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a product providing system. [Diagram 2] FIG. 2 is a conceptual diagram showing an example of main functions of a product providing device and a smart device. [Figure 3A] The outline of the specific process is shown below. [Figure 3B] The outline of the specific process is shown below. [Figure 4] 4 illustrates an outline of a functional configuration of a specific processing unit of the product provision device. [Diagram 5] 13 illustrates an example of an operational flow of a specific process performed by the product provision device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an example of an embodiment of a product providing device and a product providing method according to the technology of the present disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0017] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0021] FIG. 1 shows an example of the configuration of a product provision system 10 according to an embodiment.

[0022] As shown in FIG. 1, the product provision system 10 includes a product provision device 12 and a smart device 14. An example of the product provision device 12 is a server. An example of the smart device 14 is a smartphone. In this embodiment, the product provision device 12 is an example of a "product provision device" according to the technology of the present disclosure, and the smart device 14 is an example of a "user terminal" according to the technology of the present disclosure.

[0023] The product providing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network), etc.

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with an indicator (e.g., a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the product provision device 12. In the product provision device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to a person by outputting the data in a form of expression that the person can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of main functions of the product provision apparatus 12 and the smart device 14.

[0029] 2, in the product provision device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and a 3D image generation model 59. The data generation model 58 and the 3D image generation model 59 are used by the specific processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 62. The reception output program 62 is used in conjunction with the specific processing program 56 by the product provision system 10. The processor 46 reads out the reception output program 62 from the storage 50, and executes the read reception output program 62 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 62 executed on the RAM 48.

[0032] Next, the specification process in the specification processing unit 290 of the product provision device 12 will be described.

[0033] In the identification process in this embodiment, a process is performed in which products desired by a user are presented to the user during shopping or the like in a virtual store set in a virtual space such as the metaverse.

[0034] Specifically, as the specific process, the product providing device 12 performs a process of presenting products according to the user's desire when the user goes shopping in a virtual store 200 set in a virtual space as shown in Fig. 3A. The virtual store 200 shown in Fig. 3A includes a sports area in which sports-related information and sporting goods are displayed in the store, a health care area which displays information about health care and has a consultation desk with medical staff, a fashion area which handles clothing, and a flea market area. The following describes a case where support is provided when the user selects a product in the flea market area in the virtual store 200.

[0035] In the flea market area, as shown in FIG. 3B, sellers put up items for sale. At this time, the sellers register images of the items taken from multiple viewpoints from multiple angles. The images of multiple viewpoints may be two or more two-dimensional images taken from different angles. For example, the images may be a set of a front image, a back image, a left side image, a right side image, a top image, and a bottom image of the item. The sellers register information about the item as text data along with the photos of the item. The text data may include the item's model number, years of use, and the location and degree of scratches or stains.

[0036] When a user who is a potential purchaser inputs information on a desired item from the smart device 14, the specific processing unit 290 of the product providing device 12 accepts the user input, acquires multiple conditions related to the user's desired item through dialogue using a data generation model such as ChatGPT, and searches for and extracts candidate items. In addition, the product providing device 12 generates a three-dimensional image (hereinafter, 3D image) of the candidate item based on images of the candidate item from multiple viewpoints, and displays the 3D image of the candidate item on the display 40A, which is an image display area of ​​the smart device 14.

[0037] The specific process may further include a process of calling the seller of the candidate item when a message about the candidate item is received from the user, and enabling the user and the seller to talk to each other in the virtual store. For example, as shown in FIG. 3B, an avatar representing the user and an avatar representing the seller may be able to talk (negotiate) with each other in the virtual store.

[0038] 4, the specific processing unit 290 includes an input unit 291, a search and extraction unit 292, a three-dimensional image generating unit (hereinafter referred to as a 3D image generating unit) 294, an output unit 296, a call processing unit 297, and a dialogue processing unit 298. Note that the call processing unit 297 and the dialogue processing unit 298 are not essential components.

[0039] The input unit 291 accepts a user input input by a user to the smart device 14. Specifically, the input is acquired from the user input accepted by the smart device 14, such as "I want shoes for my child." The user input may be a text input or a voice input.

[0040] Specifically, when the control unit 46A of the smart device 14 receives a text input or a voice input related to information on a desired item as a user input, the received text or voice is transmitted to the product provision device 12, and the search and extraction unit 292 receives the voice or text representing a question. The microphone 38B of the smart device 14 acquires a voice indicating the user input related to the information on the desired item. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the product provision device 12. In the product provision device 12, the input unit 291 of the specific processing unit 290 acquires the voice data indicating the user input. Alternatively, the touch panel 38A of the smart device 14 acquires a text indicating the user input related to information on the desired item. The control unit 46A transmits the text data indicating the user input acquired by the touch panel 38A to the product provision device 12. In the product provision device 12, the input unit 291 of the specific processing unit 290 acquires the text data indicating the user input.

[0041] The search and extraction unit 292 creates a search query based on the user input, and searches for and extracts candidate items of the desired item that is the item desired by the user from the items exhibited in the virtual store 200. Specifically, the search and extraction unit 292 creates a search query from the user input using a data generation model such as ChatGPT. The search and extraction unit 292 uses an API (Application Programming Interface) to access a database in which exhibited items are registered, and searches for and extracts candidate items based on the search query.

[0042] The 3D image generating unit 294 generates a 3D image based on multiple viewpoint images, which are multiple two-dimensional images (hereinafter referred to as 2D images) of a candidate item taken from different directions. For example, the 3D image is generated based on a front image, a back image, a left side image, a right side image, a plane image, and a bottom image of an item registered by a seller. The 3D image generating unit 294 generates a 3D image, for example, using a 3D image generation model. The 3D image generation model is a so-called 3D model generation AI (Artificial Intelligence), and for example, a rendering model that generates a 3D image with a movable viewpoint when multiple 2D images (multiple viewpoint images) are input is known. According to the rendering model, a new image and information on the shooting can be inferred from a dataset of shooting information such as the position of the camera that captured the images, and a 3D image with a movable viewpoint can be generated based on the dataset and the generated image information. Also, a deep neural network that represents the density of an object at each of three-dimensional coordinates may be trained based on images from multiple viewpoints, and a 3D image generation model may be generated based on the deep neural network. As an example, multiple viewpoint images and line-of-sight information (viewpoint position, view point direction) of each viewpoint image are acquired as teacher data, and the deep neural network is trained to optimize a loss function including the difference between an image output by the deep neural network and a training image of the teacher data. Note that a method for generating this 3D image generation model may be, for example, a method described in Non-Patent Document 1, and therefore a detailed description thereof will be omitted.

[0043] [Non-patent document 1]: Mildenhall, B., Srinivasan, PP, Tancik, M., Barron, JT, Ramamoorthi, R. and Ng, R.: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Vol. 65, No. 1, New York, NY, USA, Association for Computing Machinery (2021).

[0044] The output unit 296 transmits the 3D image of the candidate item displayed in the virtual store to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the 3D image of the candidate item displayed in the virtual store. More specifically, the control unit 46A causes the display 40A of the output device 40 to display the 3D image of the candidate item in the virtual store.

[0045] The 3D image generating unit 294 may be configured to generate a 3D image of a candidate item when the user selects one of the candidate items extracted by the search and extraction unit 292 on the smart device 14. Specifically, when multiple candidate items are extracted by the search and extraction unit 292, a list of multiple candidate items is presented on the smart device 14, and the user selects one of the candidate items. Each time a candidate item is selected by the user, the 3D image generating unit 294 generates a 3D image of the selected candidate item from 2D images of multiple viewpoints.

[0046] The 3D image generating unit 294 may generate a 3D image based on text provided together with the candidate item in addition to the images from multiple viewpoints. As described above, the text provided together with the candidate item includes the item's model number, years of use, and the location and extent of scratches or stains. For example, if the candidate item is a "shoe" and the text "There is a scratch about 2 cm long on the left side" is attached, but the scratch is not clearly visible in the images from multiple viewpoints, the 3D image generating unit 294 adds a scratch about 2 cm long to the left side of the shoe based on the images from multiple viewpoints.

[0047] The 3D image generation unit 294 may also be configured to search for images of the candidate item from a website on the Internet based on the model number of the candidate item, and use the searched image as one of the images from multiple viewpoints to generate a 3D image.

[0048] The search extraction unit 292 is preferably configured to generate a question corresponding to the user input using the data generation model 58 that generates a sentence according to the user input, and to display the question corresponding to the user input on the user terminal. Specifically, the search extraction unit 292 may acquire a question inquiring about each of the items necessary for creating a search query using the data generation model 58, and output the question on the smart device 14, thereby acquiring a user input for each of the items necessary for creating a search query. For example, the search extraction unit 292 acquires questions such as "What color would you like?", "Are they for sports?", and "What size?" in response to the vague user input "I want shoes for my child" input by the user to the smart device 14 using the data generation model 58, and displays the question corresponding to the user input on the smart device 14.

[0049] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0050] The call processing unit 297 calls the seller of the candidate item when the input unit 291 accepts a message regarding a candidate item from a user.

[0051] The dialogue processing unit 298 enables a dialogue between the user and the seller in the virtual store 200. Specifically, the dialogue between an avatar representing the user and an avatar representing the seller in the virtual store 200 is enabled.

[0052] The call processing unit 297 of the specific processing unit 290 transmits a message to the seller's smart device indicating that there is a dialogue request from the potential buyer. For example, it transmits a message such as "A potential buyer wishes to dialogue about the 'shoes' you have listed. Would you like to start a dialogue?". When the specific processing unit 290 receives a response from the seller indicating that the start of the dialogue is acceptable, it enables a dialogue between the user and the seller in the virtual store 200.

[0053] The dialogue processing unit 298 is, for example, configured by a chat system, and enables the seller and the user to send messages to each other in real time. The dialogue processing unit 298 may also bring the user's avatar and the seller's avatar together in the virtual store 200, enabling them to dialogue with each other.

[0054] When the specific processing unit 290 receives a response from the seller that the seller cannot respond immediately, the specific processing unit 290 notifies the user of that effect. In this case, the specific processing unit 290 may be configured to set a reservation for the seller and the user to be able to talk to each other at a later date.

[0055] Next, the operation of the product provision system 10 will be described.

[0056] First, an example of the flow of the identification process will be described with reference to Fig. 5. Note that the flow of the identification process shown in Fig. 5 is an example of a "product provision method" according to the technology of the present disclosure.

[0057] In the identification process shown in FIG. 5, first, in step S100, the input unit 291 accepts a user input regarding information of a desired item inputted by the user to the smart device 14.

[0058] For example, when a user inputs the text "I want children's shoes" into the smart device 14 using the touch panel 28A, the control unit 46A of the smart device 14 transmits the text "I want children's shoes" to the product providing device 12 as a user input. The input unit 291 accepts this user input. The search extraction unit 292 generates a prompt such as "The user has said, 'I want children's shoes.' What question should I ask to create a search query from the database?" and inputs this to the data generation model 58, and obtains a question for the user input using the output of the data generation model 58. Here, a question for eliciting conditions for creating a search query from the user is output.

[0059] In step S102, the output unit 296 transmits a question in response to the user input to the smart device 14. At this time, in the smart device 14, the control unit 46A causes the output device 40 to output the question in response to the user input. For example, questions such as "What color would you like?", "What is the purpose?", or "What is the size?" are output, and the search and extraction unit 292 receives user input in response to the questions. The search and extraction unit 292 exchanges information about the desired item with the user to obtain multiple conditions for the item desired by the user.

[0060] In step S104, the search and extraction unit 292 creates a search query from the user input acquired in steps S100 and S102 using the output of the data generation model 58, and searches and extracts candidate items for the desired item from the database of the commodity listings. The search query incorporates conditions such as, for example, children's shoes, blue color, for outdoor play, size 15 cm, etc.

[0061] In step S106, the output unit 296 transmits the list of candidate articles searched and extracted by the search and extraction unit 292 to the smart device 14. In the smart device 14, the control unit 46A causes the display 40A of the output device 40 to display the list of candidate articles. At this time, each candidate article displayed on the display 40A is shown as a 2D image.

[0062] In step S108, when the user selects one of the multiple candidate items displayed on the smart device 14, the identification processing unit 290 accepts the selection of the candidate item. Specifically, the user selects one of the multiple candidate items displayed on the smart device 14. This selection on the smart device 14 is input, for example, via the touch panel 38A. In the smart device 14, the reception device 38 accepts the selection of the candidate item via the touch panel 38A, and transmits to the product provision device 12 which candidate item was selected by the control unit 46A. The identification processing unit 290 of the product provision device 12 accepts the selection of the candidate item from the smart device 14.

[0063] In step S110, the 3D image generator 294 generates a 3D image based on images of the candidate article from multiple viewpoints.

[0064] In step S112, the output unit 296 displays the 3D image of the candidate item in the virtual store in the image display area of ​​the smart device 14. Specifically, the output unit 296 transmits the 3D image displayed in the virtual store to the smart device 14, and the control unit 46A of the smart device 14 receives the 3D image displayed in the virtual store and displays the 3D image displayed in the virtual store on the display 40A.

[0065] The basic steps of the identification process are as described above.

[0066] In addition, the identification process may further include a step of calling the seller, and a step of the user and the seller, specifically, an avatar representing the user and an avatar representing the seller, interacting in the virtual store 200.

[0067] As described above, the product providing device 12 includes the 3D image generating unit 294, and converts candidate products into 3D images and presents them to the user, so that the user can check the candidate products with a feeling of seeing the real thing, as compared to when the candidate products are viewed as 2D images. It is sufficient to store the 2D images in the storage, and compared to when 3D images are stored in advance for each product, the capacity required for storage can be reduced, storage is not strained, and slowdowns in display operations, etc. can be suppressed.

[0068] In the above description, the candidate items are displayed in a list, and when the user selects one of the candidate items, the candidate item is displayed in a three-dimensional image, but the search and extraction unit 292 may narrow down the candidate items to one, and generate and output a 3D image of the candidate item. Since the product provision device 12 generates a 3D image of a candidate item designated by the user or extracted by the specific processing unit 290 each time, there is no need to save the 3D image as described above.

[0069] Furthermore, when the 3D image generating unit 294 generates a 3D image based on text information in addition to images from multiple viewpoints, a 3D image closer to the real thing can be generated compared to when the text information is not used.

[0070] Furthermore, when the 3D image generation unit 294 uses an image searched for from the item's model number as one of multiple viewpoint images to obtain a 3D image, the number of viewpoints can be increased beyond the number of images provided by the seller, thereby enabling the generation of a 3D image that is closer to the actual product.

[0071] Furthermore, if the device is equipped with a call processing unit 297 and a dialogue processing unit 298 and is configured to enable dialogue with the seller based on the user's request, the user can directly inquire about candidate items with the seller and negotiate prices, etc., thereby improving user convenience.

[0072] Although the smart device 14 is a smartphone, the present invention is not limited to this example. The smart device 14 may be a smart eyeglass, a tablet terminal, or a personal computer.

[0073] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0074] In the above embodiment, an example has been described in which the specific processing program 56 is stored in the storage 32, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, non-transient storage medium that is readable by a computer, such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transient storage medium is installed in the computer 22 of the product provision device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0075] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the product provision device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the product provision device 12.

[0076] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the product provision device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0077] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0078] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0079] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0080] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0081] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[0082] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0083] 10 Product provision system 12 Product provision equipment 14 Smart Devices 56 Specific Processing Program 58 Data Generation Model 290 Specific Processing Department 291 Input section 292 Search and Extraction Unit 294 3D Image Generation Unit 296 Output section 297 Call Processing Unit 298 Dialogue Processing Unit

Claims

1. A product providing device that presents products to a user terminal via the Internet, an input unit that accepts user input regarding information of a desired item desired by a user via the user terminal; a search and extraction unit that searches for and extracts candidate items for the desired item from among items exhibited in the virtual store based on the user input; a three-dimensional image generator that generates a three-dimensional image of the candidate item based on images of the candidate item from multiple viewpoints; an output unit that displays the three-dimensional image of the candidate item in an image display area of ​​the user terminal; A product provision device comprising:

2. The product provision device according to claim 1, wherein the three-dimensional image generation unit generates the three-dimensional image of the selected candidate item when any one of the candidate items extracted by the search and extraction unit is selected on the user terminal.

3. The product provision device according to claim 1 , wherein the three-dimensional image generation unit generates the three-dimensional image based on text provided together with the candidate product in addition to the images from the multiple viewpoints.

4. The three-dimensional image generating unit searches for an image of the candidate item from a website on the Internet based on a model number of the candidate item, The product provision device according to claim 1 , wherein the retrieved image is used as one of the images from multiple viewpoints to generate the three-dimensional image.

5. The product providing device according to claim 1 , wherein the search and extraction unit generates a response corresponding to the user input using a data generation model that generates sentences in response to the user input, and displays the response corresponding to the user input on the user terminal.

6. a call processing unit that calls a seller of the candidate item when the input unit receives a message regarding the candidate item from the user; A dialogue processing unit that enables the user and the seller to dialogue in the virtual store, The product providing device according to claim 1 .

7. The product providing device according to claim 6 , wherein the dialogue processing unit enables an avatar representing the user and an avatar representing the seller to dialogue with each other in the virtual store.

8. receiving a user input relating to information of a desired item desired by the user via a user terminal; A step of searching for and extracting candidate items for the desired item from among items exhibited in a virtual store based on the user input; generating a three-dimensional image of the candidate article based on multiple perspective images of the candidate article; displaying the three-dimensional image of the candidate item in an image display area of ​​the user terminal; The method of providing the product, including

Images