Method for providing shopping information by individual product and electronic device for executing the method

Abstract

The present invention relates to a method for providing shopping information per product and an electronic device for executing the method, and more specifically, to a method for providing shopping information per product using an AI recognition model obtained through machine learning of an artificial neural network, and an electronic device for executing the method. A method for providing shopping information per product according to one embodiment of the present invention comprises: an image acquisition step, in which an application linked to a camera operating in association with a camera module acquires a product image through the camera module; an identification step, in which the AI ​​recognition model receives the acquired product image and identifies product information; a transmission step, in which a communication module transmits the product information to a server; a reception step, in which the communication module receives shopping information corresponding to the product information from the server; and a display step, in which a display module displays the shopping information on a screen.

Description

Technical Field

[0001] The present disclosure relates to a method for providing shopping information by product and an electronic device for executing the method, and more specifically, to a method for providing shopping information by product using an AI recognition model obtained through machine learning of an artificial neural network, and an electronic device for executing the method. Background Art

[0002] In the operation of the conventional online product purchase system, first, in order to purchase a product, the consumer accesses an online shopping mall server known to the consumer through the Internet installed in the terminal. Then, the shopping mall server transmits the homepage information containing various product information to the corresponding terminal through the Internet and displays it on the screen of the terminal. At this time, while browsing the homepage information of the shopping mall server displayed on the screen, the terminal user checks the various text information or image information about the product provided by the shopping mall server. If there is a product that the user needs, the user selects the product that the user needs, and then presses the purchase button. The shopping mall server receives the payment through the electronic payment scheme and sends the paid product offline.

[0003] However, in the above-mentioned traditional online product purchase system, it is very troublesome and inconvenient for consumers to find out information about the desired products one by one through product search after accessing the Internet each time in order to purchase the desired products. In offline stores, if there is a desired product, it is necessary to remember the name of the product and search for the product online, which makes it difficult to accurately search or purchase the product. In addition, there is also the problem that it is impossible to query product prices, query product information, and purchase products. Summary of the invention

[0004] Technical issues

[0005] Therefore, the present disclosure is proposed to solve the above-mentioned problems, and one aspect of the present disclosure provides a method for providing shopping information by product, which can capture a product that a user wants to buy with a camera to obtain product information of the product, and provide shopping information corresponding to the captured product information to the user in real time; and an electronic device that executes the method.

[0006] Solutions to the problem

[0007] According to an embodiment of the present disclosure, a method for providing shopping information by product includes: an image acquisition step, in which a camera-associated application linked to a camera module acquires a product image through the camera module; a recognition step, in which an AI recognition model obtained by machine learning of an artificial neural network receives the product image and recognizes the product information; a transmission step, in which a communication module transmits the product information to a server; a receiving step, in which the communication module receives shopping information corresponding to the product information from the server; and a display step, in which the display module displays the shopping information on a screen.

[0008] In the image acquisition step, after the camera working screen is displayed on the screen, the camera-associated application may acquire the product image in real time while the product is displayed on the camera working screen.

[0009] In the transmitting step, the identified product information is converted into a lookup table, and the communication module may transmit the product information converted into the lookup table to the server.

[0010] In the identifying step, a purchase input window for confirming with the user whether to purchase is displayed on the screen together with the identified product information, and when a user input is received through the purchase input window, the transmitting step may be performed.

[0011] In the recognition step, a shape image of the product corresponding to the product information may also be displayed on the screen.

[0012] In the recognition step, if the AI ​​recognition model does not recognize the product information, the user input pattern and recognition failure information are displayed on the screen, and the product information input through the user input pattern can be recognized as the product information.

[0013] In the recognition step, an error input window and the product information recognized by the AI ​​recognition model are displayed on the screen, and when the error input window is selected, a user input pattern is displayed on the screen and the product information input through the user input pattern can be recognized as the product information.

[0014] In the receiving step and the displaying step, the shopping information may include lowest price information.

[0015] According to another embodiment of the present disclosure, an electronic device for providing shopping information by product includes: a camera module for capturing product images; an AI recognition model, which is composed of an artificial neural network of machine learning and which receives the product image and outputs product information; a display module, which is used to display the product image captured by the camera module; a communication module, which is used to transmit the product information output from the AI ​​recognition model to a server; and a processor, wherein the processor performs control so as to provide the product image acquired through a camera-associated application linked to the camera module to the AI ​​recognition model, performs control so as to transmit the product information output from the AI ​​recognition model to the server by providing the product information to the communication module, and performs control so as to display shopping information corresponding to the product information received from the server through the communication module on a screen through the display module.

[0016] After the camera working screen is displayed on the screen, the product image acquired by the camera associated application can be acquired by the camera associated application in real time when the product is displayed on the camera working screen.

[0017] The AI ​​recognition model is obtained by performing machine learning of the artificial neural network using pre-prepared big data, the big data includes a training set, and the training set may include multiple product images and product information labels corresponding to each of the product images.

[0018] The AI ​​recognition model may be a chip that is physically configured separately from the processor.

[0019] The AI ​​recognition model can be embedded in the processor.

[0020] The processor may perform control so that the identified product information is converted into a lookup table, and the communication module transmits the product information converted into the lookup table to the server.

[0021] The processor displays a purchase input window on the screen for confirming with the user whether to purchase, as well as the identified product information, and when receiving user input through the purchase input window, the processor can execute control so that the identified product information is transmitted to the server through the communication module.

[0022] The processor may perform control so that a shape image of a product corresponding to the product information is further displayed on the screen through the display module.

[0023] If the AI ​​recognition model does not recognize the product information, the processor may perform control so that the user input pattern and recognition failure information are displayed together on the screen and the product information input through the user input pattern is recognized as the product information.

[0024] The processor performs control so that an error input window and the product information recognized by the AI ​​recognition model are displayed on the screen, and when the error input window is selected, the processor can perform control so that a user input pattern is displayed on the screen and the product information input through the user input pattern is recognized as the product information.

[0025] The shopping information may include lowest price information.

[0026] Effects of the present disclosure

[0027] When using the method for providing shopping information by product and the electronic device executing the method according to the embodiment of the present disclosure, there is an advantage of acquiring product information of the product by capturing the product that the user wants to buy with a camera and providing the user with shopping information corresponding to the captured product information in real time.

[0028] Furthermore, it is advantageous in maximizing the convenience of use for users because users can obtain shopping information by simply capturing products without having to access a specific mall through the Internet and inputting desired products through a keyboard or a virtual keyboard. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic diagram of a system for providing shopping information according to an embodiment of the present disclosure, wherein a method for providing shopping information by product is performed.

[0030] Figure 2 It is a schematic diagram for explaining the AI ​​recognition model 155.

[0031] Figure 3a to Figure 3b It is used to explain and obtain Figure 2 A diagram of several examples of machine learning methods for training model 15 is shown.

[0032] Figure 4 is a diagram showing an example of a training set.

[0033] Figure 5 is a diagram illustrating a method for providing shopping information by product according to an embodiment of the present disclosure.

[0034] Figure 6 yes Figure 5 A flowchart of a method for providing shopping information by product according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0035] In the following detailed description of the present disclosure, reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention can be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present disclosure are different from each other, but are not necessarily exclusive. For example, the specific shapes, structures and features described herein may be implemented as modifications from one embodiment to another without departing from the spirit and scope of the present invention. In addition, it should be understood that the position or arrangement of the various elements within each embodiment may also be modified without departing from the spirit and scope of the present invention. Therefore, the detailed description hereinafter is not intended to have a limiting meaning, and if properly described, the scope of the present disclosure is limited only by the attached claims and the entire scope of the things equivalent to the claims. In the accompanying drawings, similar reference numerals in several views refer to the same or similar elements.

[0036] Figure 1 is a schematic diagram of a system for providing shopping information according to an embodiment of the present disclosure, wherein a method for providing shopping information by product is performed.

[0037] Reference Figure 1 , a system for providing shopping information according to an embodiment of the present disclosure includes an electronic device 100 , a communication network 500 , and a server 900 .

[0038] The electronic device 100 according to this embodiment of the present disclosure may be as follows Figure 1 Examples of the electronic device 100 include a tablet PC, a personal PC, a laptop computer, a smart TV, etc., and the electronic device 100 may refer to various types of electronic devices that include a display module 120, a communication module 170, and a camera module 180 and transmit and receive data to and from a server 900 via a communication network 500.

[0039] The electronic device 100 includes a processor 150 that controls overall driving of the electronic device 100 .

[0040] Processor 150 may include Figure 2 The AI ​​recognition model (artificial intelligence recognition model) 155 shown. For example, the processor 150 may be any one of a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller unit (MCU), a digital signal processor (DSP), and a neural processing unit (NPU) having the AI ​​recognition model 155. In addition, the processor 150 may be a system on chip (SoC) including all of the AI ​​recognition model, CPU, GPU, MCU, DSP, and NPU.

[0041] at the same time, Figure 2 The AI ​​recognition model 155 shown is not included in Figure 1 The processor 150 is shown in the figure, but can be installed in the electronic device 100 as a separate chip. The AI ​​recognition model 155 configured by a separate dedicated chip can be driven and controlled by the processor 150.

[0042] The processor 150 may include an artificial neural network computing device. The artificial neural network computing device may perform the calculations required by the AI ​​recognition model 155. Here, the AI ​​recognition model 155 may be a “trained model” trained in a separate machine learning device and embedded in the artificial neural network computing device inside the processor 150.

[0043] Figure 2 is a schematic diagram for explaining the AI ​​recognition model 155 included in the electronic device 100.

[0044] Figure 2 The AI ​​recognition model 155 shown can be embedded in Figure 1 The processor 150 is shown, or may be configured as a chip physically separate from the processor 150.

[0045] like Figure 2 As shown, the training model 15 for machine learning using pre-prepared big data 300 can be installed in the electronic device 100 to become an AI recognition model 155.

[0046] The training model 15 may be generated in a separate machine learning device (not shown). In the machine learning device (not shown), the training model 15 may be obtained by allowing a pre-prepared artificial neural network to perform repeated machine learning with the big data 300. Figure 3a and Figure 3b Describe it in more detail.

[0047] Figure 3a to Figure 3b It is used to explain and obtain Figure 2 A diagram of several examples of machine learning methods for training model 15 is shown.

[0048] Reference Figure 3a , the big data 300 is repeatedly provided to the fully connected artificial neural network as shown on the right side of the figure, so that the artificial neural network can perform machine learning, thereby obtaining Figure 2 The training model 15 is shown.

[0049] As an example of an artificial neural network, the artificial neural network may include input nodes (x0, x1, …, xi, …, xf-1, xf) into which an image is input, output nodes (y0, y1, …, yi, …, ym-1, ym) that output product information of the input image, hidden nodes between the input nodes (x0, x1, …, xi, …, xf-1, xf) and the output nodes (y0, y1, …, yi, …, ym-1, ym), and multiple association parameters (weights) between the output nodes (y0, y1, …, yi, …, ym-1, ym) and the input nodes (x0, x1, …, xi, …, xf-1, xf).

[0050] The input node (x0, x1, ..., xi, ..., xf-1, xf) is a node that configures the input layer and receives an image from the outside, and the output node (y0, y1, ..., yi, ..., ym-1, ym) is a node that configures the output layer and outputs predetermined output data to the outside. The hidden node set between the input node (x0, x1, ..., xi, ..., xf-1, xf) and the output node (y0, y1, ..., yi, ..., ym-1, ym) is a node that configures the hidden layer and connects the output data of the input node (x0, x1, ..., xi, ..., xf-1, xf) to the output node (y0, y1, ..., yi, ..., ym-1, ym). Three hidden layers are Figure 3a Although not shown in FIG. 1 , according to one embodiment, the neural network circuit can be implemented by providing a plurality of hidden layers (e.g., two or four or more hidden layers) between the input layer and the output layer.

[0051] Each input node (x0,x1,…,xi,…,xf-1,xf) of the input layer can be fully connected or incompletely connected to each output node (y0,y1,…,yi,…,ym) of the output layer, such as Figure 3a shown.

[0052] The input nodes (x0, x1, …, xi, …, xf-1, xf) are used to receive input data from the outside and transmit it to the hidden nodes. Then, the actual calculation is performed in the hidden nodes. After the output data is output from the hidden nodes, the output nodes (y0, y1, …, yi, …, ym-1, ym) receive the output data and perform calculations again. When calculations are performed in the hidden nodes and output nodes (y0, y1, …, yi, …, ym-1, ym), the calculations are performed by multiplying the input data input to their own nodes by a predetermined associated parameter (or weight, w). After the resulting calculation values ​​performed in each node are summed (weighted sum), the predetermined output data is output by passing the sum through a preset activation function.

[0053] Hidden nodes and output nodes (y0, y1, ..., yi, ..., ym-1, ym) have activation functions. The activation function can be one of a step function, a sign function, a linear function, a logistic sigmoid function, a hypertangent function, a ReLU function, and a softmax function. The activation function can be appropriately determined by a person skilled in the art according to a learning method of an artificial neural network.

[0054] Artificial neural networks perform machine learning by repeatedly updating or modifying the associated parameters (w) to appropriate values. Representative methods of machine learning using artificial neural networks include supervised learning and unsupervised learning.

[0055] Supervised learning is a learning method in which the associated parameters (w) are updated so that when there is a well-defined target output data that is expected to be calculated by any neural network based on the input data, the output data obtained by putting the input data into the neural network becomes close to the target data. Figure 3a Multi-layer structure.

[0056] Reference Figure 3b As another example of an artificial neural network, there is a convolutional neural network (CNN), which is a deep neural network (DNN). A convolutional neural network (CNN) is a neural network with one or more convolutional layers, a pooling layer, and a fully connected layer. A convolutional neural network (CNN) has a structure suitable for training two-dimensional data and can be trained by a back-propagation algorithm. It is one of the representative models of DNN and is widely used in various application fields such as object classification and object detection in images.

[0057] Here, it should be noted that the artificial neural network disclosed in the present invention is not limited to Figure 3a and 3b The artificial neural network shown in , and the training model 15 can be obtained by machine learning big data from various other artificial neural networks.

[0058] Refer again Figure 2 The pre-prepared big data 300 includes the training set for machine learning of the artificial neural network. Figure 4 As shown, the training set includes multiple product images and product information labels corresponding to the product images. Product information labels (label 1, ..., label 10, ..., label 100, ..., label 1000) corresponding to each of the multiple product images (image 1, ..., image 10, ..., image 1000) are prepared in advance. The prepared training set can be provided to Figure 3a Or the artificial neural network shown in 3b to obtain Figure 2 The training model shown is 15. Figure 2As shown, the acquired training model 15 is installed in the electronic device 100 to become the AI ​​recognition model 155.

[0059] When an image obtained by capturing a specific product is input to the AI ​​recognition model 155 installed in the electronic device 100, the AI ​​recognition model 155 outputs product information corresponding to the input image. Here, the product information may include the trademark (brand) of the corresponding product and / or the source of the product. Specifically, when the image is input to the AI ​​recognition model 155, the AI ​​recognition model 155 may output a plurality of pre-classified probability values ​​according to the product information, determine the product information having the maximum probability value among the probability values ​​output by the product as the product information corresponding to the input image, and output the determined product information.

[0060] Refer again Figure 1 , the electronic device 100 will Figure 2 The product information output by the AI ​​recognition model 155 shown in FIG. 1 is transmitted to the server 900. More specifically, the electronic device 100 may Figure 2 The product information output by the AI ​​recognition model 155 is converted into a lookup table and transmitted to the server 900. That is, the electronic device 100 does not transmit the captured image to the server 900, but only transmits the product information output from the AI ​​recognition model 155 to the server 900. To this end, the electronic device 100 includes a communication module 170 for transmitting the output product information to the server 900 via the communication network 500.

[0061] The processor 150 receives the product information output from the AI ​​recognition model 155 and provides it to the communication module 170 , and the communication module 170 may transmit the provided product information to the server 900 via the communication network 500 .

[0062] The electronic device 100 may receive shopping information including the lowest price information from the server 900 via the communication network 500 and display the received shopping information on the screen of the electronic device 100. Specifically, when the shopping information is received through the communication module 170, the processor 150 provides the received shopping information to the display module 120 of the electronic device 100, and the display module 120 may display the provided shopping information on the screen of the electronic device 100.

[0063] The electronic device 100 includes a camera module 180. The electronic device 100 can obtain a predetermined image through the camera module 180. The obtained image can be input to the AI ​​recognition model 155 through the processor 150. Here, the obtained image can be two types of product images. One type of product image is an image (or photographic image) obtained by the user moving the electronic device 100 to display a specific product (hand cream) on the camera working screen and then pressing the camera button, and the other type of product image is an image (or real-time image) obtained in real time when the user moves the electronic device 100 to display a specific product (hand cream) on the camera working screen. The latter image is different from the former image and is not stored in the photo library, so it has the advantage that the user does not have to open the photo library and delete it later in use. In addition, since the AI ​​recognition model 155 can recognize several to dozens of images per second, the advantage is that even with the latter image, product information can be recognized in a short time.

[0064] The electronic device 100 is installed with a camera-associated application that can drive and control the camera module 180. Here, the camera-associated application may be a camera application installed by default in the electronic device 100 or a shopping application downloaded and installed in the electronic device 100 by a user. The shopping application may drive and control the camera module 180 of the electronic device 100. Here, the camera-associated application is not limited to acquiring product images only through the camera module 180. Specifically, the camera-associated application may acquire product information through a user input mode (virtual keyboard or voice input) instead of the camera module 180 according to a user's selection.

[0065] The communication network 500 may provide the server 900 with the product information received from the electronic device 100 , and may provide the electronic device 100 with the shopping information including the lowest price information received from the server 900 .

[0066] The server 900 may receive product information provided from the electronic device 100 via the communication network 500 and may output shopping information including the lowest price information corresponding to the received product information in real time. Then, the output shopping information is transmitted to the corresponding electronic device 100 via the communication network 500.

[0067] The server 900 may pre-store shopping information of each of a plurality of products, and output the shopping information of the corresponding product in real time in response to a request for the shopping information of the corresponding product from the electronic device 100. Here, the shopping information by product may be updated in real time or periodically, and the updated shopping information by product may be stored in the server 900.

[0068] The server 900 may update the AI ​​recognition model 155 installed in the electronic device 100. Specifically, the server 900 may change the parameters (weight w) and / or bias (b) of the artificial neural network of the AI ​​recognition model 155. With the update of the AI ​​recognition model 155, the recognition rate of the product information may be improved. The processor 150 of the electronic device 100 may receive update information for updating the AI ​​recognition model 155 from the server 900 and may update the AI ​​recognition model 155 based on the received update information.

[0069] Figure 5 is a diagram illustrating a method for providing shopping information by product according to an embodiment of the present disclosure. Figure 6 yes Figure 5 A flow chart of a method for providing shopping information by product according to an embodiment of the present invention is shown.

[0070] Reference Figures 5 to 6 , a camera-associated application installed by a user in the electronic device 100 is executed in step 601. Here, the camera-associated application may be a camera application installed by default in the electronic device 100 or a shopping application downloaded and installed by a user and which can drive and control the camera module 180 of the electronic device 100.

[0071] When the camera-associated application is executed in the electronic device 100, in step 601, a camera operation screen is displayed on the screen 130 of the electronic device 100, such as Figure 5 As shown. Here, the product image can be obtained by two methods. One method is a method in which the user moves the electronic device 100 to display a specific product (hand cream) on the camera working screen, and then presses the photo button so that the camera-associated application acquires an image (or photographic image). Another method is a method in which the camera-associated application acquires an image (or real-time image) in real time while the user moves the electronic device 100 and the specific product (hand cream) is displayed on the camera working screen. The latter method is different from the former method, and the advantage in use is that the user does not have to delete the photo image stored in the photo library later because the photo image is not stored in the photo library. In addition, since the AI ​​recognition model 155 can recognize several to dozens of images per second, the advantage is that product information can be recognized in a short time even with the latter method.

[0072] Meanwhile, the camera-related application described in step 601 is not limited to acquiring product images only through the camera module. Specifically, the camera-related application can acquire product information through a user input mode (virtual keyboard or voice input) instead of a camera module according to a user's selection.

[0073] The processor 150 of the electronic device 100 provides the obtained image to the AI ​​recognition model 155, and the AI ​​recognition model 155 recognizes the product information 160 of the input image in step 602. The recognized product information 160 may include a trademark (brand) of a product present in the input image and a source of the product.

[0074] Here, the processor 150 displays the product information 160 recognized by the AI ​​recognition model 155 on the screen 130, and can display the product information 160 recognized by the AI ​​recognition model 155 to the user using the electronic device 100. In this case, the processor 150 can display the shape image of the corresponding product and the product information 160 output by the AI ​​recognition model 155 on the screen 130 together.

[0075] In addition, the processor 150 may display a predetermined purchase input window 190 asking the user whether to purchase the corresponding product on the screen 130. Here, when the user touches the purchase input window 190, that is, when the user input is received through the purchase input window 190, the processor 150 may transmit the identified product information to the server 900. Meanwhile, if the user does not touch the purchase input window 190 within a predetermined time or if the user moves the electronic device 100 and turns to another screen, the identified product information may not be transmitted to the server 900.

[0076] Meanwhile, in step 602, if the AI ​​recognition model 155 does not recognize the product information from the input product image, the AI ​​recognition model 155 notifies the processor 150 of the recognition failure, and the processor 150 may output the recognition failure information on the screen 130. Here, the processor 150 may output a user input window (not shown) on the screen 130, through which the product information and the recognition failure information may be directly obtained from the user. When the user touches the user input window (not shown), a virtual keyboard may be executed on the screen 130 or a user input mode enabling voice input may be provided.

[0077] Alternatively, in step 602, when the AI ​​recognition model 155 incorrectly recognizes product information from the input product image, the user may select an error input window (not shown) on the screen 130. When the error input window (not shown) is selected, the processor 150 may provide the above-mentioned user input mode.

[0078] The processor 150 of the electronic device 100 may perform control so as to transmit the product information identified by the AI ​​recognition model 155 to the server 900 through the communication module 170 in step 603. Here, the processor 150 may process the product information identified by the AI ​​recognition model 155 into query table information and transmit it to the server 900.

[0079] The server 900 having received the product information outputs shopping information corresponding to the received product information in step 604. Here, the shopping information includes the lowest price information corresponding to the product information.

[0080] In step 605, the server 900 transmits the shopping information including the lowest price information to the electronic device 100 via the communication network 500. Here, the server 900 may process the shopping information into information in a query table format and transmit it to the electronic device 100.

[0081] The electronic device 100 receives shopping information including the lowest price information from the server 900 through the communication module 170. In step 607, the processor 150 of the electronic device 100 outputs the received shopping information on the screen 130 of the electronic device 100. Here, the processor 150 may display the shopping information including the received lowest price information on the screen 130 in a preset manner, such as Figure 6 shown.

[0082] When the user selects a desired mall from the lowest price information displayed on the screen 130 of the electronic device 100 , the processor 150 may display a purchase page of a corresponding product of the selected mall on the screen 130 .

[0083] Meanwhile, the server 900 pre-stores shopping information including the lowest price information by product in step 650. In addition, the server 900 may update (in step 630) and store shopping information including the lowest price information by product in real time or periodically.

[0084] In addition, the server 900 may also transmit shopping information corresponding to product information provided from other electronic devices 100 ′ and 100 ″ other than the electronic device 100 to the other electronic devices 100 ′ and 100 ″.

[0085] As described above, in a method for providing shopping information by product according to an embodiment of the present disclosure, since an image containing a product is obtained through the camera module 180 by executing a camera-associated application installed in the electronic device 100, and product information of the product existing in the obtained image is obtained using the AI ​​recognition model 155, a user can obtain the trademark (brand) and source of the product he needs in a short time and in near real time through the AI ​​recognition model 155 based on an artificial neural network without searching through a virtual keyboard window.

[0086] In addition, in a method for providing shopping information by product using an artificial neural network according to an embodiment of the present disclosure, since the product information (e.g., product information in a query table format) obtained by the AI ​​recognition model 155 is transmitted to the server 900 via the communication network 500, and the server 900 searches for shopping information including the lowest price information corresponding to the transmitted product information and provides it to the electronic device 100 via the communication network 500, there is no need to transmit the captured product image to the server 900 and analyze the product image captured by the server 900, thereby having the advantage of providing the user with shopping information including the lowest price information in real time.

[0087] The features, structures, effects, etc. described in the embodiments are included in the embodiments of the present disclosure and are not necessarily limited to one embodiment. In addition, the features, structures, effects, etc. provided in each embodiment can be combined or modified in other embodiments for those skilled in the art to which the embodiments belong. Therefore, the contents related to the combination and modification should be understood to be included in the scope of the present disclosure.

[0088] Although the embodiments of the present disclosure are described above, these are merely examples and do not limit the present disclosure. In addition, those skilled in the art may change and modify the present disclosure in various ways without departing from the essential features of the present disclosure. For example, the components described in detail in the embodiments of the present disclosure may be modified. In addition, the differences caused by modification and application should be interpreted as being included in the scope and spirit of the present disclosure described in the appended claims.

[0089] [reference numerals]

[0090] 100: Electronic devices

[0091] 500: Communication Network

[0092] 900: Server

Claims

1. A method for providing shopping information for each product by a processor of an electronic device, the method comprising: an image acquisition step, wherein a camera-associated application linked to the camera module acquires an image of the product through the camera module; an identification step, wherein an AI identification model obtained by machine learning of an artificial neural network and included in the electronic device receives the product image and identifies product information corresponding to the product image; a display step, wherein a display module displays the product information identified by the AI ​​recognition model on a screen of the electronic device to display the product information to a user; a transmitting step, wherein the communication module of the electronic device transmits the product information to a server, wherein the product image is not transmitted to the server; a receiving step, wherein the communication module receives shopping information corresponding to the product information from the server; as well as A display step, wherein the display module displays the shopping information on the screen, The shopping information is output in the server based on the product information transmitted from the electronic device to the server.

2. The method of claim 1, wherein in the image acquisition step, after a camera working screen is displayed on the screen, the camera-associated application acquires the product image in real time when the product is displayed on the camera working screen.

3. The method of claim 1, wherein in the transmitting step, the identified product information is converted into a lookup table, and the communication module transmits the product information converted into the lookup table to the server.

4. The method according to claim 1, wherein in the identification step, a purchase input window for confirming with the user whether to purchase is displayed on the screen together with the identified product information, The transmitting step is performed when user input is received through the purchase input window.

5. The method of claim 4, wherein in the recognition step, a shape image of the product corresponding to the product information is further displayed on the screen.

6. The method of claim 1, wherein in the recognition step, if the AI ​​recognition model does not recognize the product information, the user input pattern and the recognition failure information are displayed together on the screen, and the product information input through the user input pattern is recognized as the product information.

7. The method of claim 1, wherein in the recognition step, an error input window and the product information recognized by the AI ​​recognition model are displayed on the screen together, and when the error input window is selected, a user input pattern is displayed on the screen, and the product information input through the user input pattern is recognized as the product information.

8. The method of claim 1, wherein in the receiving step and the displaying step, the shopping information includes lowest price information.

9. An electronic device for providing shopping information by product, the electronic device comprising: A camera module for capturing images of the product; An AI recognition model, which is composed of a machine-learned artificial neural network and which receives the product image and outputs product information corresponding to the product image; A display module, which is used to display the product image captured by the camera module; a communication module for transmitting the product information output from the AI ​​recognition model to a server, wherein the product image is not transmitted to the server; and processor, wherein the processor performs control so as to provide the product image acquired through a camera-associated application linked to the camera module to the AI ​​recognition model, performing control so as to transmit the product information output from the AI ​​recognition model to the server by providing the product information to the communication module, performing control so that the product information recognized by the AI ​​recognition model is displayed on the screen of the electronic device through the display model to display the product information to the user, and performing control so that shopping information corresponding to the product information received from the server through the communication module is displayed on the screen through the display module, The shopping information is output in the server based on the product information transmitted from the electronic device to the server.

10. The electronic device as claimed in claim 9, wherein after the camera working screen is displayed on the screen, the product image acquired by the camera associated application is acquired in real time by the camera associated application when the product is displayed on the camera working screen.

11. The electronic device as claimed in claim 9, wherein the AI ​​recognition model is obtained by performing machine learning of the artificial neural network using pre-prepared big data, The big data includes training sets, The training set includes a plurality of product images and a product information label corresponding to each of the product images.

12. The electronic device as claimed in claim 9, wherein the AI ​​recognition model is a chip that is physically configured separately from the processor.

13. The electronic device as claimed in claim 9, wherein the AI ​​recognition model is embedded in the processor.

14. The electronic device of claim 9, wherein the processor performs control so that the recognized product information is converted into a lookup table, and the communication module transmits the product information converted into the lookup table to the server.

15. The electronic device according to claim 9, wherein the processor displays a purchase input window for confirming with the user whether to purchase and the identified product information on the screen, When receiving user input through the purchase input window, the processor performs control so that the identified product information is transmitted to the server through the communication module. 16 . The electronic device of claim 15 , wherein the processor performs control so as to further display a shape image of the product corresponding to the product information on the screen through the display module.

17. The electronic device of claim 9, wherein if the AI ​​recognition model does not recognize the product information, the processor performs control so that the user input pattern and the recognition failure information are displayed together on the screen, and the product information input through the user input pattern is recognized as the product information.

18. An electronic device as claimed in claim 9, wherein the processor performs control so that an error input window and the product information recognized by the AI ​​recognition model are displayed on the screen, and when the error input window is selected, the processor performs control so that a user input pattern is displayed on the screen and the product information input through the user input pattern is recognized as the product information.

19. The electronic device as claimed in claim 9, wherein the shopping information includes lowest price information.

Images