KR102510216B1 - Method and apparatus for longitudinal search of a specific section using multiple images of the same product in a video commerce system and producing a sales video with collected images - Google Patents

Abstract

The present specification provides a method for collecting and producing images related to a specific section of a video in a video commerce system. More specifically, the method performed by the video commerce platform receives a request for producing a video, provides a video production tool including a first user interface, and at least one video produced based on the video production tool. and provides a second user interface, provides a streaming file for the specific video when a specific video is selected, and provides detailed information on the specific product and a payment screen for purchase when a specific product is selected. providing, and when a specific scene or a product within the specific scene is selected from the specific video, providing at least one video related to the specific scene or a product within the specific scene.

Description

Longitudinal search of a specific section using multiple images of the same product in a video commerce system and a method and apparatus for producing a sales video with the collected images IN A VIDEO COMMERCE SYSTEM AND PRODUCING A SALES VIDEO WITH COLLECTED IMAGES}

The present specification relates to a video commerce system, and more specifically, to a longitudinal search of a specific section using a plurality of images of the same product in the video commerce system, and a method and apparatus for producing a sales video with the collected images.

Video Commerce

Video commerce is a compound word of 'video' and 'commerce', meaning a type of e-commerce that utilizes video content.

More specifically, video commerce is also called v-commerce, and uses video content to promote sales. With the generalization of smartphones, the number of consumers who watch mobile videos is gradually increasing, and for them, video commerce is being activated centering on fashion and beauty products.

The prior art of product recommendation using video commerce was a product video service in which a video of a product was filmed using a separate video equipment and then invested in time for a long period of time, such as through post-editing.

That is, all conventional broadcasting equipment technologies require a lot of time investment in post-editing in order to recommend a product to a consumer using a photographed image of the product. In particular, an expert is required to obtain a photographed image of a product, which incurs a high cost.

Therefore, the method proposed in this specification to solve the above problem aims to provide real-time product information, which is very important, by including it in a video image transmitted in real time.

That is, the method proposed in this specification further strengthens the technology of a separate broadcasting production unit, and broadcasts (or transmits or transmits) products in real time, records on a server, or transmits images taken in real time to a server. The purpose is to provide a method of linking real-time video images and product information at once by recognizing product images, such as importing from and editing directly or editing in real time while filming.

The purpose of this specification is to provide a video commerce platform so that anyone can easily create, share, and search for videos.

In addition, an object of the present specification is to provide a video traversal search method that collects and transmits a plurality of videos related to a specific scene of a video through a video commerce platform.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In the present specification, in a method for collecting and producing images related to a specific section of a video in a video commerce system, the method performed by the video commerce platform includes receiving a request for producing a video from a provider device; providing a video production tool including a first user interface for selecting a background picture for composing at least one scene, an object to appear, a special effect, and a product to the provider device according to the request; receiving at least one video produced based on the video production tool from the provider device; providing, to a user device, a second user interface including an area in which at least one video included in the video list can be searched and a product list area in which at least one product included in the video can be viewed; When a specific video is selected from the video list, providing a streaming file for the specific video to the user device; providing detailed information about the specific product and a payment screen for purchase to the user device when a specific product is selected from the product list; and providing at least one video related to the specific scene or a product within the specific scene to the user device when a specific scene or a product within the specific scene is selected from the specific video.

In addition, in the present specification, the at least one video is characterized in that it is a video of another user corresponding to a video remade with a length of a predetermined section including the specific scene or a product within the specific scene.

In addition, in the present specification, the at least one video is characterized in that the at least one video is played randomly or sequentially in consideration of the priority of the user's preference for the at least one video.

In addition, in the present specification, the priority of the user's preference for the at least one video is determined by the number of counts of emotion data generated based on the recognition of the user's facial expression captured by the camera while the video is played. Characterized in that do.

In addition, in the present specification, the video is characterized in that it is a short clip produced by briefly editing a specific part.

In addition, the method in the present specification includes the steps of registering the produced video through the purchase of broadcasting rights of the produced video and setting of at least one broadcasting condition; and setting interlocking conditions for simultaneously broadcasting the registered video through at least one social network service (SNS) application.

In addition, the present specification provides a video commerce platform for collecting and producing images related to a specific section of a video in a video commerce system, comprising: a wireless communication unit for transmitting and receiving wireless signals with the outside; a storage unit for storing video; And a control unit functionally connected to the wireless communication unit and the storage unit, wherein the control unit receives a request for video production from a provider device, and a picture serving as a background for configuring at least one scene according to the request , Providing a video production tool including a first user interface for selecting an object to appear, a special effect, and a product to the provider device, and receiving at least one video produced based on the video production tool from the provider device. and providing a user device with a second user interface including an area for viewing at least one video included in the video list and a product list area for searching for at least one product included in the video, to the user device; When a specific video is selected from the list, a streaming file for the specific video is provided to the user device, and when a specific product is selected from the product list, detailed information on the specific product and a payment screen for purchase are displayed to the user. Provided to the device, and when a specific scene or a product in the specific scene is selected from the specific video, at least one video related to the specific scene or the product in the specific scene is provided to the user device. .

In addition, in the present specification, the control unit registers the produced video through the purchase of broadcasting rights of the produced video and setting of at least one broadcasting condition, and the registered video through at least one Social Network Service (SNS) application. It is characterized by controlling to set interlocking conditions for simultaneous broadcasting.

In addition, the present specification provides a method for providing a plurality of short clip images related to a specific section of a short clip in a video commerce system, comprising: providing the short clip images to a user device in a real-time streaming method or a VOD method; When a selection input for a specific screen among the provided short clip images, a specific playback position of a progress bar, a specific object in the short clip image, or a search word in the search box is received, a plurality of short clips related to the selection input collecting images; listing all or part of the collected short clip images according to specific conditions; and providing the listed at least one short clip image to the user device.

The method proposed in this specification can easily produce or stream a video of a service (product or product) from the point of view of a seller or service provider, and has an effect of increasing the convenience of content production.

The present specification provides a video commerce platform capable of producing/editing and sharing videos, so that anyone can easily create/edit and share videos.

In addition, the present specification has an effect of increasing user convenience and a purchase conversion rate for product sales by collecting and transmitting a plurality of videos related to a specific scene of a video through a video commerce platform.

The effects of the present 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 below.

1 is a diagram showing an example of a perceptron structure to which the method proposed in this specification can be applied.
2 is a diagram showing an example of a multilayer perceptron structure to which the method proposed in this specification can be applied.
3 is a diagram showing an example of a deep neural network to which the method proposed in this specification can be applied.
4 is a diagram showing an example of a convolutional neural network to which the method proposed in this specification can be applied.
5 is a diagram illustrating an example of a filter operation in a convolutional neural network to which the method proposed in this specification can be applied.
6 is a diagram illustrating an example of a neural network structure in which a circular loop to which the method proposed in this specification can be applied exists.
7 is a diagram showing an example of an operating structure of a recurrent neural network to which the method proposed in this specification can be applied.
8 is an example of a DNN model to which the present invention can be applied.
9 is a block diagram of an AI device according to an embodiment of the present invention.
10 shows a schematic diagram of a video commerce system to which the method proposed in this specification can be applied.
11 to 13 are diagrams illustrating examples of broadcasting device UIs proposed in this specification.
14 to 20 are diagrams illustrating examples of viewer device UIs proposed in this specification.
21 to 25 are diagrams illustrating examples of manager device UIs proposed in the present specification.
26 is for an image recognition method using machine learning proposed in this specification.
It is a flowchart showing the operation method of the machine learning server.
27 is a diagram showing an example of a live image recognition method proposed in this specification.
28 shows an example of an operating method of a viewer device for a live broadcast image recognition method proposed in this specification.
29 is a diagram showing an example of a shortcut image recognition method proposed in this specification.
30 shows an example of a conceptual diagram of a video commerce system for producing and sharing short clips proposed in this specification.
31 is a flowchart illustrating an example of a method for capturing a short clip and providing a sharing service proposed in this specification.
32 and 33 are diagrams illustrating an example of traversal search of an image proposed in this specification.

It should be noted that technical terms used in this specification are only used to describe specific embodiments and are not intended to limit the spirit of the technology disclosed in this specification. In addition, technical terms used in this specification should be interpreted in terms commonly understood by those of ordinary skill in the field to which the technology disclosed in this specification belongs, unless specifically defined otherwise in this specification. It should not be interpreted in an overly comprehensive sense or in an excessively reduced sense. In addition, when the technical terms used in this specification are incorrect technical terms that do not accurately express the spirit of the technology disclosed in this specification, it is a technical term that can be correctly understood by those of ordinary skill in the field to which the technology disclosed in this specification belongs. should be replaced with In addition, general terms used in this specification should be interpreted as defined in advance or according to context, and should not be interpreted in an excessively reduced sense.

Terms including ordinal numbers such as first and second used herein may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the technology disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the technology disclosed in this specification, the detailed description will be omitted. In addition, it should be noted that the accompanying drawings are only intended to facilitate understanding of the spirit of the technology disclosed in this specification, and should not be construed as limiting the spirit of the technology by the accompanying drawings.

Artificial Intelligence (AI)

The most important and newly introduced technology for the 6G system is AI. AI was not involved in the 4G system. 5G systems will support partial or very limited AI. However, the 6G system will be AI-enabled for full automation. Advances in machine learning will create more intelligent networks for real-time communication in 6G. Introducing AI in communications can simplify and enhance real-time data transmission. AI can use a plethora of analytics to determine how complex target tasks are performed. In other words, AI can increase efficiency and reduce processing delays.

Time-consuming tasks such as handover, network selection, and resource scheduling can be performed instantly by using AI. AI can also play an important role in machine-to-machine, machine-to-human and human-to-machine communications. In addition, AI can be a rapid communication in BCI (Brain Computer Interface). AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.

Recently, there have been attempts to integrate AI with wireless communication systems, but these have been focused on the application layer and network layer, especially deep learning in the field of wireless resource management and allocation. However, these studies are gradually developing into the MAC layer and the physical layer, and in particular, attempts to combine deep learning with wireless transmission are appearing in the physical layer. AI-based physical layer transmission means applying a signal processing and communication mechanism based on an AI driver rather than a traditional communication framework in fundamental signal processing and communication mechanisms. For example, deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO mechanism, AI-based resource scheduling and may include allocations, etc.

Machine learning may be used for channel estimation and channel tracking, and may be used for power allocation, interference cancellation, and the like in a downlink (DL) physical layer. Machine learning can also be used for antenna selection, power control, symbol detection, and the like in a MIMO system.

However, the application of DNN for transmission in the physical layer may have the following problems.

AI algorithms based on deep learning require a lot of training data to optimize training parameters. However, due to limitations in acquiring data in a specific channel environment as training data, a lot of training data is used offline. This is because static training on training data in a specific channel environment may cause a contradiction between dynamic characteristics and diversity of a radio channel.

In addition, current deep learning mainly targets real signals. However, the signals of the physical layer of wireless communication are complex signals. In order to match the characteristics of wireless communication signals, further research on a neural network for detecting complex domain signals is needed.

machine learning

Hereinafter, machine learning will be described in more detail.

Machine learning refers to a set of actions that train a machine to create a machine that can do tasks that humans can or cannot do. Machine learning requires data and a running model. In machine learning, data learning methods can be largely classified into three types: supervised learning, unsupervised learning, and reinforcement learning.

Neural network training is aimed at minimizing errors in the output. Neural network learning repeatedly inputs training data to the neural network, calculates the output of the neural network for the training data and the error of the target, and backpropagates the error of the neural network from the output layer of the neural network to the input layer in a direction to reduce the error. ) to update the weight of each node in the neural network.

Supervised learning uses training data in which correct answers are labeled in the learning data, and unsupervised learning may not have correct answers labeled in the learning data. That is, for example, learning data in the case of supervised learning related to data classification may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and an error may be calculated by comparing the output (category) of the neural network and the label of the training data. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate is used in the early stages of neural network learning to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and a low learning rate can be used in the late stage to increase accuracy.

The learning method may vary depending on the characteristics of the data. For example, in a case where the purpose of the receiver is to accurately predict data transmitted by the transmitter in a communication system, it is preferable to perform learning using supervised learning rather than unsupervised learning or reinforcement learning.

The learning model corresponds to the human brain, and the most basic linear model can be considered. ) is called

The neural network cord used as a learning method is largely divided into deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent Boltzmann Machine (RNN). there is.

An artificial neural network is an example of connecting several perceptrons.

1 is a diagram showing an example of a perceptron structure to which the method proposed in this specification can be applied.

Referring to FIG. 1, when the input vector x=(x1,x2,...,xd) is input, each component is multiplied by a weight (W1,W2,...,Wd), and after summing the results, The entire process of applying the activation function σ() is called a perceptron. The huge artificial neural network structure may extend the simplified perceptron structure shown in FIG. 1 and apply input vectors to different multi-dimensional perceptrons. For convenience of description, an input value or an output value is referred to as a node.

Meanwhile, the perceptron structure shown in FIG. 1 can be described as being composed of a total of three layers based on input values and output values. An artificial neural network in which H number of (d + 1) dimensional perceptrons exist between the 1st layer and the 2nd layer and K number of (H + 1) dimensional perceptrons between the 2nd layer and the 3rd layer can be expressed as shown in FIG. 2 .

2 is a diagram showing an example of a multilayer perceptron structure to which the method proposed in this specification can be applied.

The layer where the input vector is located is called the input layer, the layer where the final output value is located is called the output layer, and all the layers located between the input layer and the output layer are called hidden layers. In the example of FIG. 2 , three layers are disclosed, but when counting the number of layers of an actual artificial neural network, since the count excludes the input layer, it can be regarded as a total of two layers. The artificial neural network is composed of two-dimensionally connected perceptrons of basic blocks.

The above-described input layer, hidden layer, and output layer can be jointly applied to various artificial neural network structures such as CNN and RNN, which will be described later, as well as multi-layer perceptrons. As the number of hidden layers increases, the artificial neural network becomes deeper, and a machine learning paradigm that uses a sufficiently deep artificial neural network as a learning model is called deep learning. In addition, the artificial neural network used for deep learning is called a deep neural network (DNN).

3 is a diagram showing an example of a deep neural network to which the method proposed in this specification can be applied.

The deep neural network shown in FIG. 3 is a multi-layer perceptron composed of 8 hidden layers + 8 output layers. The multilayer perceptron structure is expressed as a fully-connected neural network. In a fully-connected neural network, there is no connection relationship between nodes located on the same layer, and a connection relationship exists only between nodes located on adjacent layers. DNN has a fully-connected neural network structure and is composed of a combination of multiple hidden layers and activation functions, so it can be usefully applied to identify the correlation characteristics between inputs and outputs. Here, the correlation characteristic may mean a joint probability of input and output.

On the other hand, depending on how a plurality of perceptrons are connected to each other, various artificial neural network structures different from the aforementioned DNN can be formed.

4 is a diagram showing an example of a convolutional neural network to which the method proposed in this specification can be applied.

In DNN, nodes located inside one layer are arranged in a one-dimensional vertical direction. However, in FIG. 4, it can be assumed that the nodes are two-dimensionally arranged with w nodes horizontally and h nodes vertically (the structure of the convolutional neural network in FIG. 4). In this case, a weight is added for each connection in the connection process from one input node to the hidden layer, so a total of hХw weights must be considered. Since there are hХw nodes in the input layer, a total of h2w2 weights are required between two adjacent layers.

The convolutional neural network of FIG. 4 has a problem that the number of weights increases exponentially according to the number of connections, so instead of considering all mode connections between adjacent layers, it is assumed that there is a filter with a small size. As shown in , weighted sum and activation function calculations are performed for overlapping filters.

5 is a diagram illustrating an example of a filter operation in a convolutional neural network to which the method proposed in this specification can be applied.

One filter has weights corresponding to the number of filters, and learning of weights can be performed so that a specific feature on an image can be extracted as a factor and output. In FIG. 5, a filter having a size of 3Х3 is applied to the 3Х3 area at the top left of the input layer, and an output value obtained by performing a weighted sum and an activation function operation for a corresponding node is stored in z22.

While scanning the input layer, the filter moves by a certain distance horizontally and vertically, performs weighted sum and activation function calculations, and places the output value at the position of the current filter. This operation method is similar to the convolution operation for images in the field of computer vision, so the deep neural network of this structure is called a convolutional neural network (CNN), and the hidden layer generated as a result of the convolution operation is called a convolutional layer. Also, a neural network having a plurality of convolutional layers is referred to as a deep convolutional neural network (DCNN).

In the convolution layer, the number of weights can be reduced by calculating a weighted sum by including only nodes located in a region covered by the filter from the node where the current filter is located. This allows one filter to be used to focus on features for a local area. Accordingly, CNN can be effectively applied to image data processing in which a physical distance in a 2D area is an important criterion. Meanwhile, in the CNN, a plurality of filters may be applied immediately before the convolution layer, and a plurality of output results may be generated through a convolution operation of each filter.

Meanwhile, there may be data whose sequence characteristics are important according to data attributes. Considering the length variability and precedence relationship of these sequence data, input each element on the data sequence one by one at each time step, and input the output vector (hidden vector) of the hidden layer output at a specific time point together with the next element on the sequence A structure in which this method is applied to an artificial neural network is called a recurrent neural network structure.

6 is a diagram illustrating an example of a neural network structure in which a circular loop to which the method proposed in this specification can be applied exists.

Referring to FIG. 6, a recurrent neural network (RNN) assigns an element (x1(t), x2(t), ,..., xd(t)) of any line t on a data sequence to a fully connected neural network. During the input process, the immediately preceding time point t-1 is a structure in which a weighted sum and an activation function are applied by inputting the hidden vectors (z1(t1), z2(t1), ..., zH(t1)) together. The reason why the hidden vector is transmitted to the next time point in this way is that information in the input vector at previous time points is regarded as being accumulated in the hidden vector of the current time point.

7 is a diagram showing an example of an operating structure of a recurrent neural network to which the method proposed in this specification can be applied.

Referring to FIG. 7 , the recurrent neural network operates in a sequence of predetermined views with respect to an input data sequence.

When the input vector (x1(t), x2(t), ,..., xd(t)) at time 　1 is input to the recurrent neural network, the hidden vector 　(z1(1),z2(1),.. .,zH(1)) is input together with the input vector of time 　2 (x1(2),x2(2),...,xd(2)), and the vector of the hidden layer 　 (z1( 2),z2(2) ,...,zH(2)). This process is repeatedly performed until time point 2, point 3, ,,, point T.

Meanwhile, when a plurality of hidden layers are arranged in a recurrent neural network, it is referred to as a deep recurrent neural network (DRNN). Recurrent neural networks are designed to be usefully applied to sequence data (eg, natural language processing).

As a neural network core used as a learning method, in addition to DNN, CNN, and RNN, Restricted Boltzmann Machine (RBM), deep belief networks (DBN), and Deep Q-Network It includes various deep learning techniques such as computer vision, voice recognition, natural language processing, and voice/signal processing.

Recently, there have been attempts to integrate AI with wireless communication systems, but these have been focused on the application layer and network layer, especially deep learning in the field of wireless resource management and allocation. However, these studies are gradually developing into the MAC layer and the physical layer, and in particular, attempts to combine deep learning with wireless transmission are appearing in the physical layer. AI-based physical layer transmission means applying a signal processing and communication mechanism based on an AI driver rather than a traditional communication framework in fundamental signal processing and communication mechanisms. For example, deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based MIMO mechanism, AI-based resource scheduling and may include allocations, etc.

Deep Neural Network (DNN) model

8 is an example of a DNN model to which the present invention can be applied.

A deep neural network (DNN) is an artificial neural network (ANN) composed of several hidden layers between an input layer and an output layer. Deep neural networks can model complex non-linear relationships, just like regular artificial neural networks.

For example, in a deep neural network structure for an object identification model, each object may be represented as a hierarchical composition of basic image elements. In this case, the additional layers may consolidate the characteristics of the gradually gathered lower layers. This feature of deep neural networks allows complex data to be modeled with fewer units (units, nodes) compared to similarly performed artificial neural networks.

As the number of hidden layers increases, the artificial neural network is called “deep.” The machine learning paradigm that uses a sufficiently deep artificial neural network as a learning model is called deep learning. In addition, a sufficiently deep artificial neural network used for such deep learning is collectively referred to as a deep neural network (DNN).

In the present invention, data required for training a POI data generation model may be input to the input layer of the DNN, and meaningful data usable by the user may be generated through the output layer while passing through hidden layers.

Although the artificial neural network used for this deep learning method is collectively referred to as DNN in the specification of the present invention, other deep learning methods can be applied as long as meaningful data can be output in a similar way.

AI device block diagram

9 is a block diagram of an AI device according to an embodiment of the present invention.

The AI device 20 may include an electronic device including an AI module capable of performing AI processing or a server including the AI module. In addition, the AI device 20 may be included in the configuration of at least a portion of the electronic device and may be provided to perform at least a portion of the AI processing together.

The AI device 20 may include an AI processor 21, a memory 25 and/or a communication unit 27.

The AI device 20 is a computing device capable of learning a neural network, and may be implemented in various electronic devices such as a server, a desktop PC, a notebook PC, and a tablet PC.

The AI processor 21 may learn a neural network using a program stored in the memory 25 . In particular, the AI processor 21 may learn a neural network for recognizing image-related data. Here, the neural network for recognizing image-related data may be designed to simulate the structure of the human brain on a computer, and may include a plurality of network nodes having weights that simulate neurons of the human neural network. A plurality of network modes may transmit and receive data according to a connection relationship, respectively, so as to simulate synaptic activity of neurons that transmit and receive signals through synapses. Here, the neural network may include a deep learning model developed from a neural network model. In the deep learning model, a plurality of network nodes may exchange data according to a convolution connection relationship while being located in different layers. Examples of neural network models are deep neural networks (DNN), convolutional deep neural networks (CNN), recurrent Boltzmann machines (RNNs), restricted Boltzmann machines (RBMs), deep trust It includes various deep learning techniques such as deep belief networks (DBN) and deep Q-network, and can be applied to fields such as computer vision, voice recognition, natural language processing, and voice/signal processing.

Meanwhile, the processor performing the functions described above may be a general-purpose processor (eg, CPU), or may be an AI-only processor (eg, GPU) for artificial intelligence learning.

The memory 25 may store various programs and data necessary for the operation of the AI device 20 . The memory 25 may be implemented as a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SDD). The memory 25 is accessed by the AI processor 21, and reading/writing/modifying/deleting/updating of data by the AI processor 21 can be performed. In addition, the memory 25 may store a neural network model (eg, the deep learning model 26) generated through a learning algorithm for data classification/recognition according to an embodiment of the present invention.

Meanwhile, the AI processor 21 may include a data learning unit 22 that learns a neural network for data classification/recognition. The data learning unit 22 may learn criteria regarding which training data to use to determine data classification/recognition and how to classify and recognize data using the training data. The data learning unit 22 may acquire learning data to be used for learning and learn the deep learning model by applying the obtained learning data to the deep learning model.

The data learning unit 22 may be manufactured in the form of at least one hardware chip and mounted on the AI device 20 . For example, the data learning unit 22 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or manufactured as a part of a general-purpose processor (CPU) or a graphics-only processor (GPU) for the AI device 20. may be mounted. Also, the data learning unit 22 may be implemented as a software module. When implemented as a software module (or a program module including instructions), the software module may be stored in a computer-readable, non-transitory computer readable recording medium (non-transitory computer readable media). In this case, at least one software module may be provided by an Operating System (OS) or an application.

The data learning unit 22 may include a training data acquisition unit 23 and a model learning unit 24 .

The training data acquisition unit 23 may acquire training data required for a neural network model for classifying and recognizing data. For example, the learning data acquisition unit 23 may acquire vehicle data and/or sample data to be input to a neural network model as learning data.

The model learning unit 24 may learn to have a criterion for determining how to classify predetermined data by using the obtained training data. In this case, the model learning unit 24 may learn the neural network model through supervised learning using at least some of the learning data as a criterion. Alternatively, the model learning unit 24 may learn the neural network model through unsupervised learning in which a decision criterion is discovered by self-learning using learning data without guidance. In addition, the model learning unit 24 may learn the neural network model through reinforcement learning using feedback about whether the result of the situation judgment according to learning is correct. In addition, the model learning unit 24 may train the neural network model using a learning algorithm including error back-propagation or gradient decent.

When the neural network model is learned, the model learning unit 24 may store the learned neural network model in memory. The model learning unit 24 may store the learned neural network model in a memory of a server connected to the AI device 20 through a wired or wireless network.

The data learning unit 22 further includes a training data pre-processing unit (not shown) and a learning data selection unit (not shown) to improve the analysis result of the recognition model or save resources or time required for generating the recognition model. You may.

The learning data pre-processing unit may pre-process the acquired data so that the acquired data can be used for learning for situation determination. For example, the learning data pre-processing unit may process the acquired data into a preset format so that the model learning unit 24 can use the acquired learning data for learning for image recognition.

In addition, the learning data selector may select data necessary for learning from among the learning data acquired by the learning data acquisition unit 23 or the learning data preprocessed by the preprocessor. The selected learning data may be provided to the model learning unit 24 . For example, the learning data selection unit may select only data about an object included in a specific region as training data by detecting a specific region among acquired images.

In addition, the data learning unit 22 may further include a model evaluation unit (not shown) to improve the analysis result of the neural network model.

The model evaluation unit inputs evaluation data to the neural network model, and when an analysis result output from the evaluation data does not satisfy a predetermined criterion, it may cause the model learning unit 22 to learn again. In this case, the evaluation data may be predefined data for evaluating the recognition model. For example, the model evaluator may evaluate that the predetermined criterion is not satisfied when the number or ratio of the evaluation data for which the analysis result is inaccurate among the analysis results of the learned recognition model for the evaluation data exceeds a preset threshold. there is.

The communication unit 27 may transmit the AI processing result by the AI processor 21 to an external electronic device.

Here, the external electronic device is a device capable of wired/wireless communication with the AI device, and may include a broadcasting device and a viewer device to be described later. In this case, the AI device may be implemented in the manager device.

On the other hand, the AI device 20 shown in FIG. 8 has been functionally divided into an AI processor 21, a memory 25, a communication unit 27, and the like, but the above-described components are integrated into one module and the AI module Note that it can also be called

video commerce system

10 shows a schematic diagram of a video commerce system to which the method proposed in this specification can be applied.

As shown in FIG. 10, the video commerce system 100 includes a manager device 110, a broadcasting device 120, and one or more viewer devices 130, and the devices in the video commerce system are wired/wireless networks, respectively. can be connected with Components included in the video commerce system may be less or more than this, as an example.

A network disclosed herein may include, for example, a wireless network, a wired network, a public network such as the Internet, a private network, a global system for mobile communication network (GSM) network, and a general packet wireless network. packet radio network (GPRS), local area network (LAN), wide area network (WAN), metropolitan area network (MAN), cellular network, public switched telephone network PSTN), personal area network, Bluetooth, Wi-Fi Direct, Near Field communication, UltraWide band, a combination thereof, or any other It may be a network, but is not limited thereto.

The manager device 110 may be expressed as a (management) server, a manager terminal, a manager platform, and the like.

The manager device may provide functions and screens such as purchase of broadcast rights, broadcast reservation, broadcast notification, etc. for live broadcasting of casters subscribed to the X-caster application (or app or platform).

Here, the X-caster application may refer to an application for a seller (or broadcaster) to provide product information while providing live video to viewers in real time, and may be simply referred to as X-caster.

Here, a plurality of conditions for live broadcasting may be related to thumbnail, broadcasting time, broadcasting means, viewing restriction, time sale, broadcast product, time sale, simultaneous broadcasting, and the like.

In addition, the manager device may provide a function for inducing broadcasters to download the X-caster app for live broadcasting.

More specifically, the manager device sets a live schedule screen including a broadcast list for pre-reserved live video broadcasts as the main screen, registers a new live video broadcast through purchase of broadcast rights and setting of at least one broadcast condition, and / or providing a screen for reservation, providing a screen related to inputting interlocking conditions for simultaneously broadcasting the live video broadcast through a social network service (SNS) application other than the caster application, and starting or A notification setting screen may be provided for transmitting a notification message indicating termination to the viewer device.

Here, the broadcasting rights include a starter broadcasting right, a basic broadcasting right, a professional broadcasting right, a premium broadcasting right, and a VIP broadcasting right classified based on the purchase price of the broadcasting right, and the purchase price of the broadcasting right includes broadcasting time, number of broadcast viewers, broadcasting resolution or It may be determined based on at least one of broadcast transmission rates.

The starter broadcasting rights, the basic broadcasting rights, the professional broadcasting rights, the premium broadcasting rights, and the VIP broadcasting rights have resolutions of 480 pixels, 480 pixels, 720 pixels, 720 pixels, and 720 pixels, respectively, and broadcast transmission rates of 700 Kbps, 700 kbps, and 1,500 kpbs, respectively. , 1,500 kpbs, 1,500 kpbs.

The starter broadcasting right, the basic broadcasting right, the pro broadcasting right, the premium broadcasting right, and the VIP broadcasting right may be classified based on the number of viewers.

The broadcasting time of the starter broadcasting right is 30 minutes, and the number of viewers may be 100.

The broadcasting time of the basic broadcasting right is 30 minutes, and the number of viewers may be 500.

The broadcast time of the professional broadcast rights is 60 minutes, and the number of viewers may be 1,500.

The broadcasting time of the premium broadcasting rights may be 60 minutes, and the number of viewers may be 5,000.

The broadcasting time of the VIP broadcasting right is 60 minutes, and the number of viewers may be 10,000.

The broadcasting device 120 may be expressed as a caster device, a transmitting device, a broadcasting terminal, or a broadcasting means.

The broadcasting device includes a communication unit for transmitting and receiving wireless signals, an output unit for providing audio and/or video, the communication unit and the output unit, in order to provide information on products in real time through live video broadcasting in a video commerce system. It may include a processor to which it is functionally connected.

The broadcasting device may display a list of products included in live broadcasting registered to the X-caster.

When the broadcasting device receives a selection input for a product list to be broadcast live from among the product list list and an input for a Live button, the broadcasting device starts live broadcasting.

The broadcasting device may be a mobile or broadcasting camera.

The broadcasting device may provide products to be sold in live broadcasting to viewers along with real-time streaming.

In addition, when simultaneous broadcasting (or simultaneous transmission) is set, the broadcasting device can simultaneously broadcast live video through a plurality of SNS-related apps (eg, home shopping, YouTube, Facebook, etc.).

More specifically, the broadcasting device provides a schedule of live video broadcasts registered and/or reserved in the manager device, and provides a product list including at least one product to be provided to the viewer device during live video broadcasting, A chatting window related to a currently broadcasting live video may be provided to be distinguished from the live video, and the above functions may be performed by a processor of the broadcasting device.

In addition, the broadcasting device may output the first initial of the English name of the user participating in the live video broadcasting, the remaining broadcasting time, and the number of participants participating in the live video broadcasting in the chat window.

The broadcasting device may output a count from 10 to 1 or from 3 to 1 at the center of the screen where the live video broadcast is currently being reproduced from 3 seconds before the end of the live video broadcast.

Also, the broadcasting device may output only the three most recent chatting messages to the chatting window.

Here, the broadcasting state may be displayed as one of end, absence, live, or scheduled.

The viewer device 130 may be expressed as a user device, a user terminal, and the like, and may include a personal computer (PC) as well as a tablet computer, a smart phone, a laptop (LapTop), and the like.

The viewer device may display products related to the corresponding video along with a live broadcasting video, and provide a product detailed information page and a product purchase page for the corresponding products.

If the viewer device is a mobile device such as a mobile phone, a chat window may be overlapped with a live video of a mobile web page and displayed, and when the user selects product detailed information or product purchase, the viewer device displays a product detail screen or product purchase. Live video can be displayed smaller than its original size in a specific area of the screen.

If the user device is a laptop computer or a desktop computer, the user device may separately display a live broadcasting video, a chat window screen, a product detailed information screen, etc. without overlapping each other.

More specifically, the viewer device provides information on a product registered first in a product list provided by the broadcasting device when the live video broadcasting of the caster application is executed, and is provided together with the live video broadcasting. It may include a viewer device providing a product detail screen for a product, a product purchase screen, and a chat window.

The viewer device provides information on the first registered product through a pop-up window once every 5 minutes, the pop-up window lasts for 3 seconds, and when the pop-up window is clicked, detailed product information on the product in the pop-up window can provide.

As can be seen, if the viewer device is a mobile device, the viewer device may reduce the size of the live video broadcasting to a specific area on each of the product detail screen and the product purchase screen and output the same.

As seen, if the viewer device is a PC, the viewer device may separately output the live video broadcasting, the product detail screen, and the chat window on one screen.

In addition, when the notification message transmission is set on the notification setting screen, the viewer device may output an icon enabling confirmation of whether or not the notification message is transmitted.

In addition, when the broadcasting status is set to 'end' or 'simultaneous broadcasting' in the live video broadcasting item, the viewer device may provide a video on demand (VOD) link for replaying the live video broadcasting that has ended. there is.

Further, when the viewer device detects that a specific live video broadcast is included in a shopping cart or purchased in a caster application executed in another viewer device, it can output the detected result to the currently displayed chatting window.

In addition, each of the manager device, broadcasting device, and viewer device includes a control unit (not shown) (or processor), a storage unit (temporary or non-temporary storage device) (or memory) for performing methods or functions proposed in the present specification to be described later. ), a bus (not shown) for data transmission, or a communication unit (not shown) for communicating with the outside.

The storage unit may include magnetic storage media or flash storage media, but the scope of the present invention is not limited thereto.

The communication unit may be composed of wired and/or wireless communication modules. For example, the communication unit may include wireless communication modules such as Wi-Fi (Wireless Fidelity), Bluetooth, Zigbee, near field communication (NFC), and Wireless Broadband Internet (Wibro). and a wired communication module such as a wired LAN such as Ethernet. The communication unit may perform wired/wireless communication with a user device through a network.

The controller may include all types of devices capable of processing data, such as a processor. Here, a 'processor' may refer to a data processing device embedded in hardware having a physically structured circuit to perform functions expressed by codes or instructions included in a program, for example. As an example of such a data processing device built into hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated (ASIC) circuit), field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

A method for providing product information in real time through live video broadcasting in a video commerce system

Transmission, broadcasting, transmission, supply, provision, etc. used in this specification shall be used in the same meaning in interpreting the method proposed in this specification unless otherwise specified.

In addition, real-time video, real-time video image, real-time live broadcasting image, real-time live video broadcasting, live streaming, live video image, etc. used in this specification may be interpreted as having the same meaning unless otherwise specified.

The method proposed in this specification (1) sets a number of broadcasting conditions through purchase of broadcasting rights for real-time live broadcasting, enables registration/reservation of live broadcasting, and (2) schedules live broadcasting at a scheduled time ( or (3) a method of transmitting information on a related product while providing it through real-time streaming at a set time), and (3) enabling a user to purchase the corresponding product.

In addition, as an embodiment of the method proposed in this specification, the viewer device follows (or displays) a live broadcast (smaller than the original size) on the product detailed information screen (and / or product purchase screen), It can increase the purchasing power of users.

In addition, as an embodiment of the method proposed in this specification, the viewer device displays a pre-captured image together with a live image. Through this, the video commerce system proposed in this specification can increase the user's product purchasing power.

In addition, as an embodiment of the method proposed in this specification, the broadcasting device may simultaneously transmit or transmit live video through a plurality of SNS-related apps.

Also, as an embodiment of the method proposed in this specification, a user may select a specific product, shoot a snack video (or a short cut video) of the specific product, and upload the specific product to a home shopping mall or the like. In this case, the user can view not only a simple image in relation to product information, but also a video of the corresponding product.

Also, as an embodiment of the method proposed in this specification, the broadcasting device may set a time sale function for a product of a live video and apply the time sale function to the corresponding product. In this case, the viewer device can easily know what percentage of the product or how long the sale is going on when the time sale for the product starts.

In this case, when the activated time sale button is pressed, the viewer device provides information on the changed price of the product.

How to provide product information through short cut video production in video commerce system

Hereinafter, a method of producing a real-time product broadcast called 'short cut video' will be described.

The shortcut video refers to a video in which a specific part (eg, an impressive part) is shortened, and may be expressed as a snack video, a short cut video, or a clip image.

The short cut video production method is already provided by services such as TikTok, but the short cut video production method proposed in this specification has a clear difference from the existing short cut video production method in that a product broadcast is produced before filming the video. .

That is, the method of producing (or providing) a short cut video provided in this specification is different from existing methods (e.g., TikTok, etc.) by applying background music, templates, text, etc. in advance before filming the video to provide a visually prettier and more complex video. There are advantages or effects that can be done.

In addition, the short cut video produced in this way may be provided along with the image in the thumbnail of the detailed product information.

Hereinafter, a method of producing (or providing) a shortcut image proposed in this specification will be described in more detail.

Of course, the content described in this specification centering on the user may be described based on the device when the corresponding content is implemented in a device.

Shortcut video production can be filmed or edited using the video recording function provided by the X-caster app that we looked at earlier.

The X-caster app can be divided into two parts: a live video part and a snack video part.

The video shooting process using the X-Caster app is as follows.

In other words, the video shooting process using the X-Caster app includes (1) product selection, (2) video information registration, (3) scene registration, (4) registered media editing, (5) thumbnail creation, (6) upload, etc. procedures may be included.

Product selection process

The product selection process is to select a product to shoot a (promotional) video. Only one product can be selected at a time. When a user selects a product, a screen for registering image information is provided.

Video information registration process

The image information registration procedure sets whether or not to use a template. When setting the use of a template, the template selection button is activated, and when the template selection button is entered, the X-caster app (or the device on which the X-caster app is installed) displays a list of templates. The template list may include a 1-way type list and a thumbnail type list. The 1-way form displays the template thumbnail, template name, suitable product category, required number of media (images, videos), and price.

Here, the template list may be sorted in order of price, order of popularity, and order of latest. The template list may also be classified into paid templates and purchased templates.

Purchased templates can be selected and used immediately, and paid templates that have not been purchased can be set to be used after purchase.

When the displayed template is clicked, the template detail page is provided. The template detail page displays a template thumbnail, template name, suitable product category, required number of media (images, videos), price, etc., and may include a "scene configuration" button and a "purchase" button.

When the “Scene Composition” button is pushed (or clicked), a detailed screen for viewing the screen composition for each scene in detail is provided. The scene configuration page may be configured to view thumbnails for each scene. The scene composition page displays the number of media required for each scene (images or videos), media standards (eg product front photos), and the number of texts to be entered.

When the "Buy Now" button is pushed, a purchase page is provided so that the user can purchase the template.

In the case of a template that has already been purchased, the “Use” button is changed instead of the “Buy” button, and when the “Use” button is pushed, the template is included in the image information registration screen.

Next, a screen for inputting a title name of an image to be photographed may be provided. The title of the video can be written in about 30 characters, and can be entered in English, Korean, numbers, and special symbols.

Next, a screen on which an image description can be input may be provided. Video descriptions can be written in about 100 characters, and can be entered in English, Korean, numbers, and special symbols.

Next, the user selects a scene number. If no template is used, the user selects the number of scenes to use. If using a template, the user can select a number of scenes to add to the template.

Next, the X-caster app provides a screen where you can choose whether or not to use background music. As for whether to use background music, one of 'all', 'by scene', and 'not used' can be selected.

If the user selects 'All', a button for selecting the background music to be used is displayed, and when the button is pushed, a list of background music is displayed. Also, the background music may include purchased sound sources and non-purchased sound sources.

The purchased sound source can be used immediately, and the non-purchased sound source can be used after purchasing the sound source.

If the user does not select background music, the X-caster app can be set not to go to a later step.

If the user selects 'by scene', background music may be selected for each scene when editing a scene.

If the user selects 'do not use', the background music is not selected and the next screen is provided. If it is necessary to add background music, background music can be added during editing.

And, the X-caster app displays selected product information (thumbnail, product name, product price). If a change is required for the selected product, a 'change' button may be utilized.

Here, when the 'change' button is pushed, the product list page is moved, and the user can change the product on the corresponding page.

Scene registration process

Scene registration (image, video, text, background music) can be performed by importing and shooting. After that, the user can register an image, video, text, background music (when set), etc. for the scene.

If a template is used, the media (image, video, background music) and text registered for each template scene can be displayed as follows.

- Please register a product front photo of 720 X 1280 size.

- Please enter a product description within 30 characters to be included in the product front photo.

- Please select background music.

Media and text to be registered for each scene may be determined for each selected template.

When a user selects a template and adds a scene, after adding the template scene, the user may additionally register scenes equal to the number of added scenes. Additionally, when registering a scene, media (image, video, background music) and text can be freely entered regardless of the template.

Next, if the user does not select a template, the user can freely register media (image, video, background music) and text as many as the number of scenes set during broadcast registration.

Next, when a user registers a picture of a product, the user may take a picture of the product and register it using a viewer device or import a picture stored in a photo album and register the product.

Next, when registering a product video, you can shoot and/or register the product or register a pre-stored image using the video shooting function provided by the X-Caster app.

The procedure for registering a video using the video shooting function provided by the X-Caster app is as follows.

First, the user may select background music before shooting.

When background music is selected, the selected background music is automatically registered to the scene background music.

Alternatively, image capturing may proceed immediately without selecting background music.

When background music is selected, a screen for recording an image is provided. The video capture screen may provide flash On/Off, camera switching, beauty filter, video filter, hands-free, speed control, and the like.

Video recording is recorded only when the recording button is continuously pressed, and recording is stopped when the push of the recording button is stopped.

Further, in a state in which the capture button is pushed, when a gesture of raising the capture button is input, the image is canceled, and when a gesture of pushing the capture button down is input, image capture may be canceled.

Also, a segment is created each time the photographing button is pressed and then released. Therefore, if you do not like the recorded part, you can delete the created segment and retake it.

In addition, when the hand (or hands-free) mode is used, if the photographing button is pushed once, the image is photographed to the end as much as the length of the photographing section, and then the photographing is stopped.

In addition, if the user pushes the photographing button once more while using the hands-free mode, photographing of the image is stopped.

The video speed can be controlled by adjusting the speed for each section by recording the video at 2x slow, 1/2x slow, normal speed, 1/2x fast, 2x fast, etc. during shooting.

And, when the video recording is finished, it moves to a screen where post-editing is possible. On the post editing screen, the user can change the background music or select a section of the sound source to be used.

On the post editing screen, the user can adjust the volume of the sound input into the microphone and the background music during recording.

The post editing screen provides a function to apply special effects to the recorded video.

That is, the post-editing screen provides functions for special effects that can give a desired section, such as an effect in which the RGB colors of the video appear to spread through a glitch effect, a screen shaking effect, and an afterimage effect as the screen grows and shrinks.

And, the X-caster app can provide a function to put a sticker on the video. Specifically, when the user selects a desired sticker from the sticker list, the selected sticker is placed on a photographed image, and may be enlarged, reduced, rotated, moved, or deleted.

In addition, the X-caster app provides a function to put text on top of the filmed video. When writing text, the user can select left, right, or center alignment of the text, and can change the text color. And, the user can add text background color or adjust background color transparency. After writing the text, the user can enlarge, reduce, rotate, move, delete, etc. the text written in the same way as a sticker.

Next, when the step-by-step video and image registration or shooting is finished, it moves to the outro selection screen.

Registered Media Editing Procedure

The X-caster app provides the function of playing scenes registered at the top of the media editing screen as one video.

Here, the user can cut, add, move or delete scenes. Adding a scene can be performed by calling registered images and videos or by shooting using X Caster.

Also, background music for each scene may be changed, added, moved, or deleted. When the scene changes, transition effects can be selected. Transition effects may include two types of video transition effects and audio transition effects. Video transition effects can include a black dip, white dip, and cross dissolve. Audio telephony effects may include accelerated fades, sustained accel/decel, sustained individual, and the like.

Here, it is possible to adjust the speed for each scene. Speed control for each scene may be performed by reducing or increasing the length of a section for each scene.

Then, when the editing is completed, the X-caster app provides a thumbnail creation screen.

Thumbnail creation procedure

Thumbnails can be registered by (1) calling or photographing an image and writing text on the image, or (2) selecting a frame in which a thumbnail is to be selected from a photographed image and registering the thumbnail. When thumbnail registration is completed, the X-caster app provides an upload screen.

upload process

On the upload screen, the user can view the finished video as a preview. If the finished video is not satisfactory, the user can re-edit the finished video on the editing screen. And, when uploading a video, payment for it is required.

UI functions related to real-time video broadcasting in the video commerce system

Next, the UI (user interface) of each device in relation to real-time video image transmission in the video covers system proposed in this specification will be examined in detail.

Here, each device may be the previously salpin broadcasting device or viewer device (mobile version, PC web version). As discussed above, the broadcasting device may be a caster device or a device equipped with a live transmission app.

Broadcast device UI (User Interface)

First, a live broadcasting schedule screen displayed on a broadcasting device will be described. 11 is a diagram illustrating an example of a broadcasting device UI proposed in this specification. Referring to FIG. 11 , a live broadcast schedule may include a year/month display part 1110, a day display part 1120, a reserved broadcast list display part 1130, and a LIVE button display part 1140. Here, the reserved broadcasting list display portion may include a sale product item 1131.

The year/month display part enables viewing of the broadcasting schedule, and left/right arrow buttons are displayed. When the left/right arrow buttons are clicked, the next month or the previous month can be viewed.

If the month is 'December' in the year/month display, clicking the right arrow button moves to the next month ('January'), and the year also changes to the next year. If the month is 'January' in the year/month display part, clicking the left arrow button moves to the previous month ('December'), and the year also changes to the previous year. Here, the previous month passes only one month before the base month.

In addition, the day display part is displayed below the year/month display part, and can be displayed from the 1st to the maximum of 31 days through a left/right swipe operation. Accordingly, when the user selects year/month/day, a broadcast list reserved for the selected date is displayed in the reserved broadcast list display area.

A product thumbnail 1132, a broadcast time 1133, a broadcast title 1134, a current broadcast status display 1135, and the like may be displayed in the reserved broadcast list display portion. As for the product thumbnail, when multiple products are selected, the thumbnail of the first registered product is displayed.

And, the current broadcasting state display can be classified into end, live, and scheduled. If the status display is 'scheduled (or reserved)', the status becomes 'live' 10 minutes before the reservation time, and the live button is activated when a reserved broadcast in 'live status' is clicked. And, when clicking on the item for sale, a list of products caught (tied) to a specific reserved broadcast is displayed below. In addition, when simultaneous transmission is set to SNS-related apps (Facebook, YouTube, etc.) in the broadcasting conditions of the manager device, the SNS-related apps 1136 may be displayed next to the broadcasting time of each scheduled broadcast. And, if there is a scheduled broadcast at the current time, the broadcasting device activates the live button, and when the user clicks the live button, the broadcasting device starts (or transmits) live broadcasting. If the broadcasting device is a 'camera' and is set to camera broadcasting, the broadcasting device displays a camera next to the broadcasting time.

In addition, the product list tied to a specific reserved broadcast may include the name of the product for sale, the sales price of the product for sale, and whether or not there is a time sale. In addition, when the user clicks a sales product folding button in the product list, the broadcasting device makes the product list disappear. The area next to the product thumbnail is the part where the title of the reservation broadcast is displayed, and up to 30 characters such as Korean, English, special characters, and numbers can be entered. And, if there is no reserved broadcast on the date selected by the user in the year/month/day display part, the broadcasting device may display a place holder (eg, 'There is no reserved broadcast') on the title of the reserved broadcast.

12 is a diagram illustrating another example of a broadcasting device UI proposed in this specification.

When the user clicks the LIVE button, the broadcasting device displays a screen for 'cancel' or 'confirmation' of starting live broadcasting (1210). Here, when the user clicks the 'cancel' button, the broadcasting device cancels the live start and displays the live preparation screen again. Alternatively, if the user clicks the 'OK' button, the broadcasting device starts live broadcasting and enters the live screen.

When entering the live screen, the live screen may include a live video display portion and a chat display portion (or chat window).

And, at the top of the live screen (or at the top of the chat window), there are thumbnails (D, J, C, H, O, ?) (1220) and the number of participants (e.g. 97/100) ) 1230 may be displayed. The number of viewers may include both the number of viewers who can enter and the number of viewers who have currently entered. Live broadcasting participant thumbnails may have a form in which the first letter (English) of a participant's name is displayed in a circle on an arbitrary background color. In addition, left/right swiping is possible in the participant thumbnail area. Then, a close button ('X') is displayed at the end of the participant thumbnail, and when the close button is pressed, the broadcasting device displays a confirmation pop-up window for terminating live broadcasting.

The broadcasting device displays data during live broadcasting under participant thumbnails. Here, the data may include the number of shopping carts, the number of purchases, and the like in order. Here, the number of shopping carts and the number of purchases reflect the increasing numbers during live broadcasting.

And, the live broadcasting time 1240 is limited by the time of the purchased broadcasting rights. For example, the broadcasting device deducts the time from 30 minutes and displays the count at the top of the live screen in a large size from 3 seconds before the end. In addition, when 30 minutes of the purchased broadcasting rights have elapsed, the broadcasting device automatically ends live broadcasting. If the user uses the additional broadcasting right before the end of broadcasting, the broadcasting device extends the broadcasting time by the time of the additional broadcasting right.

And, the broadcasting device displays a chatting window 1250 from the middle to the bottom of the live screen. If there is a lot of chatting, the user can check the chatting content by scrolling in the chatting window. If a user enters a chat, the thumbnail, name, and chat contents of the user who entered the chat are displayed.

Further, when the user presses the chatting input window 1260 located at the bottom of the live screen, the broadcasting device displays a keypad for inputting chatting from bottom to top. In addition, up to 100 characters can be entered at once in the chat. When the user inputs a chat and clicks the transmission button, the broadcasting device displays the chatting input in the chat window. Further, if the user presses the comment for 1 second or more, the broadcasting device allows the user to report the user who inputs the corresponding comment.

13 is a diagram illustrating another example of a broadcasting device UI proposed in this specification.

The broadcasting device displays a number count 1310 from 10 to 1 on the screen so that the caster can recognize it 3 seconds before the end of the live broadcasting time. When the number count ends, the broadcasting device ends live broadcasting and displays a live preparation screen. And, when the user presses the chatting input field of the chatting screen, the chatting area comes up to the top. When displaying chatting, the broadcasting device displays only three recently entered chats.

When the user clicks the chatting input field, the broadcasting device causes the keypad 1320 to come up from the bottom and at the same time, the chatting input window to come up on the keypad as well. As examined, when the user inputs chatting content into the chatting input field and presses the transmit button, the broadcasting device transmits the entered chatting to the chatting window. At this time, the keypad area is fixed as it is. And, when the user touches (or clicks) the chatting area, the keypad moves down. If the user clicks the 'cancel' button in the pop-up window 1330 for the end of live broadcasting, the broadcasting device displays the live screen again if it is determined that broadcasting time is still remaining. Alternatively, if the user presses the 'OK' button, the broadcasting device ends broadcasting and displays a broadcast preparation screen.

Next, when the X-caster app (or live broadcasting app) is executed by the user, the subsequent process will be looked at.

When the live broadcasting app is executed, the broadcasting device displays a splash window for about 1-2 seconds, and when the splash window (logo display) disappears, a screen for logging in to the live broadcasting app is displayed. When the ID and password registered at the time of membership registration are input from the user, the broadcasting device determines that the login is complete and executes the live broadcasting app.

If the entered ID is not in the list of registered members, the broadcasting device displays "Not a registered ID." Displays a pop-up message or, if the entered ID and password do not match, the broadcasting device displays “ID and password do not match.” A pip-up message is displayed, and if the input ID and password match, the broadcasting device logs in and brings up a list of pre-registered shopping mall products.

Here, if the broadcasting device is logged in once, it can be automatically logged in without a separate log-in procedure when accessing the next live broadcasting app. If it is determined that the live broadcasting app is not registered as a member, the broadcasting device provides a page for member registration when an input of a member registration button is received.

A brief and additional look at the membership registration process of the live broadcasting app.

When registering as a member, you can receive your ID by e-mail, and the e-mail address must include “@” and “.”.

If the above format is not included, the broadcasting device will say “The email format is not correct. Please check again." pop-up message is displayed. If the same e-mail is registered, the broadcasting device says "This e-mail has already been registered." pop-up message is displayed.

When registering as a member, the password must be at least 6 characters and up to 12 characters with a combination of English and numeric characters. If the password does not meet the above conditions, the broadcasting device displays a pop-up message saying, “Passwords can only contain 6 to 12 English characters and numbers.” In the password checkbox, the same password entered in the password field must be entered, and if they do not match, the broadcasting device displays a pop-up message saying “Passwords do not match.” Then, the user inputs a shopping mall ID assigned through the manager device or preset (or previously obtained) to the shopping mall ID item on the login screen.

And, if the broadcasting device does not agree to the terms of use and personal information processing policy, it restricts the user's membership registration. Here, if the user presses the text of the terms of use and personal information processing policy, the broadcasting device outputs or displays a page where the user can check the terms of use and personal information processing policy.

And, when the user clicks the sign-up complete button, the broadcasting device checks the un-inputted items, and if there are un-entered items, “The required field is empty. Please confirm." pop-up message is displayed. And, when the user presses the sign-up complete button, the broadcasting device checks the entered shopping mall ID, and if it is not an ID registered to the shopping mall, “The ID is not registered to the shopping mall. Please check again." pop-up message is displayed. In addition, when the broadcasting device determines that subscription completion is clicked without checking the box to agree to the terms of use, the broadcasting device outputs a pop-up message saying “Please agree to the terms of use and personal information processing policy”. In addition, when the user normally inputs membership information and agrees to the terms and conditions, the broadcasting device displays a live preparation screen after completing membership registration. Here, the terms of use and the personal information processing policy may be divided into tabs. Then, the user inputs the key value provided from the manager device into the authentication key item.

(Mobile) Viewer Device UI

Next, the mobile web view screen of the viewer device will be described in detail. 14 is a diagram illustrating an example of a viewer device UI proposed in the present specification.

When a live broadcast starts (or is transmitted), the viewer device displays a thumbnail of the live broadcast in the main banner area of the corresponding shopping mall. The viewer device displays a 'LIVE' icon indicating that it is live above the live broadcast thumbnail. To start live broadcasting, a play button 1410 may be displayed at the center of the live broadcasting screen. When the user presses the play button or thumbnail, the viewer device displays a pop-up window 1420 for live entry. Here, when the number of people watching the live broadcast exceeds, the viewer device displays a pop-up window 1430 informing of the live broadcast limit. If the login for the live broadcast is not successful, the viewer device induces the user to log in by outputting the live broadcast app login screen. If the user presses the 'cancel' button of the pop-up window related to entering the live broadcast, the viewer's device displays the main screen of the live broadcast app without activating the live broadcast. Alternatively, when the user clicks the 'confirm' button of the pop-up window, the viewer device outputs a live broadcasting screen. If the number of viewers of the live broadcast is exceeded, the viewer device displays a pop-up indicating the limit of live viewers, and when the user presses the 'OK' button on the pop-up window, the viewer device displays the main screen of the live broadcast app. When a caster makes a thumbnail for a live broadcast, the input title for the live broadcast may be displayed.

If live broadcasting starts, the viewer's device displays a pop-up window notifying the start of live broadcasting at the top when the screen is refreshed. When a live broadcast is in progress, a pop-up window is displayed at the top of each screen (or each page) whenever the screen is moved. If the user clicks the “close button (X button)” displayed on the pop-up window, the viewer device removes the pop-up window.

15 is a diagram illustrating another example of a viewer device UI proposed in the present specification.

The same as or similar to the program schedule screen of the broadcasting device, the viewer device may display the program schedule screen. That is, the program schedule screen displayed on the viewer device may include a year/month display part, a day display part, and a broadcast list display part 1510 . Similarly, a broadcast state (eg, end, missing room, LIVE, scheduled, etc.) may be displayed next to the broadcast time of each broadcast item in the broadcast list. In addition, when the user presses a sales product button included in each broadcasting item, the viewer's device displays a list of products sold during broadcasting below. Here, unlike the program schedule screen of the broadcasting device, the program schedule screen of the viewer device counts and displays only the number of viewers excluding the number of shopping carts and payments.

And, the viewer device displays a pop-up window about a product for about 3 seconds when the user accesses the live broadcasting app for the first time. If there are several products, the viewer device displays the first registered product. Then, the viewer device makes the pop-up window appear for 3 seconds once every 5 minutes and then disappears. If the user clicks the pop-up window, the viewer device displays a product (or product) detail page. When the user clicks the button on the far left of the chatting input window, the viewer's device displays a pop-up window for a product list. In addition, when other viewers put the product in their shopping cart or purchase it, the viewer's device reflects it and displays it on the screen to induce other viewers or users to purchase the product. Also, the viewer device may display a notice 1521 received through the broadcasting device at the top of the chatting window 1520 .

16 is a diagram illustrating another example of a viewer device UI proposed in the present specification.

When the product list pop-up window 1610 is displayed, the viewer device makes the pop-up window disappear when detecting a gesture of lowering the displayed pop-up window. The product list includes product information (product name, price, etc.) for each product. When the user clicks on each product information, the viewer device displays a product detail page 1620 .

In addition, the viewer device displays a video of the live broadcast on each moving screen so that a viewer watching the live broadcast can view the corresponding live broadcast even when the screen is moved. In addition, when the user clicks the “close button (X button)” displayed at the top right of the live broadcast on each screen, the viewer device ends the live broadcast and makes the video for the live broadcast disappear from the corresponding screen.

(PC, etc.) viewer device UI

Next, when the viewer device is a PC or a laptop computer rather than a mobile device, a screen provided by the viewer device will be described. 17 and 18 are diagrams illustrating another example of a viewer device UI proposed in the present specification.

When a viewer device such as a PC or laptop has a larger display portion than a mobile device, it has an advantage over a mobile viewer device in that it can display multiple functions on one screen without overlapping them. Hereinafter, unless otherwise specified, the viewer device refers to a web view screen such as a PC or a laptop computer.

During the live broadcast, the viewer device displays a live broadcast thumbnail in the main banner area of the shopping mall. When the user presses the play button for the live broadcast, the viewer device reproduces the live broadcast (or video) 1710 . If the number of viewers of the live broadcast exceeds the quota, when the user presses the play button, the viewer device displays a pop-up window informing that the number of viewers is exceeded. If the user presses the play button without logging in, the viewer device outputs a pop-up window indicating that login is required and displays the number of viewers of the corresponding live broadcast. Then, the viewer's device displays thumbnails of participants of the salpin live broadcast prior to the top of the screen.

The chatting window 1720 includes chatting contents input by users. If there are many chatting contents input by users, the viewer device creates a scroll bar 1721 on the right side of the chatting window so that the user can check the chatting contents by scrolling. Also, the viewer device does not display a chatting window when the live video is not played. When the user selects a chatting input window, inputs chatting contents into the corresponding chatting input window, and presses the enter key or the send button, the viewer device displays the chatting contents in the chatting window. Then, the viewer device outputs a product list 1730 selected from the broadcast to another area on the right side of the chatting window screen separately from the chatting window. When the user clicks a specific product in the product list, the viewer device displays a product detail screen 1810 . Here, the live broadcast reproduction screen, chat window, and product list are displayed in parallel on one screen without overlapping each other. In addition, when one of the product list screen and the product detail screen is displayed, the other screen disappears.

The viewer device displays product information (product name, selling price, shipping cost, options, etc.) being broadcasted on the product detail screen. Here, in order to add a specific product to the shopping cart or purchase it, an option must be selected.

The selected or input product up to the product option may be added to the product list. And, whenever the option of the selected product is added, the number of products added to or purchased in the shopping cart increases and the added products are sorted below. In addition, it is possible to prevent duplicate display of the same option product by adjusting the quantity.

When the user clicks the shopping cart, the selected products are included in the shopping cart. Here, when the user presses the 'purchase' button, the viewer's device displays a payment page (or payment screen) for the product in order to purchase a product for which the option is selected. In addition, when the 'heart' item displayed next to the chatting window is clicked, the viewer's device displays a heart animation on the live video. The viewer device may induce other viewers or consumers to purchase the same product by displaying information on the product that the viewer or user put in the shopping cart or purchased on the screen.

19 is a diagram illustrating another example of a viewer device UI proposed in the present specification.

The viewer device displays the corresponding live broadcasting video in a specific area 1910 of the moved page (or screen) so that the live broadcasting follows each moved page so that the live broadcasting participants can continuously watch the live broadcasting even when they move to a specific page. print out Here, the viewer's device can follow not only the live broadcasting but also the audio for the live broadcasting whenever the page is moved. In this way, when the user clicks a relatively small live broadcast on the moved page, the viewer device outputs the main screen, that is, the live broadcast screen.

Then, when live broadcasting starts and the user presses the screen refresh button, the viewer's device displays a pop-up window notifying the start of live broadcasting at the top of the screen.

20 is a diagram illustrating another example of a viewer device UI proposed in the present specification.

As shown in FIG. 20 , the viewer device may display the next or previous month of the corresponding month based on the left/right movement buttons on the calendar screen 2010. And, when a specific date is selected on the calendar screen, the viewer device displays a schedule for the selected date.

The live schedule includes weekly broadcast schedules. And, when the user clicks a specific date on the top of the broadcasting schedule, a reservation schedule of a radio broadcast corresponding to the specific date is displayed. Here, the date can be changed on a weekly basis through the left/right arrow buttons on which the date is displayed. That is, if the left arrow button is clicked, the stock price of the previous week may be displayed, and if the arrow button on the right is clicked, the stock price after the first week may be displayed.

The viewer device outputs a schedule list 2020 suitable for a corresponding date to a specific area of the screen. The schedule list may include a thumbnail 2021, broadcast status 2022, broadcast title, broadcast time, product information 2023, and the like. And, as examined above, the broadcast status (end, absence, LIVE, scheduled, etc.) can be displayed in a specific area of the live schedule screen. Here, the specific area may be a right end portion of a portion where the live broadcasting title is displayed. In addition, the schedule list may include items for sharing broadcast thumbnails, broadcast titles, and schedule page URLs to SNS-related apps. In addition, the viewer device may display a notification icon allowing notification of start or end of broadcasting through KakaoTalk or the like.

In the case of an ended live broadcast, the viewer device may display the remaining VOD link when the simulcast is performed. If a viewer or user clicks the displayed VOD link, the viewer's device displays a page where the video remains. Also, during live broadcasting, the viewer device displays product information broadcasted from the broadcasting device together. When the user clicks product information, the viewer's device displays a detailed page of the product.

The viewer's device follows the live broadcast on the moved page so that viewers watching the live broadcast can watch the live broadcast video even when the page is moved. In this case, not only the live video but also the audio of the live broadcast follows the moved page. When a live video is clicked, the viewer device outputs the main screen, that is, the live broadcasting screen. If you press the “X” button displayed on the live broadcasting screen, the live video will disappear.

Similarly, during live broadcasting, the viewer device displays a thumbnail of the live broadcasting in the main banner area of the shopping mall. Here, when the user presses the play button for the live broadcast, the viewer device reproduces the live video. If the number of viewers who can participate in the corresponding live broadcast exceeds, when the user presses the play button, the viewer device displays a pop-up window informing of the excess number of viewers. The viewer device displays the number of viewers at the top of the chat window, and displays a thumbnail for the name of the viewer in an area below the number of viewers. If the viewer clicks the left/right arrow on the thumbnail, the viewer device moves the thumbnail in the corresponding direction.

Admin device UI

21 is a diagram illustrating an example of a manager device UI proposed in the present specification.

In order for the user to access the manager device, the manager device displays a link 2110 for downloading the X-Caster app (or app related to live broadcasting) and induces the user to download the corresponding app. Here, the app download link is displayed only when the user first accesses the app. At this time, the app is selectively downloaded according to an operating system (OS) installed in the user's device. For example, the administrator device causes the X-Caster Google Play Store page or the X-Caster Apple App Store page to be displayed.

22 is a diagram illustrating another example of a manager device UI proposed in the present specification.

When the user accesses the manager account after downloading the app, the manager device displays the 16-digit authentication key value (2210) required when signing up for the manager account (X-caster). Here, the authentication key value may be configured as follows.

- First four digits: applr, first two digits + corresponding year (Example: ap20)

- The second four digits: the first two digits of cafe + the month (Example: ca12)

- Third 4 digits: 4 digit random number combination of English + numbers

- 4th digit: Authentication key generation time 4 digits (15:30 -> 1530)

Upon initial access to the manager account, if there is no broadcast reservation information, the manager device induces the user to make a broadcast reservation by displaying a broadcast rights purchase link button and a usage method button. Here, when the user clicks the purchase broadcast rights (button), the manager device displays a broadcast rights purchase page. Then, the manager device displays a usage method page when a broadcasting right usage method is clicked.

Similar to the schedules of salpin, broadcasting devices and viewer devices described above, the manager device displays live broadcasting schedules, and the schedules are organized on a weekly basis. Here, when the user clicks a specific date, the manager device displays a broadcast reservation schedule suitable for the specific date.

That is, the manager device may output a list of broadcasting schedules suitable for the specific date. Information displayed on the corresponding schedule may include a thumbnail, a broadcast status, a broadcast title, and a broadcast time. And, the manager device displays the number of broadcasting rights currently possessed by the user. When the user presses the 'view details' button at the bottom of the program schedule screen, the manager device displays a detailed page for the currently held live broadcast.

23 is a diagram illustrating another example of a manager device UI proposed in the present specification.

The live broadcasting schedule includes various information about broadcasting, such as a registered broadcasting schedule.

When the user selects a date from the calendar, the manager device outputs a broadcast list for the selected date. Then, the manager device outputs a screen for registering a broadcast in the broadcast list. And, in the case of a broadcasting state, the manager device does not display the broadcasting state of a date before today. Then, the manager device outputs broadcasting detailed information suitable for the date and time selected from the calendar.

If the user clicks the time sale start button 2310 during live broadcasting, it is displayed so that time sale can proceed in live broadcasting. And, if the user presses the time sale button once more, the manager device stops the ongoing time sale. And, the time sale button is activated only when live broadcasting is in progress. And, the time sale button is inactive for products to which time sale is not applied.

And, the manager device displays a button for deleting or modifying reserved broadcasting information. The corresponding button is available only in the last broadcast or reserved broadcast, and the corresponding button is inactive during live broadcasting. If the user clicks the 'Delete' button, the manager device displays a pop-up message saying "Do you want to delete the reservation information?", and if the user clicks "Yes", the manager device deletes the reservation information from the organization contents. Then, the manager device displays a page capable of modifying broadcast information whose broadcast state is 'scheduled'.

Here, the broadcast state may include end, unbroadcast, live, scheduled, and the like.

Among the broadcasting statuses, 'End' shows the status of broadcasting normally and the broadcasting has ended, 'Gyeolbang' indicates the status of making a reservation but not actually broadcasting, 'Live' indicates the current status of live broadcasting, and 'Scheduled' indicates a state in which a live broadcast is scheduled. And, the manager device does not deduct the broadcasting right for the 'non-broadcast reservation'.

When live broadcasting through camera broadcasting is selected at the time of broadcasting reservation, the manager device displays the Stream Name and RTMP URL on the detailed screen of the schedule. In addition, it is possible to modify whether it is camera broadcasting or mobile phone broadcasting (or mobile broadcasting) until broadcasting starts, and when changed to mobile phone broadcasting by the user, the manager device makes the Stream Name and RTMP URL disappear.

24 is a diagram illustrating another example of a manager device UI proposed in the present specification.

When the edit button of a scheduled broadcast is clicked on the broadcast registration or schedule detail screen, the manager device can register and modify broadcast information through the called page.

At this time, the manager device displays a screen for uploading an image, and the size of the image may be up to 10 MB or less. The image file format can only be png or jpg.

The manager device displays a list of broadcasting rights purchased by the user, and the user can select the purchased broadcasting rights. Types of broadcasting rights are: Starter broadcasting rights (broadcasting time: 30 minutes, viewers: 100 people), Basic broadcasting rights (broadcasting time: 30 minutes, viewers: 500 people), Pro broadcasting rights (broadcasting time: 60 minutes, viewers: 1,500 people), Premium There may be broadcasting rights (broadcasting time: 60 minutes, viewers: 5,000 people) and VIP broadcasting rights (broadcasting time: 60 minutes, viewers: 10,000 people). And, the broadcast title can be input within 50 characters. The broadcasting title may be input in numbers, English, Korean, special symbols, and the like.

The broadcasting date can be selected by clicking the calendar icon and selecting it in the calendar pop-up window. The broadcasting start time can be selected from AM/PM, 00 to 23:00, and 0 to 59 minutes. The broadcasting end time is automatically input by adding time as much as the selected broadcasting right to the broadcasting start time.

And, restrictions on viewing (only members/all members (only members for chat) can be selected by the user. If only members are selected, the manager device allows only logged-in shopping mall members to watch the broadcast. If If all members are selected, the administrator device allows non-members to watch, but it may be impossible for non-members to participate in chatting, and the administrator device displays an error message saying “Please use after logging in” when non-members enter chatting.

And, when the cancel button on the detailed screen of the schedule is clicked, the manager device displays a pop-up window saying “Reserved broadcast information is canceled.” If “Yes” is clicked on the pop-up window, the written content is deleted, Display the schedule again. If “No” is clicked on the pop-up window, the manager device maintains the corresponding screen as it is. And, when the save button is clicked on the pop-up window, the manager device stores the written contents and outputs the schedule.

And, the broadcasting means item of the program schedule provides a function for selecting whether to perform live broadcasting with a camera or a mobile phone. In the case of live broadcasting by camera broadcasting, the manager device displays the Stream Name on the reservation detail page after reservation.

In addition, the manager device provides a function of providing a product search screen so that the user can purchase a product according to a search word or input condition. Basically, the manager device loads the entire product list, and when a user's search word or condition is input, a product list that meets the search word or condition is displayed. In addition, the manager device may separately display the searched product list screen and the selected list screen. Then, the manager device displays a list of products selected for live broadcasting.

Further, when the user selects a product from the searched product list and clicks an arrow button, the manager device moves the selected product to the selected product list. Here, multiple products can be selected and moved to the selected product list.

When the user selects a product from the selected product list and presses an arrow button, the manager device may move the product selected from the searched product list to the selected product list. Similarly, multiple products can be selected and moved to the searched product list.

And, the manager device may display the LIVE video management screen. The LIVE video management screen is displayed in a list as many as the number of videos selected by the user. Here, when the number of selected images is 5, 10, 20, or 50, the manager device displays the selected number in the list. And, LIVE video can be searched for by broadcasting title. And, the manager device may download the video selected by the user and delete the video selected by the user among the downloaded LIVE videos.

The LIVE video management shows video information of a live broadcast. Displayed information may include a broadcast title, file name, file size, resolution, bit rate, playback time, upload date, and the like. If the 'preview' button for the video selected by the user is clicked, the manager device displays a pop-up window and plays the selected video. And, the manager device may display a list of products tied to the selected image on a pop-up window.

During live broadcasting, the manager device may display a selected product list.

When a specific product is clicked in the displayed product list, the manager device

Go to the product page related to the product. If the 'X' button displayed on the pop-up window is clicked by the user, the manager device closes the pop-up window and displays the previous screen.

Additionally, when the preview button is clicked by the user, the manager device displays a video player as a pop-up and plays the corresponding video. At this time, the manager device may pause the played video. When the video is paused, the pause button changes to a play button. In addition, the manager device may display a button capable of adjusting the video sound. Also, the played video may be displayed so that the video can be viewed in full screen. Here, the played video has a smaller video size so that it can be floated on the screen and followed. And, the user can move the image forward or backward by moving the Seek bar. A method of displaying an image may vary depending on the type of the image. That is, in the case of a vertical image, the manager device displays a vertical image in the middle of the screen according to the ratio, and in the case of a horizontal image, the manager device fills the screen and displays the horizontal image.

In addition, when the user clicks the product view button of the video view item on the VOD video management screen, the manager device may display a product list as many as the preset selected number value (three pieces, five pieces, etc.). For example, when a view of 5, 10, 20, or 50 items is selected, the manager device displays as many product lists as the selected number. And, the manager device may display the image through product name search. That is, the manager device displays an image linked to a product in a pop-up window. Also, the manager device may display numbers for turning pages at the bottom of the VOD video management screen.

When the 'product view' button is clicked in the video view item, the manager device displays a pop-up window related to the video view and plays the corresponding video.

In addition, when a button in the shape of a trash can is clicked in the pop-up window, the manager device deletes the corresponding image. In addition, the bar indicating the activation/deactivation of the pop-up window activates or deactivates an image connected to the corresponding product, and it is possible to set whether to display the corresponding image. Then, a video upload pop-up window is displayed, and when the video is uploaded, the manager device displays the video on the corresponding product.

A video file can be uploaded by selecting a file on the video upload screen. Here, the extensions of video files that can be uploaded are mp4, avi, mkv, ? etc. The capacity of an image file that can be uploaded may be limited to 2 GB. When the 'X' button is clicked on the video upload screen, the manager device cancels the video file upload and closes the displayed pop-up window.

25 is a diagram illustrating another example of a manager device UI proposed in the present specification.

That is, FIG. 25 is a UI related to a method of simultaneously transmitting a live video through an SNS related app or the like.

First, if it is not linked to an SNS-related app, if the 'Link' button (2510) is clicked on the SNS-related app linkage screen, it is connected to an SNS-related app such as Facebook or YouTube, and you can post after logging in. authority is set. And, if it is already interlocked with the SNS-related app, if the 'disconnect' button is selected, the manager device disconnects the interworking with the SNS-related app (SNS-related platform).

The manager device may provide to select a timeline exposure position of an SNS-related app when simultaneously transmitting live broadcasting. The exposure position may be selected from a timeline, a page, or a group.

In addition, the SNS-related app-linked screen may include permission setting items for viewing live broadcasting. Permission setting items can be as follows.

- Public: You can watch everyone regardless of whether you follow them or not

- Friends Only: Only users who are friends can watch

- Specific Friends: Only friends you set can watch

- Only me: Only me can watch

In addition, the SNS-related app-linked screen may include an item 2520 for setting simultaneous broadcasting on/off. This item can be activated only when the account is linked. When set to ON, the manager device transmits simultaneous broadcasting to the corresponding platform or SNS during live broadcasting.

For reference, in the case of broadcasting live broadcasting through a camera, the manager device guides live broadcasting through the camera through XSplit.

Let's take a look at how to set AlimTalk (eg, Kakao AlimTalk, etc.) on the administrator's device.

When the user inputs all required information on the Notification Talk setting screen provided by the manager device, the manager device can provide Notification Talk to broadcasting devices or viewer devices. Here, when setting notification talk, when the user clicks the file selection button on the business registration tab of the notification talk setting screen, the manager device displays an image upload window. At this time, the user can upload a business license in the form of an image file. At this time, the size of the image file is 1 MB or less, and only jpg or png files are allowed.

In addition, the notification talk setting screen may include a category item for selecting a category for broadcasting. Here, the types of businesses that can be selected are furniture/interior, electronics, living/kitchen/stationery, food, clothing, fashion accessories, flower delivery/gifts, hobbies, general shopping malls/department stores, home shopping, social commerce, network marketing shopping malls, and purchasing agencies. , etc.

In addition, the notification talk setting screen may include a mobile phone number authentication item. When the user inputs a mobile phone number in the corresponding item and clicks Send authentication number, the manager device transmits the authentication number to the input mobile phone. Here, the mobile phone number should be the same as the number authenticated when signing up for Plus Friend, for example, when the notification talk setting is Kakao Talk notification talk. Also, when entering a mobile phone number, a high phone (-) may be excluded and inputted.

The notification talk message checked on the notification talk setting screen can be transmitted to the viewer's device when broadcasting starts or ends.

When the 'Edit' button on the AlimTalk message sending screen is clicked, the manager device is activated to edit the text of the AlimTalk message window. Here, when the 'modify' button is clicked, the manager device changes the edit button to a save button. And, when the user changes the phrase in the activated message window and clicks Save, the manager device applies the changed phrase as a new notification talk message.

In addition, the manager device may provide a screen for charging AlimTalk to send AlimTalk messages. The screen for charging the Notification Talk may include the number of Notification Talk cases that currently remain and a list of Notification Talk that can be charged. Here, only one AlimTalk charge can be selected.

Here, payment for charging the AlimTalk is possible only with a credit card. The manager device displays payment information suitable for the selected number. The payment amount is the price of the selected number of cases plus 10% VAT. If the user clicks the payment button, the manager device proceeds with the payment in conjunction with the PG company.

Next, a method of creating a broadcasting account and granting broadcasting authority will be described.

An ID for setting a broadcasting account may be a combination of 4 to 10 digits of English numbers. If an ID format different from the defined ID format is entered, the manager device displays an error message. Here, on the permission setting screen, the name may be input in Korean or English with 2 to 20 digits. If a name format different from the defined name format is entered, the manager device displays an error message. In the authority setting screen, the password can be input from 6 to 20 digits in a combination of English numbers. If a password format different from the defined password format is entered, the administrator device displays an error message.

In addition, for password confirmation, the same contents as those entered in the password must be input, and if they are different, the manager device displays an error message.

When ID, name, password, and password confirmation are all entered, the manager device can create a broadcasting account. If there are fields that have not been entered, the manager device displays an error message. A list of administrator accounts created by the above procedure can be displayed. Through the broadcasting authority On/Off function, broadcasting authority for each account can be granted. In addition, a function of deleting a selected account may be provided.

1 to 9, that is, description of AI or machine learning, which was previously salpin', can be applied to an image recognition method using machine learning to be described later, or can be specified or supplemented with details to be described later.

26 is for an image recognition method using machine learning proposed in this specification.

It is a diagram showing a flow chart of the operation method of the machine learning server.

First, the data collection server collects data through an external DB or through data crawling on the web (S2610).

Thereafter, the data collection server performs data quantification through inspection and search of the data collected through step S2610 (S2620).

The data set processed through step S2620 is input to the machine learning server.

The machine learning server is implemented separately from the data collection server, but the data collection server and the run learning server may be included in one server.

The machine learning server performs pre-processing and refinement on the data set (S2630).

Then, the machine learning server performs modeling and training (S2640), and evaluates data through it (S2650). The modeling and training may utilize the methods described in FIGS. 1 to 8 . Here, the machine learning server may utilize the test data for data evaluation after pre-processing and refining in step S2630.

That is, step S2650 may be a step of extracting data that satisfies a specific condition through modeling and training (or machine learning) in which a large amount of data that has passed through step S2630 is compared with product-related test data.

The test data may mean data related to a product to be compared with the collected data.

If the data evaluation passes in step S2650, the machine learning server transmits the data for which evaluation is completed in step S2650 to the broadcast transmission app (or broadcasting device) and the VOD server (S2660). If the data evaluation does not pass in step S2650, the machine learning server performs step S2640.

Through this procedure, the broadcasting device can provide information about the live video broadcasting proposed in this specification and related products using data of higher quality.

The data collection server and machine learning server of FIG. 26 may be implemented separately from the Salpin manager device described above.

In addition, using the salpin machine learning (eg, deep learning) technology described above, the broadcasting device may provide more accurate product information together with real-time live video to the viewer device.

Specifically, the AI device (the AI device may be implemented separately or in a manager device) may learn images and/or detect product information in images through the process of FIG. 26 and the like. Here, learning for detecting product information in an image may include detailed product information, product price comparison, information about a seller in an image, location information of a product, and the like.

Thereafter, the AI device transmits the result of the learning to a broadcasting device, and the broadcasting device may provide real-time live video and product information to a viewer device based on the result of the learning.

In addition, when detecting a product, the AI device may produce a clip image related to the product automatically detected by a digital video recorder (DVR) and provide it as an option item of the product when providing product information. Accordingly, the viewer device may receive product information including the clip image as an option item of the product, and when the clip image is selected by the user, the viewer device may output the clip image. In this case, the output clip image may be provided in various colors.

The information on the seller may include the seller's sales status, and the seller's sales status may include video recording. In this case, when the AI device detects a seller's sales situation, such as video recording, the AI device may also provide price tagging of the detected product when detecting a product.

27 is a diagram showing an example of a live image recognition method proposed in this specification.

In FIG. 27 , a broadcasting device may be simply expressed as a broadcasting app or a device equipped with a broadcasting app for convenience of description.

First, the broadcasting device captures an image using a camera (S2710). Here, the captured video is transmitted to the CDN server based on RTMP, and the live video can be provided to the viewer device based on HLS from the CDN server.

Alternatively, in order to relay a multi-party video call, the HLS structure in WebRTC rather than the HLS structure in RTMP may be used. That is, the video captured by the broadcasting device may be transmitted to the CDN server based on WebRTC, and the live video may be provided to the viewer device based on HLS from the CDN server.

Thereafter, the broadcasting device extracts image data related to the product from the photographed image (S2720).

Thereafter, the broadcasting device detects product data from the extracted image data using the model data received from the salpin machine learning server in FIG. 26 (S2730).

Thereafter, the product data may be broadcast live through the server.

Let's take a closer look at the WeRTC-HLS structure we looked at earlier.

The broadcasting device may classify inquiries or inquiries in the chat window looked at above, and select candidates (approximately 2 to 5 candidates) for exchanging conversations with the seller based on the classification. The selected candidates may be selected from a list of about 100 candidates.

The broadcasting device transmits conversation contents between the seller and the selected candidates to a specific server (media server), and the specific server may relay the received conversation contents to a plurality of candidates.

In addition, the broadcasting device transmits the contents of the conversation between the seller and the selected candidates to the AI device, and the AI device extracts product information, price comparison information, information about the seller in the video, and location information from the video. and transmits the information to the broadcasting device, and the broadcasting device may provide information received from the AI device when providing product information.

If an AI device is implemented in a broadcasting device, the broadcasting device uses an AI algorithm (eg, machine learning, etc.) to provide product information, price comparison information, seller information in the image, location information, etc. can be extracted from and provided together with product information.

28 shows an example of an operating method of a viewer device for a live broadcast image recognition method proposed in this specification.

First, the viewer device outputs a live broadcasting image transmitted from the broadcasting device through FIG. 27 (S2810).

Thereafter, the viewer device checks whether the product image is displayed during live video output (S2820).

If it is a section where a product image appears, the viewer device detects the product (S2830) and determines a method for outputting corresponding product information (S2830).

Here, a method of outputting product information may be (1) displaying product information in text, (2) slow image processing of a product section, (3) zoom-in of a product image, or (4) product information pop-up.

Thereafter, when the viewer device detects continuous display of product information, the viewer device displays detailed product information (S2840).

Thereafter, the TKDRL viewer device checks whether to purchase a product (S2850).

If product purchase is detected, the viewer device outputs a product purchase screen (S2860), and if product purchase is not detected, the viewer device displays a live video screen or ends the live video (S2860).

If continuous display of product information is not detected, the viewer device outputs a live video screen (S2870).

Additionally, the broadcasting device may provide information for inducing product purchase along with product information by combining voice synthesis, image synthesis, and AR technologies with the previously salpin AI algorithm. Specifically, the broadcasting device applies AR technology and image synthesis to output a seller image (eg, seller's face) on the AR screen of a viewer device, and applies voice synthesis to output the seller's video with the voice of a specific person (eg, lover). can be output.

That is, the broadcasting device may provide the seller's face synthesized with a specific person's voice to the viewer device, and the viewer device may output the received seller's face on the AR screen.

29 is a diagram showing an example of a shortcut image recognition method proposed in this specification.

First, the photographing device photographs a video and uploads the photographed video to a VOD server (S2910).

Next, the VOD server stores the VOD (S2920) and detects the product using the model data received from the machine learning server (S2930). Here, the VOD server may determine the exposure location, exposure time, and exposure information of the product. And, the VOD server can transmit/receive product data and image data with an external DB.

The viewer device plays VOD through a VOD viewing app (S2940).

Then, the viewer device checks whether it is a section where a product image appears (S2950).

If it is a section where a product image appears, the viewer device detects the product (S2960) and determines a product information exposure method (S2960).

Here, a method of exposing product information may be one of the four methods shown in FIG. 28 .

Subsequent steps are the same as those of FIG. 28, so detailed descriptions thereof will be omitted.

Hereinafter, a method of producing/editing and sharing a “short video” including product information in the video commerce system proposed in this specification will be described.

The short video refers to a short video of a specific part (eg, an impressive part), and may be expressed as a short cut, short video, short clip, snack video, or clip image. Hereinafter, for convenience of explanation, a short video will be collectively referred to as a “short clip”.

The content related to the production of the short cut described above may be combined with or supplemented with the method of producing/editing and sharing the short clip described later.

Of course, the contents to be described later can be equally applied to methods of producing/editing and sharing not only short clips but also entire videos.

30 shows an example of a conceptual diagram of a video commerce system for producing and sharing short clips proposed in this specification.

As shown in FIG. 30 , the video commerce system 200 may include a video commerce platform 210 , a provider device 220 and a user device 230 . The user device and the provider device may be connected to the video commerce platform through a wired/wireless network.

The video commerce platform may perform the same function as the above-described manager device (or manager platform) or may perform a function including both a manager device and a broadcasting device.

The provider device refers to a device that produces and edits a short clip and provides the produced short clip to a video commerce platform and a user device, and the user device receives the produced or edited short clip from the video commerce platform and produces a short clip. It refers to a device capable of viewing, and may be the same as or including the above-described viewer device. In addition, the user device may perform a function of a provider device that produces and edits short clips.

The video commerce platform 210 may provide a short clip production tool according to a short clip production request from a provider device. When the video commerce platform receives a short clip produced using a short clip production tool from the provider device, it stores the received short clip and allows the user to share it. In addition, the short clip production tool provided by the video commerce platform may be capable of producing images as well as short clips.

The video commerce platform includes a user interface for selecting a picture that is the background of a scene, an object to appear (or a person or a virtual person), a special effect to be applied, and a product to configure at least one scene (or scene). A short clip production tool can be provided.

Also, the video commerce platform may provide a streaming file for a short clip according to a request of the user device.

At this time, the user interface through which the streaming file is provided to the user device is composed of an area for searching for at least one short clip included in the short clip list and an area for a product list related to the appearing object, and the video commerce platform When a user's selection input for a specific product is received from the product list related to the appearing object of the user device, detailed information of the specific product and a screen for purchase may be displayed.

The user device 230 is a device owned by a user or a computing device installed in a specific place, and may have a short clip shooting and sharing service providing application installed therein. The user device may receive the short clip uploaded from the provider device through the short clip shooting and sharing service providing application through the video commerce platform and provide the short clip to the user.

In addition, the user device transmits a request for a specific short clip shooting mode to the video commerce platform through a short clip shooting and sharing service providing application, and the video commerce platform transmits the short clip shooting mode requested by the user device to the user. can provide

The provider device 220 is a device possessed by a person who produces a short clip or a computing device installed in a specific place, and may have a short clip shooting and sharing service providing application installed therein. The provider device may request a short clip production tool through a short clip shooting and sharing service providing application, receive the corresponding tool, and provide it to the short clip producer. In this case, when the short clip producer is a user, the provider device and the user device may be the same.

For example, a user possessing the user device can create/edit and share a specific short clip by becoming a short clip producer.

The video commerce platform may also provide a short clip production tool at the request of the user device, and the user device may receive it and provide it to the user.

That is, through the user device, the user can create or edit a short clip through a short clip shooting mode uploaded by a short clip producer, and the user himself/herself can become a short clip producer and produce a short clip.

Hereinafter, a short clip creation tool provided to a provider device for providing a short clip shooting and sharing service proposed in this specification will be described in detail.

When the provider device transmits a request for a short clip production tool to the video commerce platform, the provider device may receive a user interface related to short clip production from the video commerce platform.

That is, the short clip produced through the provider device may be produced including one or more scenes. The scene may consist of a background, a character (or person or virtual person), special effects, products, etc., and a plurality of backgrounds, a plurality of characters, and a plurality of special Effect, a plurality of products can be provided. Also, each scene may be identified based on a template file for a background image. A template file for a background image may be provided to a provider device through a background list described later.

The short clip production tool user interface may provide a scene list, a background list, appearance objects, special effects, and merchandise to the short clip producer through the provider device.

When receiving a selection input for background, appearing object, special effect, and product, the provider device may create a scene by applying the selected input background, appearing object, special effect, and product.

At this time, the special effect plays a secondary role of the scene, can be a tool that connects the content with the scene when shooting a short clip, and can set the time for the special effect to appear when the short clip is played. The special effect may be a specific sound, an image of a specific shape appearing at a specific location, or an animated image in which a specific shape changes into another shape appearing at a specific location.

In addition, the special effect used for shooting the short clip may be a sound source or music suitable for the short clip or a specific scene of the short clip.

Also, a special effect included in an image or short clip uploaded by a provider device and a special effect provided to a user device may have the same properties.

Hereinafter, a user interface and a short clip shooting mode provided to a user device in a method for providing a short clip shooting and sharing service will be described in detail.

The video commerce platform provides a user interface to a user device in which a short clip shooting and sharing service providing program (application) is stored, and the user interface may provide a short clip uploaded by a short clip producer.

The user interface consists of an image uploaded by a short clip producer or an image including a short clip or an area for searching for at least one image or short clip included in a short clip list and an area for a product list related to an appearing object. And, when a selection input for a specific product is received from the product list, detailed information of the specific product may be provided.

For example, a short clip search page is provided to the user through a user device, a list of a plurality of scenes is provided on the short clip search page, and when a selection input for any one scene among the plurality of scenes is received, the corresponding A short clip produced by another user for a scene may be provided.

In addition, a product list related to an object appearing in the scene is provided on the short clip search page. When a selection input for a specific product is received from the corresponding product list, detailed information on the specific product and a screen for purchase are provided It can be.

When a selection input for any one scene is received through the user device, another user's short clip list page related to the one scene may be provided to the user device.

The other user's short clip list page may be configured with an area where at least one short clip included in the other user's short clip list can be searched and a short clip shooting mode button.

The short clip of another user may have a special effect previously generated through a supplier device applied, and the corresponding short clip may include related product information.

In this case, another user's short clip for a specific scene may be automatically played, and after one video is finished, another video may be played randomly or in the order of high user preference.

In addition, among the short clips of the short clip list uploaded by other users, only videos corresponding to the length of a specific section including the specific scene may be collected and provided to the user device.

In addition, when a streaming file for any one short clip of the short clip list is provided to the user device, the user's facial expression is recognized through the camera of the user device, and when a preset facial expression is recognized, the streaming file is provided to the short clip provided. Emotion data may be automatically counted.

In other words, if a streaming file for a specific short clip is provided and the user's expression of joy, such as smiling or smiling, is recognized through the camera of the user device while the short clip is playing, 'Like' for the short clip A numerical value of preference information such as ' may be counted.

As an additional embodiment, when a short clip registered by another user does not exist for a specific scene selected by the user, a tutorial video for shooting a short clip using a short clip shooting mode may be played.

When receiving a selection input for the short clip shooting mode button, the user device may transmit a request for the short clip shooting mode to the video commerce platform. At this time, identification information about which image of a certain short clip producer or which scene of a short clip is in the requested short clip shooting mode may be transmitted to the video commerce platform.

When the video commerce platform receives the corresponding request, it may refer to the corresponding identification information and provide a corresponding short clip shooting mode to the user device.

The user can shoot a short clip by directing the arrangement or position, movement, color, etc. of the product that appeared in the scene, and the short clip is provided by overlapping special effects with the same properties as the special effects applied to the scene through the provider's device It can be. Specifically, the video commerce platform transmits the identification information on the special effect to the user device so that the short clip shooting mode in which the specified special effect overlaps with reference to the identification information on the scene is executed, and the short clip creator's image or short clip The same special effect as the existing special effect may be provided in the short clip shooting mode of the user device.

That is, when a short clip is produced through a provider device, the appearance time may be set by applying special effects. The special effect serves to provide guide information to the user by being provided on the short clip shooting mode at the same time as the image provided from the provider device or the special effect of the short clip.

The applied special effect is set to appear at a predetermined time and for a preset time, so that the user can shoot according to the timing of the applied special effect.

In this case, a recording function may be supported so that a function for sound or music in relation to a special effect or a specific scene may be possible. A recording function may be provided at any time of shooting a short clip.

Also, at this time, the short clip shooting mode may be provided for a time corresponding to a playback time for a selected specific scene. As described above, after shooting a short clip using the short clip shooting mode, a confirmation page for the shot clip is provided through the user device, and the short clip can be re-shot or uploaded.

Additionally, after the upload of the short clips filmed through the user device is completed, a menu for synthesizing the short clips uploaded from the user device and the short clips of other scenes uploaded by other users into one short clip will be provided. can

Additionally, each user may capture all of the short clips through the short clip shooting mode, and then tag identification information on products appearing in the short clips to the short clips.

Hereinafter, a method for performing the short clip shooting and sharing service providing method proposed in this specification will be described in detail.

The video commerce platform provides a short clip production tool capable of producing a short clip according to a request of a provider device, receives a short clip produced by the short clip production tool from the provider device, and stores and shares the short clip with the user device. Also, the video commerce platform may receive an image other than a short clip from the provider device.

The short clip production tool includes a user interface for selecting a picture that is the background of a scene, an object to appear (or a person or a virtual person, etc.), a special effect to apply, and a product to configure at least one scene (or scene). It can be provided as a provider device.

In addition, the video commerce platform may provide an image or short clip including at least one scene and a product, uploaded from the provider device, to the user device.

The process of producing and editing a short clip on the provider device or the user device and uploading it to the video commerce platform is largely divided into (1) product selection procedure, (2) video information registration procedure, and (3) scene (or scene) registration procedure. , (4) a registered video editing procedure, (5) a thumbnail creation procedure, and (6) an uploading procedure.

When receiving a selection input for any one short clip from the short clip list provided from the user device, the video commerce platform may provide a streaming file for the selected short clip to the user device.

When receiving a selection input for any one short clip or any one scene of the short clip from the short clip list provided from the user device, the video commerce platform selects the selected short clip or a shot uploaded by another user related to the selected scene A clip list may be provided to the user device.

In addition, when the video commerce platform provides a short clip list uploaded by another user related to the selected scene to the user device, only the length of a specific section including the selected scene is collected from among the short clips in the short clip list. It can be provided to the user device.

The method of collecting the aforementioned short clips (or videos) or other short clips or videos (including short clips or videos reconstructed to a specific length) related to the scene selected from the short clips and providing them to the user device can be expressed as a video traversal search function. can

At this time, the user's facial expression is recognized through the camera of the user device, and when a preset facial expression is recognized, emotion data for a short clip provided with a streaming file may be automatically counted. That is, preference information for the corresponding short clip may be counted.

In addition, the user interface provided to the user device may include an area for searching for at least one short clip included in the short clip list and an area for a product list for products to be advertised or sold in the short clip. In addition, when receiving a selection input for a product corresponding to an appearing object in the product list, detailed information on the selected product and a screen for payment may be provided.

When a short clip creation request is received from the user device in an area where the short clip list of the user device is provided, the video commerce platform may provide a short clip shooting mode in which preset special effects are overlapped.

When a short clip shooting is performed through a user device, a preset special effect may be provided according to a predetermined timing, and a recording function may be provided.

Then, according to the upload input of the user device, the user device may add the captured short clip to the short clip list.

The special effect used for shooting a short clip can be an image of a specific shape appearing at a specific location on the user device and an animated image in which a specific shape changes to another shape appearing at a specific location on the user device. Special effects provided by the user device may be a special effect having the same properties as the special effect included in the short clip uploaded by the provider device.

In addition, the special effect used for shooting the short clip may be a sound source or music suitable for the short clip or a specific scene of the short clip.

That is, when a specific sound source is selected by a user and the video commerce platform receives the selected specific sound source from a user device, the video commerce platform analyzes the atmosphere of the specific sound source with a specific algorithm to produce the short clip or the short clip. The specific sound source may be overlapped with the clip scene, or a scene or special effect suitable for the specific sound source may be provided overlapping with the short clip or the scene of the short clip.

In addition, the short clip shooting mode is provided for a time corresponding to the playback time of the scene, but the special effect is provided on the short clip shooting mode at the same time as the image provided from the provider device or the special effect of the short clip, thereby providing a guide to the user can provide information.

31 is a flowchart illustrating an example of a method for capturing a video and providing a sharing service proposed in this specification.

In order to perform the method described later, the video commerce platform may be implemented by including the aforementioned wireless communication unit, storage unit, and control unit.

The video described in FIG. 31 can be interpreted in a broad sense that includes both short clips and full videos, and each step can be applied to both short clips and full videos.

First, the video commerce platform receives a request for producing a video from a provider device (S3101).

In addition, the video commerce platform provides a video production tool including a first user interface for selecting a background picture, an object to appear, a special effect, and a product for configuring at least one scene according to the request. Provided as (S3102).

And, the video commerce platform receives at least one video produced based on the video production tool from the provider device (S3103).

And, the video commerce platform provides a user device with a second user interface including an area in which at least one video included in the video list can be searched and a product list area in which at least one product included in the video can be viewed. It is provided (S3104).

And, when a specific video is selected from the video list, the video commerce platform provides a streaming file for the video to the user device (S3105).

Further, when a specific product is selected from the product list, the video commerce platform provides detailed information on the specific product and a payment screen for purchase to the user device (S3106).

And, when a specific scene (or scene) or a product in the specific scene is selected from the specific video, the video commerce platform provides at least one video related to the specific scene or a product in the specific scene to the user device. (S3107).

Here, the at least one video may be a short clip of another user corresponding to a video remade with a length of a predetermined section including the specific scene or a product within the specific scene.

In addition, the at least one video may be played randomly or sequentially in consideration of the priority of the user's preference for the at least one video when one video ends.

Here, the priority of the user's preference for the at least one video may be determined by the number of counts of emotion data generated based on recognizing the user's facial expression captured by a camera while the video is being played.

Additionally, the video commerce platform registers the produced video through purchase of broadcasting rights of the produced video and setting of at least one broadcasting condition, and simultaneously transmits the registered video through at least one social network service (SNS) application. Interlocking conditions for broadcasting may be set, and the registered video may be simultaneously transmitted to the at least one SNS.

Transversal search of image

Let's take a closer look at the cross-searching of images (e.g., short clips) and the methods of providing/selling the retrieved images.

32 and 33 are diagrams illustrating an example of traversal search of an image proposed in this specification.

First, the video commerce platform provides a short clip image to a user device in a real-time streaming method or a VOD method.

Then, the user device outputs the provided short clip image through the display unit.

In addition, in the specific screen 3210 of the short clip video while the short clip video is being played, the specific playback position 3230 of the progress bar 3220, the specific object 3240 on the screen of the short clip video, and the search window When a selection input for a search input or the like is detected (or when a selection input is received), the user device performs a search based on the information on the detected selection input and/or the title 3250 of the short clip image. and requests the video commerce platform to provide a plurality of short clip images related to the selection input.

Here, the progress bar may mean a UI displaying a playback position or playback level of a short clip image.

For example, when the title of the short clip image being output is 'how to upload a short video', the plurality of short clip images related to the selection input may be short clip images related to the short video upload method.

And, the video commerce platform provides the requested plurality of short clip images to the user device.

Here, the plurality of short clip images may be provided by an external server and received and provided by the video commerce platform, or may be images previously stored in the video commerce platform.

Here, the video commerce platform is provided with an AI device, particularly an AI processor, and can learn a plurality of short clip images collected from the inside or outside through a learning model.

More specifically, the video commerce platform uses a plurality of short clip images related to the selection input requested by the user device as training data through the learning data acquisition unit of the AI processor, and the learning model stored in the model learning unit of the AI processor can be learned through Through this, the video commerce platform can provide a plurality of more specific and accurate short clip images to the user device in response to a request related to a selection input of the user device.

In addition, the user device identifies the metadata (number of reviews, number of views, number of subscriptions, total playback length, etc.) of each of the plurality of short clip images provided, and displays the plurality of short clip images other than the currently playing short clip video screen. At least one of the number of reviews, the number of views, the number of subscriptions, or the length of the total playback time of the short clip video may be listed (3310) in the order of higher or lower order.

In addition, the user device may produce and provide all or part of the listed plurality of short clip images as new images.

Here, in order to produce some of the plurality of short clip images as a new image, the user device displays a short clip image included in the production of the new image at a specific location (eg, the top left corner of the screen) of each of the plurality of short clip images. A check box 3320 for checking whether to select can be output.

In this case, the new video can be produced and provided by collecting only the short clip video checked in the check box.

In addition, producing all or part of the plurality of short clip images as a new image may be performed not only in the user device but also in the video commerce platform.

That is, the video commerce platform may create a new video from all or part of the plurality of short clip images and provide the created new video to the user device.

Here, when the video commerce platform provides the new video to the user device, it may also provide price information for the new video.

When there are a plurality of new videos provided by the video commerce platform, the video commerce platform may include and provide price information for each video.

In addition, the user device may output the received new video and price information, and if any one video is selected by the user, perform a payment procedure for the selected video, and play the selected video after payment. there is.

The term “module” used in this document may refer to a unit including one or a combination of two or more of, for example, hardware, software, or firmware. “Module” may be used interchangeably with terms such as, for example, unit, logic, logical block, component, or circuit. A “module” may be a minimum unit or part of an integrally formed part. A “module” may be a minimal unit or part thereof that performs one or more functions. A “module” may be implemented mechanically or electronically. For example, a "module" is any known or future developed application-specific integrated circuit (ASIC) chip, field-programmable gate arrays (FPGAs), or programmable-logic device that performs certain operations. may contain at least one.

At least some of the devices (eg, modules or functions thereof) or methods (eg, operations) according to various embodiments may be stored on computer-readable storage media in the form of, for example, program modules. It can be implemented as a command stored in . When the command is executed by a processor, the one or more processors may perform a function corresponding to the command. The computer-readable storage medium may be, for example, a memory.

Computer-readable recording media include hard disks, floppy disks, magnetic media (eg magnetic tape), optical media (eg CD-ROM (compact disc read only memory), DVD ( digital versatile disc), magneto-optical media (such as floptical disk), hardware devices (such as read only memory (ROM), random access memory (RAM), or flash memory, etc.) ), etc. In addition, the program command may include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may include various It may be configured to act as one or more software modules to perform the operations of an embodiment and vice versa.

A module or program module according to various embodiments may include at least one or more of the aforementioned elements, some may be omitted, or additional elements may be further included. Operations performed by modules, program modules, or other components according to various embodiments may be executed in a sequential, parallel, repetitive, or heuristic manner. Also, some actions may be performed in a different order, omitted, or other actions may be added.

In the above, a preferred embodiment of the technology of this specification has been described with reference to the accompanying drawings. Here, terms or words used in this specification and claims should not be construed as being limited to ordinary or dictionary meanings, but should be interpreted as meanings and concepts consistent with the technical spirit of the present invention.

The scope of the present invention is not limited to the embodiments disclosed herein, and the present invention can be modified, changed, or improved in various forms within the spirit of the present invention and the scope described in the claims.

100: video commerce system
110: manager device
120: broadcasting device
130: user device

Claims (12)

A method for collecting and producing images related to a specific section of a video in a video commerce system, the method performed by the video commerce platform,
Receiving a request for producing a video from a provider device;
providing a video production tool including a first user interface for selecting a background picture for composing at least one scene, an object to appear, a special effect, and a product to the provider device according to the request;
receiving at least one video produced based on the video production tool from the provider device;
providing, to a user device, a second user interface including an area in which at least one video included in the video list can be searched and a product list area in which at least one product included in the video can be viewed;
When a specific video is selected from the video list, providing a streaming file for the specific video to the user device;
providing detailed information about the specific product and a payment screen for purchase to the user device when a specific product is selected from the product list; and
And if a specific scene or a product in the specific scene is selected from the specific video, providing at least one video related to the specific scene or a product in the specific scene to the user device. According to claim 1,
characterized in that the at least one video is a video of another user corresponding to a video re-produced with a length of a predetermined section including the specific scene or a product in the specific scene. According to claim 2,
The method of claim 1 , wherein the at least one video is played at random or sequentially in consideration of a user's preference for the at least one video when one video is finished. According to claim 3,
Wherein the priority of the user's preference for the at least one video is determined by the count number of emotion data generated based on the recognition of the user's expression captured by a camera while the video is being played. According to claim 1,
The method characterized in that the video is a short clip produced by briefly editing a specific part. According to claim 1,
registering the produced video by purchasing a broadcasting right of the produced video and setting at least one broadcasting condition; and
The method further comprising setting interlocking conditions for simultaneously broadcasting the registered video through at least one Social Network Service (SNS) application. In a video commerce platform for collecting and producing images related to a specific section of a video in a video commerce system,
A wireless communication unit for transmitting and receiving wireless signals to and from the outside;
a storage unit for storing video; and
Including a control unit functionally connected to the wireless communication unit and the storage unit, wherein the control unit,
Video production including a first user interface for receiving a request for video production from a provider device and selecting a background picture, an object to appear, a special effect, and a product for configuring at least one scene according to the request A tool is provided to the provider device, at least one video produced based on the video production tool is received from the provider device, and at least one video included in the video list can be searched. Provides a second user interface including a product list area in which at least one product can be searched to the user device, and when a specific video is selected from the video list, a streaming file for the specific video is provided to the user device and when a specific product is selected from the product list, detailed information on the specific product and a payment screen for purchase are provided to the user device, and a specific scene or a product within the specific scene is selected from the specific video, The video commerce platform, characterized in that for controlling to provide at least one video related to the specific scene or a product within the specific scene to the user device. According to claim 7,
The video commerce platform, characterized in that the at least one video is a video of another user corresponding to a video re-produced with a length of a predetermined section including the specific scene or a product in the specific scene. According to claim 8,
The video commerce platform, characterized in that the at least one video is played at random or sequentially in consideration of the priority of the user's preference for the at least one video when one video is finished. According to claim 9,
The priority of the user's preference for the at least one video is determined by the number of counts of emotion data generated based on the recognition of the user's facial expression photographed by a camera while the video is being played. Video commerce platform. The method of claim 7, wherein the control unit,
Registering the produced video through purchase of the broadcast rights of the produced video and setting of at least one broadcasting condition, and setting linkage conditions for simultaneous broadcasting of the registered video through at least one Social Network Service (SNS) application. A video commerce platform characterized by controlling to do so. delete

Images