KR20230011041A - Method and Sever for Providing Video Interaction Platform Performed - Google Patents

Abstract

The present invention relates to a method for providing a video interaction platform and a server system for performing the same and, more specifically, to a method for providing a video interaction platform that includes: providing a user with a specific image according to the position of a user in an image tree in an image tree composed of a plurality of images; moving the position of the user in the image tree according to the interaction of the user for the provided specific image; and finally providing a preset service according to one or more user interactions in the image tree, and a server system that performs the same. It is possible to arouse a user interest in participating in a service.

Description

Method and Server for Providing Video Interaction Platform Performed

The present invention relates to a method for providing a video interaction platform and a server system for performing the same, and more particularly, in a video tree composed of a plurality of videos, providing and providing a specific video according to a user's location in the video tree to the corresponding user. A method for providing a video interaction platform that moves a user's position in a video tree according to a user's interaction with a received specific video and finally provides a preset service according to one or more interactions of a user in the video tree, and performs the same It is about a server system that does.

Recently, as the demand for non-face-to-face services increases in society, various technologies for implementing non-face-to-face services are being developed. In particular, in order to provide non-face-to-face services suitable for users, a technology is being developed that provides users with a set of questions prepared in advance, such as a questionnaire, and provides suitable services based on the contents of the user's answers (interactions) to the questions.

Meanwhile, in the conventional case, a method of providing a text-based question set to a user and providing a service according to the answer selected by the user by allowing the user to select a specific answer from among a plurality of predetermined answers with respect to the question set has been developed.

However, in the case of the conventional technology, it is based on text, and the user selects a specific answer from among a plurality of pre-determined answers to the question, so there is a need for answering (interaction) to the question provided from the user's side. Since it is difficult to arouse interest and merely determines a specific option among predetermined options, it is difficult to provide a service that is very suitable for the user.

Therefore, there is a need to develop a new interaction platform to provide a more suitable service to the user while giving interest to the user's interaction.

The present invention relates to a method for providing a video interaction platform and a server system for performing the same, and more particularly, in a video tree composed of a plurality of videos, providing and providing a specific video according to a user's location in the video tree to the corresponding user. A method for providing a video interaction platform that moves a user's position in a video tree according to a user's interaction with a received specific video and finally provides a preset service according to one or more interactions of a user in the video tree, and performs the same Its purpose is to provide a server system that does.

In order to solve the above problems, in one embodiment of the present invention, as a method for providing a video interaction platform performed in a server system, the server system has a plurality of images for a video tree or a basis for generating a plurality of images. Image information including data, location condition information including a determination condition for determining a user's interaction with each image and location movement information for location movement according to the determination condition, and the user's location in the image tree or Result information corresponding to the user's interaction with the video is stored, the user's position in the video tree can be moved according to the user's interaction with the video, and the video interaction platform provides the video An image information providing step of providing a user with an image corresponding to the user's current position in the tree; a positioning step of determining the user's next position by applying position condition information corresponding to the user's current position in the image tree to the user's interaction with the image provided through the image information providing step; and a result information providing step of providing result information to the user when the user's location or the user's interaction with one or more images corresponds to a predetermined condition.

In one embodiment of the present invention, the result information corresponding to the user's position in the video tree or the user's interaction with the video includes other service connection information for providing other services to the user, and the video interaction platform In the providing method, when a user requests a connection to another service through the other service connection information provided through the result information providing step, user interaction including interaction with each of one or more images performed in the image tree It may further include a user interaction information transmission step of transmitting information to another service server performing the other service or an internal configuration of the server system performing the other service.

In one embodiment of the present invention, the result information corresponding to the user's position in the video tree or the user's interaction with the video includes other service connection information for providing other services to the user, and the video interaction platform In the providing method, when a user requests a connection to another service through the other service connection information provided through the result information providing step, one or more location information where the corresponding user is located in the image tree performs the other service. It may further include a user location history transmission step of transmitting to another service server or an internal configuration of the server system executing the other service server.

In one embodiment of the present invention, the result information corresponding to the user's location in the video tree or the user's interaction with the video includes other service connection information for providing other services to the user, and is included in the video tree. The selected specific image may be linked to service result information obtained by the user performing the other service.

In one embodiment of the present invention, the interaction includes at least one of text input, voice input, face information input, pose input, gesture input, and background information input for an image, and the positioning step includes the interaction with a machine. The user's next location may be determined by applying inference information input and output to the learned evaluation model and location condition information corresponding to the user's current location in the image tree.

In one embodiment of the present invention, the interaction includes a selection input for a specific option among a plurality of options for an image; and at least one input of text input, voice input, face information input, pose input, gesture input, and background information input for an image, wherein the positioning step includes a selection input for the specific option, a selection input for the image At least one input among text input, voice input, facial expression input, pose input, gesture input, and background information input is input to the machine learning evaluation model, and the inference information output and the position condition corresponding to the user's current position in the image tree The information can be applied to determine the user's next location.

In one embodiment of the present invention, the location movement information may include first location movement information for moving the user's location from an image corresponding to an interaction input by the user to another image according to the determination condition; and second location movement information for re-inputting an interaction with respect to an image corresponding to an interaction previously input by the user according to the determination condition.

In one embodiment of the present invention, the method for providing the video interaction platform includes a video tree creation interface that receives a plurality of videos according to a user's request and receives setting of location condition information and result information for each video. It may further include; production builder provision step provided to the user.

In one embodiment of the present invention, a plurality of video trees are stored in the server system, and the location movement information of the video trees is based on a determination condition according to a user's interaction with the video included in the corresponding video tree to another video. Third location movement information for moving the user's location to a specific image included in the tree may be included.

In one embodiment of the present invention, the result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user, and the providing result information step Other services connected to other service connection information provided in may derive response information for user interaction through a machine-learned evaluation model, and provide the user with an object that ignites according to the response information.

In order to solve the above problems, in one embodiment of the present invention, as a server system that performs a method of providing a video interaction platform, the server system includes a plurality of images for a video tree or a basis for generating a plurality of images. Image information including data, location condition information including a determination condition for determining a user's interaction with each image and location movement information for location movement according to the determination condition, and the user's location in the image tree or Result information corresponding to the user's interaction with the video is stored, and the user's position in the video tree can be moved according to the user's interaction with the video, corresponding to the user's current position in the video tree. Image information providing step of providing the image to the user; a positioning step of determining the user's next position by applying position condition information corresponding to the user's current position in the image tree to the user's interaction with the image provided through the image information providing step; and a result information providing step of providing result information to the user when the user's location or user's interaction with one or more images corresponds to a preset condition.

According to an embodiment of the present invention, by providing a video tree based on a video to a user, it is possible to exert an effect of arousing interest in service participation of the user.

According to an embodiment of the present invention, at the final stage of the video tree, one or more positions of the user in the video tree or user interaction information is provided to another service server or other service providing unit of the server system that provides other services to the user. However, it can exert an effect of providing other services that are more suitable for users.

According to an embodiment of the present invention, since other services are provided to users through a video tree, and service result information derived by the user receiving other services is connected to a specific video in the video tree, various types of services are provided to users. can exert the effect that can provide.

According to an embodiment of the present invention, the user can input various interactions with respect to the images of the image tree, and since the user's interactions can be input to the machine-learned evaluation model to derive the discrimination condition, a preset option is selected. Compared to the conventional method of doing so, it is possible to exert an effect of arousing the user's interest and at the same time providing more accurate other services to the user.

According to an embodiment of the present invention, since a video tree creation interface is provided to a user so that the user can directly build a video tree, an effect of activating a video interaction platform can be exhibited.

According to an embodiment of the present invention, since the user's position can be moved to a specific video of another video tree according to the user's interaction with the video of the video tree, a plurality of video trees are linked to provide various other services to the user. You can exert the effect you can.

1 schematically illustrates components performing a method of providing a video interaction platform according to an embodiment of the present invention.
2 schematically illustrates internal components of a server system according to an embodiment of the present invention.
3 schematically illustrates an image tree according to an embodiment of the present invention.
4 schematically illustrates detailed steps of a method for providing a video interaction platform according to an embodiment of the present invention.
5 schematically illustrates a user interaction information transmission step and a user location history transmission step according to an embodiment of the present invention.
6 schematically illustrates a process of deriving inference information according to an interaction input by a user with respect to an image according to an embodiment of the present invention.
7 schematically illustrates the internal configuration of a feature extraction model according to an embodiment of the present invention.
8 schematically illustrates the internal configuration of a feature inference model according to an embodiment of the present invention.
9 schematically illustrates a configuration in which a plurality of image trees are connected according to an embodiment of the present invention.
10 schematically illustrates movement of a user's location according to user interaction in a video tree according to an embodiment of the present invention.
11 schematically illustrates an image tree creation interface according to an embodiment of the present invention.
12 schematically illustrates a process of providing other services according to an embodiment of the present invention.
13 schematically illustrates the internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are disclosed with reference now to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth in order to facilitate a general understanding of one or more aspects. However, it will also be appreciated by those skilled in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings describe in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in principle of the various aspects may be used, and the described descriptions are intended to include all such aspects and their equivalents.

Moreover, various aspects and features will be presented by a system that may include a number of devices, components and/or modules, and the like. It should also be noted that various systems may include additional devices, components and/or modules, and/or may not include all of the devices, components, modules, etc. discussed in connection with the figures. It must be understood and recognized.

"Example", "example", "aspect", "exemplary", etc., used herein should not be construed as preferring or advantageous to any aspect or design being described over other aspects or designs. . The terms '~unit', 'component', 'module', 'system', 'interface', etc. used below generally mean a computer-related entity, and for example, hardware, hardware It may mean a combination of and software, software.

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. It should be understood that it does not.

In addition, terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not 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. The terms and/or include any combination of a plurality of related recited items or any of a plurality of related recited items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are generally understood by those of ordinary skill in the art to which the present invention belongs. has the same meaning as Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the embodiments of the present invention, an ideal or excessively formal meaning not be interpreted as

1 schematically illustrates components performing a method of providing a video interaction platform according to an embodiment of the present invention.

As shown in FIG. 1 , the method of providing a video interaction platform may be performed by communicating with a user terminal in the server system 1000 . Specifically, the service user may request another service to be provided from the server system 1000 or an image tree to perform an interaction through the corresponding user terminal 2000.1, and the server system 1000 may request the user terminal 2000.1 By providing a video tree corresponding to the other service or a video tree corresponding to the request, the service user can interact with the video tree.

A user (service user) who receives the video tree performs an interaction with the first video of the video tree, and the server system 1000 provides the next video according to the interaction input by the user with respect to the first video. By performing interactions with the images of the image tree that are sequentially provided, other services may be finally provided according to one or more interactions of the corresponding user. That is, a plurality of images are included in the image tree, and each of the plurality of images may have a specific position. Therefore, the user using the image tree is initially located at the first image of the image tree, and when the user interacts with the first image, the user can move to the image corresponding to another location according to the interaction. In this way, the user's position in the image tree can be moved by the user performing one or more interactions, and when the user is located in a specific image among one or more final images of the image tree, or the user's specific interaction in one or more specific images When inputting , other services corresponding to the specific video may be provided.

Meanwhile, the video interaction platform performed by the server system 1000 of the present invention may directly provide other services, but as shown in FIG. 1, the other services are provided to the user through a separate other service server 3000. can be provided. Therefore, when the user is located in a specific image among the final images of the image tree or the user inputs a specific interaction in the specific image, the server system 1000 provides other service connection information to the user, and the user receives the other service It is possible to receive the other service by performing communication with the separate other service server 3000 through the connection information. On the other hand, the other service server 3000 can provide one or more other services to the user, and although the server system 1000 is shown in FIG. 1 as communicating with one other service server 3000, this In another embodiment of the invention, when there are a plurality of other services connected through the server system 1000, the server system 1000 may communicate with a plurality of other service servers 3000. Also, in another embodiment of the present invention, the other service may be provided through the other service provider 1700 included in the server system 1000.

In addition, the method of providing a video interaction platform performed by the server system 1000 not only provides the stored video tree to the user and provides other services according to the user's interaction, but also according to the user's (service builder's) request. An interface for the corresponding user to directly create an image tree may be provided. Specifically, when a user terminal (2000.2) of a user (service builder) requests an interface for generating an image tree from the server system 1000, the server system 1000 provides the interface to the user terminal 2000.2 and , the user (service builder) can configure the image tree through the interface. The video tree configured in this way can be used by other users (service users).

In one embodiment of the present invention, each of the user terminals (2000.1 and 2000.2) connects to the server system 1000 through a separate application or a separate web page in order to receive a video interaction platform through the server system 1000. It is possible to perform communication, and accordingly, the separate application is installed in each user terminal (2000.1 and 2000.2), or the separate web page is installed through a web browser installed in each user terminal (2000.1 and 2000.2). can access In addition, the user can create an account to access the server system 1000 through the application or the web page, and the user terminals 2000.1 and 2000.2 can access the server system 1000 through the account information input from the user. ) to receive a video interaction platform.

2 schematically illustrates internal components of a server system 1000 according to an embodiment of the present invention.

As shown in FIG. 2, the server system 1000 performing the method of providing a video interaction platform includes a video information providing unit 1100, a positioning unit 1200, a result information providing unit 1300, and a user interaction information transmitting unit. 1400, a user location history transmission unit 1500, a manufacturing builder providing unit 1600, a third-party service providing unit 1700, a machine-learned evaluation model 1800, and a DB 1900.

The server system 1000 includes a plurality of images for a video tree or image information including basic data for generating a plurality of images, a determination condition for determining a user's interaction with each image, and a location according to the determination condition. Location condition information including location movement information about movement and result information corresponding to the user's location in the image tree or the user's interaction with the image may be stored.

Specifically, the image information, the location condition information, and the result information may be stored in the DB 1900. The image information includes a plurality of images included in the image tree or basic data for generating a plurality of images. In one embodiment of the present invention, when an image tree is provided to a user, a specific image corresponding to a corresponding position among the plurality of images may be provided to the user according to the user's position in the image tree. In an example, when an image tree is provided to a user, the server system 1000 automatically generates an image according to the user's location in the image tree, and the generated image may be provided to the user. The basic data may correspond to an element for automatically generating an image in the server system 1000 . Specifically, the basic data may correspond to data for automatically generating an image corresponding to the user's input through a separate machine learning model according to the user's input in the server system 1000, like the conventional AI human. can

The location condition information includes determination conditions and location movement information. The determination condition corresponds to information for determining an interaction input by the user with respect to each image of the image tree provided to the user, and more specifically, the determination condition may include one or more detailed determination conditions. For example, when a user inputs an interaction with respect to a video provided to the user, the server system 1000 determines whether the interaction is a positive response or a negative response to the corresponding video according to a determination condition for the corresponding video. can do. In this case, each of the positive response and the negative response may correspond to each detailed determination condition included in the determination condition. The location movement information corresponds to information for moving a user's location according to an interaction determined according to a determination condition for each image. For example, when it is determined that the interaction input by the user with respect to a specific video is a positive response to the specific video, the server system 1000 determines the user's location according to the location movement information for the specific video. It can be moved to an image or moved to a position where interaction can be input again.

The result information corresponds to information provided to the user when the user inputs an interaction in the image tree and is located in a specific image or inputs a specific interaction in the specific image. Specifically, the result information includes information about an analysis result of an image finally provided to the user according to one or more interactions input by the user in the image tree or an analysis result of one or more interactions input by the user, and the result information is may further include other service connection information for providing other services separate from interactions in the image tree to the user according to one or more interactions input in the image tree.

The other service connection information corresponds to information for connecting other services that are provided when a user inputs an interaction in a video tree and is located in a specific video or inputs a specific interaction in a specific video. Specifically, the image tree may include one or more other service connection information, and each other service connection information may be matched with one or more specific images of the image tree or a specific interaction in one or more specific images. Therefore, when the user is located in one of one or more specific images of the image tree or inputs a specific interaction with respect to one or more specific images among one or more specific images, the matched other service connection information is provided to the user. According to the interaction, the user communicates with the other service server 3000 or the other service provider 1700 corresponding to the internal configuration included in the server system 1000 through the other service connection information. Other services may be provided. In addition, as shown in FIG. 1 , user information for each user registered in the server system 1000 may be stored in the DB 1900 .

On the other hand, as shown in FIG. 1, the elements constituting the image tree (image information, location condition information, and other service connection information) are individually stored in the DB 1900, but in another embodiment of the present invention A plurality of image trees may be individually stored in the DB 1900, and image information, location condition information, and result information corresponding to the corresponding image tree may be included for each stored image tree.

As described above, the server system 1000 may perform the video interaction platform providing method through the image information, location condition information, and result information stored in the DB 1900.

Specifically, the image information providing unit 1100 provides an image tree corresponding to the user's request by performing the image information providing step (S10). Preferably, the image information providing unit 1100 responds to the user's request. Provides an image corresponding to the user's current location in the corresponding image tree. Through this, the user can input an interaction for the corresponding video.

The location determination unit 1200 determines the next location of the user according to the interaction input by the user with respect to the image provided to the user by performing the location determination step (S11). Specifically, the location determination unit 1200 determines the interaction input by the user with respect to the image according to the determination condition corresponding to the corresponding image, and determines the user's next interaction based on the determined interaction and the location movement information corresponding to the corresponding image. determine the location The next location determined by the location determination unit 1200 corresponds to an image different from the image provided to the user by the image information providing unit 1100, or the user returns to the image provided by the image information providing unit 1100. It may correspond to a position where an interaction can be input.

The result information providing unit 1300 performs the result information providing step (S13) to access other services when the location of the user in the image tree or the interaction input with respect to the image provided to the user corresponds to a preset condition. It provides the result information to the user. Specifically, one or more conditions may be preset in the image tree, and each of the one or more conditions may correspond to one or more other service connection information. Therefore, when the user is located in a video corresponding to a specific condition in the video tree or inputs an interaction corresponding to the specific condition, the result information providing unit 1300 includes other service connection information corresponding to the specific condition. result information can be provided to the user. In this way, the user can communicate with the other service server 3000 that provides other services or the other service provider 1700 included in the server system 1000 through the received other service connection information.

The user interaction information transmitting unit 1400 performs the user interaction information transmitting step to send the video tree to the other service server 3000 that provides other services or to the other service providing unit 1700 included in the server system 1000. Provides user interaction information including one or more inputted interactions. Through this, the other service server 3000 or the other service provider 1700 providing other services can receive the user interaction information and provide other services suitable for the user.

The user location history transmission unit 1500 performs the user location history transmission step to send the video tree to the other service server 3000 that provides other services or to the other service provider 1700 included in the server system 1000. Provides one or more location information that was located with respect to . Through this, like the aforementioned user interaction information transmitter 1400, the other service server 3000 or other service provider 1700 that provides other services receives the one or more location information and provides other services suitable for the user. can

As shown in FIG. 1, the server system 1000 includes both the user interaction information transmission unit 1400 and the user location history transmission unit 1500, and other service servers 3000 or server systems providing other services ( 1000), user interaction information and one or more location information where the user has been located in the image tree may be provided to the other service provider 1700, but in another embodiment of the present invention, the server system 1000 may provide the user interaction information Including only one of the transmission unit 1400 and the user location history transmission unit 1500, information of one of user interaction information and one or more pieces of location information to the other service server 3000 or the other service provider 1700 It is also possible to provide only

The fabrication builder provision unit 1600 performs the fabrication builder providing step and provides the image tree creation interface 1610 through which the user can directly create the image tree according to the user's request to the user terminal of the corresponding user. Through the video tree creation interface 1610, the user inputs video information, location condition information, and other service connection information corresponding to the elements constituting the above-described video tree to create a video tree, and the video tree creation interface 1610 Information input through ) may be stored in the DB 1900 of the server system 1000.

The other service provider 1700 provides other services to the user according to other service connection information included in the result information provided to the user through the result information provider 1300 . Specifically, the user is provided with other service connection information through which other services suitable for the user can be provided according to one or more interactions input on the video tree, and the other service provider 1700 is provided with other service connection information corresponding to the other service connection information. Services can be provided to users. Meanwhile, the other service may correspond to a service linked according to one or more interactions input by the user in the video tree provided to the user or one or more locations where the user was located in the video tree. For example, the image tree may correspond to determining the type of mental illness of the user, and when the type of mental illness possessed by the user is determined through the image tree, other services may determine the mental illness. It may correspond to a solution for treatment. In addition, the other service provider 1700 may provide a plurality of other services related to the image tree, and in another embodiment of the present invention, a plurality of other services corresponding to the number of other services related to the image tree. The study 1700 may be included in the server system 1000 individually.

The evaluation model 1800 receives an interaction input by a user with respect to an image included in a video tree and derives inference information about the interaction. Specifically, the evaluation model 1800 corresponds to the machine-learned evaluation model 1800, a feature extraction model that extracts feature values by receiving interactions, and a feature extraction model that derives inference information based on feature values derived from the feature extraction model. Feature inference models may be included. In this way, in the present invention, through the evaluation model 1800, a corresponding interaction can be inferred not only for an interaction in which a user selects a specific option from among preset options, but also for an unstandardized interaction.

As shown in FIG. 2, the server system 1000 of the present invention is composed of a single server, and all internal components of the server system 1000 may be included in the single server, but in another embodiment of the present invention, the The server system 1000 may be composed of a plurality of servers, and one or more of the internal components of the above-described server system 1000 may be included in the plurality of servers, and the plurality of servers may communicate with each other. there is.

3 schematically illustrates an image tree according to an embodiment of the present invention.

As shown in FIG. 3, the image tree may be composed of a plurality of images. Specifically, the image tree is connected to a plurality of images corresponding to the image tree stored in the DB 1900, or the image tree includes only an initial image, and the interaction input by the user with respect to the initial image, the The image tree may be configured in such a way that a next image is automatically generated from the initial image based on location condition information for the initial image and basic data corresponding to the image tree.

As shown in FIG. 3, each of the plurality of images included in the image tree may include a unique position value, and when the user interacts with the image tree, the user's initial position in the image tree ( The video (video #1) corresponding to the position P1) is provided to the user, and when the user inputs an interaction (interaction #1) with respect to the video (video #1), the user's position in the video tree moves. It can be.

Specifically, the image tree may include conditions for determining an interaction input by a user for each image and moving a location to another image according to the determined interaction. The condition may correspond to the above-described location condition information. More specifically, when a user inputs an interaction with respect to an image corresponding to the user's current location in the image tree provided by the image information providing unit 1100, the location determining unit 1200 determines the corresponding image The interaction is determined according to conditions, and the next location of the user is determined according to the determined interaction and location movement information for the corresponding image.

For example, as shown in FIG. 3 , when the user's current position in the video tree is video #1 and the user inputs interaction #1 with respect to the video #1, the positioning unit 1200 may determine the user's next location as image #2 (position P2) based on the location condition information corresponding to interaction #1 and condition #1 input by the user.

In this way, the process of providing the user with an image corresponding to the user's current location in the image tree and determining the next location according to the user's interaction in the image is the process of determining the user's location or the interaction input by the user in advance. It can be repeated sequentially until the condition is satisfied.

Specifically, for images to which position condition information is not connected in the image tree, such as image #4, image #5, image #6, image #8, image #9, image #10, and image #11 shown in FIG. When the user's location is moved to the corresponding location, the result information providing unit 1300 determines that the user's location satisfies a preset condition and provides result information including other service connection information corresponding to the corresponding location to the user. can be provided to In addition, even when a user inputs a specific interaction for an image to which location condition information is connected, the result information providing unit 1300 determines that the specific interaction input by the user satisfies a preset condition, Result information including other service connection information corresponding to a specific interaction input in the video may be provided to the user.

For example, as shown in FIG. 3 , when the user's position is moved to image #10 (position P3) based on interaction #2 and condition #4 input with respect to image #2 (position P2). The result information provider 1300 may determine that the user's location satisfies a preset condition and provide result information including other service connection information corresponding to the image #10 to the user. In this way, the user accesses the other service server 3000 that provides other services corresponding to the image #10 or the other service provider 1700 included in the server system 1000 through the other service connection information provided. Other services corresponding to the above image #10 may be provided.

Meanwhile, the result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user, and the specific image included in the image tree It may be connected to service result information obtained by the user performing the other service.

Specifically, in one embodiment of the present invention, the service of the video interaction platform may end when the user is provided with another service through other service connection information included in the result information provided, but in another embodiment of the present invention, the user When other services are provided, the service result information derived from the other service server 3000 or the other service provider 1700 is connected to a specific image included in the image tree, so that the user can view the information from a location corresponding to the specific image. Interaction can be performed again.

For example, this corresponds to the case where the user has received another service for depression treatment by performing one or more interactions with an image tree for determining mental illness, and the service result information for the other service is to perform depression determination again. In the image tree, the user can interact at a position corresponding to a specific image (image #3 in FIG. 3) capable of re-determining depression.

In this way, in the present invention, since service result information provided from other services can be linked to a specific location of the image tree, various types of services such as feedback on other services can be provided.

Meanwhile, although the present invention describes an image tree composed of a plurality of images, in another embodiment of the present invention, a tree composed of a plurality of texts or a tree composed of a plurality of audios may be used, and the user may input an interaction for text corresponding to the current position in the corresponding tree or an interaction for audio corresponding to the current position.

4 schematically illustrates detailed steps of a method for providing a video interaction platform according to an embodiment of the present invention.

As shown in FIG. 4 , the method of providing the video interaction platform includes a video information providing step (S10) of providing a video corresponding to the user's current location in the video tree to the user; Position determination step (S11) of determining the user's next position by applying position condition information corresponding to the user's current position in the image tree to the user's interaction with the image provided through the image information providing step (S10) ; and a result information providing step (S13) of providing result information to the user when the user's location or the user's interaction with one or more images corresponds to a preset condition.

Specifically, in the image information providing step (S10), an image corresponding to the user's current location in the image tree requested by the user is provided to the user. Specifically, when an image is provided for the first time in a video tree requested by a user, the user may be provided with an image corresponding to the initial position, with the user's current position as the initial position in the corresponding video tree. In another embodiment of the present invention, the image information providing step (S10) does not simply provide the image corresponding to the current location to the user, but provides an interface in which the image corresponding to the current location is reproduced, and the user uses the interface Through this, the video can be played, and the interaction for the video can be input.

The user who has been provided with an image corresponding to the current location through the image information providing step (S10) can input an interaction for the image, and the positioning step (S11) is based on the interaction input by the user with respect to the image. Accordingly, the user's next position in the image tree can be determined. Specifically, in the location determination step (S11), the user's next location may be determined based on the interaction input by the user with respect to the corresponding image and the location condition information corresponding to the corresponding image. More specifically, the positioning step (S11) determines the interaction according to the determination condition included in the interaction for the corresponding video and the position condition information for the corresponding video, and includes the determined interaction and the position condition information for the corresponding video. The user's next location may be determined based on the location movement information.

Meanwhile, the image information providing step (S10) and the positioning step (S11) may be sequentially repeated in order to move the user's position in the image tree. Specifically, whether the user's next location determined through the location determination step (S11) satisfies a preset condition, or whether the interaction input by the user with respect to the image corresponding to the corresponding location satisfies the preset condition. It is determined whether or not (S12).

If, in step S12, the user's next location or a specific interaction input with respect to an image corresponding to the user's current location does not satisfy the preset condition, the image information providing step (S10) and the positioning step (S11) can be repeated sequentially.

On the other hand, when the user's next location or the specific interaction input with respect to the image corresponding to the user's current location in step S12 satisfies the preset condition, the result information providing step (S13) may be performed.

Specifically, the result information providing step (S13) provides the user with result information corresponding to the image of the user's next location or result information corresponding to a specific interaction input by the user with respect to the image of the current location. On the other hand, the result information may include one or more interactions input by the user on the image tree, a final image according to an image of the user's next location, or an analysis result of one or more interactions input by the user, and the like. The information may further include other service connection information for providing a separate other service to the user.

The other service connection information is sent to the other service server 3000 or server system 1000 that provides other services related to the video of the user's next location or other services related to the specific interaction input by the user with respect to the video of the current location. It may correspond to information that allows the user to access the included other service provider 1700 . For example, the other service connection information may correspond to link information for accessing the other service server 3000 or the other service provider 1700 .

5 schematically illustrates a user interaction information transmission step and a user location history transmission step according to an embodiment of the present invention.

FIG. 5(A) schematically shows a user interaction information transmission step according to an embodiment of the present invention, and FIG. 5(B) schematically shows a user location history transmission step according to an embodiment of the present invention. do.

As shown in (A) of FIG. 5, the result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user, and the In the method of providing a video interaction platform, when a user requests a connection to another service through the other service connection information provided through the result information providing step (S13), each of one or more videos performed in the video tree Further comprising a user interaction information transmission step of transmitting user interaction information including an interaction to the other service server 3000 performing the other service or the internal configuration of the server system 1000 performing the other service. can

Specifically, the user accesses the other service server 3000 or other service provider 1700 that provides other services through the other service connection information included in the result information provided through the result information providing step (S13), In the case of requesting the other service (S20), the user interaction information transmitting step derives user interaction information including one or more interactions input by the user with respect to one or more images included in the image tree, and The information is transmitted to the other service server 3000 or other service provider 1700 requested by the user for other services (S21).

Through the above configuration, the other service server 3000 or the other service provider 1700 providing other services to the user provides user interaction information including interactions input by the user in providing other services requested by the user. It is possible to exert the effect of providing user-customized services by using.

On the other hand, as shown in (B) of FIG. 5, the result information corresponding to the user's location in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user. , In the video interaction platform providing method, when a user requests a connection to another service through the other service connection information provided through the result information providing step (S13), one or more information where the user is located in the video tree is requested. A user location history transmission step of transmitting location information to the other service server 3000 performing the other service or the internal configuration of the server system 1000 performing the other service server; may be further included.

Specifically, the user requests the other service by accessing another service server or other service provider that provides other service using the other service connection information included in the result information provided through the result information providing step (S13). In the case of (S20), the user location history transmission step transmits one or more location information where the user was located in the video tree to the other service server 3000 or other service provider 1700 requested by the user for another service ( S22).

In another embodiment of the present invention, the one or more location information may include not only location information of one or more users in the image tree, but also information about one or more images where the user is located.

Through the above configuration, the other service server 3000 or the other service providing unit 1700 that provides other services to the user provides one or more location information where the user was located in the image tree when providing other services requested by the user. It is possible to exert the effect of providing user-customized services by using.

In an embodiment of the present invention, only one of the user interaction information transmission step and the user location history transmission step is performed to determine whether the user interaction information and the user were located in the other service server 3000 or the other service provider 1700. Only one piece of location information can be provided, and in another embodiment of the present invention, the other service server 3000 or other service provider ( 1700), both user interaction information and one or more location information where the user is located may be provided.

6 schematically illustrates a process of deriving inference information according to an interaction input by a user with respect to an image according to an embodiment of the present invention.

As shown in FIG. 6, the image corresponding to the user's current position in the image tree is provided to the user through the image information providing step (S10), and the user can input an interaction for the provided image, In the position determination step (S11), the user's next position in the image tree may be determined based on the interaction input by the user.

Specifically, the interaction includes at least one of text input, voice input, face information input, pose input, gesture input, and background information input for an image, and the positioning step (S11) is performed by machine learning the interaction. The user's next location may be determined by applying inference information input and output to the evaluation model 1800 and location condition information corresponding to the user's current location in the image tree.

Through the image information providing step (S10), the user is provided with an image corresponding to the user's current position in the image tree, and the user can input an interaction for the provided image. Specifically, through the image information providing step (S10), an interface capable of reproducing an image corresponding to the user's current location is displayed on the user terminal corresponding to the user, and the user inputs an interaction with the image through the interface. can do.

The interaction input by the user through the interface may include one or more of text input, voice input, face information input, pose input, gesture input, and background information input. The interaction may correspond to a user's reaction, answer, emotion, etc. to an image provided to the user, and the user inputs using one or more types among text, voice, face, pose, and background on the interface. Interactions can be added. In this way, the interaction input by the user on the interface may be transmitted to the server system 1000 . Meanwhile, the face information input, the pose input, the gesture input, and the background information input may correspond to information separately input by the user, but in another embodiment of the present invention, the user inputs the face information and the pose input. , It is possible to input an interaction in an integrated form of the gesture input and the background information input. For example, when a user inputs an image or video including a place where he is located, his face, a pose, and a gesture as an interaction, the face information input, the pose input, the gesture input, and the background information input It can be entered in an integrated form.

To this end, the user terminal may include a physical or virtual keyboard to receive text input on the interface, a microphone to receive voice input, and a camera to receive facial expression, pose, and gesture input. may be provided.

The server system 1000 receives an interaction for an image input by a user, and the positioning step (S11) determines the interaction by using the machine-learned evaluation model 1800 included in the server system 1000. Derive inferential information about Afterwards, in the positioning step (S11), it is checked whether the corresponding inference information satisfies the determination condition based on the inference information about the interaction and the determination condition for the corresponding image. Next, in the location determination step (S11), the user's next location may be determined by applying a location movement condition corresponding to the determination condition. For example, when a user inputs a facial expression of gazing at a different place as an interaction with an image, the machine-learned evaluation model 1800 infers that the interaction is a facial expression of gazing at a different place. is derived, and in the location determination step (S11), after confirming whether there is a determination condition corresponding to the inference information, the next position of the user can be determined according to the location movement information corresponding to the determination condition.

Specifically, the inference information corresponds to inference information about the user's facial expression, age, and gender recognized through a face information input included in the interaction, or information recognized through two or more inputs included in the interaction. can do. For example, the reasoning information includes the user's mental state, emotional state, It may correspond to inference information about a place where a user is located.

Meanwhile, in another embodiment of the present invention, the interaction may include a selection input for a specific option among a plurality of options for an image; and at least one input of text input, voice input, face information input, pose input, gesture input, and background information input for an image, wherein the positioning step includes a selection input for the specific option, a selection input for the image At least one input among text input, voice input, facial expression input, pose input, gesture input, and background information input is input to the machine learning evaluation model, and the inference information output and the position condition corresponding to the user's current position in the image tree The information can be applied to determine the user's next location.

Specifically, the interaction input by the user with respect to the image is provided to the user with respect to the corresponding image as well as one or more of the above-described text input, voice input, face information input, pose input, gesture input, and background information input for the image. A selection input for a specific option selected by the user among a plurality of options may be further included.

Through this, the positioning step (S11) is machine learning for one or more inputs among the selection input for the specific option and the text input, voice input, face information input, pose input, gesture input, and background information input for the above-described image. After confirming whether there is a discrimination condition corresponding to the inference information derived from the evaluated model 1800, the user's next location may be determined according to the location movement information corresponding to the discrimination condition.

For example, 'option 1. Get to know me' for the video provided to the user. and 'Option 2. Goodbye', the user may select option 1 and additionally input an interaction for inputting face information.

At this time, in the location determination step (S11), when it is inferred that the user is in his twenties based on 'option 1' selected by the user and inference information about the age of the user in the machine learning evaluation model 1800 for the face information input. , the user's next location can be determined by a video that responds "I'm not dating a younger woman", whereas if the user is inferred to be in her 30s, a video that responds "I like it too" can determine the user's next location. can decide

As such, in the present invention, the user's location is not simply determined according to the user's selection, but includes at least one of text input, voice input, face information input, pose input, gesture input, and background information input additionally input by the user. The next location of the user may be determined by additionally considering the interaction.

As such, in the present invention, by selecting a specific option among a plurality of preset options for a video, the user's position in the video tree is not only moved, but also other services are provided through the video tree for non-standard interactions from the user. can be provided, so that users can use the video interaction platform of the present invention more interestingly.

Meanwhile, specific embodiments of the machine-learned evaluation model 1800 will be described with reference to FIGS. 7 and 8 to be described later.

7 schematically illustrates the internal configuration of a feature extraction model according to an embodiment of the present invention.

The machine-learned evaluation model 1800 described above in FIG. 6 may include a feature extraction model and a feature inference model, and the feature extraction model according to the embodiment shown in FIG. A first deep neural network for extracting spatial feature information for deriving a plurality of image feature information from image information of a frame; a second deep neural network for extracting spatial feature information for deriving a plurality of voice feature information from voice information of interaction input by a user; a first recurrent neural network module for receiving the plurality of image feature information and deriving first feature information; a second recurrent neural network module for receiving the plurality of voice feature information and deriving second feature information; A third recurrent neural network module for receiving text information of the interaction and deriving third feature information.

The first deep neural network and the second deep neural network may correspond to a CNN module or the like. In an embodiment shown in FIG. 7, the first deep neural network corresponds to a first CNN module and a second deep neural network. The neural network may correspond to the second CNN module.

The first recurrent neural network module, the second recurrent neural network module, and the third recurrent neural network module may correspond to an RNN module, more specifically, an LSTM module corresponding to a sub-concept of the RNN module, and the like. In the illustrated embodiment, the first recurrent neural network module may correspond to the first LSTM module, the second recurrent neural network module may correspond to the second LSTM module, and the third recurrent neural network module may correspond to the third LSTM module.

Hereinafter, the operation of a neural network according to an embodiment of the present invention will be described based on the embodiment shown in FIG. 7 .

The plurality of frames may be generated by dividing an image of a video at predetermined time intervals. In addition, it is preferable that the plurality of image feature information derived by the first CNN module be input in time series to the first LSTM module.

On the other hand, feature information (pitch, intensity, etc.) or voice data for a preset time period is input to the 2nd CNN module, and voice feature information derived from the 2nd CNN module is input in time series to the 2nd LSTM module. It is desirable to be In addition, the feature information on the voice may include the pitch or strength of the voice, but preferably, the voice is divided into certain sections, and features are extracted through Cepstral analysis by applying Mel Filter Bank to the spectrum for each section. It may include a Mel-Frequency Cepstral Coefficient (MFCC) that

The text information of the interaction into which the feature extraction model is input may preferably correspond to a plurality of vectors in which the corresponding text information is embedded in token units.

Meanwhile, feature information (vector train) corresponding to the output of the feature extraction model is derived based on the first detailed feature information, the second detailed feature information, and the third detailed feature information. In the simplest way, the feature information may be derived by simply combining the first detailed feature information, the second detailed feature information, and the third detailed feature information, or the first detailed feature information and the second detailed feature information. The feature information may be derived by applying a weight or the like to information and the third detailed feature information.

Also, in another embodiment of the present invention, the feature extraction model may be configured differently according to the type of interaction that can be input by the user. For example, when a user can input an interaction including text, voice, and video in a complex manner, the feature extraction model, as shown in FIG. 7, derives feature information for image information; It may include both a component for deriving feature information for voice information and a component for deriving feature information for text information. Meanwhile, when a user can input an interaction using at least one type among text, voice, and video, the feature extraction model may include only components corresponding to the corresponding type.

8 schematically illustrates the internal configuration of a feature inference model according to an embodiment of the present invention.

As shown in FIG. 8, the feature inference model performs a process of deriving an intermediate result (Representative Vector) by assigning weights learned by a plurality of fully connected layers to the feature information derived from the feature extraction model. Derives the result value for the input interaction. For example, the above-described machine-learned evaluation model 1800 may analyze an interaction input by a user and derive inference information about the interaction.

The number of fully connected layers is not limited to the number shown in FIG. 8, and the feature inference model may include one or more fully connected layers. When the feature inference model is composed of a single fully connected layer, the intermediate result may be omitted.

On the other hand, in another embodiment of the present invention, the feature inference model may be implemented in such a way that a Softmax activation function is used to process the problem of classifying according to a predetermined criterion or a score is derived using a Sigmoid activation function or the like. .

9 schematically illustrates a configuration in which a plurality of image trees are connected according to an embodiment of the present invention.

As shown in FIG. 9 , the location movement information includes first location movement information for moving the user's location from an image corresponding to an interaction input by the user to another image according to the determination condition; and second location movement information for re-inputting an interaction with respect to an image corresponding to an interaction previously input by the user according to the determination condition.

Specifically, the location movement information corresponding to information for moving the user's location according to the user's interaction in the image tree includes first location movement information and second location movement information. The first location movement information is when the interaction input by the user with respect to the image corresponding to the user's current position in the image tree meets the discrimination condition of the corresponding image, and more specifically, to a specific detailed discrimination condition included in the discrimination condition. If it matches, it corresponds to information capable of moving the user's location from the image corresponding to the current location to another image.

On the other hand, the second location movement information is used to determine specific details included in the determination condition in more detail, when the interaction input by the user with respect to the video corresponding to the user's current position in the video tree meets the determination condition of the corresponding video. When the condition is satisfied, it corresponds to information that allows the user to input an interaction again with respect to an image that the user interacted with immediately before, that is, an image corresponding to the user's current location. Accordingly, when the interaction input by the user with respect to the image of the current location corresponds to the second location movement information, the server system 1000 provides the image of the current location to the user again, so that the user can input the interaction again. or by providing the user with a separate video requesting the user to perform the interaction again, so that the user can input the interaction again.

In addition, as shown in FIG. 9, a plurality of image trees are stored in the server system 1000, and the location movement information of the image trees is a determination condition according to a user's interaction with the image included in the corresponding image tree. Third location movement information for moving the location of the corresponding user to a specific image included in another image tree based on the image tree may be included.

Specifically, the location movement information not only determines the user's location within a single image tree, but also moves the user's location from a specific image tree to a location corresponding to a specific image of another image tree. It may contain more information. That is, the third location movement information is used for specific detailed determination included in the determination condition when the interaction input by the user with respect to the video corresponding to the user's current position in the video tree meets the determination condition of the corresponding video. When the condition is met, it corresponds to information that can move the user's location from the image corresponding to the current location to a specific image included in another image tree.

As described above, since the location movement information of the present invention includes the above-described first location movement information, second location movement information, and third location movement information, various routes to the user's location can be set, and thus one or more user interactions It is possible to demonstrate the effect of providing various other services according to

10 schematically illustrates movement of a user's location according to user interaction in a video tree according to an embodiment of the present invention.

10 corresponds to an exemplary view of the above-described image tree. In the video tree shown in FIG. 10, when the user's current location is located on the video C1, the video information providing step (S10) provides the video C1 to the user, and the user can input an interaction with the video C1.

As described in the location condition information of FIG. 10, the user can input various types of interactions with respect to the image C1. For example, the user may input an interaction by selecting a specific text among a plurality of preset action texts, input an interaction by uttering a voice, or input an interaction by photographing a facial expression and/or a pose. Meanwhile, the interaction may include only one type among various types, but preferably may include one or more types among various types.

In the location determination step (S11), the next location of the user in the image tree is determined according to the interaction input by the user and location condition information of the corresponding image. 10 as an example, when the user selects a specific action text as an interaction with the image C1, the positioning step (S11) moves the user's next position to the image C2 according to the location movement information corresponding to the specific action text selected by the user. Decide.

On the other hand, when the user inputs a facial expression or pose of gazing at a different place as an interaction with the image C1, the positioning step (S11) uses the machine-learned evaluation model 1800 to indicate that the interaction is gazing at a different place. and determine the next location of the user as image C3 according to the location movement information corresponding to the interaction of staring at a different place.

In addition, when the location movement information for determining the user's next location as the image C3 is the above-described first location movement information, the user can input an interaction for the image C3, whereas the location movement information is the above-described second location movement information. In the case of location movement information, the user may be provided with the image C3 and input an interaction related to the image C1 again.

11 schematically illustrates an image tree creation interface 1610 according to an embodiment of the present invention.

As shown in FIG. 11, the method of providing the video interaction platform includes a video tree creation interface (1610) that receives a plurality of videos according to a user's request and receives location condition information and result information settings for each video. It may further include; a manufacturing builder providing step of providing a) to the user.

Specifically, the video interaction platform of the present invention not only provides the user with a video tree pre-stored in the server system 1000, but also provides the user with the user's request through the production builder providing step performed in the server system 1000. An image tree creation interface 1610 capable of directly generating an image tree may be provided.

As shown in FIG. 11, the image tree creation interface 1610 is displayed on the user terminal of the user who requested the creation of the image tree, and the image tree creation interface 1610 can input various elements for setting the image tree. areas may be included.

The image tree creation interface 1610 includes an image upload area 1611, a video playback area 1612, a determination condition setting area 1613, a location movement information setting area 1614, and an image tree preview area 1615. can do. The image upload area 1611 corresponds to an area where a plurality of images included in the image tree can be uploaded. When a user uploads a plurality of images through the image upload area 1611 and selects a specific uploaded image (image #1 in FIG. 11), the image tree creation interface 1610 determines a specific image Conditions and location movement information can be set.

The video playback area 1612 corresponds to an area where a user can check a specific video selected in the video upload area 1611, and corresponds to a case where the user selects a playback element included in the video playback area 1612. Images can be reproduced in the image play area 1612 .

The determination condition setting area 1613 corresponds to an area in which determination conditions for a selected image can be set. In the determination condition setting area 1613, the user can set a determination condition for an interaction input by the user with respect to the corresponding image, specifically one or more detailed determination conditions included in the determination condition. For example, as shown in FIG. 11, a user who wants to create a corresponding image tree as a detailed discriminant condition for an image asking if she ate lunch has a detailed discriminant condition for a positive interaction (a in FIG. 11) and A detailed discrimination condition (b in FIG. 11 ) for the negative interaction of not eating lunch can be set on the discrimination condition setting area 1613 .

The location movement information setting area 1614 corresponds to an area in which location movement information for determining the user's next location can be set when the interaction with the image input by the user satisfies a specific detailed determination condition. The user may set the location movement information by setting an image corresponding to the user's next location for each detailed discrimination condition for the corresponding image. For example, as shown in FIG. 11, when a user creating a video tree meets the detailed discrimination condition for a positive interaction, the interaction input by the user using the video tree to be created for video #1 is met. Location movement information for determining the user's next location can be set to the location corresponding to image #2, and when the interaction entered by the user meets the detailed discrimination condition for negative interaction, the location corresponding to image #4 Location movement information for determining the user's next location may be set. In addition, in the location movement information setting area 1614, it can be set to provide result information to the user as the next location corresponding to the detailed discrimination condition in the image tree to be created. For example, when an interaction input by a user satisfies a specific detailed discrimination condition, one or more interactions of a user input in the video tree and/or a final result according to the location history of the user in the video tree or an input in the video tree It may be set to provide the user with result information including other service connection information for providing other services according to one or more interactions of one user and/or location history of the user in the image tree.

The image tree preview area 1615 corresponds to an area in which the overall shape of the image tree set or being set by the user through the image tree creation interface 1610 is visually schematized and displayed. Therefore, the user can effectively review the image tree to be created through the image tree preview area 1615.

12 schematically illustrates a process of providing other services according to an embodiment of the present invention.

As shown in FIG. 12, the result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user, and the result information providing step The other service connected to the other service connection information provided in (S13) derives response information for the user's interaction through a separate machine-learned evaluation model, and creates an object 1710 that is ignited according to the response information to the user. can be provided to

In one embodiment of the present invention, other services provided to the user through the image tree may be implemented as non-face-to-face consultation with experts or provision of preset content, but preferably, the other services, such as AI human, Response information may be generated according to the interaction with the user, and an object 1710 ignited according to the response information may be provided to the user.

Accordingly, the other service server 3000 providing the other service or the other service provider 1700 included in the server system 1000 infers the interaction for the answer to the question input by the user receiving the other service. To do this, a separate machine-learned evaluation model can be used, and text-type response information corresponding to the interaction input by the user can be derived according to inference information derived through the machine-learned evaluation model. Subsequently, the other service server 3000 or the other service provider 1700 may provide the derived response information to the user through the object 1710.

Specifically, the object 1710 may simply be implemented in a form of displaying response information in text form as it is, and the other service server 3000 or the other service provider 1700 converts the response information into a voice form. It can be implemented in a form of converting and providing the response information converted to voice to the user in the form of audio through the object 1710.

Preferably, the other service server 3000 or the other service provider 1700 converts the response information into a voice form and causes the object 1710 to speak naturally based on the response information converted into voice. By deriving motion information, the object 1710 may utter the response information converted into voice while the expression of the face changes according to the response information converted into voice and the facial movement information. Meanwhile, when implemented in this form, the object 1710 may have a human appearance or face shape. In addition, the other service server 3000 or the other service provider 1700 is a Text to Speech (TTS) module for converting text-type response information into voice form and an object ( 1710) may include a Speech to Face module for generating facial movements. Meanwhile, the TTS module and the Speech to Face module may be implemented in various conventional methods.

In this way, since other services provided to the user by the other service server 3000 or the other service provider 1700 are implemented through the object 1710 that fires according to the user's interaction, user-customized services can be provided, An effect capable of arousing user interest may be exerted.

13 schematically illustrates the internal configuration of a computing device according to an embodiment of the present invention.

The server system 1000 shown in FIG. 1 may include components of the computing device 11000 shown in FIG. 13 .

As shown in FIG. 13, a computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( It may include at least an I/O subsystem (11400), a power circuit (11500), and a communication circuit (11600). In this case, the computing device 11000 may correspond to the server system 1000 shown in FIG. 1 .

The memory 11200 may include, for example, high-speed random access memory, magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. . The memory 11200 may include a software module, a command set, or other various data necessary for the operation of the computing device 11000.

In this case, access to the memory 11200 from other components, such as the processor 11100 or the peripheral device interface 11300, may be controlled by the processor 11100.

Peripheral interface 11300 may couple input and/or output peripherals of computing device 11000 to processor 11100 and memory 11200 . The processor 11100 may execute various functions for the computing device 11000 and process data by executing software modules or command sets stored in the memory 11200 .

The input/output subsystem can couple various input/output peripherals to peripheral interface 11300. For example, the input/output subsystem may include a controller for coupling a peripheral device such as a monitor, keyboard, mouse, printer, or touch screen or sensor to the peripheral device interface 11300 as needed. According to another aspect, input/output peripherals may be coupled to the peripheral interface 11300 without going through the input/output subsystem.

The power circuit 11500 may supply power to all or some of the terminal's components. For example, power circuit 11500 may include a power management system, one or more power sources such as a battery or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator or power It may contain any other components for creation, management and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, the communication circuit 11600 may include an RF circuit and transmit/receive an RF signal, also known as an electromagnetic signal, to enable communication with other computing devices.

The embodiment of FIG. 13 is just one example of the computing device 11000, and the computing device 11000 may omit some components shown in FIG. 13, further include additional components not shown in FIG. 13, or 2 It may have a configuration or arrangement combining two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 11000 may be implemented as hardware including one or more signal processing or application-specific integrated circuits, software, or a combination of both hardware and software.

Methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in computer readable media. In particular, the program according to the present embodiment may be composed of a PC-based program or a mobile terminal-specific application. An application to which the present invention is applied may be installed in the computing device 11000 through a file provided by a file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of the computing device 11000 .

The device described above may be implemented as a hardware component, a software component, and/or a combination of hardware components and software components. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA) , a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computing devices and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

According to an embodiment of the present invention, by providing a video tree based on a video to a user, it is possible to exert an effect of arousing interest in service participation of the user.

According to an embodiment of the present invention, at the final stage of the video tree, one or more positions of the user in the video tree or user interaction information is provided to another service server or other service providing unit of the server system that provides other services to the user. However, it can exert an effect of providing other services that are more suitable for users.

According to an embodiment of the present invention, since other services are provided to users through a video tree, and service result information derived by the user receiving other services is connected to a specific video in the video tree, various types of services are provided to users. can exert the effect that can provide.

According to an embodiment of the present invention, the user can input various interactions with respect to the images of the image tree, and since the user's interactions can be input to the machine-learned evaluation model to derive the discrimination condition, a preset option is selected. Compared to the conventional method of doing so, it is possible to exert an effect of arousing the user's interest and at the same time providing more accurate other services to the user.

According to an embodiment of the present invention, since a video tree creation interface is provided to a user so that the user can directly build a video tree, an effect of activating a video interaction platform can be exerted.

According to an embodiment of the present invention, since the user's position can be moved to a specific video of another video tree according to the user's interaction with the video of the video tree, a plurality of video trees are linked to provide various other services to the user. You can exert the effect you can.

As described above, although the embodiments have been described with limited examples and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (11)

As a method of providing a video interaction platform performed in a server system,
The server system includes a plurality of images for a video tree or image information including basic data for generating a plurality of images, a determination condition for determining a user's interaction with each image, and a location movement according to the determination condition. Location condition information including location movement information and result information corresponding to the user's location in the image tree or the user's interaction with the image are stored, and the user's location in the image tree corresponds to the corresponding user's image. It can be moved according to the interaction with
The method of providing the video interaction platform,
an image information providing step of providing a user with an image corresponding to the user's current position in the image tree;
a positioning step of determining the user's next position by applying position condition information corresponding to the user's current position in the image tree to the user's interaction with the image provided through the image information providing step; and
Result information providing step of providing result information to the user when the user's location or user's interaction with one or more images corresponds to a preset condition;
The method of claim 1,
The result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user,
The method of providing the video interaction platform,
When a user requests a connection to another service through the other service connection information provided through the result information providing step, user interaction information including interactions with each of one or more videos performed in the video tree is transmitted to the other service. A method of providing a video interaction platform, further comprising: transmitting user interaction information to another service server performing a service or an internal configuration of the server system performing the other service.
The method of claim 1,
The result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user,
The method of providing the video interaction platform,
When a user requests a connection to another service through the other service connection information provided through the result information providing step, one or more location information where the corresponding user is located in the image tree is sent to the other service server that performs the other service or The method of providing a video interaction platform, further comprising; transmitting the user location history to the internal configuration of the server system that performs the other service server.
The method of claim 1,
The result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user,
The method of providing a video interaction platform, wherein the specific video included in the video tree is connected to service result information obtained by the user performing the other service.
The method of claim 1,
The interaction includes at least one of text input, voice input, face information input, pose input, gesture input, and background information input for an image,
In the positioning step, the next position of the user is determined by applying inference information output by inputting the interaction to a machine-learned evaluation model and position condition information corresponding to the current position of the user in the image tree. How the platform is provided.
The method of claim 1,
The interaction includes a selection input for a specific option among a plurality of options for the image; And one or more inputs among text input, voice input, face information input, pose input, gesture input, and background information input for an image;
In the positioning step, one or more of the selection input for the specific option, text input for the image, voice input, facial expression input, pose input, gesture input, and background information input is input to the machine learning evaluation model and output. A method of providing a video interaction platform for determining a user's next location by applying the obtained inference information and location condition information corresponding to the user's current location in the video tree.
The method of claim 1,
The location movement information,
first location movement information for moving the user's location from an image corresponding to the interaction input by the user to another image according to the determination condition; and
A method for providing a video interaction platform comprising: second location movement information for allowing a user to input an interaction again with respect to an image corresponding to an interaction input immediately before according to the determination condition.
The method of claim 1,
The method of providing the video interaction platform,
A production builder providing step of receiving a plurality of images according to a user's request and providing the user with a video tree generation interface for receiving location condition information and result information settings for each image; further comprising a video interaction platform. How to provide.
The method of claim 1,
A plurality of image trees are stored in the server system,
The location movement information of the image tree includes third location movement information for moving the user's location to a specific image included in another image tree based on a determination condition according to the user's interaction with the image included in the corresponding image tree. How to provide a video interaction platform.
The method of claim 1,
The result information corresponding to the user's position in the image tree or the user's interaction with the image includes other service connection information for providing other services to the user,
The other service connected to the other service connection information provided in the result information providing step derives response information for the user's interaction through a machine learning evaluation model, and provides the user with an object that ignites according to the response information , How to provide a video interaction platform.
As a server system that performs a method of providing a video interaction platform,
The server system includes a plurality of images for a video tree or image information including basic data for generating a plurality of images, a determination condition for determining a user's interaction with each image, and a location movement according to the determination condition. Location condition information including location movement information and result information corresponding to the user's location in the image tree or the user's interaction with the image are stored, and the user's location in the image tree corresponds to the corresponding user's image. It can be moved according to the interaction with
an image information providing step of providing a user with an image corresponding to the user's current position in the image tree;
a positioning step of determining the user's next position by applying position condition information corresponding to the user's current position in the image tree to the user's interaction with the image provided through the image information providing step; and
A server system that performs a result information providing step of providing result information to a user when the user's location or user's interaction with one or more images corresponds to a preset condition.

Images