KR20210053739A - Apparatus for creation of contents of game play - Google Patents

Abstract

According to an embodiment of the present invention, provided is a gameplay content creation device, which generates video contents including contents of game contents being played and contents responding to feedback received from a user during a play process. The gameplay content creation device uses a first artificial neural network to generate a manipulation input according to a first progress state, which is a progress state of the game contents, while playing the game contents by inputting the generated manipulation input to the game content, generates the video contents including a process of changing a progress state from the first progress state to a second progress state according to the input of the manipulation input, receives the feedback of the user watching the video contents, and may generate response contents including a response to the feedback by using a second artificial neural network.

Description

Gameplay content creation device {APPARATUS FOR CREATION OF CONTENTS OF GAME PLAY}

An embodiment of the present invention relates to a game play content production apparatus that generates video content including content on which game content is played and response content to a feedback received from a user during a process of playing the game content.

Due to the rapid development of information and communication technology, various types of terminals such as mobile communication terminals and personal computers are being implemented to perform various functions.

Taking a mobile communication terminal as an example, the mobile communication terminal is implemented to use various functions such as data communication, photographing or video recording using a camera, playing music or video files, playing games, and watching broadcasts, in addition to basic voice communication functions. have.

Recently, the demand for viewing video content using a mobile communication terminal is increasing, and in particular, the demand for video content including content in which game content is played by another person is steadily increasing.

On the other hand, in the case of such game play contents, there is a problem in that it is difficult to mass-produce contents or to produce various contents due to the temporal and quantitative limitations of content production in that it records scenes played by humans.

An object of the present invention is to create game play content for playing game content using a learned artificial neural network.

In addition, the present invention is to provide a user with a sense of immersion as if the game content is being played by a person by providing various types of response content along with video content including game play content.

In addition, an object of the present invention is to reduce the temporal and physical constraints of creating game play contents, thereby enabling the creation of a larger amount of game play contents.

According to an embodiment of the present invention, an apparatus for producing game play content that generates video content including content on which game content is played and response content to a feedback received from a user during the play process, uses a first artificial neural network. An operation input according to a first progress state, which is a progress state of the game content, is generated, and while playing the game content by inputting the generated operation input to the game content, the first progress state is controlled according to the input of the operation input. 2 Generate video content including a process of changing the progress as progress, receive feedback from a user viewing the video content, and generate response content including a response to the feedback using a second artificial neural network. Can be generated.

The first artificial neural network performs the first progress based on a progress result of the game content according to a plurality of progress states of the game content, an operation input in each of the plurality of progress states, and an operation input in each of the plurality of progress states. It may be a neural network that has been trained to generate manipulation inputs in the context. In this case, the first artificial neural network may be learned in a direction in which the result of the game content is achieved according to the manipulation input.

The first artificial neural network includes a plurality of progress states of the game content, an operation input in each of the plurality of progress states, a progress result of the game content according to an operation input in each of the plurality of progress states, and each of the plurality of progress states. It may be a neural network that has been trained to generate an operation input in the first progress situation based on the feedback of a plurality of users at. In this case, the first artificial neural network may be trained in a direction in which the user's feedback level is maximum according to the manipulation input.

The response content is a message in consideration of the first progress situation, and may include a message that is a response to the user's message.

The response content is an avatar image in consideration of the first progress situation, and may be an image including an avatar image whose display is changed according to the user's message.

The apparatus for producing game play content according to an embodiment of the present invention may provide the response content together with the video content to one or more user terminals.

According to the present invention, it is possible to generate game play content for playing game content using the learned artificial neural network. In particular, by learning the artificial neural network according to the purpose, it is possible to generate not only game play content proceeding in the direction in which the degree of achievement of the game content is the maximum, but also game play content proceeding in the direction in which the degree of user's feedback is maximum.

In addition, according to the present invention, by providing various types of response content along with video content including game play content, it is possible to provide a user with an immersion feeling as if the game content is being played by a person.

Furthermore, the present invention reduces the temporal and physical constraints of generating game play contents, thereby enabling the creation of a larger amount of game play contents.

1 is a diagram schematically showing the configuration of a system according to an embodiment of the present invention.
2 is a diagram schematically showing the configuration of a content production device 110 provided in the content production server 100 according to an embodiment of the present invention.
3 is a diagram illustrating a process of learning the first artificial neural network 520 using the training data 510.
4 is a diagram illustrating a process of learning the 2-1 artificial neural network 540 using the training data 530.
5 is a diagram for describing a process of learning the 2-2 artificial neural network 560 using the training data 550.
6 is a view for explaining a process of generating game play content by the control unit 112 according to an embodiment of the present invention.
7 is a diagram for explaining a process in which the controller 112 generates video content according to an embodiment of the present invention.
8 is an example of a screen 810 in which game play content provided by the content creation server 100 is displayed on the user terminal 200.
9 is a flowchart illustrating a method of producing game play contents performed by the server 100 including the apparatus 110 for producing game play contents according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. Effects and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described later in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when describing with reference to the drawings, the same or corresponding constituent elements are assigned the same reference numerals, and redundant descriptions thereof will be omitted. .

In the following embodiments, terms such as first and second are used for the purpose of distinguishing one constituent element from other constituent elements rather than a limiting meaning. In the following examples, expressions in the singular include plural expressions unless the context clearly indicates otherwise. In the following embodiments, terms such as include or have means that the features or elements described in the specification are present, and do not preclude the possibility of adding one or more other features or components in advance. In the drawings, components may be exaggerated or reduced in size for convenience of description. For example, the size and shape of each component shown in the drawings are arbitrarily shown for convenience of description, and thus the present invention is not necessarily limited to what is shown.

1 is a diagram schematically showing the configuration of a system according to an embodiment of the present invention.

Referring to FIG. 1, a system according to an embodiment of the present invention may include a content production server 100, a user terminal 200, an image streaming server 300, and a communication network 400.

The system according to an embodiment of the present invention may generate video content including content in which game content is played and response content for feedback received from a user during a process of playing the game content and transmit it to the user terminal 200.

In the present invention, “game content” may mean content in which an output element that can be recognized by a person, such as a screen or a voice, is changed according to a predetermined operation. For example, the game content may be block breaking content that breaks a block at the top according to a bar operation at the bottom, as shown in FIG. 8. However, this is exemplary, and the spirit of the present invention is not limited thereto, and various genres and/or types of game contents may correspond to the game contents of the present invention.

Such game content may be generated in consideration of the fact that the operating subject is mainly human, but in the present invention, the game content will be described centering on content that is manipulated by a learned artificial neural network rather than a person.

In the present invention,'playing' the game content may mean performing an operation (or input) on the game content in order to achieve a predetermined purpose within the game content. For example, in the block breaking content as shown in FIG. 8, playing the game content may mean appropriately moving the position of the lower bar in order to obtain a higher score by breaking the upper block. have.

In the present invention, the'progress status' of the game content means a situation in which the game content is in progress at a specific point in time, and may be described as various factors according to the type of the game content. For example, in the block breaking content as shown in FIG. 8, the progress status may include the number of blocks remaining at a specific point in time, the position of the ball, the position of the lower bar, and the score, and is set differently according to the type of game. Can be.

In the present invention, “video content” including content on which game content is played refers to an image representing a process of playing the game content, and may include sound representing the process of playing.

In the present invention,'response content' is various types of content that responds to user feedback, and may include any one of video content, text content, and sound content.

In the present invention, the'artificial neural network' is a neural network learned according to a predetermined purpose, and may mean a neural network learned by a machine learning or deep learning technique. A detailed description of individual neural networks will be described later.

The user terminal 200 according to an embodiment of the present invention includes a user and a content production server 100 so that the user can use various services provided by the content production server 100 and/or the video streaming server 300. / Or may mean various types of devices that mediate the video streaming server 300.

In other words, the user terminal 200 according to an embodiment of the present invention may refer to various types of devices that transmit and receive data with the content production server 100 and/or the video streaming server 300.

As shown in FIG. 1, such a user terminal 200 may refer to portable terminals 201, 202, and 203, or may refer to a computer 204.

Meanwhile, the user terminal 200 may include a display means for displaying content or the like in order to perform the above-described functions, and an input means for acquiring a user's input for such content. In this case, the input means and the display means may be configured in various ways. For example, the input means may include a keyboard, a mouse, a trackball, a microphone, a button, and a touch panel, but are not limited thereto.

The user terminal 200 receives feedback on the video content provided by the content production server 100 from the user, transmits it to the content production server 100, and receives response content for the feedback from the content production server 100 Can be displayed.

The communication network 400 according to an embodiment of the present invention may mean a communication network that mediates data transmission/reception between components of a system. For example, the communication network 400 is wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks), ISDNs (Integrated Service Digital Networks), wireless LANs, CDMA, Bluetooth, satellite communication, etc. It may cover wireless networks of, but the scope of the present invention is not limited thereto.

The video streaming server 300 according to an embodiment of the present invention may mean a device for streaming video content generated by the content production server 100. Such an image streaming server 300 may refer to a server of an image streaming company that provides an image streaming service to the user terminal 200, for example. In this case, the video streaming server 300 may provide the response content generated by the content production server 100 together with the video content generated by the content production server 100 to the user terminal 200.

In an optional embodiment, the video streaming server 300 may be integrally configured with the content production server 100. In this case, the content creation server 100 may generate video content and response content and stream (or provide) to the user terminal 200.

The content creation server 100 according to an embodiment of the present invention generates video content including content on which game content is played, and response content to the feedback received from the user during the process of playing the game content, so that the user terminal 200 Can be transferred to. To this end, the content creation server 100 according to an embodiment of the present invention may include a content creation device 110 as shown in FIG. 2.

2 is a diagram schematically showing the configuration of a content production device 110 provided in the content production server 100 according to an embodiment of the present invention.

Referring to FIG. 2, the content production apparatus 110 according to an embodiment of the present invention may include a communication unit 111, a control unit 112, and a memory 113. In addition, although not shown in the drawings, the content production apparatus 110 according to the present embodiment may further include an input/output unit, a program storage unit, and the like.

The communication unit 111 is a hardware required for the content production device 110 to transmit and receive signals such as control signals or data signals through wired or wireless connection with other network devices such as the user terminal 200 and/or the video streaming server 300 And a device including software.

The control unit 112 may include all types of devices capable of processing data, such as a processor. Here, the'processor' may refer to a data processing device embedded in hardware, which has a circuit physically structured to perform a function represented by a code or command included in a program. As an example of such a data processing device built into the hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an ASIC (Application-Specific Integrated) Circuit) and processing devices such as a Field Programmable Gate Array (FPGA) may be covered, but the scope of the present invention is not limited thereto.

The memory 113 performs a function of temporarily or permanently storing data processed by the content creation device 110. The memory may include a magnetic storage medium or a flash storage medium, but the scope of the present invention is not limited thereto. For example, the memory 113 may temporarily and/or permanently store data (eg, coefficients) constituting an artificial neural network. Of course, the memory 113 may also store training data for learning an artificial neural network. However, this is merely an example, and the spirit of the present invention is not limited thereto.

Hereinafter, artificial neural networks generated by the control unit 112 of the content production apparatus 110 will be first described, and a process of producing game play content using the generated artificial neural network will be described later.

The control unit 112 according to an exemplary embodiment of the present invention may generate or learn one or more artificial neural networks used in the production of game play contents to be used for production of game play contents. For example, the control unit 112 may generate and use a first artificial neural network that generates an operation input in a progress situation at a specific point in time of the game content. In addition, the control unit 112 may generate and use a 2-1 artificial neural network that generates a response message to the user's feedback, or may generate and use a 2-2 artificial neural network that generates a response image to the user's feedback. have.

3 is a diagram for describing a process of learning the first artificial neural network 520 using the training data 510.

As described above, in the present invention, the'artificial neural network' is a neural network learned according to a predetermined purpose, and may mean a neural network learned by a machine learning or deep learning technique. In this case, the type of artificial neural network (or a technique for generating the artificial neural network) may be appropriately determined according to the type of game content. For example, when the progress of the game content is acquired from the display screen of the game content, an artificial neural network according to a convolutional neural network (CNN) model may be used. However, this is exemplary, and the spirit of the present invention is not limited thereto, and as described above, various types and/or forms of artificial neural networks may be used depending on the type of game content and/or the method of acquiring the progress of the game content. have.

In the present invention, the first artificial neural network 520 may be an artificial neural network generated to generate a manipulation input for the progress of game content at a specific point in time. For example, in an example in which the progress of the game content is obtained from the display screen of the game content, the first artificial neural network 520 may output a manipulation input for the game content in response to the input to the display screen of the game content. The manipulation input output at this time may be, for example, an input for moving the position of a character in the game content, an input for selecting a specific item in the game content, or the like. However, this is merely an example, and the spirit of the present invention is not limited thereto.

Meanwhile, prior to using the first artificial neural network 520 to play game content, the first artificial neural network 520 may be learned based on predetermined training data 510. In this case, the learning data 510 may include data sets 511, 512, and 513 corresponding to manipulation inputs in each of a plurality of progress situations of game content. At this time, in the data set 511 for the first progress situation, the first progress status (Situation 1), the operation input (Control) in the first progress status, and the progress result of the game content according to the corresponding manipulation input in the first progress status. (Result) may be included. The data set 512 for the second progress status and the data set 513 for the N-th progress status may also include the same items as the data set 511 for the first progress status.

In an optional embodiment, the learning data 510 may further include an operation goal and a user's feedback item.

In the present invention, the'object of manipulation' relates to the direction in which the manipulation input generated by the first artificial neural network 520 will lead the game content, for example,'the purpose of achieving the maximum result' or'the user It may be the purpose that the level of feedback is the maximum. However, such objects are exemplary, and the spirit of the present invention is not limited thereto, and the purpose of operation may be set in various ways.

In the present invention,'user feedback' may include various types of information received from the user terminal 200. For example, the user's feedback may include a text message and a voice message received from the user terminal 200. In addition, the user's feedback may include an item use input, an empathy input, a sharing request input, etc. for the video content being streamed, or may include the total amount of feedback. However, this is merely an example, and the spirit of the present invention is not limited thereto.

According to an optional embodiment, the first artificial neural network 520 may generate a game operation input at a specific time point according to the progress of the game content at a specific time point, feedback from the user, and input of the purpose of operation. For example, in an example in which the progress of the game content is obtained from the display screen of the game content, the first artificial neural network 520 inputs an input to the display screen of the game content, the user's feedback, and the purpose of operation (for example, the user's In response to the purpose of the maximum feedback level), a manipulation input for the game content may be output. The manipulation input output at this time may be, for example, an input for moving the position of a character in the game content, an input for selecting a specific item in the game content, or the like.

The controller 112 according to an embodiment of the present invention may play a game by using a manipulation input of game content generated by the first artificial neural network 520. The controller 112 can continuously play the game content by generating a new operation input using the first artificial neural network 520 and a new progress status of the game content generated according to the game play.

In this way, the present invention generates an operation input of the game content using the learned first artificial neural network 520, but by generating an operation input to meet a predetermined purpose, it is possible to generate the play content of the game content according to the purpose. .

4 is a diagram for describing a process of learning the 2-1 artificial neural network 540 using the training data 530.

In the present invention, the 2-1 artificial neural network 540 responds according to the progress of the game content at a specific point in time, an operation input generated by the first artificial neural network 520 in the corresponding situation, and an input of a user's feedback message. It can mean a neural network that has been trained to generate a message. For example, in an example in which the progress of the game content is obtained from the display screen of the game content, the 2-1 artificial neural network 540 is an input to the display screen of the game content and the first artificial neural network 520 according to the input of the screen. In response to the generated operation input and the user's feedback message, a response message to the user's feedback message may be generated.

In an optional embodiment, the controller 112 according to an embodiment of the present invention converts a feedback message including a user's voice message into text and inputs it to the 2-1 artificial neural network 540, or the 2-1 artificial neural network ( 540), the response message generated in the form of this text may be voiced.

Meanwhile, prior to using the 2-1 artificial neural network 540 to generate a response message as described above, the 2-1 artificial neural network 540 may be trained based on the predetermined training data 530.

In this case, the learning data 530 may include data sets 531, 532, and 533 corresponding to response messages for each of the plurality of user feedback messages. At this time, in the data set 531 for the first feedback message, the first feedback message (Feedback MSG1), the situation of the game content when the first feedback message is received, and the first artificial neural network 520 in the corresponding progress state. ) May include the generated operation input (Control) and response message (Response MSG). The data set 532 for the second progress status and the data set 533 for the N-th progress status may also include the same items as the data set 531 for the first progress status.

The control unit 112 according to an embodiment of the present invention generates a response message to the user's feedback message received during the process of playing game content using the 2-1 artificial neural network 540 and sends it to the user terminal 200. Can be transmitted.

Accordingly, the present invention may allow generation of a more natural response message in consideration of the flow of the game.

5 is a diagram illustrating a process of learning the 2-2 artificial neural network 560 using the training data 550.

In the present invention, the 2-2 artificial neural network 560 responds according to the progress of the game content at a specific point in time, an operation input generated by the first artificial neural network 520 in the corresponding situation, and an input of a user's feedback message. It may mean a neural network that has been trained to generate an avatar image. For example, in an example in which the progress of the game content is obtained from the display screen of the game content, the 2-2 artificial neural network 560 is an input to the display screen of the game content, the first artificial neural network 520 according to the input of the screen. In response to the generated manipulation input and the user's feedback message, an avatar image that responds to the user's feedback message may be generated.

In the present invention, the'avatar image' may mean an image in which a virtual character's actions, facial expressions, etc. are displayed. In this case, the avatar image may further include the voice of the virtual character (for example, a voice for reading a response message).

In an optional embodiment, the controller 112 according to an embodiment of the present invention converts a feedback message including a user's voice message into text and inputs it to the 2-2 artificial neural network 560, or the 2-2 artificial neural network ( 560) The response message generated in the form of text may be voiced and included in the avatar image.

Meanwhile, as described above, prior to using the 2-2 artificial neural network 560 for generating an avatar image, the 2-2 artificial neural network 560 may be trained based on the predetermined training data 550.

In this case, the training data 550 may include data sets 551, 552, and 553 corresponding to avatar images for each of the plurality of user feedback messages. At this time, in the data set 551 for the first feedback message, the first feedback message (Feedback MSG 1), the situation of the game content when the first feedback message is received, and the first artificial neural network ( A manipulation input (Control) generated by 520 and information related to the avatar image (Response AVT) may be included. The data set 552 for the second progress status and the data set 553 for the third progress status may also include the same items as the data set 551 for the first progress status.

The control unit 112 according to an embodiment of the present invention uses the 2-2 artificial neural network 560 to generate a response avatar image to the user's feedback message received during the playing process of the game content, and the user terminal 200 Can be transferred to.

Accordingly, the present invention may allow the creation of a virtual game BJ more naturally in consideration of the flow of the game.

Hereinafter, a method of generating game play content by using the artificial neural networks 520, 540, and 560 generated by the control unit 112 according to the above-described process will be described.

6 is a view for explaining a process of generating game play content by the control unit 112 according to an embodiment of the present invention. 7 is a diagram for explaining a process in which the control unit 112 generates video content according to an embodiment of the present invention. Hereinafter, it will be described with reference to FIGS. 6 and 7 together.

The control unit 112 according to an embodiment of the present invention uses the first artificial neural network 520 to generate an operation input 630 according to the first progress status 610, which is the progress status of the game content 660. I can. In this case, the controller 112 may generate a manipulation input 630 according to the first progress situation 610 by further considering the user's feedback 620.

In addition, the control unit 112 inputs the operation input 630 generated in the game contents 660 to play the game contents 660, and the second operation in the first progress situation 620 according to the input of the operation input 630 The video content 700 including the process of changing the progress status to the progress status 670 may be generated.

For example, if the game content 660 is a block breaking content as shown in FIG. 8, the control unit 112 moves the lower bar according to the generated manipulation input 630, the process of bounced on the moved bar, and the process of bounced up. Video content 700 including a process in which some blocks are broken by a ball may be generated.

Meanwhile, in the present invention, the'progress status' of the game content 660 may be defined in various ways. For example, the progress status may be defined as a new progress status when a specific event occurs in the game content 660, or may be defined as a new progress status when a certain time elapses even if a specific event does not occur. Of course, the progress status may be defined as a new progress status whenever a screen constituting the game screen is changed by a predetermined number of frames. However, this is merely an example, and the spirit of the present invention is not limited thereto.

The control unit 112 according to an embodiment of the present invention may generate the video content 700 by connecting progress statuses 610, 670, and 690 generated according to the play of the game content 660 in a time series. . In this case, the video content 700 may include at least some screens of a play process of the game content 660.

The controller 112 according to an embodiment of the present invention may transmit the image content 700 generated by the above-described process to the user terminal 200. At this time, the control unit 112 may provide the video content 700 to the user terminal 200 using the video streaming system provided by the above-described streaming server 300, or directly to the user terminal 200 ( 700).

The controller 112 according to an embodiment of the present invention may receive a feedback 620 from a user viewing the video content 700 in parallel with the generation and transmission of the video content 700 described above. In addition, the controller 112 may generate response content including a response to the received feedback 620 using the second artificial neural networks 540 and 560.

For example, the controller 112 responds to the user's feedback 620 received during the playing process of the game content 660 (or during the streaming process of the video content 700) using the 2-1 artificial neural network 540 The message 640 may be generated and transmitted to the user terminal 200. At this time, the controller 112 may generate a response message 640 for the user's feedback 620 by additionally considering the first progress status 610 and the manipulation input 630 according to the first progress status 610. .

In addition, the controller 112 responds to the user's feedback 620 received during the playing process of the game content 660 (or during the streaming process of the video content 700) using the 2-2 artificial neural network 560 An avatar image 650 may be generated and transmitted to the user terminal 200. Of course, also at this time, the control unit 112 generates a response avatar image 650 to the user's feedback 620 by additionally considering the operation input 630 according to the first progress status 610 and the first progress status 610. You may.

Accordingly, the present invention can generate game play content for playing the game content 660 using the learned artificial neural network. In particular, by learning an artificial neural network according to the purpose of the present invention, it is possible to generate not only game play content that proceeds in the direction in which the degree of achievement of the game content is the maximum, but also game play content that proceeds in the direction in which the level of feedback from users is maximum. have.

In addition, the present invention may provide a user with an immersion feeling as if the game content 660 is being played by a person by providing various types of response content along with a play image of the game content.

Furthermore, the present invention reduces the temporal and physical constraints of generating game play contents, thereby enabling the creation of a larger amount of game play contents.

8 is an example of a screen 810 in which game play content provided by the content creation server 100 is displayed on the user terminal 200.

Referring to FIG. 8, the progress of the game is displayed on the screen 810 as a whole, and along with it, an area 811 in which messages are displayed, an area 812 in which an avatar is displayed, and the degree of achievement of the game content result are displayed. It may include an area 813.

At this time, messages displayed in the area 811 in which messages are displayed may be messages sent by a user or messages generated by the content creation server 100 using the 2-1 artificial neural network.

Meanwhile, the avatar displayed in the area 812 in which the avatar is displayed may be an avatar image generated by the content creation server 100 using the 2-2 artificial neural network.

9 is a flowchart illustrating a method of producing game play contents performed by the server 100 including the apparatus 110 for producing game play contents according to an embodiment of the present invention. Hereinafter, descriptions of contents overlapping with those described in FIGS. 1 to 8 will be omitted, but will be described with reference to FIGS. 1 to 8 together.

The server 100 according to an exemplary embodiment of the present invention may check the first progress of the game content (S910). Meanwhile, the server 100 transmits the video content including the confirmed first situation to the external device 300. (S920) In some steps (S920, S960, S990) of FIG. 9, video content streaming is shown to take place between different steps, but this is only to indicate that video content is streamed in real time. , The predecessor relationship with other stages or the number of streaming are not limited thereto.

The server 100 according to an embodiment of the present invention uses the first artificial neural network 520 to generate an operation input 630 according to the first progress status 610, which is the progress status of the game content 660. (S930) At this time, the server 100 may generate a manipulation input 630 according to the first progress status 610 by further considering the user's feedback 620.

The server 100 according to an embodiment of the present invention can play the game content 660 by inputting the manipulation input 630 generated in the game content 660. (S940) In addition, the server 100 operates According to the input of the input 630, a second progress status 670, which is a changed progress status, can be checked. (S950) Parallel to this, the server 100 according to an embodiment of the present invention provides a first progress status ( The image content 700 including a process of changing the progress status from 620 to the second progress status 670 may be generated. The generated image content 700 may be streamed to the external device 300 in steps S920 described above and steps S960 and S980 described later. For example, if the game content 660 is a block breaking content as shown in FIG. 8, the server 100 moves the lower bar according to the generated manipulation input 630, the process of bounced on the moved bar, and the process of bounced up. Video content 700 including a process in which some blocks are broken by a ball may be generated.

The server 100 according to an embodiment of the present invention may receive a feedback 620 from a user viewing the video content 700 in parallel with the generation and transmission of the video content 700 described above. S970) At this time, the time point at which the feedback is received is not limited to the time point shown in FIG. 9.

In addition, the server 100 may generate response content including a response to the received feedback 620 using the second artificial neural networks 540 and 560 (S980). For example, the server 100 may generate a second artificial neural network (S980). -1 By using the artificial neural network 540 to generate a response message 640 to the user's feedback 620 received during the playing process of the game content 660 (or during the streaming process of the video content 700) It can be transmitted to the terminal 200. (S990) At this time, the server 100 additionally considers the first progress status 610 and the manipulation input 630 according to the first progress status 610, and the user's feedback 620 A response message 640 for may be generated.

In addition, the server 100 responds to the user's feedback 620 received during the playing process of the game content 660 (or during the streaming process of the video content 700) using the 2-2 artificial neural network 560 The avatar image 650 may be generated and transmitted to the user terminal 200 (S990). Of course, also at this time, the server 100 may input a manipulation input 630 according to the first progress status 610 and the first progress status 610. ) May be additionally considered to generate a response avatar image 650 to the user's feedback 620.

Accordingly, the present invention can generate game play content for playing the game content 660 using the learned artificial neural network. In particular, by learning an artificial neural network according to the purpose of the present invention, it is possible to generate not only game play content that proceeds in the direction in which the degree of achievement of the game content is the maximum, but also game play content that proceeds in the direction in which the degree of feedback from users is maximum have.

In addition, the present invention may provide a user with an immersion feeling as if the game content 660 is being played by a person by providing various types of response content along with a play image of the game content.

Furthermore, the present invention reduces the temporal and physical constraints of generating game play contents, thereby enabling the creation of a larger amount of game play contents.

The embodiment according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded in a computer-readable medium. In this case, the medium may store a program executable by a computer. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be ones configured to store program instructions, including ROM, RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to a person skilled in the computer software field. Examples of the computer program may include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

Specific implementations described in the present invention are examples, and do not limit the scope of the present invention in any way. For brevity of the specification, descriptions of conventional electronic configurations, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection or connection members of the lines between the components shown in the drawings exemplarily represent functional connections and/or physical or circuit connections. It may be referred to as a connection, or circuit connections. In addition, if there is no specific mention such as "essential", "important", etc., it may not be an essential component for the application of the present invention.

Accordingly, the spirit of the present invention is limited to the above-described embodiments and should not be defined, and all ranges equivalent to or equivalently changed from the claims to be described later as well as the claims to be described later are the scope of the spirit of the present invention. It will be said to belong to.

100: server
110: gameplay content creation device
111: communication department
112: control unit
113: memory
200: user terminal
300: video streaming server
400: communication network

Claims (9)

A game play content production apparatus for generating video content including content on which game content is played and response content to a feedback received from a user during the playing process, the device comprising:
Using a first artificial neural network, an operation input according to a first progress situation is generated, and the generated operation input is input to the game content to play the game content according to the input of the operation input. Generate video content including a process of changing a progress situation from the first progress situation to a second progress situation,
Receiving the feedback of the user viewing the video content, and generating a response content including a response to the feedback by using a second artificial neural network, game play content production apparatus. The method according to claim 1
The first artificial neural network
An operation input in the first progress situation is performed based on a plurality of progress states of the game content, an operation input in each of the plurality of progress states, and a progress result of the game content according to an operation input in each of the plurality of progress states. A device for creating gameplay content, a neural network that has been trained to generate. The method according to claim 2
The first artificial neural network
According to the operation input, the game play content production device is learned in a direction in which the result of the game content is achieved at a maximum level. The method according to claim 1
The first artificial neural network
A plurality of progress statuses of the game content, an operation input in each of the plurality of progress situations, a progress result of the game content according to an operation input in each of the plurality of progress situations, and a plurality of users in each of the plurality of progress situations A device for producing game play content, which is a neural network that has been trained to generate an operation input in the first progress situation based on feedback. The method of claim 4
The first artificial neural network
According to the operation input, the user's feedback degree is learned in a direction in which the maximum degree of feedback is maximized. The method according to claim 1
The response content is
As a message in consideration of the first progress situation, the game play content production apparatus including a message that is a response to the user's message. The method according to claim 1
The response content is
The apparatus for producing game play content, which is an avatar image taking into account the first progress situation, which is an image including an avatar image whose display is changed according to a message of the user. The method according to claim 1
The device is
Apparatus for producing game play content, providing the response content together with the video content to one or more user terminals. Using a computer
A computer program stored in a medium to execute the method of any one of claims 1 to 8.

Images