Spatial user-customized content creation service system using generative artificial intelligence

Abstract

The present invention relates to a spatial user-customized content creation service system using generative artificial intelligence. According to an embodiment of the present invention, there are effects capable of: automatically generating spatially optimized content by learning user data; adjusting, in real time, the generated content according to multiple spaces and various display environments; easily creating high-quality content on the basis of prompts such as text, voice, and images input by a user; increasing user satisfaction and reducing time and cost by providing customized content by effectively utilizing the user data in a content creation process; and automatically projecting content according to spatial characteristics and user preference.

Description

Space-specific user-customized content creation service system using generative AI

[0001] The present invention relates to a space-specific user-customized content creation service system using generative artificial intelligence.

[0002] This application claims priority based on Korean Patent Application No. 10-2024-0180692 filed on December 6, 2024, and all contents described in the specification and drawings of said application are incorporated into this application.

[0003] Recently, generative AI technology has been demonstrating outstanding performance in generating new content based on input data.

[0004] These technologies are being utilized in various fields such as image generation, text creation, and video production, and are dramatically improving the user experience.

[0005] Existing content creation systems generally provide simple creation tasks or standardized workflows, and had limitations in creating user-customized content.

[0006] In particular, content creation and display optimization that reflect the characteristics of a specific space or user data often required manual work or additional tools.

[0007] For example, when utilizing content across multiple spaces, the process of creating content tailored to the characteristics of each space and adapting it to the display environment requires specialized expertise and necessitates significant time and cost.

[0008] Therefore, there is a growing demand for systems that learn user data, generate content optimized for each space based on it, and automatically adjust the generated content to suit the display environment.

[0009] The technical objective of the present invention is to provide a space-specific user-customized content production service system using generative artificial intelligence, which can automatically generate content optimized for each space by learning user data, adjust the generated content in real time to suit multiple spaces and various display environments, easily produce high-quality content based on prompts such as text, voice, and images entered by the user, increase user satisfaction and reduce time and costs by effectively utilizing user data during the content production process to provide customized content, and automatically project content according to the characteristics of the space and user preferences.

[0010] The objectives of the present invention are not limited thereto, and other unmentioned objectives will be clearly understood by a person skilled in the art from the description below.

[0011] An embodiment of the present invention for achieving the above technical objectives provides a space-specific user-customized content creation service system using generative artificial intelligence, comprising: a communication module unit that receives prompt information including at least one of text information, image information, and voice information from a user terminal device; a data storage unit that separates and stores content information utilized by each user for each predetermined space; a first generative artificial intelligence model that generates first generative image information based on the prompt information authorized from the communication module unit; a second generative artificial intelligence model that learns the content information to extract popular content information of the user for each space and generates second generative image information using the first generative image information based on the extracted popular content information; an artificial intelligence agent module unit; and a content output module unit that outputs the second generative image information to the outside.

[0012] In addition, the above prompt information is selected by the user terminal device from a plurality of recommendation prompt information authorized by the artificial intelligence agent module to the user terminal device through the communication module, thereby providing a space-specific user-customized content creation service system using generative artificial intelligence.

[0013] Additionally, the artificial intelligence agent module further includes a third generative artificial intelligence model that generates generative video information using the second generative image information, and the content output module outputs the second generative image information or the generative video information to the outside, thereby providing a space-specific user-customized content production service system using generative artificial intelligence.

[0014] According to one embodiment of the present invention, content optimized for each space can be automatically generated by learning user data, and the generated content can be adjusted in real time to suit multiple spaces and various display environments. High-quality content can be easily produced based on prompts such as text, voice, and images entered by the user. Furthermore, by effectively utilizing user data during the content production process to provide customized content, user satisfaction can be increased and time and costs can be reduced. Additionally, content can be automatically projected according to the characteristics of the space and the user's preferences.

[0015] FIG. 1 is a block diagram showing a space-specific user-customized content production service system using generative artificial intelligence according to an embodiment of the present invention.

[0016] Figure 2 is a diagram showing content information stored in a data storage unit and an example of a second generative artificial intelligence model learning the content information.

[0017] FIG. 3 is a diagram briefly illustrating the entire process of generating second generative image information through a space-specific user-customized content production service system using generative artificial intelligence according to an embodiment of the present invention.

[0018] [Explanation of the symbol]

[0019] 100: Space-specific user-customized content creation service system using generative AI

[0020] 101 : User terminal device

[0021] 103 : Communication Module

[0022] 105 : Data storage unit

[0023] 107 : The first generative artificial intelligence model

[0024] 109 : Second Generative Artificial Intelligence Model

[0025] 111 : Artificial Intelligence Agent Module

[0026] 113 : Content Output Module

[0027] 115 : Third Generative Artificial Intelligence Model

[0028] i1 : Text information

[0029] i3 : Image information

[0030] i4 : Voice information

[0031] i5 : Prompt information

[0032] i7 : Content Information

[0033] i9 : First generated type image information

[0034] i11 : Popular Content Information

[0035] i13 : Second generation shape image information

[0036] i15 : Recommended prompt information

[0037] i17 : Generated video information

[0038] Hereinafter, some embodiments of the present invention will be described in detail with reference to the exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present invention, if it is determined that a detailed description of related known components or functions could obscure the essence of the invention, such detailed description is omitted.

[0039] In addition, terms such as first, second, A, B, (a), (b), etc., may be used when describing the components of the present invention. These terms are intended only to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the terms. Where it is stated that a component is "connected," "combined," or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but that another component may also be "connected," "combined," or "connected" between each component.

[0040] FIG. 1 is a block diagram illustrating a space-specific user-customized content production service system using generative artificial intelligence according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of content information stored in a data storage unit and a second generative artificial intelligence model learning the content information. FIG. 3 is a diagram briefly illustrating the entire process of generating second generative image information through a space-specific user-customized content production service system using generative artificial intelligence according to an embodiment of the present invention.

[0041] As illustrated in these drawings, a space-specific user-customized content creation service system (100) using generative artificial intelligence according to an embodiment of the present invention comprises: a communication module (103) that receives prompt information (i5) including at least one of text information (i1), image information (i3), and voice information (i4) from a user terminal device (101); a data storage unit (105) that distinguishes and stores content information (i7) utilized by each user for each predetermined space; and a first generative artificial intelligence model (107) that generates first generative image information (i9) based on the prompt information (i5) authorized from the communication module (103); The AI ​​agent module (111) includes: a second generative AI model (109) that learns content information (i7) to extract user's popular content information (i11) for each space and generates second generative image information (i13) using first generative image information (i9) based on the extracted popular content information (i11); and a content output module (113) that outputs the second generative image information (i13) to the outside.

[0042] Below, each component is described in detail.

[0043] Communication module (103)

[0044] The communication module (103) receives prompt information (i5) including at least one of text information (i1), image information (i3), and voice information (i4) from the user terminal device (101).

[0045] Meanwhile, the prompt information (i5) may be selected by the user terminal device (101) from a plurality of recommended prompt information (i19) authorized to the user terminal device (101) through the communication module (103) by the artificial intelligence agent module (111) to be described later.

[0046] The user terminal device (101) can be various terminal devices, such as a PC, laptop, smartphone, tablet, KIOSK, etc.

[0047] The communication module (103) can communicate with the user terminal device (101) via wired or wireless means.

[0048] The prompt information (i5) received by the communication module (103) from the user terminal device (101) includes at least one of text information (i1), image information (i3), and voice information (i4).

[0049] A prompt is one of the core concepts of generative artificial intelligence, referring to a command or question that a user inputs into an AI model.

[0050] Through prompts, the AI ​​model can generate various content such as text, images, and music.

[0051] Beyond simply asking questions, prompts serve as an important tool that helps AI models generate desired results effectively.

[0052] The user terminal device (101) may include, for example, an input window displayed on a display to receive a text input signal or an image input signal from a user to generate text information (i1) or image information (i3), and a microphone to receive voice input from a user to generate voice information (i4).

[0053]

[0054] Artificial intelligence agent module (111)

[0055] The artificial intelligence agent module (111) includes a data storage unit (105), a first generative artificial intelligence model (107), and a second generative artificial intelligence model (109).

[0056] The data storage unit (105) stores content information (i7) used by each user separately for each designated space.

[0057] For example, if the content used by the user in space A (e.g., the Oriental painting hall of an exhibition hall) is content a (ink painting), content b (landscape painting), etc., and the content used by the user in space B (e.g., the Western painting hall of an exhibition hall) is content c (portrait painting), content d (landscape painting), etc., the data storage unit (105) can distinguish the content used for each space and store it as content information (i7).

[0058] Next, the first generative artificial intelligence model (107) generates the first generative image information (i9) based on the prompt information (i5) authorized from the communication module (103).

[0059] The first generative artificial intelligence model (107) generates first generative image information (i9) that can be imagined based on prompt information (i5) including text information such as, for example, ‘blue sea and sky and people on the beach’.

[0060] At this time, various algorithms (natural language processing (NLP) algorithms, image generation algorithms, deep learning networks, etc.) are utilized within the first generative artificial intelligence model (107) to analyze and understand input prompt information (i5).

[0061] The first generative artificial intelligence model (107) generates the first generative image information (i9) after analyzing the information included in the prompt information (i5) based on learned patterns and styles.

[0062] Next, the second generative artificial intelligence model (109) learns content information (i7) to extract user's popular content information (i11) by space, and generates second generative image information (i13) using the first generative image information (i9) based on the extracted popular content information (i11).

[0063] The second generative artificial intelligence model (109) utilizes the first generative image information (i9) as basic information for generating the second generative image information (i13).

[0064] Content information (i7) may include user behavior data regarding the content (time the user utilized (watched) the content, content utilization cycle, preference for specific content, etc.), and the second generative artificial intelligence model (109) can extract user popular content information (i11) by space through the analysis of such behavior data.

[0065] In addition, the second generative artificial intelligence model (109) can utilize the main features of the content (e.g., content tone, texture, art style, etc.) related to the extracted popular content information (i11) when generating the second generative image information (i13).

[0066] Meanwhile, the artificial intelligence agent module (111) may further include a third generative artificial intelligence model (115) that generates generative video information (i17) using the second generative image information (i13).

[0067] To explain it more specifically step-by-step,

[0068] (1) Understanding input images and information

[0069] The third generative artificial intelligence model (115) uses the second generative image information (i13) as input data and utilizes it as basic data for generating generative video information (i17).

[0070] (2) Frame generation

[0071] The third generative artificial intelligence model (115) generates each frame in the process of arranging multiple images in chronological order based on the second generative image information (i13).

[0072] In this process, the elements of each frame are meticulously planned and adjusted to create dynamic movement based on static images.

[0073] (3) Motion and animation design

[0074] The third generative artificial intelligence model (115) uses animation techniques to bring life to the images, which are the basic components of each frame.

[0075] The third generative artificial intelligence model (115) sets key points through keyframe technology and automatically interpolates the movement between them.

[0076] (4) Rendering and final modification

[0077] The third generative artificial intelligence model (115) renders the final video by comprehensively combining all of the above elements.

[0078] The third generative artificial intelligence model (115) checks the quality of each frame, corrects errors, and sets the resolution and ratio of the final output.

[0079] In addition, the third generative artificial intelligence model (115) allows each element to flow smoothly through detailed adjustment of specific effects or animations.

[0080]

[0081] Content output module (113)

[0082] The content output module (113) outputs the second generated image information (i13) authorized from the artificial intelligence agent module (111) to the outside.

[0083] The content output module (113) can output the second generated image information (i13) or the generated video information (i17) to the outside when the artificial intelligence agent module (111) generates the generated video information (i17) through the third generated artificial intelligence model (115) as described above.

[0084] The content output module (113) may be provided in multiple numbers.

[0085] The content output module (113) can be provided as, for example, a projector.

[0086]

[0087] As described above, according to one embodiment of the present invention, content optimized for each space can be automatically generated by learning user data, and the generated content can be adjusted in real time to suit multiple spaces and various display environments. High-quality content can be easily produced based on prompts such as text, voice, and images entered by the user. Furthermore, by effectively utilizing user data during the content production process to provide customized content, user satisfaction can be increased and time and costs can be reduced. Additionally, content can be automatically projected according to the characteristics of the space and the user's preferences.

[0088] Although it has been described above that all components constituting an embodiment of the present invention are combined or operate as a single unit, the present invention is not necessarily limited to such an embodiment. That is, within the scope of the purpose of the present invention, all components may be selectively combined in one or more ways to operate.

[0089] The foregoing description is merely an illustrative explanation of the technical concept of the present invention, and those skilled in the art to which the present invention pertains will be able to make various modifications and variations within the scope of the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are intended to explain, not limit, the technical concept of the present invention, and the scope of the technical concept of the present invention is not limited by these embodiments. The scope of protection of the present invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present invention.

Claims

1. A communication module that receives prompt information including at least one of text information, image information, and voice information from a user terminal device; An artificial intelligence agent module comprising: a data storage unit that separates and stores content information utilized by each user for each predetermined space; a first generative artificial intelligence model that generates first generative image information based on the prompt information authorized from the communication module unit; and a second generative artificial intelligence model that learns the content information to extract popular content information of the user for each space, and generates second generative image information using the first generative image information based on the extracted popular content information; and A content output module that outputs the above-mentioned second generated image information to the outside; including, Space-specific user-customized content creation service system using generative artificial intelligence.

2. In Paragraph 1, The above prompt information is, Selected by the user terminal device from a plurality of recommendation prompt information authorized by the artificial intelligence agent module to the user terminal device through the communication module, Space-specific user-customized content creation service system using generative artificial intelligence.

3. In Paragraph 1, The above artificial intelligence agent module is, It further includes a third generative artificial intelligence model that generates generative video information using the second generative image information above, and The above content output module is, Outputting the above-mentioned second generated image information or the above-mentioned generated video information to the outside, Space-specific user-customized content creation service system using generative artificial intelligence.

Images