Media platform, method, medium and program for performing text input into three-dimensional (3D) models

Abstract

The graphics-specialized search engine receives a search input from a user account on the media platform, determines a search query parsed from the input, and searches a graphics-specialized database for existing images corresponding to the search query. The image generator generates a new image corresponding to the search query if the search results do not exceed a predetermined number. The graphics display engine sends the plurality of images to the instance of the account on the media platform.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Application No. 18 / 054592, filed November 11, 2022, entitled "TEXT INPUT TO THREE-DIMENSIONAL (3D) MODELS," the entirety of which is incorporated herein by reference.

[0002] SUMMARY OF THE INVENTION Embodiments described herein generally relate to providing three-dimensional (3D) models to media accounts based on text input into a media platform. [Background technology]

[0003] Text-to-image generation is increasingly being implemented on a large scale, based on both open source and proprietary solutions. Image generators receive natural language descriptors and produce images that correspond to the input descriptors, as a result of the generator being trained on both descriptors and images obtained from a variety of sources, including results obtained from internet search engines. Summary of the Invention

[0004] In one embodiment, the media platform includes a graphics-specialized search engine that receives a search input, determines a search query from the received search input, and searches a graphics-specialized database for existing images corresponding to the search query. The media platform further includes an image generator that generates new images corresponding to the search query if the search results do not exceed a predetermined number, and a graphics display engine that sends at least a number of the generated new images to an instance of an account of the media platform.

[0005] According to at least one other exemplary embodiment, a method for generating three-dimensional (3D) models includes receiving a search input, searching a database for 3D models corresponding to keywords corresponding to the search input, and displaying a plurality of 3D models corresponding to the search for selection on an instance of an account of a multimedia platform. If the search results in less than a threshold number of existing 3D models, at least a portion of the displayed 3D models are generated based on the keywords.

[0006] According to at least one other exemplary embodiment, a non-volatile computer-readable medium has stored thereon computer-executable instructions that, when executed, cause one or more processors to perform the following operations: receiving an input, parsing searchable parameters from the input, expanding the searchable parameters, searching a database for existing images corresponding to the expanded searchable parameters, and if the number of results of the search is greater than or equal to a threshold, displaying a predetermined number of the existing images for selection on an instance of a social media account; if the number of results of the search is less than the threshold, generating new images based on the expanded searchable parameters, and displaying the predetermined number of generated new images for selection on the social media account. [Brief explanation of the drawings]

[0007] In the following detailed description, embodiments are described by way of example only, and various changes and modifications will become apparent to those skilled in the art from the following detailed description. The same reference numerals in different figures indicate similar or identical items.

[0008] [Figure 1] FIG. 1 illustrates a system capable of implementing text entry into a 3D model, arranged in accordance with at least some embodiments described and cited herein.

[0009] [Figure 2]FIG. 1 is a schematic diagram of a storage / database utilized in implementing text entry into 3D models, arranged in accordance with at least some embodiments described and cited herein.

[0010] [Figure 3] FIG. 1 illustrates an exemplary process flow for implementing text entry into a 3D model in accordance with at least some embodiments described and illustrated herein.

[0011] [Figure 4] FIG. 1 illustrates an exemplary computing embodiment in which the process of obtaining a 3D model based on text input and any of the sub-processes are implemented as executable instructions stored on a non-volatile computer-readable medium. DETAILED DESCRIPTION OF THE INVENTION

[0012] In the following detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, like symbols generally refer to like components unless context dictates otherwise. Furthermore, unless otherwise stated, the description of each successive drawing may reference one or more features of the previous drawing to provide clearer context and a substantive description of the present exemplary embodiments. However, the exemplary embodiments described in the detailed description, drawings, and claims are not intended to be limiting. Other embodiments may be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein. It will be readily understood that the aspects of the present disclosure as generally described and illustrated herein, and illustrated in the drawings, can be arranged, substituted, combined, separated, and designed in a wide variety of different configurations, all of which are expressly contemplated herein.

[0013] Furthermore, portions of the disclosure may be described herein in terms of functional block components and various processing steps, it being understood that such functional blocks may be realized by any number of hardware and / or software components configured to perform the specified functions.

[0014] In this explanation and description, the following terms may be used in addition to their ordinary meaning as follows:

[0015] This specification refers to learning or trained computer or processor-related technologies in which decisions and / or actions are made autonomously, instead of human intervention. Such technologies include software, i.e., algorithms and / or programs, hardware, or firmware, or any combination thereof, supporting machine learning, natural language understanding, natural language processing, speech recognition, computer vision, etc. The scope of functionality and capabilities associated with the embodiments disclosed, cited, and suggested herein also includes image generation, in which an image or model is generated based on an input. 3D models are one type of generated image contemplated by the non-limiting embodiments disclosed, cited, and suggested herein. While the exemplary embodiment also utilizes text input, utilizing voice or image input is also within the scope of such embodiments.

[0016] The generated image may refer to a latent representation of a user or machine input to an enabled computer or processor. The generated image is obtained from an enabled computer or processor that has been trained with a large number of images corresponding to input, such as text, audio, or images, obtained from various sources, including predefined or general searches from various internet resources. According to at least some embodiments, the generated image is further the result of at least a portion of the user or machine input being augmented, supplemented, or expanded with appropriately classified descriptors.

[0017] Algorithms and programs for creating images containing 3D models are known in the art, and further, the aforementioned descriptors are matched or associated with an input or portion thereof based on known learning techniques.

[0018] As disclosed and described herein, a social media application refers to an online application that enables users who have an account to interact with each other on various scales using various media, including creating and / or sharing media content. As disclosed and described herein, a user device may have a locally stored instance of a social media application account, or the user's account may be accessed through a web-based version of the particular social media application.

[0019] As disclosed and described herein, a platform, e.g., a social media platform, may refer to an application capable of hosting algorithms and / or programs that enable the execution or implementation of a collection of communication-based or media-sharing technologies, non-limiting examples of which include the creation, sharing, and / or storage of multimedia offerings.

[0020] Media or multimedia offerings or experiences referred to herein include, but are not limited to, recorded or live transmittable content such as text, audio, images, animation, video, etc. Additionally, such offerings or experiences may include, but are not limited to, interactive augmented reality (AR) and / or interactive virtual reality (VR) experiences.

[0021] Augmented reality (AR), as referred to herein, may refer to one or more interactive reality-based display environments that utilize computer-generated displays, audio, text, and other sensory-driven effects to enhance the user's experience. AR integrates digital information into the user's real-world environment.

[0022] Virtual reality (VR), as referred to herein, may refer to one or more interactive reality-based viewing environments that utilize computer-generated displays, audio, text, and other sensory-driven effects to allow users to experience and interact with their surroundings as if they were in a real-world environment. VR provides sensory stimuli that, combined with the user's physical movements, affect a corresponding digital environment.

[0023] An engine or generator as disclosed, cited, and / or suggested herein may refer to any type of software, firmware, hardware, or any combination thereof that facilitates the generation of source code or markup for generating elements that initiate another process. Additionally or alternatively, the engine or generator facilitates an automated process in which various software elements interact to generate an intended product, whether physical or virtual. In accordance with known machine learning technologies, the engine or generator as disclosed, cited, and / or suggested herein may be trained according to a unimodal or multimodal training model.

[0024] A 3D (three-dimensional) image or model disclosed, cited, and / or suggested herein may refer to a single image or image model that can incorporate multiple viewpoints simultaneously. 3D imaging is known in the art.

[0025] FIG. 1 illustrates a system in which inputs to a 3D model may be implemented and arranged in accordance with at least some embodiments described and cited herein. As illustrated, system 100 includes at least a media platform 105 that includes at least a storage / database 110, a search engine 115, an image generator 120, and a display engine 125. System 100 also includes a device 130 that can host or access an instance of a user account 135 corresponding to media platform 105. While shown as separate components, various components may be divided into additional components, combined into fewer components, or eliminated entirely within the scope of the disclosed subject matter. Those skilled in the art will appreciate that the functionality and / or operation of each of the components may be implemented individually or collectively by various hardware, software, firmware, or any combination thereof.

[0026] Media platform 105 may refer to a server or cluster of servers on which one or more algorithms and / or programs designed, programmed, or otherwise configured to execute or implement various media-related technologies are hosted. A non-limiting exemplary embodiment of media platform 105 is provided as a social media platform. As such, media platform 105 may provide a variety of services, such as providing recorded or live-streaming content or interactive AR or VR experiences, to accounts 135 hosted or accessed on devices 130.

[0027] Storage / database 110 may refer to algorithms, programs, components, and / or modules hosted on media platform 105 or remotely and communicatively associated with media platform 105. Storage / database 110 may be designed, programmed, or otherwise configured to receive and store queries and / or search terms corresponding to input 140 received at platform 105 from accounts 135.

[0028] The storage / database 110 and / or search engine 115 can be trained, designed, programmed, or otherwise configured to parse one or more search parameters (e.g., keywords and / or associated physical characteristics) from the input 140. According to at least some embodiments, the parsed search parameters (i.e., keywords) serve as the basis for an image search. In addition to such embodiments, the parsed search parameters are categorized and stored in the storage / database 110 according to known techniques.

[0029] Storage / database 110 is also trained, designed, programmed, or otherwise configured to store and / or retrieve for displaying at least graphical images, e.g., 3D models, generated by image generator 120 in accordance with the non-limiting exemplary embodiments described and cited herein.

[0030] Search engine 115 may refer to algorithms, programs, components, and / or modules hosted on media platform 105 or remotely and communicatively associated with media platform 105. Search engine 115 may be trained, designed, programmed, or otherwise configured to receive input 140 from account 135 and search the contents of storage / database 110 for content (e.g., 3D models) that matches or corresponds to at least one search parameter parsed from input 140 from account 135. The input may be received directly from input 140 or, according to at least some embodiments, from storage / database 110.

[0031] According to at least some non-limiting exemplary embodiments described, cited, and suggested herein, search engine 115 and / or storage / database 110 are further trained, designed, programmed, or otherwise configured to expand, supplement, or augment with appropriately categorized descriptors at least one search parameter parsed from input 140 received from account 135. Thus, search engine 115 and / or storage / database 110 can expand the scope of stored content that is searched and / or retrieved for display.

[0032] Image generator 120 may refer to a trained algorithm, program, component, and / or module hosted on media platform 105 or remotely and communicatively associated with media platform 105. Image generator 120 may be designed, programmed, or otherwise configured to newly generate an image corresponding to at least one search parameter analyzed from input 140 received from account 135. According to various embodiments disclosed, cited, and suggested herein, image generator 120 may receive augmented, supplemented, or expanded analyzed search parameters from storage / database 110 before generating the new image.

[0033] That is, based on known iterative training techniques, storage / database 110 is populated and stored with a library of query and / or search term categories and descriptors corresponding to each query / term. Thus, as keywords or other parameters are parsed from input 140 and corresponding descriptors are attached or added, image generator 120 generates new images that match or correspond to the augmented, supplemented, or expanded query / terms. According to at least some embodiments, if a search result in storage / database 110 results in less than a threshold (e.g., 30) number of matching or corresponding existing images, generation of new images is performed based on input 140 or the augmented, supplemented, or expanded query / terms.

[0034] Display engine 125 may refer to a trained algorithm, program, component, and / or module hosted on media platform 105 or remotely and communicatively associated with media platform 105. Display engine 125 may be designed, programmed, or otherwise configured to execute instructions to display content retrieved from storage / database 110 if the number of existing images that match or correspond to at least a portion of input 140 received from account 135 or an expanded, supplemented, or expanded query / term is greater than or equal to a threshold value (e.g., 30). The threshold scale may be dynamic depending on user context, user preferences, display capabilities, local storage capacity, etc. Additionally or alternatively, display engine 125 may be designed, programmed, or otherwise configured to execute instructions to display content generated by image generator 120.

[0035] Device 130 may refer to one or more embodiments of a conventional computing environment that is or includes a conventional computer, processing device, microprocessor, microcontroller, digital signal processor, or any combination thereof, on which account 135 or an instance thereof is assembled, managed, compiled, and / or executed. Device 130 may be one or a combination of various electronic devices that have one or more display screens with audio and / or video input / output and support the provision and consumption of content related to media platform 105. Various electronic devices include, but are not limited to, smartphones, tablet computers, laptop computers, desktop computers, e-readers, MP3 (moving picture experts group audio layer III) players, MP4, and / or other suitable electronic devices.

[0036] The one or more servers or server clusters on which the media platform 105 is hosted and the devices 130 may refer to a high-performance computing (HPC) environment that includes at least a CPU and a GPU present on a video card embedded in a motherboard or on a CPU die. As disclosed and described herein, conversion of text input, etc., into a 3D model can be performed entirely on the CPU or partially on the CPU and GPU. Alternative embodiments can be performed on evolving HPC components known in the art. In any event, the CPU, GPU, and / or HPC components can store one or more algorithms and / or programs that, when executed, can cause the execution or performance of the operations and / or functions disclosed and / or described herein. Furthermore, computer-readable non-volatile media may be provided in accordance with the embodiments described herein. The computer-readable media stores a computer program. When executed by a processor, the computer program is used to perform at least the operations or functions associated with the embodiments described and illustrated herein.

[0037] Input 140, according to at least some of the embodiments disclosed and described herein, may refer to text, audio, or images manually or automatically entered into an appropriate input interface corresponding to an instance of account 135. Input 140 may be transmitted or communicated to a receiving component corresponding to media platform 105 via a wired or wireless network. Such a network may be considered a medium that serves as a two-way communication link between media platform 105 and device 130. Networks may include the Internet, a local area network (LAN), a wide area network (WAN), a local interconnect network (LIN), a localized cloud, etc.

[0038] FIG. 2 is a schematic diagram of a storage / database 110 utilized to implement input to a 3D model, arranged in accordance with at least some embodiments described and referenced herein. As shown, the storage / database 110 includes at least a query library 205 and an image library 210. The query library 205 includes category sub-libraries 215A-215N and corresponding descriptor sub-libraries 220A-220N. Those skilled in the art will appreciate that the number of libraries and sub-libraries herein is not limited to the number shown in the figure, as "N" is intended to mean an unlimited number. Furthermore, unless the context requires otherwise, reference may be made to the singular or plural "category library 215" and / or "descriptor library 220," without excluding other examples. It will also be understood that each storage function and / or operation of the various libraries or storage components may be implemented, individually and / or collectively, by a wide variety of hardware, software, firmware, or any combination thereof.

[0039] The query library 205 may be designed, configured, or otherwise programmed to receive raw, parsed, or expanded, supplemented, or augmented input 140. When the expansion, supplementation, or expansion of the parsed search parameters is performed in the storage / database 110, the expanded parameters are assigned or otherwise stored in one of the category libraries 215 based on known training techniques.

[0040] The query library 205 may also be designed, configured, or programmed to expand, supplement, or extend the categorized parsed search parameters with descriptors from an appropriate corresponding one of the libraries 220 .

[0041] The library 210 may refer to one or more sub-libraries that receive and / or store images that are subject to searching by the search engine 115. The descriptors may be obtained from a variety of sources, including the results of one or more internet search engines.

[0042] By way of a non-limiting example, if input 140 is "armchair furniture," search engine 115 and / or storage / database 110 may parse "armchair" from input 140, either alone or in combination, which, by way of example, corresponds to category N 215N, and may expand, supplement, or extend "armchair" with descriptor N in sub-library 220N. Thus, search engine 115 and / or storage / database 110 may expand the scope of content stored in library 210, which stores, for example, 3D models of armchairs. Non-limiting examples of expanded query / search terms include "purple armchair," "oak armchair," "60s armchair," "modern armchair," etc. The search engine may then search the corresponding portion of library 210 or sub-library 210N for images matching or corresponding to the expanded query / search terms. This example is not limiting. For example, if the input 140 is "armchair furniture," the search engine 115 and / or storage / database 110 may instead parse "furniture" from the input 140, which corresponds to another category from categories A through N. Furthermore, for any non-limiting exemplary embodiment, the parsed search term may correspond to multiple categories from categories A through N.

[0043] 3 illustrates an example process flow for implementing input to a 3D model in accordance with at least some embodiments described and cited herein. As shown, process flow 300 includes sub-processes performed by various components of system 100, including media platform 105. However, process flow 300 is not limited to such components and processes, and obvious modifications may be made by changing the order of two or more of the sub-processes described herein, deleting at least one of the sub-processes, adding additional sub-processes, substituting components, or assigning various components to perform sub-processing responsibilities assigned to other components in the following description.

[0044] According to at least a non-limiting exemplary embodiment of an implementation process for inputting into a 3D model, the various components or modules of FIGS. 1 and 2 are trained, designed, programmed, or otherwise configured to receive a text search input from an instance of an account on a multimedia platform, magnify a keyword from the received text search input, search a database for existing three-dimensional (3D) models corresponding to the magnified keyword, and display a plurality of existing 3D models corresponding to the magnified keyword for selection on the instance of the account on the multimedia platform.

[0045] According to at least one other non-limiting exemplary embodiment, the various components or modules of FIGS. 1 and 2 are trained, designed, programmed, or otherwise configured to receive input from a user interface of a social media account, parse at least one searchable parameter from the received input, expand the at least one searchable parameter, search a database for existing images corresponding to the expanded at least one searchable parameter, and if the search results in a number of existing images equal to or greater than a threshold, display a predetermined number of the existing images for selection on the social media account; and additionally or alternatively, if the search results in a number of existing images less than the threshold, generate new images based on the expanded at least one searchable parameter, and display a predetermined number (e.g., 15) of the generated new images for selection on the social media account.

[0046] Process flow 300 may include various operations, functions, or actions, as indicated by one or more of blocks 305, 310, 315, 320, 325, 330, 335, 340, and 345. These various operations, functions, or actions may correspond to, for example, software, program code, or program instructions executable by a digital processor that cause the performance of a function. Processing begins at block 305.

[0047] In block 305 (receive input), the storage / database 110 and / or search engine 115 receives and / or stores the input 140 from the account 135. Processing may proceed to block 310.

[0048] At block 310 (Parse Searchable Parameters), the storage / database 110 and / or search engine 115 parses one or more search parameters (such as keywords and / or associated physical characteristics) from the received input. The parsed search parameters (keywords) are used as the basis for an image search, which are then categorized according to known techniques and stored in one of the appropriate libraries 215. Processing continues at block 315.

[0049] In block 315 (Expanding Searchable Parameters), the storage / database 110 and / or search engine 115 expands, supplements, or extends the parsed search parameters using appropriately categorized descriptors stored in the storage / database 110. Processing may proceed to block 320.

[0050] In block 320 (Search for existing images), the search engine 115 searches for existing images (such as 3D models stored in the storage / database 110) that match or correspond to the expanded search parameters. Processing may proceed to decision block 325.

[0051] At decision block 325 (Existing Images > Threshold), the search engine 115 determines whether the number of existing images, such as 3D models, stored in the storage / database 110 that match or correspond to the expanded search parameters exceeds a threshold. The threshold scales dynamically depending on the user context, user preferences, display capabilities, local storage capacity, etc. If the determination at decision block 325 is "yes," processing continues at block 330. If the determination at decision block 325 is "no," processing continues at block 340.

[0052] At block 330 (Display Existing Images), the display engine 125 displays the retrieved content from the storage / database 110 for viewing and / or selection by the user corresponding to the account 135. The retrieved content is displayed if the number of existing images that match or correspond to the expanded search parameters is equal to or exceeds a threshold. According to at least some example embodiments, the existing images are displayed based on a popularity or likeability ranking determined by previous use or selection by the community of user accounts 135 that also accessed the content on the storage / database 110. Such popularity or likeability within the community may relate to images most frequently used in videos published on the platform. Processing may proceed to block 335.

[0053] In block 335 (Store Images), once displayed and / or selected or used by account 135, the displayed images are stored back in storage / database 110 and configured for retrieval in order of ranking or popularity. The order or sequence of storing the images corresponds to the popularity or popularity ranking of the images based on the selections made during execution of block 330.

[0054] In block 340 (Generate New Image), the image generator 120 generates a new image corresponding to the expanded search parameters received from the storage / database 110 .

[0055] According to some non-limiting exemplary embodiments, block 340 is executed if the determination at decision block 325 is "No." However, according to some alternative embodiments, block 340 may be executed consecutively or sequentially with respect to executing block 330. In either case, processing may proceed to block 345.

[0056] In block 345 (Display New Image), the display engine 125 displays the newly generated content by the image generator 120. Processing may continue to block 335.

[0057] In block 335 (Store Images), after display and / or selection or use of the newly generated images in the account 135, the new images are stored in the storage / database 110. The order or sequence of storing the images corresponds to a ranking of the popularity or likeability of the images based on the selection made during execution in block 340. Additionally, said popularity or likeability by others in the community may relate to the images most frequently used in videos published on the platform.

[0058] Once the existing images and / or newly generated images are stored, per block 335, the existing images may then be displayed based on a popularity or likeability ranking based on previous use or selection by the community of user accounts 135 that have accessed the content on the storage / database 110.

[0059] 4 illustrates an exemplary computing embodiment in which the process and any of the sub-processes for generating a 3D model based on text input are implemented as executable instructions stored on a non-volatile computer-readable medium. The computer-readable instructions are executed, for example, by a processor of a device having a network element and / or other device corresponding thereto, as referenced herein, and are particularly applicable to the applications and / or programs described above corresponding to system 100 for generating a 3D model based on text input.

[0060] In a very basic configuration, a computing device 400 typically includes at least one or more processors 402, memory 404, one or more input components 406, one or more output components 408, a display component 410, a computer-readable medium 412, and a transceiver 414.

[0061] The processor 402 may refer to, for example, a microprocessor, a microcontroller, a digital signal processor, or any combination thereof.

[0062] Memory 404 may refer to, for example, volatile memory, non-volatile memory, or any combination thereof. Memory 404 stores an operating system, one or more applications corresponding to media platform 105, and / or their program data. That is, memory 404 is considered a computer-readable medium because it stores executable instructions for implementing any of the functions or operations described above.

[0063] Input component 406 may refer to an integrated or communicatively coupled keyboard, touchscreen, or communication device. Alternatively, input component 406 may include a microphone configured to receive voice commands from a user of computing device 400 in conjunction with a voice recognition program stored in memory 404. Additionally, if input component 406 is not integrated into computing device 400, it may be communicatively coupled via a short-range communication protocol, including, but not limited to, radio frequency or Bluetooth®.

[0064] Output component 408 may refer to a component or module, either integrated into computing device 400 or removable from computing device 400, configured to output commands and data to an external device.

[0065] Display component 410 may refer to, for example, a solid-state display with touch input capabilities, i.e., display component 410 may include functionality that shares with or replaces functionality of input component 406.

[0066] The computer-readable medium 412 may refer to a separable machine-readable medium configured to store one or more programs that embody any of the functions or operations described above. That is, the computer-readable medium 412 contained in or otherwise connected to a drive component of the computing device 400 may store executable instructions that perform any of the functions or operations described above. These instructions may be complementary to or independent of the instructions stored in the memory 404.

[0067] The transceiver 414 may refer to the network communication link of the computing device 400 configured as a wired network or a direct wired connection, or the transceiver 414 may be configured as a wireless connection, such as radio frequency (RF), infrared, Bluetooth, and other wireless protocols.

[0068] From the foregoing, it will be understood that various embodiments of the present invention have been described herein for purposes of illustration and that various modifications may be made without departing from the scope and spirit of the invention. Accordingly, the various embodiments disclosed herein are not intended to be limiting, with the true scope and spirit being indicated by the following claims. Aspects

[0069] Aspect 1 is a media platform, A graphics-specific search engine, an image generator, and a graphics display engine are provided, The graphics-specialized search engine receives the search input, determines a search query from the received search input, and searches a graphics-specialized database for existing images that correspond to the expanded search query; the image generator generates a new image corresponding to the search query when the search results do not exceed a predetermined number; The graphics display engine sends at least a plurality of the generated new images to an instance of the media platform account.

[0070] In a second aspect of the media platform of the first aspect, the graphics display engine further transmits at least some of the existing images to an instance of the account of the media platform.

[0071] Aspect 3 is the media platform of aspect 1 or 2, wherein the image generator is a three-dimensional (3D) image generator.

[0072] In a fourth aspect of the media platform of any one of the first to third aspects, existing and new images are stored in a storage system for use and ranking by popularity.

[0073] In a fifth aspect, in the media platform of any one of the first to fourth aspects, a search query is expanded.

[0074] A sixth aspect is a method for generating a three-dimensional (3D) model, comprising: receiving a text search input; searching the database for 3D models corresponding to keywords corresponding to the expanded search input; displaying, for selection on the instance of the multimedia platform account, a plurality of existing 3D models corresponding to the expanded keywords; If the search results in less than a threshold number of existing 3D models, at least some of the displayed 3D models are generated based on keywords.

[0075] In an embodiment 7, the method of the embodiment 6 is characterized in that the search input is in text format and the keywords are expanded from the received text search input.

[0076] In an eighth aspect, in the method of the sixth or seventh aspect, the multimedia platform is a social media platform.

[0077] A ninth aspect is the method of any one of the sixth to eighth aspects, wherein the multimedia platform is a virtual reality (VR) platform.

[0078] In embodiment 10 and the method of any one of embodiments 6 to 9, the 3D model is generated by an image generator.

[0079] Aspect 11 is the method of any one of aspects 6 to 10, wherein if the search results in a number of existing 3D models less than a threshold, the method further comprises: sending the expanded keywords to an image generator; and This includes displaying a 3D model that includes the existing image and the generated new image.

[0080] A twelfth aspect of the present invention is the method of any one of the sixth to eleventh aspects, wherein the representations of the 3D models are ranked by matching characteristics and popularity.

[0081] A thirteenth aspect of the present invention is the method of any one of the sixth to twelfth aspects, wherein the display of the existing 3D model and the display of the new 3D model are performed on a social media platform.

[0082] A fourteenth aspect is the method of any one of the sixth to twelfth aspects, wherein the display of the existing 3D model and the display of the new 3D model are performed on a VR media platform.

[0083] Aspect 15 is a non-volatile computer-readable medium having stored thereon computer-executable instructions that, when executed, cause one or more processors to: receiving input; Parsing at least one searchable parameter from the received input; Expanding at least one searchable parameter; searching the database for existing images corresponding to the at least one extended searchable parameter; if the search results in a threshold number of existing images or more, displaying a predetermined number of existing images for selection on the instance of the social media account; generating a new image based on the expanded at least one searchable parameter if the search results in a number of existing images less than a threshold; and Displaying a predetermined number of generated new images for selection on a social media account Perform an operation that includes

[0084] Aspect 16 is the computer-readable medium of aspect 15, wherein the received input is a text input.

[0085] Example 17 is the computer-readable medium of Example 15, wherein the received input is in the form of audio.

[0086] In an eighteenth aspect of the computer-readable medium of any one of the fifteenth to seventeenth aspects, the database stores existing images and new images for use and ranking by other accounts on the same platform as the social media account.

[0087] Aspect 19 is the computer-readable medium of any one of aspects 15 to 18, wherein the existing image and the generated new image are 3D models generated by an image generator.

[0088] A twenty-first aspect of the present invention is a computer-readable medium according to any one of the fifteenth to nineteenth aspects, in which a predetermined number of existing images are displayed according to a ranking protocol.

[0089] Example 21 is the computer-readable medium of example 20, wherein the ranking protocol is based on a number of uses of each of the existing images by at least some of the other accounts on the same platform as the social media account.

Claims

1. It is a media platform A graphics-specific search engine, an image generator, and a graphics display engine are provided, the graphics-specialized search engine receives a search input, determines a search query from the received search input, and searches a graphics-specialized database for existing images corresponding to the search query; the image generator generates a new image corresponding to the search query if the search results do not exceed a predetermined number; The graphics display engine transmits at least a plurality of generated new images to an instance of a media platform account. Media platform.

2. The graphics display engine further transmits at least some of the existing images to an instance of an account on the media platform. The media platform of claim 1 .

3. The image generator is a three-dimensional (3D) image generator. The media platform of claim 1 .

4. The existing images and the new images are stored in a storage system for use and ranking by popularity. The media platform of claim 1 .

5. The search query is expanded The media platform of claim 1 .

6. 1. A method for generating a three-dimensional (3D) model, comprising: receiving a search input; searching a database for 3D models corresponding to keywords corresponding to the search input; displaying, for selection on an instance of an account of the multimedia platform, a plurality of 3D models corresponding to the search; If the search results in less than a threshold number of existing 3D models, at least some of the displayed 3D models are generated based on the keywords. A method for generating a three-dimensional (3D) model.

7. The search input is in text format, and the keywords are expanded from the received text search input. The method of claim 6.

8. The multimedia platform is a social media platform The method of claim 6.

9. The multimedia platform is a virtual reality (VR) media platform. The method of claim 6.

10. The 3D model is generated by an image generator The method of claim 6.

11. If the search results in a number of existing 3D models less than a threshold, the method further comprises: transmitting the keyword to the image generator; and displaying a 3D model including the existing image and the generated new image. The method of claim 10.

12. The representations of the 3D models are ranked by matching quality and popularity. The method of claim 11.

13. The display of existing 3D models and the display of new 3D models will be on social media platforms. The method of claim 11.

14. The display of existing 3D models and the display of new 3D models are performed on the VR media platform. The method of claim 11.

15. A non-volatile computer-readable medium having computer-executable instructions stored thereon, comprising: The computer-executable instructions, when executed, cause one or more processors to: receiving input; Parsing at least one searchable parameter from the received input; expanding said at least one searchable parameter; searching the database for existing images corresponding to the expanded at least one searchable parameter; if the search results in a threshold number of existing images or more, displaying a predetermined number of existing images for selection on the instance of the social media account; generating a new image based on the expanded at least one searchable parameter if the search results in a number of existing images less than a threshold; and Displaying a predetermined number of generated new images for selection on a social media account Perform an operation that includes A non-volatile computer-readable medium.

16. The received input is a text input.

16. The computer-readable medium of claim 15.

17. The database stores the existing and new images for use and ranking by other accounts on the same platform as the social media account.

16. The computer-readable medium of claim 15.

18. The existing image and the generated new image are 3D models generated by an image generator.

20. The computer-readable medium of claim 17.

19. The predetermined number of existing images are displayed according to a ranking protocol.

20. The computer-readable medium of claim 17.

20. The ranking protocol is based on the number of uses of each of the existing images by at least some of the other accounts on the same platform as the social media account.

20. The computer-readable medium of claim 19.

Images