1623 results about "Media content" patented technology

Disclosed are apparatuses, systems, and techniques for efficient instance segmentation with vision language models (VLMs). In an embodiment, the techniques include processing an input into the VLM to generate a segmentation map of a media item. The input includes the media item, which includes a plurality of media item units (e.g., pixels, groups of pixels), and further includes a prompt associated with the media item. The segmentation map includes identification of media item units associated with individual objects of one or more objects in the media item, and the VLM includes a dynamic portion having parameters that are determined in view of the media item.

A recommendation system is described, which identifies engaged fans for an artist and requests input from the engaged fans regarding a collaboration by the artist with at least one different artist. In implementations, engaged fans are identified as having user profiles on a media content platform that satisfy at least one threshold engagement criteria based on consumption of at least one media content item associated with the artist. The recommendation system presents a user interface that includes at least one prompt for feedback that enables engaged fans to recommend how the artist collaborate with others. In some implementations, the user interface includes controls that are selectable to define artist characteristics to feature in a collaboration and the recommendation system is configured to generate a synthesized collaboration by automatically combining different artists' characteristics using a trained machine learning model. Recommendations based on engaged fan feedback are then provided to artists.

The invention discloses a private network content copyright monitoring and evidence obtaining system based on AI and a large model, which utilizes AI and large model technologies to carry out copyright monitoring and evidence obtaining on multimedia content in a private network environment, and carries out deep semantic understanding and cross-modal feature extraction through a large model processor to generate unified semantic representation. The method comprises the steps that a copyright content database is established and stored in a copyright content knowledge base, the copyright content knowledge base is used for storing metadata of original content protected by copyright, unified semantic representation and copyright declarations in a natural language form provided by a copyright party, and the copyright declarations are converted into query vectors through a semantic understanding technology; the method comprises the following steps: acquiring a semantic representation of a multimedia content, performing similarity calculation with the semantic representation of the multimedia content, identifying infringement content, when the infringement content is identified, recording an original source, publishing time and publisher information of the infringement content, performing differentiation analysis, generating an evidence chain, displaying a copyright monitoring result through a user interface, generating infringement alarm information, and presenting details of the evidence chain.

The invention provides an artificial intelligence semantic processing system and method oriented to digital media creation, and relates to the technical field of artificial intelligence semantic process.The artificial intelligence semantic processing method comprises the steps that predicate argument relation pairs of language texts are extracted, object space relation pairs of sketch images are extracted at the same time, and a basic semantic unit set is constructed; the integrity and accuracy of cross-modal semantic understanding are ensured, further, semantic units are clustered by using a dynamic routing algorithm, a semantic concept cluster with a clear importance weight is generated, deep mining and structured representation of creation intentions are realized, and the creation intentions are quickly and accurately understood. An initial semantic relation graph is constructed, a graph attention network is used for dynamic reweighting, finally, an enhanced dynamic semantic graph is generated, complex association and a hierarchical structure between semantic concepts are effectively captured, finally, hierarchical analysis is carried out on the semantic graph, and a structured semantic blueprint is output, so that the dynamic semantic graph is obtained. And a reliable semantic processing technology is provided for creation of high-quality digital media contents.

The embodiment of the invention provides a media editing method and device, equipment and a storage medium. The method comprises the following steps: displaying a first sub-lens component in a sub-lens editing area of an editing interface; displaying a media generation area in the editing interface in response to a preset operation received in the first sub-lens assembly; on the basis of parameter information acquired in the media generation area, generating a first sub-lens section corresponding to the first sub-lens assembly; and displaying the first sub-lens segment in a content preview area of the editing interface. In this way, according to the embodiment of the invention, the corresponding segment of the media content can be efficiently edited through the sub-mirror component, so that the media editing efficiency is improved.

A playback device is configured to (i) operate as part of a synchrony group including at least one other group member, (ii) obtain a respective indication of each group member's capability to play back media content, (iii) based on the respective indications, determine a group capability to play back media content, (iv) transmit, to a cloud-based computing system, a request for a media item, (v) receive, from the cloud-based computing system, a list of different renditions of the requested media item, the list including a respective media item identifier usable to obtain each different rendition, (vi) select a rendition of the requested media item that corresponds to the determined group capability, (vii) use a media item identifier corresponding to the selected rendition to retrieve the selected rendition of the requested media item, and (viii) play back the selected rendition in synchrony with the at least one other group member.

A multi-selection shutter camera application and method selectively sends images to different artificial intelligence and innovative platforms for fast sharing and informational purposes. An electronic device with a touch sensitive display and a processor is utilized. A capture screen on the display includes a multi-shutter view (a live view and at least two selective capture buttons (e.g., shutters)) for capturing media content. The method may include receiving input from the buttons to capture the content and direct it to an artificial intelligence platform; processing the content information based on the selected button; analyzing the content through parameters and show options to the user on the same screen that displays the content; and presenting a plurality of selectable options related to the user's selected shutter and intent of capturing the content, including, but not limited to uses related to at least one of the following: discovery, shopping and sharing functionality alternatives.

The invention discloses an intelligent media content association propagation and influence analysis method based on a knowledge graph, and the method comprises the following steps: collecting multi-source media data from social media, a news website, a video platform and a forum, and constructing and forming a heterogeneous knowledge graph; performing feature initialization and embedding on nodes in the heterogeneous knowledge graph to generate initial node embedding representation; constructing a dynamic heterogeneous graph attention network based on the node initial embedding representation to obtain a node dynamic propagation state representation; calculating a propagation influence score based on the node dynamic propagation state representation to obtain a node influence sorting result and a core propagation path; and introducing a causal consistency training mechanism based on the core propagation path, optimizing parameters of the dynamic heterogeneous graph attention network, and outputting a propagation influence evaluation result. According to the method, the dynamic heterogeneous graph attention network is adopted, and intelligent analysis of the media content propagation influence is realized.

The invention discloses an advertisement creativity matching method based on multi-modal content generation, and relates to the technical field of digital media content generation, and the method comprises the following steps: building a cross-modal time anchoring belt facing advertisement creativity matching, carrying out metaphor level decomposition on input text information, marking a symbol axis for image information, and carrying out data processing on the image information; obtaining an initial semantic boundary list; and constructing a culture fingerprint database according to the initial semantic boundary list, and mapping the territory taboo information and the brand symbol information into constraint tags to obtain a semantic guardrail set. According to the method, through cross-modal time anchoring and semantic boundary control, accurate correspondence of the text and the image in time and semantic levels is achieved, and it is ensured that generated content is clear in semantic meaning and adaptive in culture. In combination with breathing type phase traction and cultural fingerprint dynamic adjustment, multi-modal content rhythm and emotion are coordinated and unified, brand expression is kept stable, and the overall consistency and propagation effect of advertisement creativity are improved.

Described are systems and processes for identifying relevant media content for users in response to natural language requests. The media content may be formed as a playlist of music. Requests may be sent to various models to obtain results, such as a large language model (LLM) and a local search model. Results may be selected from one or both models. The results may be used to fetch media content and provide user interfaces with a playlist with the media content to a user that submitted the request. User interfaces may include selectable search terms suggested for the user and animations during processing of the request.

This application is directed to media content compensation at an electronic device having a head-mounted display. The electronic device determines a multifocal eyewear prescription of a user associated with the electronic device. The multifocal eyewear prescription includes a multifocal parameter for a lens having a plurality of focal lengths. The electronic device obtains input media content, converts the input media content to corrective media content based on the multifocal eyewear prescription of the user, and renders, on the HMD, the corrective media content. In some embodiments, the lens includes a plurality of segments corresponding to the plurality of focal lengths. Each image frame of the input media content is divided into a plurality of regions based on the plurality of segments. The electronic device compensates the plurality of regions of the input media content based on the plurality of focal lengths to generate the corrective media content.

Apparatuses, systems, and techniques to enable verification of content, such as media content. Hashes of content can be digitally signed and stored to a distributed ledger, such that a source of content can be verified and any modification determined.

Techniques for individualized media content generation and delivery are provided. In one example, a request to provide media content to a user via a user device is received and a profile of the user comprising user values for each of one or more attributes is identified. A portion of the media content is identified for modification based on a user value and a content value for the portion. The media content is modified using alternative content generated for the portion based on the user value and provided to the user via an application executing on the user device.

An example method for user interaction with media content includes receiving, by a chat interface, a user query and determining a query embedding for the user query. The method includes receiving feature vectors from a hierarchical structure of the media content; comparing the query embedding with the feature vectors; identifying one or more feature vectors similar to the query embedding. A feature vector identifies a node in a knowledge graph. Nodes represent entities and portions of media content, and an edge indicates a relationship between entities and portions of media content associated with two nodes. The method includes traversing edges of the knowledge graph; extracting a relevant subgraph including content relevant to the user query; providing the user query and the extracted relevant subgraph to a generative AI model, with instructions to generate a response; receiving a response from the generative model; and providing the response from the generative model.

The application relates to the field of information technology, in particular to an intelligent processing method and system for new media data. The method comprises the following steps: reading historical new media material data; analyzing the historical new media material data, calculating an availability estimation value of the historical new media material, and sorting and screening the historical new media resource according to the availability estimation value; storing the analyzed historical new media material data in a classified manner, and establishing a multidimensional index of the historical new media material data; receiving a new media content generation demand, converting the new media content generation demand into a new media material matching condition; screening and sorting new media materials based on the new media material matching condition, and selecting the first N new media material data as basic new media material data; and fusing a theme content based on the basic new media material, generating multi-form new media content, and realizing intelligent processing of high-efficiency, high-quality and self-optimizable new media content.

The invention provides a video evidence obtaining method based on Transform and quantum features, and belongs to the technical field of crossing of multimedia content security and computer vision, and the method comprises the steps: S1, collecting multi-modal original data; s2, preprocessing the multi-modal data; s3, single-mode authenticity preliminary detection is carried out; s4, multi-modal feature fusion of quantum optimization is carried out; and S5, multi-modal authenticity comprehensive judgment is carried out. Through multi-mode cooperation and quantum technology innovation, the problems of insufficient robustness, inaccurate positioning and the like of a traditional evidence obtaining technology are effectively solved, and an efficient, accurate and feasible technical scheme is provided for authenticity verification of video content.

A network entity for processing a data stream into which media content is encoded, the data stream comprising packets, each packet comprising a packet type identifier identifying a packet type associated with the respective packet from a plurality of packet types, wherein each packet having a packet type associated therewith from a first set of packet types from the plurality of packet types comprises an operation point identifier identifying an operation point associated with the respective packet from a plurality of operation points within a scalability space spanned by n scalability axes, wherein each packet having a packet type associated therewith from a second set of packet types from the first set of packet types additionally carries data. The network entity is configured to read a scalability axes descriptor from packets having a predetermined packet type associated therewith that is disjoint from the second set and to interpret the operation point identifier in accordance with the scalability axes descriptor.

Disclosed herein is an apparatus and method for generating media content based on generative AI. The apparatus generates combined media by combining existing media with synthetic media generated using a generative AI, defines metadata required for the generative AI to generate media content for the combined media, and generates the media content using the generative AI by adjusting the text prompt to be input into the generative AI using the metadata.

Systems and methods are described for transcoding at least a portion of a live media asset ingested from a media content source. The systems and methods may be configured to, in real time, after ingesting the at least a portion of the live media asset, determine parameters of the at least a portion of the live media asset. The systems and methods may be further configured to, in real time, after ingesting the at least a portion of the live media asset, determine, based on the parameters, a plurality of optimal bitrate-resolution pairs for the at least a portion of the live media asset. The systems and methods may be further configured to, in real time, after ingesting the at least a portion of the live media asset, cause the at least a portion of the live media asset to be transcoded based on the plurality of optimal bitrate-resolution pairs.

Embodiments of the present disclosure provide a sending method and device of interactive information, an electronic device and a storage medium. The method comprises: displaying an object flow display interface corresponding to target media content, the object flow display interface being used to display at least one associated object of at least part of interactive information of the target media content, object information of the associated object being contained in the corresponding interactive information, and the object flow display interface supporting switching display of the at least one associated object based on a trigger operation; in response to an information generation operation acting on the object flow display interface, displaying an information generation interface, the information generation interface being used to generate first interactive information of the target media content; and in response to an information sending operation, sending the first interactive information as interactive information of the target media content. The above technical solution can enrich the interactive mode of the object flow display interface.

Embodiments of the present disclosure provide a media content picture display method and device, electronic equipment, storage medium and program product. The method comprises: obtaining a media content display interface to be displayed, the media content display interface comprising a first region and a second region, the first region displaying at least part of an interactive control of the media content display interface, and the second region being an original picture display region of the media content display interface; determining a target picture display region of the media content display interface, wherein whether the target picture display region contains the first region is associated with an interface size of the media content display interface; displaying the media content display interface and displaying a target media content picture in the target picture display region. The above technical solution can enrich the determination method of the picture display region in the media content display page.

The invention discloses a digital media content block chain copyright protection method comprising the following steps: S1, digital media content preprocessing: obtaining target digital media content, extracting a multi-dimensional feature set of the content, the feature set comprising content hash features and semantic features; s2, hierarchical block chain evidence storage: constructing a three-layer block chain architecture of a right confirmation chain, an evidence storage chain and a right protection chain, and splitting and storing the multi-dimensional feature set in the step S1; S3, automatically executing a smart contract: deploying a copyright management smart contract; and S4, copyright version association: when target digital media content is updated and iterated, extracting a multi-dimensional feature set of a new version, associating new version feature Hash with historical version feature Hash through a Merkle tree, and storing the new version feature Hash and the historical version feature Hash to an evidence storage chain to realize integration of version tracing and ownership continuation. The infringement content with Hash change but similar semantics can be recognized through multi-dimensional feature comparison, the tampering recognition accuracy is larger than or equal to 95%, and safety is improved.

Embodiments of the present disclosure relate to a method, apparatus, device and storage medium for content sharing. The method proposed herein comprises: receiving a sharing request for target media content; and controlling target sharing content associated with the target media content to be published according to the sharing request, wherein the target sharing content comprises media content generated based on the target media content independently of a user editing operation, and the target sharing content comprises a first media content frame, which is generated by applying a preset style to a second media frame in the target media content. In this way, the embodiments of the present disclosure can improve the efficiency of content sharing.

An embedded artificial intelligence system for preventing exposure to, and the creation of, inappropriate content by automatically detecting and blocking harmful content, including self-generated content. The system includes a machine learning (ML) model, built on efficient vision transformer (EVT) architecture, wherein the EVT architecture is operable to balance high performance with low computational overhead, such that the system is operable to be embedded in the operating system of a device. The ML model is trained on a dataset including images, text descriptions, videos, audio and / or other multimedia content, wherein the dataset content includes neutral images and / or inappropriate images, including not safe for work (NSFW) images and illegal child sexual abuse material (CSAM). The system is operable to detect and block content being shown on a device, camera-captured content taken on a device, and / or camera-captured content broadcasted in real-time / livestreamed from a device.

Example implementations include methods and systems that relate to search results and recommendations in a media content delivery system. An example method includes providing a search query to a multi-task language model associated with a media content delivery system. The method also includes providing user engagement information to the multi-task language model. The user engagement information indicates user engagement activity with the media content delivery system. The method also includes retrieving, using the multi-task language model and based on the search query, one or more candidate media items from a media item database of the media content delivery system. The method also includes identifying, using the multi-task language model and based on the user engagement information, one or more recommended media items from the media item database.

Methods and systems for determining quality of media content are disclosed. The method performed by a server system includes extracting textual data related to a screenplay associated with media content being produced by a first user. Method includes segmenting the textual data into multiple sections to display each section to second user(s). Method includes receiving user input(s) from each of the second user(s) for each section. Method includes determining, by Machine Learning (ML) model(s) associated with the server system, user behavior of each second user, and a set of interpretations for the screenplay based on the textual data and user input(s). Method includes generating, by the ML model(s), a prediction indicative of a predicted quality of the media content based on the user behavior and the set of interpretations.

The present disclosure provides techniques enabling large language models (LLMs) to access and integrate media content, such as images, video, or audio, using a semantic data store like a knowledge graph. The disclosed techniques involve processing user prompts through a knowledge graph to identify relevant nodes linked to media files. These media files or their identifiers are then provided to the LLM, enhancing response accuracy and comprehensibility. The techniques also include creating new classes in the knowledge graph to represent media files with properties like type, location, and associations. This approach allows LLMs to deliver integrated textual and visual content in real-time, improving user interaction and response quality. Furthermore, the techniques allow the general knowledge of an LLM to be supplemented with media files, and optionally other information, in the knowledge graph. The techniques are fundamentally computer-implemented, leveraging technologies such as RDF triples, named entity recognition, and vector embeddings.

Approaches presented herein provide for the identification of relevant media content in response to a received prompt or query. A plurality of video files, or other instances of content, can be broken into segments that can each be analyzed by a vision language model (or other such mechanism) to generate text-based segment summaries with timestamps. A language model can then generate an overall summary for a video file based in part on the segment summaries and timestamps, and a vector representation may be generated that may also include image features or other aspects of the video file. The vector representation can be stored to a vector database. When a prompt or query is received that includes text, image, and / or video content, for example, a search vector can be generated that can be used to identify relevant results from the vector database. Relevant portions of the identified video files can then be provided for playback based in part upon the timestamps associated with those relevant portions.

Embodiments provide for improved machine learning. A request for supplemental content to be provided in association with a media content item is received, and a set of candidate supplemental content items for the request is determined. A user embedding corresponding to a user embedding corresponding to a user associated with the media content item, a media embedding corresponding to the media content item, and a set of supplemental content embeddings corresponding to the set of candidate supplemental content items are accessed from one or more storage repositories. A set of interaction scores is generated based on processing the user embedding, the media embedding, and the set of supplemental content embeddings using an interaction machine learning model. A first supplemental content item of the set of candidate supplemental content items is selected for the request based on the set of interaction scores.

A system for synchronizing and spatializing media, comprising client device and server device. A method for operation includes: tracking the real-time spatial coordinates of both devices via wireless sensors; synchronizing media playback using a timestamp-based protocol that compensates for network latency and clock offset; and applying directional audio filters, such as Head-Related Transfer Functions (HRTF), on the client device to render audio appearing to originate from server device's physical location. The method is further characterized by compensating for acoustic propagation and signal processing delays to ensure accurate spatiotemporal alignment. The system may be enhanced by a multimodal Al configured to perform operations such as real-time voice-preserving translation and the generation of synchronized, spatialized haptic feedback based on semantic event markers.