598 results about "Live streaming" patented technology

The invention relates to a digital human live broadcast method and system. The method comprises the following steps: acquiring a live broadcast room visual effect picture and a digital human live broadcast audio; generating digital human live broadcast content under the driving of the digital human live broadcast audio by taking the visual effect picture of the live broadcast room as a visual manuscript through an I2V model; in the process of playing the digital human live broadcast content, if the current interaction behavior of the user in the live broadcast room is monitored, generating digital human interaction content responding to the current interaction behavior; selecting an insertion frame from the key frames of the digital human live broadcast content so as to insert the digital human interaction content at the position of the insertion frame; the key frame is a video frame corresponding to a statement demarcation point in the digital human live broadcast content. According to the scheme provided by the invention, the contradiction between long content production period, high implementation cost and slow real-time interaction feedback in digital human live broadcast in related technologies can be solved.

Systems and methods that determine whether a progressive award triggering event occurred in association with a live stream including at least a portion of a play of a wagering game occurring at a streaming device in communication with a live streaming platform server. Responsive to the determination being that the progressive award triggering event occurred in association with the live stream, for each of a plurality of client devices displaying the live stream based on data received from the live streaming platform server, the systems and methods determine whether that client device qualifies as an eligible client device. For each of any determined eligible client devices, the systems and methods cause at least a portion of a progressive award maintained in association with at least the plurality of client devices to be made available to that client device.

A method for processing media data includes identifying in a media presentation description (MPD) an indication of a Tuning-In Media Segment. The Tuning-In Media Segment comprises a latest media data for a client device to start with when tuning into an ongoing live streaming service. The latest media data is selected from either a current media segment that is being generated by the ongoing live streaming service or a previous media segment generated by the ongoing live streaming service based on a length of the current media segment. The MPD is stored by the client device prior to the client device tuning into the ongoing live streaming service. The method further includes performing a conversion between a visual media data and a bitstream according to the MPD.

A live streaming platform server that, responsive to a determination to place, in association with a client device, a wager on a play of a wagering game displayed by a streaming device, receives, from a first remote game server operating with the streaming device, first data determined by the first remote game server. Responsive to a validation of the first data received from the first remote game server operating with the streaming device, the live streaming platform server communicates the first data to a second remote game server operating with the client device. Responsive to a receipt, from the second remote game server operating with the client device, of second data determined by the second remote game server and based, at least in part, on the first data received from the first remote game server, the live streaming platform server communicates the second data to the client device.

To provide a server, a method and a computer program in live streaming.SOLUTION: Sending, by the live streamer, a PK invitation to another live streamer, the PK invitation indicating that two or more live streamers compete for a specific period of time, determining, by the another live streamer, whether to accept the invitation from the live streamer, and obtaining, by the server, the streaming data such as the thumbnails of the two live streamers from a stream or the like when the server is notified of PK establishment; Context data is obtained from a context DB or the like, a thumbnail is generated for a live streaming room, the thumbnail is cut into a plurality of pieces based on a quantity of live streaming rooms or the like and distributed to a corresponding live streamer, and the thumbnail is replaced with an original one when interaction ends.SELECTED DRAWING: Figure 16

The invention discloses a teaching live broadcast control method, a teaching live broadcast control system, a teaching live broadcast control medium and teaching live broadcast control equipment based on multi-protocol signal flow scheduling, a multi-protocol signal source is adaptively accessed, a protocol analysis plug-in is correspondingly loaded to analyze a protocol, and different types of heterogeneous flows are converted into standardized data flows. Extracting stream features, and performing scene recognition; and dynamically adjusting the bandwidth allocation strategy based on the network state and the terminal capability. And on the basis of the multi-target reinforcement learning model, generating an optimal strategy of bandwidth allocation for live broadcast stream pushing and local distribution requirements. Stream transcoding and format conversion are carried out, and multi-signal stream timestamps are dynamically calibrated and synchronized; based on a Transform model, multi-modal content matching is carried out, knowledge chain marks are generated, and finally terminal output is carried out. The method has the advantages of full-scene protocol compatibility, dynamic scene adaptive scheduling, intelligent resource dynamic allocation, high-precision time synchronization calibration and content intelligent association matching.

In various examples, techniques for optimizing object detection models are described herein. Systems and methods are disclosed that process sensor data using a backbone of a machine learning model(s) in order to generate feature maps at different resolutions. The systems and methods then use the machine learning model(s) to generate a vector based at least in part on one or more of the feature maps. For example, if the backbone generates four feature maps, then the machine learning model(s) may generate the vector using two feature maps from the four feature maps. The systems and methods then process the vector using a transformer of the machine learning model(s) in order to generate data representing a class label(s) for an object(s) depicted by an image represented by the sensor data and / or a location(s) of the object(s) within the image.

A remote game server that determines data associated with a play of a wagering game displayed by a streaming device in communication with a live streaming platform server, and communicates the data to the streaming device. Additionally and independent of the live streaming platform server, the remote game server communicates the data to another remote game server operating with a client device in communication with the live streaming platform server.

The present invention relates to methods and systems for dynamically rendering interactive elements in a live broadcast. The method performed by an application server includes identifying chroma key areas in a live broadcast created by a creator and streamed to users via a live streaming interactive platform. The method includes obtaining an interactive element to be displayed in the chroma key areas based on user inputs from the creator and the users in the live streaming interactive platform, and live broadcast data. Further, the method includes rendering at least a portion of the interactive element in the chroma key areas based on an image fusion technique. The method includes rendering the live broadcast of the creator to the users upon post-processing of the interactive element, thereby enabling the users to view the interactive element rendered in the chroma key areas of the live broadcast.

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.

Systems and methods that enable a live streaming platform to selectively store game data associated with a wagering game streamed from a streaming device operating with the live streaming platform and wagered on by a client device operating with the live streaming platform.

A live streaming platform server that receives, from client devices associated with remote game servers, data associated with amounts of wagers placed on a play of a wagering game displayed by a streaming device associated with another remote game server. Responsive to an occurrence of a benefit realization event, the live streaming platform server determines benefits attributable to the client devices and communicates to the remote game servers data that results in the determined benefits being made available to a user of the streaming device.

Systems and methods that determine whether a progressive award triggering event occurred in association with a live stream including at least a portion of a play of a wagering game occurring at a streaming device in communication with a live streaming platform server. Responsive to the determination being that the progressive award triggering event occurred in association with the live stream, for different client devices of a plurality of client devices displaying the live stream based on data received from the live streaming platform server, the systems and methods determine respective portions of a progressive award maintained in association with the plurality of client devices, and causes the respective portions to be made available to the users of the client devices.

Systems and methods that enable, in association with a client device, a first wager to be placed on a play of a game displayed by a streaming device in which the first wager to be placed includes an amount of fiat currency and a second wager placed via the streaming device includes an amount of virtual currency. Following a placement of the first wager and responsive to a receipt, from a remote game server associated with the live streaming platform server, of first data associated with the play of the game displayed by the streaming device, the systems and methods determine, based on the received first data associated with the play of the game displayed by the streaming device, second data associated with a result of the first wager, and communicate the second data to a remote gaming platform associated with the client device.

This disclosure provides a live streaming processing method, apparatus, device, and storage medium. The method includes: displaying a live streaming room page of a first streamer user, where the live streaming room page displays a video feed of a connection between the first streamer user and at least one second streamer user; responding to a trigger operation on an object information page, displaying an object information page on the live streaming room page, and displaying recommended objects corresponding to the second streamer user on the object information page. In a live streaming scenario involving streamer connections, this disclosure allows viewers to view the recommended objects of the connected streamer user within the current streamer user's live streaming room by displaying recommended objects of the connected streamer user on the current streamer user's live streaming room page. This eliminates the need for viewers to exit and re-enter the connected streamer user's live streaming room, shortening the operation path for viewers in the current live streaming room to view the recommended objects of the connected streamer user and improving operational efficiency.

The invention discloses a multi-camera live broadcast stream pushing realization method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: calling a plurality of cameras to carry out the video collection of a current live broadcast scene, obtaining a plurality of video data, and distributing an independent thread for each camera; collecting audio data of the current live broadcast scene; encoding the audio data and the plurality of video data, and synchronizing the audio data and the plurality of video data based on a timestamp to obtain a plurality of audio and video data; and pushing the audio and video data to a live broadcast platform based on the independent thread. The problem that multi-camera live broadcast stream pushing cannot be realized in the prior art is solved.

The invention discloses a digital human live broadcast microphone connection and video generation method based on computer vision, and belongs to the technical field of artificial intelligence, and the method comprises the following steps: 1, real-time vision capture and action expression driving: employing a computer vision tool to carry out face key point detection, facial feature points of lips, eyes and the like of a live anchor or a microphone-connected guest are accurately captured; and then a voice conversion model is matched, microphone-connected audio features and lip key point movement are bound, precise synchronization of the sound and the lip is achieved, and for limb actions, limb joint data can be collected through a monocular camera in combination with a posture estimation algorithm or a simple action capture device and mapped to a digital human skeleton model. According to the digital human live broadcast microphone connection and video generation method based on computer vision, through multi-dimensional technical innovation and systematic design, the problems of insufficient sense of reality, interaction lagging, poor scene adaptability and the like existing in current digital human application are effectively solved.

Clinical-quality eye examinations are provided at locations remote from the physician and outside of a clinical setting. A portable optical device and corresponding software are delivered to the patient's location. The portable optical device is configured for patient use in self-conducting an eye or vision exam and taking optical measurements. As a function of type of optical measurement data or health consideration of the patient, the corresponding software provides uploading and live streaming of the optical measurement data to the physician. The corresponding software is executed during the patient conducting the eye (vision) exam and enables the remotely located physician, to participate in the same via video conference. Alternatively, an artificial intelligence resource operating remotely or locally can provide physician-type guidance and eye health assessments. Alignment of device and patient eyes can be facilitated for remote exams.

The invention discloses a clothing live broadcast real-time conversion rate prediction method and system based on multi-modal deep learning, and relates to the deep learning related field, and the method comprises the steps: carrying out the multi-scene sample collection based on the influence factors of the live broadcast conversion rate, and constructing a sample cluster; performing multi-modal analysis according to a corresponding relation between the sample cluster and the influence factor, determining a causal probability relation between each modal data change and the real-time conversion rate, and constructing a causal probability network; carrying out segmentation and marking, establishing multi-modal training, and testing a data set; carrying out training convergence on the multi-modal encoder and the time sequence fusion predictor; and the multi-modal encoder is used for performing multi-modal data segmentation encoding on the live broadcast picture, and the time sequence fusion predictor performs conversion rate real-time prediction by using the multi-modal data subjected to segmentation encoding. The technical problem of insufficient prediction accuracy of the existing garment live broadcast real-time conversion rate prediction is solved, and the technical effect of accurately predicting the garment live broadcast real-time conversion rate is achieved.

According to embodiments of the present disclosure, a method, apparatus, device and storage medium for online live streaming are provided. The method includes: presenting, in a user interface of a live stream, a first interface element associated with an object in a live streaming content; in response to receiving a first predetermined operation on the first interface element, presenting a media content associated with the object in the user interface; presenting a second interface element in association with the media content; and in response to receiving a second predetermined operation on the second interface element, triggering, in the live stream, a predefined interaction associated with the object.

To provide a real-time distribution system that is capable of enhancing communication between a distributor and a viewer at low costs and enables the distributor to obtain a benefit.SOLUTION: A real-time live distribution system for performing real-time live distribution of an idle talk dialog content toward a plurality of viewer terminals comprises a distributor terminal 1 including: an extraction section 11 having a virtual human for extracting viewer comments input from the plurality of viewer terminals in real time; an analysis section 12 for performing text analysis on the extracted viewer comments; a reading section 13 for reading a text using voice synthesis on the basis of a text analysis result; a feeling parameter setting section 14 for setting a virtual human feeling parameter for categorizing the viewer comments, which are at least a positive comment or negative comment, to determine the positive comment as a plus comment and the negative comment as a minus comment; and a change section 15 for changing a way of speaking according to the set feeling parameter.SELECTED DRAWING: Figure 2

The current invention relates to a live broadcasting system comprising at least one media capture device in communication with an encoder, which encoder is in further communication with a plurality of cloud-based pods and a control module configured to manage said pods. Each pod is functionally reconfigurable and can function as a stream receiver, stream sender or transcoder. The system is also reached by a method of broadcasting a live stream.

A user interface interaction method, apparatus, device, storage medium, and program product are provided. The proposed method includes: presenting first content related to a first question on a live streaming interface, the first content being configured based on a first operation by a first user, where the first user is the live streamer; receiving a second operation instructing a second user to provide a first response to the first question; and presenting a first prompt message on the live streaming interface, the first prompt message indicating the evaluation of the first response. This approach enriches the interactive forms associated with live streaming.

Provided is a method for allocating resource objects based on live streaming rooms. The method is applicable to a primary node on a server side, and includes: acquiring synchronization data and local data corresponding to a predetermined resource object in a target live streaming room, wherein the synchronization data is synchronously stored between the primary node and a secondary node, and includes a waiting queue of waiting users; and the local data is stored in the primary node, and includes second user data of an invited user; determining a target user based on a sequence of the waiting users in the waiting queue; acquiring a current state of the target user by comparing the synchronization data and the local data for the target user; and determining, based on the current state, whether to send an invitation for allocating the predetermined resource object to a target user side.

The invention discloses an RPA automatic live broadcast system based on a WebView module embedded in a mobile device, the RPA automatic live broadcast system comprises the mobile device and a Web end, the mobile device comprises a pushing end and a watching end, and the WebView module is embedded in the pushing end; the WebView module is used for loading a customized JS script and calling a required JS method, can receive various data and instructions transmitted by the pushing end, and feeds back an execution result of the Web end to the pushing end; the Web end is provided with an RPA function module and has a live broadcast platform function; and the RPA function module can realize automatic simulation operation of account authorization, commodity popup and bullet screen sending. The invention also discloses a method of the live broadcast system. The method comprises the following steps: S1, initializing; s2, authorizing login; s3, live broadcast operation (including commodity pushing and bullet screen replying) is carried out; and S4, ending live broadcast. The method improves the live broadcast efficiency, reduces manual errors, improves the live broadcast quality, enhances the live broadcast flexibility, can be customized and developed according to different platforms, and is wide in application range.

A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.

Systems and method for live streaming are disclosed. An example method includes capturing, image data including a field of view of the imaging device. The method includes presenting, a live streaming user interface (UI) including the image data and one or more live streaming UI elements. The method further includes, in response to an input selecting a live streaming UI element configured to initiate a broadcast, identifying a plurality of potential regions of interest within the field of view of the imaging device and responsive to a user input selecting a region of interest of the plurality of potential region of interest, providing broadcasted image data including the region of interest within the field of view of the image data. The method further includes replacing the image data included in the live streaming UI with the broadcasted image data, and presenting an audience interaction UI element within the live-stream UI.

This APP is about live streaming inside and outside of a rideshare to authinticate and determine the saftey of everyone inside of the ride share. This APP will also determine the drivers identity to the passanger so they do not enter the wrong vehicle. This APP will store all video on the cloud. Aslo a code will be generated for each ride so it may be shared. All this is for saftey.

This invention discloses an adjustable frequency response microphone integrating XLR and USB outputs, comprising a microphone body, a dynamic microphone driver, a passive filter, a pass-through / preamp circuit, an XLR XLR interface, a USB module, and a function control circuit. The passive filter employs an LC circuit structure, supporting three frequency modes: low-frequency cutoff, mid-frequency boost, and flat response, effectively filtering out ambient noise and enhancing vocal quality. The pass-through / preamp circuit offers both pass-through and preamp modes, with adjustable preamp gain to accommodate dynamic microphone drivers of varying sensitivities, and can be externally or internally powered by phantom power. The USB module integrates a Type-C interface and an audio chip, supporting analog-to-digital / digital-to-analog conversion, real-time headphone monitoring, and external power supply. The function control circuit integrates an encoder and a touch panel, enabling adjustments such as volume, mixing, and mute, and enhances the interactive experience with an RGB lighting module. This invention combines the advantages of professional XLR output with convenient USB output, making it suitable for professional recording, live streaming, gaming, and other scenarios.

To provide a technique capable of easily performing a setting change for synchronizing time codes among a plurality of imaging devices used for live distribution of a moving image at a suitable timing.SOLUTION: According to an aspect of the present invention, there is provided an image capturing apparatus which is one of a plurality of image capturing apparatuses used for live streaming of a moving image, the image capturing apparatus comprising a communication unit configured to communicate with an external apparatus, and a control unit configured to set, when a notification of a start of the live streaming is received by the communication unit, free run in which a time code advances regardless of whether the moving image is being recorded, as a method of advancing the time code.SELECTED DRAWING: Figure 7