Abstract: Methods, apparatus, systems, and computer-readable media are provided for providing context specific schema files that allow an automated assistant to broker human-to-computer dialogs between a user and an application that is separate from the automated assistant. The context specific schema file can provide the automated assistant with sufficient data to be responsive to user queries without necessarily communicating with a remote device, such as a server. Multiple different context specific schema files can be made available to the automated assistant according to a context in which a user is interacting with the automated assistant. In this way, latency otherwise exhibited by the automated assistant can be mitigated by providing the automated assistant with the information needed to respond to a user without continually retrieving the information over a network.

Abstract: Aspects of the disclosure relate to annotated video content. A computing platform may train a model using video content, which may configure the model to classify topics and identify speakers of future video content using STT and NLP. The computing platform may input new video content into the model, which may output an annotated version of the new video content. The model may be configured to generate the annotated version of the new video content by: 1) using one or more STT techniques to produce STT results, 2) classifying topics based on the STT results, 3) identifying speakers based on analysis of voice information, and 4) generating an index indicating a speaker and/or a topic corresponding to time segments. The computing platform may store the annotated version of the new video content, which may be navigable by a user using the visual index.

Abstract: Techniques are disclosed for automatically generating new content using a trained 1-to-N generative adversarial network (GAN) model. In disclosed techniques, a computer system receives, from a computing device, a request for newly-generated content, where the request includes current content. The computer system automatically generates, using the trained 1-to-N GAN model, N different versions of new content, where a given version of new content is automatically generated based on the current content and one of N different style codes, where the value of N is at least two. After generating the N different versions of new content, the computer system transmits them to the computing device. The disclosed techniques may advantageously automate a content generation process, thereby saving time and computing resources via execution of the 1-to-N GAN machine learning model.

Abstract: In an example implementation, a method is described. The implementation accesses first and second media clips. The implementation also matches a first fingerprint of the first media clip with a second fingerprint of the second media clip and determines an overlap of the first media clip with the second media clip. The implementation also, based on the overlap, merges the first and second media clips into a group of overlapping media clips, transmits, to a client device, data identifying the group of overlapping media clips and specifying a synchronization of the first media clip with the second media clip, and generates for display on a display device of the client computing device, a graphical user interface that identifies the group of overlapping media clips, specifies the synchronization of the first media clip with the second media clip, and allows access to, and manipulation of, the first and second media clips.

Abstract: The disclosed technology includes at least one method performed by a system to dynamically adapt a computer desktop of a customer service agent to a live audio dialogue. The system can cause a speech feature analyzer to process a segment of the live audio dialogue to output multiple speech features and obtain search results by querying a database for the multiple speech features. The method can further include generating control signals based on the search results and cause an API to configure the computer desktop based on the control signals. The system can dynamically adapt the computer desktop in accordance with additional control signals that are generated based on next segments of the live audio dialogue.

Abstract: Certain aspects of the present disclosure provide techniques for training decision trees representing users of a software application. An example method generally includes generating, from a transaction history data set for a plurality of users of a software application, a plurality of grouped data sets including transactions grouped by counterparty. A plurality of feature vectors are generated from the plurality of grouped data sets. Each feature vector generally corresponds to a user of the plurality of users and includes a plurality of features describing relationships between the user and a plurality of counterparties in a transaction history associated with the user. A decision tree is trained based on the plurality of feature vectors. The decision tree generally includes a plurality of paths terminating in a similar or different classification, and the plurality of paths distinguishes a user associated with the decision tree from other users of the software application.

Abstract: This invention relates to a System and Method for generating Primary Output and a Secondary Output programmatically. The method may include extracting a transcript, topics, a hierarchy of the topics of a video file, and generating a Primary Output and a Secondary Output programmatically. The Primary Output comprises a visual, editable, clickable, and hierarchical Mind map for the video file. It further comprises a Unique address of parent and child nodes in the hierarchical Mind map and Time-stamps of corresponding topics. The Secondary Output comprises an index table of a Proximity score, details on whether a Secondary Input is found or not in the video file, a Unique address P[u,m,n], From and To Time-stamps, and a corresponding topic in the video file.

Abstract: Systems and methods are provided for enabling a smart automatic skip mode during playback of a content item. A content item is generated for output at a first time at a computing device, and input associated with navigating the content item is received. Metadata associated with a plurality of segments of the content item is identified and, based on the input and the metadata, a segment to skip is identified. The segment to skip is skipped, and the content item is generated for output at a second time.

Abstract: To prevent intent classifiers from potentially choosing intents that are ineligible for the current input due to policies, dynamic intent classification systems and methods are provided that dynamically control the possible set of intents using environment variables (also referred to as external variables). Associations between environment variables and ineligible intents, referred to as culling rules, are used.

Abstract: A trophy and card printing kiosk apparatus for creating secure and customizable cards and trophies associated with digital games and other databases includes a kiosk body with a CPU coupled within the kiosk body. A touch screen, a display screen, a payment card reader, and a card printer are coupled to a body front side of the kiosk body and are in operational communication with the CPU. A data transceiver and a memory card are coupled within the kiosk body and are in operational communication with the CPU. The data transceiver sends and receives data with a data base and a smartphone app. A power source is coupled to the kiosk body and is in operational communication with the CPU.

Abstract: The present application provides techniques of presenting bullet screens for live broadcast playback. The techniques comprise receiving a request for bullet screens sent from a client computing device during playback of at least one portion of a live broadcast video, wherein the bullet screens comprise comments moving across frames of the live broadcast video, the request comprises a timestamp, and the timestamp is associated with a playback progress of the at least one portion of the live broadcast video; determining a bullet screen segment file among a plurality of bullet screen segment files based on the timestamp, wherein the plurality of bullet screen segment files are generated by segmenting live bullet screen data associated with the live broadcast video into N bullet screen segment files, and the N is a positive integer; and transmitting the bullet screen segment file to the client computing device for display of the bullet screens.

Abstract: The issue-discovery services described herein may access data from the messaging platform and/or the issue-tracking platform to automatically determine issue attributes for creating a new issue in the issue-tracking platform based on activity in the messaging platform. The issue-discovery service may provide or otherwise be associated with a user input element presented on a client device (e.g., presented in the chat user interface), which allows a user of the client device to provide a user input to create a new issue in the issue-tracking platform based on activity in the chat channel. The user input may identify content associated with the chat channel (e.g., one or more messages displayed in the chat user interface) for use in creating the new issue in the issue-tracking platform.

Abstract: Disclosed in some examples are methods, systems, and machine-readable mediums which provide for an agent support application with a plurality of plug-in communication support assistants. Each of the plurality of plug-in communication support assistants monitors communications between the agents and customers for different conversational triggers. Conversational triggers may be any conversation, either by the agent or the customer, that the communication support assistant is trained to detect. Upon detecting one of these conversational triggers, the plug-in communication support assistant provides one or more suggestions to the agent.

Abstract: Review videos on product pages are enhanced with user interface elements that cause playback of the review videos at points at which particular topics are discussed. A review video is processed by converting speech to text and timestamping the text. Topics are identified in the text, and a time in the review video corresponding to each topic is identified from the timestamps for the text. In some configurations, sentiment is also determined for each topic. User interface elements corresponding to each identified topic are presented with the review video on the product page. When a user viewing the product page selects a user interface element, the review video is played at a time corresponding to the topic of the selected user interface element.

Abstract: A screen recording method includes obtaining operation data of an electronic device and response data generated by the electronic device based on the operation data; obtaining a virtual device image matching the electronic device; and associating the operation data and the response data with the virtual device image according to a pre-determined processing strategy to generate a first video.

Abstract: Provided is a method for classifying information technology (IT) service request messages. The method may include receiving data associated with an IT service request message, determining a plurality of number values associated with a plurality of characters included in the IT service request message, generating a vector that includes index values, generating a first bitmap based on generating the vector, generating a second bitmap based on the first bitmap, where the second bitmap has a first dimension and a second dimension, and where the first dimension and the second dimension are equal, and determining a classification of the IT service request message using a neural network algorithm. A system and computer program product are also disclosed.

Abstract: A computing device and method for providing a user interface for summarizing and presenting information regarding dynamic provisioning and deployment of media processing resources, in a manner that is easy and intuitive and analogizes well to conventional physical media processing deployment. Users are not required to understand hypervisor configuration or virtual machine deployment, or switch through various layers and screens to find configuration information or controls, a process that may be particularly slow, complex, and difficult to learn, particularly for media and broadcast engineers unfamiliar with virtualization technologies. Instead, the present user interface improves efficiency of use of the computing environment for media processing, by providing deployment information in a format similar to physical processing deployment.

Abstract: An information processing apparatus according to the present invention includes: an acceptance unit that accepts a process request to an operation system; a specifying unit that, based on the process request, specifies an operation task to be executed in the operation system; an extraction unit that performs text analysis on the process request and extracts an answer item corresponding to an input item required at execution of the operation task from the process request; and an execution unit that executes the operation task based on the answer item.

Abstract: A system and method that converts the digital typesetting documents used in publishing to a device-specific format for electronic publishing. A “smart file and device-specific application” approach maintains the “look and feel” (design) of the source document used for print publication while typesetting for a specific device. Although this approach requires considerably more resources to create a smart file for each device-specific format, the smart file retains the unique typesetting characteristics of the printed book, is more aesthetically pleasing, and is easier to read. Furthermore, the device-specific application can render the smart file more quickly thereby eliminating any latency.

Abstract: Embodiments of the present disclosure relate to administration of an electronic survey via third-party content. For example, an electronic survey system receives a request to provide an electronic survey within a survey placeholder of a third-party webpage provided to a client device associated with a respondent. The survey system determines characteristics of the webpage or the respondent. The survey system then selects an electronic survey by comparing the characteristics of available electronic surveys to the characteristics of the webpage or the respondent. Additionally, the survey system provides electronic questions from the selected electronic survey for display within the survey placeholder of the webpage. The survey system also administers the electronic survey within the survey placeholder without redirecting the respondent client device away from the third-party webpage.