Abstract: Aspects of the disclosure relate to a dynamic caching platform. The dynamic caching platform may train a machine learning model based on historical complexity score information. The dynamic caching platform may receive information streams from a client metaverse device and a metaverse host system. The dynamic caching platform may generate a complexity score based on the interaction information streams using the machine learning model. The dynamic caching platform may compare the complexity score to complexity thresholds. Based on the comparison, the dynamic caching platform may identify caching rules. The dynamic caching platform may cache interaction information based on the caching rules. The dynamic caching platform may update the complexity score using the machine learning model. The dynamic caching platform may update the caching rules based on the updated complexity score. The dynamic caching platform may cache interaction information based on the updated caching rules.

Abstract: A message reminder system, to perform operations that include: causing display of a presentation of a message addressed to a user, at a first position among a message feed of the user at a client device; receiving a request to open the message from the user of the client device, the request including a timestamp; detecting a trigger event based on at least the timestamp of the request to open the message, the trigger event comprising event attributes; generating a notification to be applied to the presentation of the message, the notification based on at least the event attributes of the trigger event; moving the presentation of the message from the first position among the message feed to a second position among the message feed; and applying the notification to the presentation of the message.

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

Abstract: Apparatus, systems and methods for augmenting a group of media content items by forming a graph including a plurality of nodes and a plurality of edges, where each node represents a segue option at a position in the graph and each edge represents a connection between a first node in the graph at a first position and a second node in the graph at a second position and finding a path in the graph.

Abstract: Aspects of the present disclosure involve a system and a method for performing operations comprising: receiving, by a messaging application implemented on a client device of a first user, input comprising a message directed to a second user; in response to receiving the input, obtaining contextual information associated with the message; identifying, based on the contextual information, a plurality of sounds representing the message; receiving a selection from the first user of a given sound of the plurality of sounds; and sending the given sound to the second user in response to receiving the selection of the given sound received from the first user.

Abstract: Among other things, embodiments of the present disclosure improve the functionality of electronic messaging and imaging software and systems by generating and displaying media overlays with avatars of different users. For example, media overlays can be generated by the system and displayed in conjunction with media content (e.g., images and/or video) generated by an image-capturing device (e.g., a digital camera).

Abstract: Auto-generation of dialog for a skill executed by a digital assistant is performed. Details descriptive of a digital assistant persona are received from a personality studio user interface. A personality type is generated based on the details. A standard vocabulary is auto-generated using the personality type. The standard vocabulary is exported for use in a skill. Prompts are auto-generated for the skill based on the standard vocabulary.

Abstract: A processing device that causes a virtual-space image to be displayed on a display device mounted on a player's head is provided with a first display processor and a second display processor. The first display processor causes first external information input from outside to be displayed on a specified object included in the virtual-space image when the virtual-space image is being caused to be displayed by the HMD. The second display processor causes second external information that is second external information input from outside and includes a real-space image to be displayed along with the virtual-space image when the virtual-space image is caused to be displayed by the HMD. The virtual-space image is, for example, the virtual-space image of a game, and the real-space image is, for example, an image imaged by an imaging device installed in the surroundings of the player.

Abstract: Data processing apparatus comprises a data memory; a selection controller comprising a computer processor; and a digital interface between a control process implemented by the selection controller and a text handling process implemented by the computer processor or another processor; in which: the selection controller is configured to provide a text document from the data memory to the text handling process to identify one or more characteristics of words in the text document; the selection controller is configured to provide user selection of one or more of the words in the text document to be substituted and of one or more target characteristics; and the selection controller is configured to request from the text handling process a set of one or more substitute words for the selected words such that the substitute words comply with the selected one or more of the target characteristics.

Abstract: Provided are an artificial intelligence (AI) system that utilizes a machine learning algorithm such as deep learning, etc., and an application of the AI system. A method performed by a device for providing a voice assistant service through a voice assistant program includes: receiving, from an external device, a character specialized model for the voice assistant program; receiving a user voice input including a request for a response of the voice assistant program and a word indicating a character; determining the character specialized model according to the word indicating the character; generating a response message to the request for the response of the voice assistant program, using the character specialized model; and outputting the generated response message.

Abstract: The following relates generally to computer security, and more particularly relates to computer security in a virtual environment, such as a metaverse. In some embodiments, one or more processors: receive a set of known events (e.g., security threats) including event classifications; receive data of layers of the virtual environment; detect events in the data of the layers of the virtual environment; and determine correlations between the events in the data of the layers of the virtual environment. The correlations may be between events in different layers of the virtual environment. The one or more processors may also predict future events by analyzing the detected events.

Abstract: A method for generating a user interface is described. A script file for a software component is received, the software component being configured by source code that specifies a plurality of variables for the software component. The script file is parsed for markup language that describes a graphical user interface for the plurality of variables of the software component. A graphical user interface for modifying values of the plurality of variables of the software component is automatically generated using the markup language.

Abstract: An example augmented reality system includes: obtaining information about an instance of a device; recognizing the instance of the device based on the information; selecting a digital twin for the instance of the device, with the digital twin being unique to the instance of the device; and generating augmented reality content based on the digital twin and an actual graphic of the instance of the device.

Abstract: The subject invention functions to use available data and information to automatically create narrative stories that describes domain events, circumstances and/or entities in a comprehensible and compelling and audience customized, manner. Computer executable instructions provide for generating a narrative story using standard and uniform structures and data for receiving domain related data and a story specification, parsing the story specification to provide constituent components, transforming the constituent components into executable code, instantiating content blocks having at least one feature for the domain according to the story specification and rendering the narrative story using the constituent components specified by the content blocks.

Abstract: Data captured during a movement by the user in a real-world environment may be received from a user device associated with a user. A corresponding movement is rendered by a virtual character within a virtual environment based on the data. Video of the corresponding movement within the virtual reality environment is captured and associated with the data. The captured video and the data are provided to a recipient designated by the user. It is then verified that the recipient is performing the movement by comparing data regarding the recipient during play of the captured video to the data associated with the captured video.

Abstract: Community-driven, context-aware (e.g., geospatially and space-time aware) intelligent research assistant systems are provided. A virtual assistant application of a user computing system may receive a query from a user and provide the query to a server. The server may determine a category and topic of the query and determine whether an application exists for the category and topic. When the application exists, the server may call an application programming interface (API) associated with the application that executes finite state machine (FSM) logic to determine a context-aware answer to the query and provide the determined context-aware answer to the virtual assistant application.

Abstract: Aspects of the present disclosure relate to determining computer graphics objects (CGOs) to render for a device of a user in a virtual environment having a plurality of participants, each participant corresponding to a CGO. A priority value of each CGO corresponding to each participant can be determined. A CGO priority list can be generated based on the determined priority values, wherein the CGO priority list ranks the CGOs based on the priority values. A rendering list of CGOs can be generated, wherein the rendering list includes a subset of the CGOs of the CGO priority list based on applied rendering processing constraints. The CGOs of the rendering list can then be rendered.

Abstract: A system and method provides a video chat capability where the video portion of the chat is initially impaired, but gets progressively clearer, either as time elapses, or as the users speak or participate with relevant information.

Abstract: Embodiments of this application disclose an augmented reality communication method. A specific solution is: sending, by a first electronic device, AR communication request information to a second electronic device, to request to perform AR communication with the second electronic device; establishing, by the first electronic device, an AR communication link with the second electronic device; and displaying, by the first electronic device on a touchscreen, a first AR communication interface including an image of a first real scenario and a first AR model and a second AR model, where in an AR communication process, the first AR model makes a corresponding expression and action based on an expression and action of a first user that are obtained by the first device, and the second AR model makes a corresponding expression and action based on an expression and action of a second user that are obtained by the first device.

Abstract: A mobile device communicates content to an external presentation device, such as a display device, for display or other presentation at the external presentation device. The mobile device identifies an impairment of a user of the mobile device. One or more configuration settings for a user interface of the external presentation device are determined based on the impairment of the user. These configuration settings are, for example, an indication of a particular audio level, an indication to perform text to speech, an indication of a particular type of color blindness, and so forth. The configuration settings are communicated to the external presentation device, allowing the external presentation device to be configured for or adapted to the impairment of the user.

Abstract: An interactive virtual world having avatars. Scenes in the virtual world as seen by the eyes of the avatars are presented on user devices controlling the avatars. In one approach, a method includes identifying a location of an avatar in a virtual world, and a point of gaze of the avatar; adjusting, based on the point of gaze, a lens that directs available light received by the lens so that the lens can focus on objects at all distances; collecting, using the adjusted lens, image data; and generating a scene of the virtual world as seen by the avatar, the scene based on the collected image data, the location of the avatar, and the point of gaze of the avatar.

Abstract: An operation method of a dialog agent includes obtaining an utterance history including at least one of an outgoing utterance to be transmitted to request a service or at least one of an incoming utterance to be received to request the service, updating a requirement specification including items requested for the service based on the utterance history, generating utterance information to be used to request the service based on the updated requirement specification, and outputting the generated utterance information.

Abstract: Method of generating customized avatars based on location information includes processor receiving from first client device location information including a location of the first client device. Processor causes a status interface to be displayed on first client device that includes selectable location items corresponding to locations based on the location information. Processor receives a selection from first client device of first selectable location item and causes avatar selection interface to be displayed on first client device that includes versions of first avatar performing actions related to the first selectable location item. Processor receives selection of first selectable version of the first avatar and generates a map interface that includes a map display based on the location information and the first selectable version of the first avatar. Processor causes the map interface to be displayed on at least one of the plurality of client devices. Other embodiments are disclosed.

Abstract: An avatar output device includes an avatar storage unit that stores, for each of two or more avatars, avatar information including first model information for displaying the avatar; a determination unit that determines at least one first avatar displayed using the first model information and at least one second avatar displayed using second model information with a data size smaller than a data size of the first model information from among the two or more avatars; an avatar acquisition unit that acquires an avatar using the second model information for each of the at least one second avatar determined by the determination unit, and acquires an avatar using the first model information for each of the at least one first avatar; and an avatar output unit that outputs the two or more avatars acquired by the avatar acquisition unit.

Abstract: Media content event review systems and methods are operable to present member content reviews of a media content event by presenting a plurality of member avatars in a virtual world, wherein the member avatars present audio commentary about a media content event identified in a user request, and wherein the community members who generated the audio commentary about the media content event have an interpersonal relationship with the requesting user.

Abstract: A cognitive information processing system environment which includes a plurality of data sources; a cognitive inference and learning system coupled to receive a data from the plurality of data sources, the cognitive inference and learning system processing the data from the plurality of data sources to provide cognitively processed insights, the cognitive inference and learning system further comprising performing a learning operation to iteratively improve the cognitively processed insights over time; and, a destination, the destination receiving the cognitively processed insights.

Abstract: A method for enabling the enhanced user-to-user communication in digital realities comprising generating a marker of a target user that is persistently applied on the target user; detecting, through a wireless network, the presence of a target user device and counterpart user device connected to the server via the wireless network; sending a notification to the counterpart user device informing about the presence of the target user device based on a set of rules; receiving one or more forms of interaction from the counterpart user device on the marker of the target user; opening up a communication channel between the counterpart user device and target user device; and receiving, processing and accordingly redirecting corresponding communications through and between the counterpart user device and target user device. A system thereof is also disclosed.

Abstract: An information management method collects log information of one or more home electrical apparatuses corresponding to service providers. Display screen data is generated which indicates a status of the log information. The display screen data includes groups of information which each contain information on an apparatus, a service provider corresponding to the apparatus, and log information output from the apparatus. Provision of the log information of each group is individually selectable. The display screen data is provided via a network to a display terminal that performs access to a server device. Information is received from the display terminal, which indicates that selection on whether or not provision of the log information is performed. Provision of the log information is not performed on the selected group when a determination is made that refusal of provision of the log information on the selected group is performed.

Abstract: Interface and mode selection for digital action execution is provided. For example, a system loads a script library embedded in an electronic resource. The system determines a historic level of engagement between a client computing device and one or more digital assistants. The system selects, based on a first property of the client computing device and the historic level of engagement, a type of digital interface. The system generates, based on the type of digital interface, a digital interface with the call-to-action. The system determines, responsive to an instruction to execute the call-to-action, a mode of execution. The system selects a digital assistant and a second client device to execute the call-to-action. The system transmits the call-to-action to the second client device for execution.

Abstract: A system, method and computer readable media are disclosed to provide an automatic emotional response to a digital communication. The response may include an automatically captured photo, video or audio clip taken immediately after a communication is received which is then transmitted to the sender or other parties copied on the communication. The response may also include a standardized graphical representation of an emotional response, such as an emoticon or emoji generated from an image before transmission back to the sender.

Abstract: Among other things, embodiments of the present disclosure provide systems and methods for modifying avatar components of avatar datasets for multiple users, generating avatars based on the datasets, and displaying multiple avatars on a display screen of a graphical user interface.

Abstract: Switching real-time data stream connections between network nodes sharing a virtual area is described. In one aspect, the switching involves storing a virtual area specification. The virtual area specification includes a description of one or more switching rules each defining a respective connection between sources of a respective real-time data stream type and sinks of the real-time data stream type in terms of positions in the virtual area. Real-time data stream connections are established between network nodes associated with respective objects each of which is associated with at least on of a source and a sink of one or more of the real-time data stream types. The real-time data stream connections are established based on the one or more switching rules, the respective sources and sinks associated with the objects, and respective positions of the objects in the virtual area.

Abstract: [Problem] The problem of the present disclosure relates to proposing an information processing device, an information processing terminal, an information processing method, and a program, which are capable of controlling the output of a voice so as to be adaptive to an action purpose of a user. [Solution] An information processing device including: an inference unit that infers an action purpose of a user on the basis of a result of sensing by one or more sensors; and an output control unit that controls, on the basis of a result of inference by the inference unit, output of a voice to the user performed by an audio output unit.

Abstract: A message reminder system, to perform operations that include: causing display of a presentation of a message addressed to a user, at a first position among a message feed of the user at a client device; receiving a request to open the message from the user of the client device, the request including a timestamp; detecting a trigger event based on at least the timestamp of the request to open the message, the trigger event comprising event attributes; generating a notification to be applied to the presentation of the message, the notification based on at least the event attributes of the trigger event; moving the presentation of the message from the first position among the message feed to a second position among the message feed; and applying the notification to the presentation of the message.

Abstract: Methods, systems, and computer-readable medium for personalized weather forecast videos are provided. In one implementation, a weather forecast may be obtained, and a personalized profile associated with a user may be obtained. Further, the personalized profile may be used to select at least one characteristic of a character. Further, the personalized profile and the weather forecast may be used to generate a personalized script related to the weather forecast. Further, the selected at least one characteristic of a character and the generated personalized script may be used to generate a video of the character presenting the generated personalized script.

Abstract: The present invention describes methods to customize massively-multiplayer-online-game (MMOG) Avatars beyond what can be displayed during general game-play. General game play refers to when a user is in a game with control of their Avatar. One knowledgeable in the art would understand that MMOGs are limited by their game engines to the complexity of Avatars that may be displayed to a user during general game-play, while maintaining acceptable frame rates. Furthermore one knowledgeable in the art would understand that Avatar complexity may further be limited due to the target machine the MMOG is designed to run on. The current invention describes methods to produce a custom Avatar image for non-game use, wherein the custom Avatar has higher resolution and greater choices than are available in-game.

Abstract: Systems and methods are provided for facilitating the presentation of expressive intent and other status information with messaging and other communication applications. The expressive intent is based on expressive effect data associated with the message recipients and/or message senders. The expressive intent can be conveyed through avatars and modified message content. The avatars convey gestures, emotions and other status information and the presentation of the avatars can be reactive to detected state information of the message recipient(s), message sender(s) and/or corresponding messaging device(s).

Abstract: An example augmented reality system includes: obtaining information about an instance of a device; recognizing the instance of the device based on the information; selecting a digital twin for the instance of the device, with the digital twin being unique to the instance of the device; and generating augmented reality content based on the digital twin and an actual graphic of the instance of the device.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for virtual-life-based human-machine interaction. One of the method includes obtaining cognitive data for a target user in response to a human-machine interaction from the target user by performing perception analysis on the target user. Target response content is identified based on the cognitive data and sent to the target user. A virtual interactive animation that comprises a virtual life image is dynamically generated based on the cognitive data and the target response content, where the virtual life image has an animation effect that matches the human-machine interaction performed by the target user.

Abstract: The disclosed technology is generally directed to chatbot conversation management. In one example of the technology, a generic model associated with a first property associated with a chatbot manager is received. The generic model is generated based on machine learning. A refined model that is associated with the first property is generated based on the generic model and a first plurality of phrases. A first conversation is held between a chatbot and an end user. Upon determining that the value of the first property for the end user is not stored in the database, via the chatbot, during the first conversation, the refined model is used to dynamically ask questions to the end user to determine a value of the first property for the end user. In a second conversation between the chatbot and the end user, the value of the first property for the end user is referenced.

Abstract: Techniques are described by which set-top boxes receive closed-captioning data streams as input to a Sign Language Interpretation (SLI) library. Depending on the demographics, different SLIs are provided. Additionally, input audio stems, e.g., for video programs without closed captioning, are sent to a speech-to-text processor before the SLI library. The text stream is then converted into sign language view mode in a PIP window for single view mode or to a multiview window for dual view mode. The current accessibility setup menu holds the ‘SLI’ option on/off button. SLI library contains videos for vocabulary which are sequenced in the SLI mode view window based on input text from closed captioning stream. If there is a word without a matching video in the SLI library, then the word itself is displayed in the SLI window. Such words are reported to a server for possible future package release with the additions.

Abstract: Human speech signals that are uttered within an environment are transcribed; the environment includes one or more avatars representing one or more software agents; the human speech signals are directed to at least one of the avatars. At least one non-speech behavioral trace is obtained within the environment; the trace is representative of non-speech behavior directed to the at least one of the avatars. The transcribed human speech signals and the at least one non-speech behavioral trace are forwarded to the one or more software agents. A proposed act is obtained from at least one of the agents; responsive thereto, a command is issued to cause the avatar corresponding to the software agent from which the proposed act is obtained to emit synthesized speech and to act visually in accordance with the proposed act.

Abstract: In a method modifying a user's virtual environment, a tracking module identifies a user identity and determines the location of the user. The tracking module retrieves historical user data associated with the user identity and the user location and identifies one or more patterns of user behavior using an analytical technique based on the historical user data. Upon determining one or more patterns from the data, the tracking module predicts user behavior associated with at least one parameter associated with the location and modifies at least one of a user virtual environment and a user avatar characteristics based on the predicted user behavior.

Abstract: Methods and systems are provided for generating animation for non-player characters (NPCs) in a game. The method includes operations for examining a scene for an NPC that is providing voice output. The method further includes operations for examining the voice output to identify am intensity modulation of the voice output. In addition, the method further includes processing the intensity modulation to predict body language signals (BLS) for the NPC. Moreover, the BLS is used to cause features of the NPC to react consistent with an emotion content of the intensity modulation identified in the voice output.

Abstract: Disclosed herein is a method of generating a customized response based on a context, in accordance with some embodiments. Accordingly, the method may include receiving, using a communication device, at least one sensor data from at least one sensor, analyzing, using a processing device, the at least one sensor data, determining, using the processing device, a context based on the analyzing, identifying, using the processing device, a customized profile associated with the context, retrieving, using a storage device, the customized profile, and generating, using the processing device, a customized response based on the at least one sensor data and the customized profile.

Abstract: Systems and methods disclosed herein create or modify a personalized mixed reality environment by taking into consideration both a user preferences and the actual location characteristics of the user.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR A DIGITAL CONVERSATION MANAGEMENT PLATFORM (“DCM-Platform”) transforms digital dialogue from consumers, client demands and, Internet search inputs via DCM-Platform components into tradable digital assets, and client needs based artificial intelligence campaign plan outputs. In one implementation, The DCM-Platform may capture and examine conversations between individuals and artificial intelligence conversation agents. These agents may be viewed as assets. One can measure the value and performance of these agents by assessing their performance and ability to generate revenue from prolonging conversations and/or ability to effect sales through conversations with individuals.

Abstract: Methods and systems for determining an action to be executed in response to a user query as a function of pre-query context information. One system includes an electronic computing device that includes a microphone, a transceiver, and an electronic processor. The electronic processor is configured to receive audio data from the microphone prior to receiving a user query, and determine, at predetermined time intervals, context information from the audio data. The electronic processor is further configured to store the context information in a memory. The electronic processor is further configured to receive second audio data from the microphone, and determine that the second audio data corresponds to the user query. The electronic processor is further configured to determine an action to be executed as a function of the second audio data and the context information, and execute the action in response to the user query.

Abstract: The present disclosure provides a method and system based on speech and augmented reality environment interaction. The method comprises: obtaining a user's speech data and obtaining an operation instruction corresponding to the speech data; performing processing for the augmented reality environment according to the operation instruction, and displaying an augmented reality processing result. According to the present embodiment, it is possible to improve an interaction efficiency of the augmented reality environment by means of the speech and augmented reality environment interaction.

Abstract: Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate automated answers to a complex query (e.g., a query that includes more than one search parameter). A user query comprising a complex query may be received and decomposed into a number of simple queries. A simple query may be executed with a search engine to obtain a set of search results. An answer for the simple query may be obtained from the search results and then substituted for a term of the next simple query identified from the complex query. The next simple query may then be executed to obtain another set of search results. These steps may occur any suitable number of times. An answer for the complex query may be generated based at least in part on the answers one or more of the simple queries.