90 results about "Message passing system" patented technology

A method, computer system, and computer program product are provided for dynamic user personalization using large language models. A conversation history is obtained comprising a plurality of messages associated with a user’s activity in a messaging system. The conversation history and a request to identify interests of the user, based on the conversation history, are provided to a large language model. A natural language output is received from the large language model comprising one or more identified interests of the user. A text sample, the natural language output, and a request to summarize the text sample based on the natural language output are provided to the large language model. A summary of the text sample that is personalized based on the one or more identified interests of the user is received from the large language model.

A system and method for contextual three-dimensional messaging in augmented reality (AR) environments is disclosed. The system receives chat messages with specified real-world destinations and stores them associated with those locations. When a user wearing an AR device enters a destination location, the system detects their presence using techniques like GPS, Wi-Fi positioning, or computer vision. It then generates a 3D visual representation of the message and determines an appropriate spatial position within the physical environment based on environmental analysis and object detection. The 3D message is displayed at the determined position in the AR view. The system can analyze message content to identify topics and match them to detected real-world objects for contextual placement. Users can interact with displayed messages through gestures or voice commands to reply, forward, delete, or reposition messages. This enables immersive, location-aware messaging experiences that seamlessly blend digital content with the physical world.

The subject technology detects a location and a position of a representation of a finger in a set of frames captured by a camera of a client device. The subject technology generates a first virtual object based at least in part on the location and the position of the representation of the finger. The subject technology renders the first virtual object within a first scene. The subject technology detects a first collision event corresponding to a first collider of the first virtual object intersecting with a second collider of a second virtual object. The subject technology modifies a set of dimensions of the second virtual object to a second set of dimensions. The subject technology renders the second virtual object based on the second set of dimensions within a second scene. The subject technology provides for display the rendered second virtual object within the second scene.

Embodiments are provided for suggesting topics in a messaging system. A set of queries is received from a chat transcript history, where the set of queries includes a set of unhandled queries, and each unhandled query comprises a query for which a bot did not identify a corresponding topic (e.g., queries that did not trigger selection of a topic by the bot). A vector representation is generated for each unhandled query in the set of unhandled queries. The vector representations for the set of unhandled queries are clustered to generate one or more clusters of vector representations, each cluster corresponding to a group of unhandled queries. A corresponding suggested topic is generated for each cluster and provided to an authoring tool that comprises one or more interactive elements to enable an author to select at least one of the suggested topics for implementation in the bot.

The present invention provides a secure system and method for sharing medical information among authorized medical professionals. The system ensures that only verified medical professionals can access the platform by requiring a medical license and utilizing facial recognition technology for authentication. The platform includes a content management component for uploading and accessing medical information, a digital rights manager to prevent unauthorized copying or removal of content, and a messaging system for secure communication between users. The system is designed to be HIPAA-compliant and includes features such as patient consent for video content, native voice triggers for camera movements during surgical procedures, and a customizable chat system for enhanced user experience. The invention aims to streamline the verification process, enhance security, and promote patient safety while facilitating the sharing of medical knowledge and techniques.

The disclosure provides a system / method / scheme to securely send data from a cloud, or cloud service provider, to users via a secure connectionless system, referred to herein as a C-VPN communication infrastructure (C-VPN CI). In one example a method of communicating from a cloud service provider to a user via a C-VPN CI includes: (1) obtaining, by a cloud service provider, security parameters from a SDE Cloud server operating on a computing system of the cloud service provider, wherein the security parameters include a set of mathematical rules and values for converting plain text to ciphertext, (2) creating a secure communication using the security parameters received from the SDE Cloud server, wherein the secure communication includes a secure header and secure data, and (3) sending the secure communication to the user via a generic electronic message delivery system.

The subject technology receives a set of frames. The subject technology detect a first gesture correspond to an open trigger finger gesture. The subject technology receives a second set of frames. The subject technology detects from the second set of frames, a second gesture correspond to a closed trigger finger gesture. The subject technology detects a location and a position of a representation of a finger from the closed trigger finger gesture. The subject technology generates a first virtual object based at least in part on the location and the position of the representation of the finger. The subject technology renders a movement of the first virtual object along a vector away from the location and the position of the representation of the finger within a first scene. The subject technology provides for display the rendered movement of the first virtual object along the vector within the first scene.

A method includes: receiving an initial request message in a request queue of the messaging system; receiving an aggregation reply message in a reply queue of the messaging system, wherein the aggregation reply message is received from an integration system that processes the initial request message, and wherein the aggregation reply message includes an aggregation identifier associated with the initial request message; in response to receiving the aggregation reply message, starting a timeout process; monitoring the timeout process; holding one or more messages that are in the reply queue and that include the aggregation identifier until the timeout process expires or an expected number of responses has been received; and making available the one or more messages that are in the reply queue and that include the aggregation identifier based on the timeout process expiring or the expected number of responses having been received.

The present invention relates to a messaging system configured to: receive a request to generate a message at a first client device; cause display of a message notification within an interface of a second client device, wherein the message was addressed to a recipient of the second client device; receive a request to un-send the message from the first client device; and remove the message notification from the interface at the second client device in response to the request to un-send the message, according to some example embodiments.

Systems and methods are provided for streamlined communications between clients and client agents during a transaction (e.g., in real estate or other industries) and / or other information from engagement platforms and other applications. A core system architecture is provided that comprises a system application server, a system session server, a user profile database, and a messaging application server, that use modular user interfaces, intelligent message delivery, enhanced client interaction, responsive messaging based on transaction progression, and agent-initiated updates to facilitate such communications, and which can be used by human and / or artificial intelligence agents to enhance the particular application.

A method uses natural language processing for visual analysis of a dataset, in a messaging application. The method includes receiving a first natural language (NL) input directed to a data source, in a messaging application. The first NL input includes at least one underspecified or ambiguous utterance. The method also includes parsing the first NL input into tokens based on a grammar and the data source. The method also includes generating and displaying an intermediate NL response, based on the tokens. In response to receiving a user input to provide missing information in the at least one underspecified or ambiguous utterance, the method includes generating an input query based on the user input and querying the data source using the input query, to obtain a result set. The method also includes generating and displaying a first NL output and a snapshot of a data visualization based on the result set.

A first process executing on a first HPC compute node of an HPC cluster sends a write command, including a global identifier for a memory window that is globally accessible to processes executing in the HPC cluster, to an HPC memory node of the HPC cluster instructing the HPC memory node to write first data to the memory window allocated at the HPC memory node. The first data is sent by the first process to a memory window allocated on the HPC memory node. The first data is written by the HPC memory node to the memory window that includes randomly accessed, addressable memory locations.

A voice communications system comprises a user interface with a push-to-talk (PTT) button, a communication module configured to transmit a signal from a first user to a second user upon activation of the PTT button without establishing a communication channel, and a receiver module that allows the second user to either accept the signal, thereby initiating a live audio stream, or ignore it. The system includes a voice streaming module for transmitting audio data while the PTT button is engaged and an artificial intelligence filtering module for real-time classification and moderation of the audio data, ensuring that the audio data is sent to the recipient only after approval by the filtering module. Additionally, the system can moderate pre-recorded digital messages prior to their transmission to a recipient.

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing augmented reality-based makeup. The program and method provide for receiving, by a messaging application running on a device of a user, a request to present augmented reality content in association with an image captured by a device camera, the image depicting a face of the user; accessing an augmented reality content item configured to generate a plurality of completed looks with respect to applying makeup to the face; presenting the augmented reality content item, including the plurality of completed looks, in association with the face depicted in the image; receiving user input selecting a completed look of the plurality of completed looks; and displaying, in response to receiving the user input, an interface with a set of makeup products associated with the selected completed look.

A messaging system is provided to communicate messages between computing devices. The computing devices can include vehicles and service computers. The messaging system includes nodes and virtual entities that may forward messages between computing devices. The messaging system may be a publish-subscribe system. The messaging system may allocate a allocating virtual entities that are associated with the computing devices. The virtual entity may be endpoints for the messages.

The present invention relates to a live message delivery system, including: user and recipient communication devices; an interface device with display and accessed by the user; an interface server which controls the interface device and adapts the display of the interface device to a conference event; a conference dialer which establishes a first communication link with the recipient communication device; a conference device which multiplexes communication links from the recipient to the user communication device, enabling group communication; and a conference controller which initiates and manages the conference event to deliver a real-time message reading from the user to the recipient via communication links, manages the conference dialer to contact each participant, and allows the user to deliver the live message to the participants with a time offset between each reading by the users such that each of the participants receives the live message during the conference event.

Provided is a method including receiving a message that is destined to one or more recipients and that includes a plurality of data fields, where a first set of data fields of the plurality of data fields includes unstructured data. The method includes parsing the unstructured data in at least a portion of the first set of data fields to obtain parsed data and processing, with a large language model, the parsed data to determine an interpretation of the data and a confidence score in that interpretation. The method determines, based on the interpretation and the confidence score, one or more actions to take with at least one of the message or the unstructured data in the at least the portion of the first set of data fields, performs the one or more actions, and sends the message to the one or more recipients.

A secure end-to-end messaging system utilizes location-based computer readable media encoding cryptographic codes to facilitate encryption and decryption of messages between electronic devices. A first device reads a cryptographic code from a first media, encrypts a message, and transmits it to a server where only the ciphertext is stored. A second device, at a different location, reads a second cryptographic code from a paired media to decrypt the message locally. The codes represent symmetric keys or asymmetric key pairs, enabling message authenticity verification through digital signatures. Cryptographic data embedded in URL fragments to avoid transmission to the server, enhancing security against interception. The media also encodes permissions, expiration dates, and device identifiers for granular control and notification capabilities. The system supports hierarchical access, group messaging, and various formats including audio / video, ensuring scalable, secure, and verifiable communication across distributed users without exposing plain text or private keys to the server.

The subject technology applies a three-dimensional (3D) effect to image data and depth data based at least in part on an augmented reality content generator. The subject technology generates a segmentation mask based at least on the image data. The subject technology performs background inpainting and blurring of the image data using at least the segmentation mask to generate background inpainted image data. The subject technology generates a packed depth map based at least in part on the a depth map of the depth data. The subject technology generates, using the processor, a message including information related to the applied 3D effect, the image data, and the depth data.

An electronic message computing system tracks new activity items that reflect activities that have not yet been seen by the user. A. generative artificial intelligence (AI) model generates a digest summary that is provided to the user the next time the user accesses the electronic message system. The digest summary summarizes new activity. The generative AI model also generates importance summaries that summarize the importance of a particular activity to the user, and content summaries that summarize the content of an activity item (such as an electronic mail message). The electronic messaging system also assigns a priority to each new activity item and provides the summaries, along with a priority, to a client computing system. The client computing system conducts a user experience, navigating the user through the new activity items, based upon the priority assigned by the electronic message computing system.

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing shared content collections. The program and method provide for receiving, from a first device of a first user, an indication of first user input to share a content collection between the first user and a second user selected by the first user, the content collection comprising at least one media content item, the second user corresponding to a contact of the first user; storing the content collection in association with the first user and the second user; receiving an indication of second user input to share the content collection with a third user selected by the second user, the third user corresponding to a contact of the second user; and associating the content collection with the third user.

A messaging system for a distributed quantum system (e.g. a quantum control system and / or a quantum error correction unit). The system has a plurality of real-time units (e.g. decoders, sequencers or

There is provided a communication system for communicating messages between a group comprising a plurality of user accounts on a plurality of communication channels. At least some user accounts operate on a first communication channel and at least some of the other user accounts operate on at least a second communication channel different to the first communication channel. A plurality of integration modules are provided, associated with a unique communication channel. Data stores retain user account identification information and membership in groups are accessible by a central messaging module to send and receive messages. A method is also provided for performing the same.

A method includes: receiving an initial request message in a request queue of the messaging system; receiving an aggregation reply message in a reply queue of the messaging system, wherein the aggregation reply message is received from an integration system that processes the initial request message, and wherein the aggregation reply message includes an aggregation identifier associated with the initial request message; in response to receiving the aggregation reply message, starting a timeout process; monitoring the timeout process; holding one or more messages that are in the reply queue and that include the aggregation identifier until the timeout process expires or an expected number of responses has been received; and making available the one or more messages that are in the reply queue and that include the aggregation identifier based on the timeout process expiring or the expected number of responses having been received.

A method comprises transmitting by a client device in a publish / subscribe messaging system, in accordance with a publish / subscribe messaging protocol, a subscribe request to a data broker, and transmitting, by the client device to the data broker, a sleep indication, the sleep indication indicating that a messaging client of the client device is entering a sleep state until a sleep state end time and requesting that, while the messaging client is in the sleep state, the data broker is to refrain from sending data to the client device. The method further comprises transmitting, by a network interface of the client device via a wireless communications link, a low power mode request signal for requesting to operate the network interface in a low power mode until a low power mode end time, wherein the sleep state end time and the low power mode end time are substantially aligned.

The subject technology receives image data including a representation of a physical item. The subject technology analyzes the image data to determine an object corresponding to the physical item. The subject technology extracts product metadata based on the determined object. The subject technology sends, to a server, the product metadata to determine second product metadata associated with the product metadata. The subject technology receives, from the server, the second product metadata, the second product metadata including additional information related to the physical item. The subject technology causes display, at a client device, the additional information related to the physical item based at least in part on the second product metadata.

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing shared content collections. The program and method provide for receiving, from a first device of a first user, an indication of first user input to share a content collection between the first user and a second user selected by the first user, the content collection comprising at least one media content item, the second user corresponding to a contact of the first user; storing the content collection in association with the first user and the second user; receiving an indication of second user input to share the content collection with a third user selected by the second user, the third user corresponding to a contact of the second user; and associating the content collection with the third user.

The subject technology applies, to image data and depth data, a 3D effect including at least one beautification operation based on an augmented reality content generator, the 3D effect including a beautification operation, the beautification operation comprising modifying image data, the image data including a region corresponding to a representation of a face, the beautification operation comprising using a machine learning model for at least one of smoothing blemishes or preserving facial skin texture. The subject technology generates a depth map using at least the depth data. The subject technology generates a segmentation mask based at least on the image data. The subject technology performs background inpainting and blurring of the image data using at least the segmentation mask to generate background inpainted image data. The subject technology generates a 3D message based at least in part on the applied 3D effect including the at least one beautification operation.

The subject technology receives metadata corresponding to a respective media overlay, the metadata including information indicating that the respective media overlay is configured to be applied as an image processing operation during post-processing of image data during a post-capture stage. The subject technology selects the respective media overlay in response to the information indicating that the respective media overlay is configured to be applied as an image processing operation during post-processing of image data. The subject technology, based at least in part on a category indicator associated with the respective media overlay, populates a group of media overlays with at least the respective media overlay. The subject technology sends, to a client electronic device, second metadata including at least information related to the group of media overlays.

A messaging method and dynamic messaging system for automated equipment and robots that provides flexible data transmission, presentation, and scheduling. Customized message instructions are provided to a robot controller using loadable configuration templates without restarting the controller or affecting the ongoing operation of the robot. The configuration templates contain only data definitions and no executable code. Customized data messages are sent from the robot controller based on triggering events including periodic timing, transmission of current messages, changes in equipment elements, and programmed requests. Custom message attributes such as transmission rate and priority can be set and messages can include file attachments. A message template creator external to the robot controller creates the configuration templates, ensures message uniqueness, and generates data ingestion patterns. The patterns are used by a cloud data parser to translate and load the data into data tables where customers can analyze the data from the messages using applications in a web portal.