A computer-implemented method, a computer system, and a computer program product are proposed. According to the method, chat information of a chatbot is obtained in response to receiving one or more chat messages from the chatbot. Then a matching data object of a matching data model from one or more data models is determined based on the chat information. And a data value of the matching data object is obtained as a response to the one or more chat messages.

A filtering system for received content, uses a computer, which receives content to be posted, the computer receiving content from a plurality of different users; the computer including a content filtering system, receiving the content from the plurality of different users, and operating to carry out a first autonomous screening of the content to use rules to determine whether the content meets a posting criteria, and categorizing the content as to whether the autonomous screening indicates that the content has met the posting criteria, the computer further receiving input from a human screening process which carries out humans to screen the criteria; and a machine learning system, that uses differences between the autonomous rules and the results of the human screening to learn from the human screening more about which autonomous rules are properly written, which rules are suspect, and also to create new autonomous rules.

Techniques for directive-based messaging synchronization are described. In one embodiment, an apparatus may comprise a local network component operative to receive a directive package at a messaging client on a client device; and a local database synchronization component operative to execute the directive package with a messaging-sync virtual machine to modify a local messaging database of the messaging client; and refresh a user interface component of the messaging client in response to modifying the local messaging database of the messaging client. Other embodiments are described and claimed.

Systems, methods, and computer readable storage media for controlling the transmission of electronic messages are provided. Aspects of the disclosure provide a method for controlling electronic transmission of electronic communications generated by authoring services. The method includes receiving a first message from a first authoring service of the plurality of authoring services, the first message comprising at least one recipient and content for at least one electronic communication, adding the first message to a message queue associated with the at least one recipient, determining one or more characteristics associated with the at least one recipient, evaluating the first message using the one or more characteristics to determine a first message state for the first message, in response to determining that the message state indicates the first message is to be transmitted, forwarding the first message to message transmission circuitry, and transmitting the first message to the recipient.

Aspects of the present disclosure involve systems, methods, devices, and the like for communicating with a unified messaging center using multi-channel messaging with block-based datastore. In one embodiment, a system is introduced that can provide a unified experience and capability for messaging with one or more entities across platforms. The messaging capability includes the ability to provide user interaction using a single architecture with data store in a centralized form. In one embodiment, the data store includes the use of blockchain technology wherein each interaction with the user and across platforms is recorded and stored on a cryptographed block.

In one embodiment, a method includes receiving a user input from a user from a client system associated with the user, wherein the client system comprises one or more cameras, determining one or more points of interest in a field of view of the one or more cameras based on one or more machine-learning models and sensory data captured by the one or more cameras, generating a plurality of media files based on the one or more points of interest, wherein each media file is a recording of at least one of the one or more points of interest, generating one or more highlight files based on the plurality of media files, wherein each highlight file comprises a media file that satisfies a predefined quality standard, and sending instructions for presenting the one or more highlight files to the client system.

In one embodiment, a method includes receiving a user input comprising one or more words at a client system, wherein each word comprises one or more characters, inputting the words to a convolutional neural network (CNN) model stored on the client system, accessing a plurality of character-embeddings for a plurality of characters, respectively, from a data store of the client system, generating one or more word-embeddings for the one or more words, respectively, based on the accessed character-embeddings by processing the accessed character-embeddings with one or more convolutional layers and one or more gated linear units of the CNN model, determining one or more tasks corresponding to the user input for execution based on an analysis of the one or more word-embeddings by the CNN model, and providing an output responsive to the user input based on the execution of the one or more tasks at the client system.

A computer system identifies threads in a communication session. A feature vector is generated for a message in a communication session, wherein the feature vector includes elements for features and contextual information of the message. The message feature vector and feature vectors for a plurality of threads are processed using machine learning models each associated with a corresponding thread to determine a set of probability values for classifying the message into at least one thread, wherein the threads include one or more pre-existing threads and a new thread. A classification of the message into at least one of the threads is indicated based on the set of probability values. Classification of one or more prior messages is adjusted based on the message's classification. Embodiments of the present invention further include a method and program product for identifying threads in a communication session in substantially the same manner described above.

Various embodiments are directed to an improved group-based communication apparatus that is configured to efficiently manage draft messaging communications in a group-based communication system. The group-based communication apparatus is configured to synchronize draft messaging communications, including creating, updating, deleting, and posting of such draft messaging communications, across multiple client devices and with a group-based communication repository. Utilizing draft message metadata associated with the draft messaging communications, the group-based communication apparatus is also configured to implement validation rules and conflict resolution procedures associated with draft messaging communications. Additionally, the group-based communication apparatus is configured to render a draft list icon or other visual indicia to a group-based communication interface to inform a user that there is a draft messaging communication associated with one or more of the group-based communication channels.

Non-volatile memory may contain definitions of: (i) a plurality of message queue implementations respectively associated with different queue behaviors, the different queue behaviors specified by corresponding sets of modes, and (ii) an application programming interface (API) through which applications can access one or more message queues. One or more processors may be configured to: create a message queue of a particular message queue type, supported by a corresponding message queue implementation, by specifying a set of modes corresponding to a queue behavior; receive, from a producing application and by way of the API, one or more messages for the message queue; store the one or more messages in a data structure associated with the message queue; receive, from a consuming application and by way of the API, a request to read from the message queue; and provide a message from the message queue to the consuming application.