Disclosed is an approach for allowing an entity to perform semantic analysis in a SaaS semantic analysis platform upon private data possessed by one or more entities. In one or more embodiments, separate processing pipelines may be provided to the plurality of entities thereby keeping private data secure within the semantic analysis platform. In one or more embodiments, a common processing pipeline is provide with data associated a first entity being assigned a first identification code, and data associated with a second entity being assigned a second identification code.

Systems and methods that enable an information management system to utilize machine learning processes to modify and/or reconfigure presentation of mailbox contents, such as mail objects (e.g., email messages), are described. The systems and methods may provide data associated with mail objects to a machine learning system, which runs various machine learning processes using the mail object data. The machine learning processes may discover and/or identify connections between mail objects, such as connections between objects based on two or more objects sharing an associated product or service, an object being associated with a trending topic or issue, an object being associated and/or identified as having a relative high (or, low) priority, and so on.

A method of classifying electronic communications includes receiving an electronic message. A whitelist is input comprising at least one entry associated with an authoritative entity. At least one similarity score is computed based on an extent to which the message matches the entry in the whitelist. When the similarity score exceeds that threshold value, an indicator is output of a risk that the message appears to be associated with the authoritative entity. It is determined whether the message was sent from the authoritative entity based on at least one of attempting to verify an email authentication, and comparing an email address of a sender of the message to an email address associated with the authoritative entity. Responsive to determining that the message was sent from the authoritative entity, the message is delivered. Responsive to determining that the message was not sent from the authoritative entity, a security action is performed.

A method of classifying electronic communications includes receiving an electronic message. A whitelist is input comprising at least one entry associated with an authoritative entity. At least one similarity score is computed based on an extent to which the message matches the entry in the whitelist. When the similarity score exceeds that threshold value, an indicator is output of a risk that the message appears to be associated with the authoritative entity. It is determined whether the message was sent from the authoritative entity based on at least one of attempting to verify an email authentication, and comparing an email address of a sender of the message to an email address associated with the authoritative entity. Responsive to determining that the message was sent from the authoritative entity, the message is delivered. Responsive to determining that the message was not sent from the authoritative entity, a security action is performed.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for dynamically controlling ephemeral messaging threads and ephemeral message duration settings across computing devices while improving security by maintaining end-to-end encryption. In particular, in one or more embodiments, the disclosed systems can transmit encrypted ephemeral messages, including ephemeral message duration settings and ephemeral setting timestamps. The disclosed systems can decrypt received messages on receiving client devices and dynamically apply ephemeral message duration settings to different message threads. For example, the disclosed systems can modify existing duration settings at a receiving client device to match a received ephemeral message duration setting based on determining that the received ephemeral setting timestamp predates an existing setting timestamp. Further, the disclosed systems can apply the ephemeral message duration setting to delete ephemeral messages from an ephemeral message thread.

Discovery of communication platform features or exposure of such features to the user may include generating embeddings for a variety of types of communication platform content and communications. These embeddings may be used to characterize and compare various communication platform features and ultimately expose these features to a user when the user may not have otherwise encountered them. The embeddings may additionally or alternatively be used to determine a degree of alignment.

A system and method displays lists of users or messages in segments, with some segments showing messages or users believed to be more relevant to the user than others on the list.

A system and method displays lists of users or messages in segments, with some segments showing messages or users believed to be more relevant to the user than others on the list.

An electronic device displays a messaging user interface on a display, the messaging user interface including a conversation transcript of a messaging session between a user of the electronic device and at least one other user, a keyboard, a message-input area, and a digital image affordance. While displaying the messaging user interface, the device detects an input that activates the digital image affordance. In response, the device replaces display of the keyboard with display of a plurality of digital images, the plurality of digital images including one or more digital images stored in memory and a live preview image from a digital camera. The device detects an input that selects the live image displayed within the plurality of digital images. In response, the device captures a digital image with the digital camera, while maintaining display of the conversation transcript.

An information processing method includes displaying an input box and a status bar, where the status bar includes at least one status icon; receiving a first input on a target status icon in the status bar; and in response to the first input, displaying target information in the input box or sending the target information, where the target information includes prompt information that corresponds to a state represented by the target status icon.