Abstract: Various embodiments of this disclosure relate generally to utilizing a machine-learning model to determine an electronic communication priority. The method comprises receiving an electronic communication dataset reflecting an electronic communication inbox of a user from one or more databases, wherein the electronic communication dataset includes a plurality of electronic communications, utilizing a trained machine-learning model to determine a priority for at least one of the plurality of electronic communications based on the electronic communication dataset, wherein the priority corresponds to an importance level of the at least one of the plurality of electronic communications, filtering the electronic communication dataset according to the priority, and displaying the filtered electronic communication dataset via an electronic communication interface of a user device, wherein the electronic communication interface corresponds to an electronic communication application.

Abstract: Various embodiments of this disclosure relate generally to utilizing a machine-learning model to process natural language email instructions. The method comprises receiving, by one or more processors, at least one instruction from a user via an email interface displayed on a user device, the email interface corresponding to an email application, processing, by a trained machine-learning model, the at least one instruction to determine at least one response, wherein processing the at least one instruction includes applying at least one persona of the user to the at least one instruction, performing, by the one or more processors, at least one action or at least one query corresponding to the at least one response, and displaying, by the one or more processors, a confirmation on the email interface of the user device that the at least one response was completed.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, electronic files stored in association with a user account, (ii) analyzing, by a large language model (LLM) executed by the processor, the electronic files and identifying, based on the LLM analysis, at least one file that is a candidate for deletion, (iii) compiling, by the processor, an electronic message comprising an output indicating deletion of the at least one file, (iv) causing display, by the processor, the electronic message, (v) receiving, by the processor, user input related to the at least one file, (vi) analyzing, by the LLM executed by the processor, the user input, and (vii) performing, by the processor based on the analysis of the user input via the LLM, an action on the at least one file conforming to the user input.

Abstract: Disclosed embodiments are directed toward a computer-implemented system and method for providing an email digest in association with an interface display of an electronic inbox. The disclosed digest includes non-native inbox functionality related to a summary data structure that includes an interactive portion, whereby upon generation of electronic prompts via a large language model (LLM), the digest can leverage functionality of the LLM to determine how electronic inbox content can be rendered for display.

Abstract: Disclosed are systems and methods for receiving a meeting request via an electronic account of a user; determining a conflict between the meeting request and a pre-existing meeting, extracting and comparing information associated with each meeting based on an analysis of each meeting; determining a priority associated with each meeting based on the analysis of the information of each meeting; and utilizing a machine learning model to generate an output associated with the priority of each meeting to the electronic account of the user.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, an electronic message that comprises content generated by a user, (ii) predicting, by the processor, a potential action for the user by inputting the content of the electronic message into a large language model, (iii) suggesting, by the processor, the potential action to the user, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) identifying, by a processor, a plurality of electronic messages addressed to a user, (ii) analyzing, by a large language model executed by the processor, the plurality of electronic messages to identify potential actions, (iii) suggesting, by the processor, to the user, a potential action identified by the large language model, (iv) receiving, by the processor, user input related to the potential action, and (v) performing, by the processor, on behalf of the user, a subsequent action conforming to the user input.

Abstract: In some implementations, the techniques described herein relate to a method including: (i) accessing, by a processor, a plurality of messages for a user, (ii) analyzing, by a large language model executed by the processor, the plurality of messages to extract a context of each message, (iii) determining, by the processor, a current context of interest to the user, (iv) identifying, by the processor, a subset of the plurality of messages that each comprises a context related to the current context of interest to the user, and (v) causing display, by the processor, of the subset of the plurality of messages in a digital message inbox.

Abstract: The example embodiments are directed toward leveraging the power of large language models (LLMs) in a messaging application. In a first embodiment, LLMs are utilized to generate message content (both original and reply). In a second embodiment, LLMs are utilized to provide enhanced semantic search functionality. In a third embodiment, LLMs are utilized to provide intelligent actions to take based on message content.

Abstract: Embodiments are directed towards displaying an animated video emoticon by augmenting features identified in a video stream. Augmenting features identified in the video stream may include modifying, in whole or in part, some aspects of the identified features but not other aspects. For example, a user may select an animated video emoticon indicating surprise. Surprise may be conveyed by detecting the location of the user's eyes in the video stream, enlarging a size aspect of the eyes so as to appear ‘wide-eyed’, but leaving other aspects such as color and shape unchanged. Then, the location and/or orientation of the eyes in the video stream are tracked, and the augmentation is applied to the eyes at each tracked location and/or orientation. In another embodiment, identified features may be removed from the video stream and replaced with images, graphics, video, and the like.