Ditto Technologies, Inc.

People.ai, Inc.

Interviewstreet Incorporation

Sergey Surkov

Dmitry Kornilov

Sitaram Bhagavathy

Robert Curtis Randolph

Robert Charlie Daugherty

Oleg Rogynskyy

Mykola Pavlov

Ryan Osilla

Andrii Kvachov

Dmitry Starshov

Liubov Yaronskaya

The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

Systems and methods for automatic generation of electronic activity content for record objects using machine learning architectures

The present disclosure relates to linking electronic activities between systems of record based on a comparison of electronic activity signals and system of record signals. Indexed files can be generated for each of a plurality of record objects of a system of record. An electronic activity may be accessed. A search query may be generated. Match scores for the record objects may be generated. An association between an electronic activity and a record object may be stored. Instructions to link to the electronic activity to the record object may be transmitted.

Systems and methods for matching record objects to electronic activities using indexing

A user profile may be generating from a source accordingly to embodiments of the present disclosure. In some embodiments, a process (e.g., implemented by a client) includes obtaining a set of commits associated with a user from a source code version control system, extracting at least one signal from the set of commits, obfuscating the signal(s), and outputting the obfuscated signal(s). In some embodiments, a process (e.g., implemented by a server) includes receiving a signal associated with source code, where the signal is extracted from a commit obtained via a source code version control system. The process further includes aggregating the signal with at least one other signal, generating a user profile based at least on part on the aggregated signals, and rendering the user profile on a graphical user interface.

Generation of user profile from source code

Constructing a user's face model using particle filters is disclosed, including: using a first particle filter to generate a new plurality of sets of extrinsic camera information particles corresponding to respective ones of a plurality of images based at least in part on a selected face model particle; selecting a subset of the new plurality of sets of extrinsic camera information particles corresponding to respective ones of the plurality of images; and using a second particle filter to generate a new plurality of face model particles corresponding to the plurality of images based at least in part on the selected subset of the new plurality of sets of extrinsic camera information particles.

Constructing a user's face model using particle filters

Rendering glasses with shadows is disclosed, including: generating a face image corresponding to an image of a set of images based at least in part on a face model, wherein the set of images is associated with a user's face; generating a face with shadows image corresponding to the image based at least in part on shadows casted by a glasses model on the face model; generating a shadow transform based at least in part on a difference determined based at least in part on the face image and the face with shadows image; generating a shadowed image based at least in part on applying the shadow transform to the image; and presenting the shadowed image including by overlaying a glasses image associated with the glasses model over the shadowed image.

Rendering glasses shadows

Processing a set of images is disclosed, including: determining a set of user head measurements from a set of images; and determining a fit score corresponding to a glasses frames based at least in part on comparing the set of user head measurements to glasses frame measurements associated with the glasses frames.

Fitting glasses frames to a user

Smart image enhancements are disclosed, including: obtaining a representation of a user's face associated with a set of images associated with the user's face; obtaining a set of extrinsic information corresponding to an image of the set of images; determining a modified smoothing map by modifying a model smoothing map to correspond to the representation of the user's face; and determining an enhanced image based at least in part on the set of extrinsic information corresponding to the image, the modified model smoothing map, and the image.

Smart image enhancements

A system for fitting glasses frames to a user is disclosed. The system includes an interface for receiving images of a user's head at different angles. A processor compares user head measurements determined from the images with a database of glasses frame information that includes glasses frame measurements. One or more glasses frames are selected based on the comparison and the selected glasses frames are output.

Processing a set of images is disclosed, including: receiving a set of images; and searching for a representation of a user's face associated with the set of images and a plurality of sets of extrinsic information corresponding to respective ones of at least a subset of the set of images. Rendering a glasses frame is disclosed, including: receiving a selection associated with the glasses frame; rendering the glasses frame using at least a representation of a user's face and a set of extrinsic information corresponding to an image in a recorded set of images; and overlaying the rendered glasses frame on the image.

Growing community of inventors

Foster City, CA, United States of America

Sergey Surkov