Snap Inc.

Yiwei Ma

Shuo Wu

Masoud Akhoondi

Nima Khajehnouri

Rohan Monga

Yuncheng Li

Xuan Huang

Harsh Agrawal

Ye Tao

Tao Ning

Jung Hyun Kim

Yu Chen

Tolga Can

Jeremy Baker Voss

Nathan Kenneth Boyd

Douglas Cohen

Yamill Antonio Vallecillo

Jason Brewer

Manish Malik

Mai Chi Tran

Hangqi Zhao

Yang Zhou

Yining Zhang

Ding Zhou

Joshua Siegel

Juliet Shen

Jerome Sinocruz

Yinan Na

Jinchao Ye

Dan Xie

Shuo Han

James Li

Lili Zhang

Mingtao Zhang

Houshmand Shirani-Mehr

Chang Kuang Huang

Techniques for creating an interest graph include obtaining content items from multiple content sources and applying tailored (e.g., source-specific) preprocessing to the content items based on their respective content source. Text is extracted and salient keywords and key phrases are identified using unsupervised machine learning models. The keywords and key phrases become nodes in an interest graph, each node comprising an embedding of a keyword or key phrase in a common embedding space, with edges representing semantic similarity based on embeddings or co-engagement patterns. The graph provides an expansive, granular, and dynamic taxonomy easily adaptable to emerging interests. The interest graph overcomes limitations of conventional taxonomies that lack depth, fail to capture niche interests, and cannot adapt to reflect evolving user preferences. The described techniques construct a rich interest graph from diverse content for improved content understanding.

Automatic techniques for constructing an evolving interest taxonomy from user-generated content

Systems, methods, devices, computer readable instruction media, and other embodiments are described for automated image processing and insight presentation. One embodiment involves receiving a plurality of ephemeral content messages from a plurality of client devices, and processing the messages to identify content associated with at least a first content type. A set of analysis data associated with the first content type is then generated from the messages, and portions of the messages associated with the first content type are processed to generate a first content collection. The first content collection and the set of analysis data are then communicated to a client device configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data.

Automated image processing and insight presentation

A survey distribution system receives a selection of a first subset of a user population. For example, an administrator of the system may select one or more user attributes of the users among the user population. In response, the survey distribution system identified the first subset of users based on the selected attributes. In some example embodiments, the administrator of the system may additionally define a maximum or minimum number of users to be exposed to the content, as well as targeting parameters for the content, such as a period of time in which to distribute the content to the first subset of users, as well as location criteria, such that the content may only be distributed to users located in specific areas.

Survey distribution system

A visitation tracking system tracks user visitation to locations of interest to generate and report visualizations of the user visitation data. The visitation tracking system may be or include a group of one or more server machines configured to receive a user input specifying a location of interest, cause display of a presentation of a set of proximity borders within a region in response to the user input specifying the location of interest, wherein the region is based on the location of interest, receives a selection of a region to monitor (e.g., proximity borders, geo-fences), detects entries of client devices to a geo-fence represented by the region to monitor, and causes display of a notification in response to the detection of the entries.

System to track visitation metrics

Methods and systems are disclosed for performing operations for monitoring user activity on a messaging platform. The operations include receiving, from a first client device, a request to access a group portal associated with a group of users; in response to receiving the request, generating, for display in a first section of the group portal, a first identifier of a first user of the group of users; accessing activity information associated with the first user being descriptive of one or more messages sent by a second client device of the first user to a set of recipients; and generating, for display in a second section of the group portal, the activity information associated with the first user excluding contents of the one or more messages sent by the second client device.

Monitoring user activity on messaging platform

Targeted surveys to a subset of client devices based on geolocation, user application activities, and display duration

A location based measurement system monitors user interactions with media items, and visitation data to physical locations, to calculate an engagement score of the media item, wherein the engagement score serves as an indication of a 'lift' incited by the media item on a population of users exposed to the media item. The location based measurement system may be or include any instrumentality or aggregate of instrumentalities operable to compute, process, store, display, generate, communicate, or apply various forms of data for geo-fencing, control, or other purposes.

System to calculate an engagement score of location based media content

Growing community of inventors

Los Angeles, CA, United States of America

Yiwei Ma