Facebook, Inc.

Maxime Boucher

Xiao Li

Yofay Kari Lee

Alisson Gusatti Azzolini

Michael Benjamin Cohen

Lars Eilstrup Rasmussen

Tao Xie

Rousseau Newaz Kazi

Necip Fazil Ayan

Kathryn Hymes

Lars Rasmussen

Russell Lee-Goldman

Alexander Perelygin

Yunnan Wu

Rajat Raina

William Russell Maschmeyer

Colin Dunn

Sahil Prakash Thaker

Kurchi Subhra Hazra

Veselin S Stoyanov

Martin Jean Raison

Arpit Suresh Jain

Amy Campbell

Jinlong Zhou

Christopher Joseph Kalani

Anuj Bindal

Mahsa Ghafourian

Michael Curtiss

Chaitanya Mishra

Bogdan State

Ehud Weinsberg

Amaç Herda{umlaut Over (g)}delen

Rousseau Kazi

In particular embodiments, a method includes receiving, from a client system of a first user, a structured query comprising references to one or more objects associated with the online social network, identifying a set of target objects corresponding to the structured query, wherein each target object in the set is an object that is connected within the online social network to at least one of the objects referenced in the structured query, filtering the set of target objects based on a privacy setting of each of the connections to the target object, and generating search results comprising references to each target object from the post-filtered set that is connected to the first user within the online social network by a series of connections that have a visibility that is visible to the first user.

Filtering search results for structured search queries

In one embodiment, a method includes receiving a search query to search for multimedia objects of the online social network; searching an index to identify multimedia objects based on the search query, wherein the index indexes multimedia objects and associated keywords, each keyword being extracted from communications associated with a respective multimedia object, wherein each communication is of a particular communication-type, and wherein each identified multimedia object is indexed with keywords matching at least a portion of the search query; calculating, for each identified multimedia object, an object-score based on a communication-type of a communication from which one or more of the matching keywords were sourced; and sending instructions for presenting a search-results page to a client system, the search-results page including references to identified multimedia objects having an object-score greater than a threshold object-score.

Multimedia search using reshare text on online social networks

In one embodiment, a method includes scoring a set of content objects based on one or more user-engagement factors, identifying one or more related content objects, wherein each related content objects is connected within the online social network to one or more content objects of the set of content objects having a score greater than a threshold score, generating a plurality of structured queries that each comprise references to one or more content objects, wherein at least one of the structured queries is a personalized query comprising a reference to at least one of the related content objects, and sending instructions to a client device for presenting one or more of the generated structured queries to a first user for display on an interface currently accessed by the first user, wherein at least one of the sent structured queries is a personalized query.

Personalizing default search queries on online social networks

Systems, methods, and non-transitory computer readable media configured to acquire data associated with a content item, the data associated with the content item including contextual information. The data associated with the content item can be provided to a model trained by machine learning. A set of hashtags associated with the content item can be determined based on the model.

Systems and methods to predict hashtags for content items

In one embodiment, a method includes receiving, from a client system of a first user, a text query to search for posts of the online social network, the text query comprising one or more n-grams, searching a personalized index of keyword phrases associated with the first user to identify one or more keyword phrases matching one or more of the n-grams of the text query, the index of keyword phrases being based on content extracted from posts by one or more second users that have been viewed by the first user, and providing to the client system in response to receiving the text query, instructions for displaying a user interface comprising one or more of suggested queries to search for posts of the online social network, wherein each suggested query comprises one or more n-grams from the text query and one or more of the identified keyword phrases.

Keyword search queries on online social networks

In one embodiment, a method includes receiving, at the mobile client system, a text string inputted into a query field by a first user, accessing, from a local data store, a set of grammar templates, each grammar template comprising query tokens referencing an object stored in the local data store, generating one or more natural-language suggested queries by matching portions of the text string to query tokens of the grammar templates, each suggested query comprising references to one or more of the objects stored in the local data store and the natural-language string of the matching grammar template, calculating a cost for each grammar template based at least in part on one or more portions of text string not corresponding to one of the query tokens, and displaying one or more suggested queries to the first user, each having a calculated cost below a threshold cost value.

Client-side search templates for online social networks

In one embodiment, a method includes receiving a search query from a user and identifying one or more objects that match the search query. The method includes determining one or more search intents of the search query based on one or more topics associated with the identified objects and a ratio of object-types of the identified objects. The method includes generating search-result modules corresponding to the search query based on the determined search intents. Each search-result module is associated with a particular object-type and includes search results of that object-type. The method includes sending instructions for presenting a search-results interface to the client system of the user for display. The search-results interface may include one or more of the search result modules displayed in a blended order based on the determined search intents.

Blending by query classification on online social networks

In particular embodiments, a method includes receiving, from a client device associated with a first user of an online social network, a text query comprising one or more character strings, identifying one or more data objects that match at least a portion of one or more of the character strings, wherein each of the identified data objects is connected to the first user within the online social network, generating one or more recommended queries that each comprise the character strings of the text query and references to one or more of the identified data objects, and sending, to the client device associated with the first user in response to receiving the text query, one or more of the recommended queries for display to the first user.

Personalized structured search queries for online social networks

In particular embodiments, a method includes receiving, from a client device associated with a first user of an online social network, an unstructured text query, parsing the text query to identify one or more n-grams, determining a score for each n-gram, wherein the score for each n-gram is a probability that the n-gram corresponds to a particular data object of a plurality of data objects associated with the online social network, identifying one or more data objects based on the scores of their corresponding n-grams, each identified data object corresponding to at least one of the n-grams, and generating one or more structured queries that each comprise references to one or more of the identified data objects.

Detecting social graph elements for structured search queries

In one embodiment, a method includes presenting, by a client system, grammar tokens, each grammar token being based on a natural-language string and comprising references to objects associated with an online social network, receiving, at the client system, a selection of one of the presented grammar tokens, the selected grammar token being based on a first natural-language string, presenting, by the client system, completion tokens, wherein each completion token is based on a natural-language string corresponding to the first natural-language string and comprises references to objects associated with the online social network, receiving, at the client system, a selection of one of the completion tokens, the selected completion token being based on a second natural-language string, and generating, by the client system, a structured query corresponding to the selected grammar and completion tokens, the structured query comprising references to the objects referenced in the selected grammar and completion tokens.

Query construction on online social networks

In particular embodiments, a method includes receiving an unstructured text query, identifying nodes and edges from a social graph that correspond to n-grams in the text query, generating structured queries that include references to the identified nodes and edges, receiving a selection of a structured query, identifying target nodes that correspond to the structured query, and then generating search results that include target nodes with privacy settings where the nodes and edges along the path connecting the target node and the querying user are all visible to the user.

Filtering structured search queries based on privacy settings

In one embodiment, a method includes receiving a search query for multimedia objects of an online social network from a user of the online social network; searching an index of multimedia objects to identify multimedia objects indexed with keywords that match n-grams of the search query, the keywords having been extracted from reshares associated with the multimedia objects; calculating an object-score for each identified multimedia object based on social signals; generating search results with references to the identified multimedia objects that have an object-score greater than a threshold object-score; and sending to the user one or more of the search results as part of a search-results page.

In one embodiment, a method includes receiving an unstructured text query to search for posts of the online social network. The method includes parsing the text query to identify one or more n-grams. The method includes searching an index of keyword phrases associated with the first user to identify one or more keyword phrases matching one or more of the n-grams of the text query. The index of keyword phrases is based on posts by one or more second users of the online social network. The method includes calculating a keyword score for each of the identified keyword phrases. The method includes generating one or more suggested queries. Each suggested query includes one or more n-grams identified from the text query and one or more identified keyword phrases. The method includes sending one or more of the suggested queries to search for posts of the online social network.

In one embodiment, a method includes receiving a search query from a first user and identifying one or more second nodes that match the search query. The method includes determining one or more search intents of the search query. Search intent may be based on one or more topics associated with the identified nodes and one or more node-types of the identified nodes. The method includes generating one or more search results corresponding to the search query, the search-results being generated based on the determined search intents. The method includes sending a search-results page to the client system of the first user for display. The search-results page may include one or more of the generated search results.

Growing community of inventors

Mountain View, CA, United States of America

Maxime Boucher