Facebook, Inc.

Samsung Electronics Co., Ltd.

Hewlett Packard Enterprise Development LP

Rajesh Krishna Shenoy

Keith E Moore

Laurent Nicolas Landowski

James Delli Santi

Anthony Robert Kesich

Deepak Thrakal

In one embodiment, a method includes accessing a mention table of entries that each have: (1) a string, (2) a count of a number of times the string is used in a corpus, and (3) a count of a number of times the string is linked to another document. The method also includes calculating, for each n-gram of a search query from a querying user, a link probability that represents the likelihood that the n-gram corresponds to an entity associated with a communication network. The method also includes identifying content objects that match the search query and ranking the content objects based at least in part on on the calculated link probability. The method also includes sending instructions to present the search results on a client system of the querying user.

Using related mentions to enhance link probability on online social networks

In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user, analyzing the message from the first user to identify one or more intents and one or more slots of the received message, computing a confidence score for the intent to offer entity information based on user behavior history records associated with the second user, sending, to a second client system associated with the second user, if the confidence score exceeds a threshold score, instructions for presenting a suggestion to the second user to store the values for entity information in association with a profile record for the entity, and receiving, from the second client system associated with the second user, an indication from the second user confirming the values for entity information should be stored with the profile record for the entity.

Automatically detecting and storing entity information for assistant systems

In one embodiment, a method includes receiving, from a first client system associated with a first user, a message sent from the first user to a second user, where the message includes one or more n-grams, analyzing the received message to identify one or more named-entities corresponding to one or more of the n-grams, tagging one or more of the n-grams of the message with references to the one or more identified named-entities, and sending, to a second client system associated with the second user, instructions for presenting the message to the second user, where the message includes the one or more tagged n-grams corresponding to the one or more identified named-entities, where each tagged n-gram is selectable to retrieve additional information associated with the corresponding named-entity.

Providing additional information for identified named-entities for assistant systems

According to some implementations of the present disclosure, a method that is executed by a processing system is described. The method includes receiving an ad request, determining a context category structure based on the ad request, and identifying one or more app-specific rules based on the category defined in the context category. The method further includes, for each app-specific rule: determining whether the identified entities in the context category structure are received by the template defined in the app-specific rule; generating a function identifier based on the set of identified entities and the template when the identified entities are received by the template defined in the app-specific rule; and determining a score for each of the generated function identifiers. The method includes selecting one or more of the generated function IDs based on the respective scores of the function IDs and generating an advertisement object corresponding to the function ID.

Deep link advertisements

Communications methods and appliances are described. According to one embodiment, a communications method includes prior to deployment of an appliance, establishing a trusted association between the appliance and a certificate authority, during deployment of the appliance, associating the appliance with a communications address of a communications medium, using the certificate authority, creating a signed certificate including the communications address of the appliance, announcing the signed certificate using the appliance, after the announcing, extracting the communications address of the appliance from the signed certificate, and after the extracting, verifying the communications address of the appliance.

Growing community of inventors

Cupertino, CA, United States of America

Rajesh Krishna Shenoy