Event-based search engine
As an example, a server hosting a search engine may receive a search query and determine a searched time interval, a searched object, and a searched event. The server may select, based on the searched time interval, a portion of an object-event bipartite graph that was created using information gathered from social media sites. The server may compare attributes of individual events in the portion with attributes of the searched event to identify a set of relevant events. The server may determine objects associated with the relevant events and compare attributes of individual objects with the attributes of the searched object to identify a set of relevant objects. The search engine may provide search results that include the set of relevant objects ordered according to their similarity to the searched object.
1. A method comprising:
receiving, by one or more processors, a search query;
determining, by the one or more processors and based on the search query, a searched time interval;
determining, by the one or more processors and based on the search query, a searched object;
determining, by the one or more processors and based on the search query, a searched event;
selecting, by the one or more processors, a portion of an object-event graph derived from information gathered from a plurality of social media sites;
determining, by the one or more processors, in the portion of the object-event graph, a set of relevant events that are similar to the searched event;
determining, by the one or more processors, one or more objects associated with individual relevant events in the set of relevant events;
determining, by the one or more processors and based on the one or more objects, a set of relevant objects that are similar to the searched object, the determination comprising:
performing a comparison of object attributes of individual objects in the set of relevant objects to the object attributes of the searched object;
determining, using a Naïve Bayes classifier, an object similarity score associated with individual objects; and
selecting the set of relevant objects based on the object similarity score; and
sending, by the one or more processors, search results including the set of relevant objects.
2. The method of claim 1 , wherein determining, in the portion of the object-event graph, the set of relevant events that are similar to the searched event comprises:
performing a comparison of event attributes of individual events in the portion of the object-event graph to the event attributes of the searched event;
determining, based on the comparison, an event similarity score associated with individual events; and
selecting the set of relevant events from the portion of the object-event graph based on the event similarity score.
3. The method of claim 2 , wherein determining, based on the comparison, the event similarity score associated with individual events comprises:
determining, using a Naïve-Bayes classifier, the event similarity score associated with individual events.
4. The method of claim 1 wherein:
the object comprises a person; and
the object attributes comprise at least one of:
a name of the person,
an age of the person,
a job title of the person,
a company where the person works,
a hair color of the person,
an eye color of the person, or
an attire of the person.
5. The method of claim 1 , wherein:
each event in the portion of the object-event graph occurs within the searched time interval.
6. The method of claim 1 , wherein:
the set of relevant objects in the search results are ordered according to a similarity of individual relevant objects to the searched object.
7. The method of claim 1 , wherein determining the searched time interval comprises identifying the time interval based on the search query using natural language processing.
8. A server comprising:
one or more processors; and
one or more non-transitory computer readable media to store instructions executable by the one or more processors to perform operations comprising:
receiving a search query;
determining, based on the search query, a searched time interval;
determining, based on the search query, a searched object;
determining, based on the search query, a searched event;
selecting a portion of an object-event graph derived from information gathered from a plurality of social media sites;
determining, in the portion of the object-event graph, a set of relevant events that are similar to the searched event;
determining one or more objects associated with individual relevant events in the set of relevant events;
determining, based on the one or more objects, a set of relevant objects that are similar to the searched object, the determination comprising:
performing a comparison of object attributes of individual objects in the set of relevant objects to the object attributes of the searched object;
determining, using a Naïve Bayes classifier, an object similarity score associated with individual objects; and
selecting the set of relevant objects based on the object similarity score; and
sending search results including the set of relevant objects.
9. The server of claim 8 , wherein determining, in the portion of the object-event graph, the set of relevant events that are similar to the searched event comprises:
performing a comparison of event attributes of individual events in the portion of the object-event graph to the event attributes of the searched event;
determining, based on the comparison, an event similarity score associated with individual events; and
selecting the set of relevant events from the portion of the object-event graph based on the event similarity score.
10. The server of claim 9 , wherein determining, based on the comparison, the event similarity score associated with individual events comprises:
determining, using a Naïve-Bayes classifier, the event similarity score associated with individual events.
11. The server of claim 8 , wherein:
the object comprises a person; and
the object attributes comprise at least one of:
a name of the person,
an age of the person,
a job title of the person,
a company where the person works,
a hair color of the person,
an eye color of the person, or
an attire of the person.
12. The server of claim 8 , wherein:
each event in the portion of the object-event graph occurs within the searched time interval.
13. The server of claim 8 , wherein:
the set of relevant objects in the search results are ordered according to a similarity of individual relevant objects to the searched object.
14. The server of claim 8 , wherein determining the searched object comprises identifying the object based on the search query using natural language processing.
15. One or more non-transitory computer readable media to store instructions executable by the one or more processors to perform operations comprising:
receiving a search query;
determining, based on the search query, a searched time interval;
determining, based on the search query, a searched object;
determining, based on the search query, a searched event;
selecting a portion of an object-event graph derived from information gathered from a plurality of social media sites;
determining, in the portion of the object-event graph, a set of relevant events that are similar to the searched event, the determination comprising:
performing a comparison of event attributes of individual events in the portion of the object-event graph to the event attributes of the searched event;
determining, using a Naïve-Bayes classifier and based on the comparison, an event similarity score associated with individual events; and
selecting the set of relevant events from the portion of the object-event graph based on the event similarity score;
determining one or more objects associated with individual relevant events in the set of relevant events;
determining, based on the one or more objects, a set of relevant objects that are similar to the searched object; and
sending search results including the set of relevant objects.
16. The one or more non-transitory computer readable media of claim 15 , wherein determining, based on the one or more objects, the set of relevant objects that are similar to the searched object comprises:
performing a comparison of object attributes of individual objects in the set of relevant objects to the object attributes of the searched object;
determining, using a Naïve-Bayes classifier and based on the comparison, an object similarity score associated with individual objects; and
selecting the set of relevant objects based on the object similarity score.
17. The one or more non-transitory computer readable media of claim 16 , wherein:
the object comprises a person; and
the object attributes comprise at least one of:
a name of the person,
an age of the person,
a job title of the person,
a company where the person works,
a hair color of the person,
an eye color of the person, or
an attire of the person.
18. The one or more non-transitory computer readable media of claim 15 , wherein:
each event in the portion of the object-event graph occurs within the searched time interval.
19. The one or more non-transitory computer readable media of claim 15 , wherein:
the set of relevant objects in the search results are ordered according to a similarity of individual relevant objects to the searched object.
20. The one or more non-transitory computer readable media of claim 15 , wherein determining the searched event comprises identifying the event based on the search query using natural language processing.