Search results for pseudo-content
Various embodiments of a Title Engine generate search results that identify content available in a content corpus in response to receiving a search query for content that is currently unavailable in the content corpus. Rather than returning output merely indicating absence of the requested content set forth in the received search query, the Title Engine identifies various content available in the content corpus that is similar to the search query's requested—but unavailable—content. The Title Engine identifies content in a content corpus that is similar to requested content that has been determined as unavailable. Upon determining unavailability of the requested particular content in the content corpus, the Title Engine generates a pseudo-identifier for the requested particular content. The Title Engine inserts the pseudo-identifier into a sequence of content identifiers. The Title Engine generates an embedding for the pseudo-identifier.
1. A computer-implemented method, comprising:
receiving a search query, from a user account, for content submitted to a content corpus;
determining the content identified in the search query is unavailable;
generating a pseudo-identifier for the unavailable content identified in the search query;
inserting the pseudo-identifier into a sequence of content identifiers, the sequence associated with the user account;
generating an embedding for the pseudo-identifier;
identifying, via the embedding, a plurality of sequences of content identifiers, wherein a respective sequence corresponds to a different user account that previously sent a search query for the unavailable content identified by the pseudo-identifier;
for one or more of the respective sequences identified via the embedding:
(i) determining content interactions that occurred within a particular time range from an instance of the pseudo-identifier placed in the respective sequence, each of the determined content interactions associated with a proximate content identifier; and
(ii) identifying neighbor content from at least a portion of the proximate content identifiers;
generating search results responsive to the user account's search query based on the neighbor content.
2. The computer-implemented method of claim 1 , wherein each content identifier uniquely identifies a different portion of content accessed by the user account; and
wherein the sequence of content identifiers orders the content identifiers according to an access time by the user account of each respective content identifier.
3. The computer-implemented method of claim 1 , further comprising:
generating, via the embedding, search results responsive to the search query from the user account, the search results including at least one recommendation of similar content, the similar content comprising content available in the content corpus and similar to the unavailable content identified in the search query.
4. The computer-implemented method of claim 1 , wherein identifying a plurality of sequences of content identifiers further comprises:
identifying previous matching search queries from one or more of the different user accounts that match the search query from the user account within a threshold of similarity;
identifying respective different pseudo-identifiers that correspond to the previous matching search queries; and
identifying a plurality of sequence content identifiers, wherein a respective sequence includes an instance of at least one of the respective different pseudo-identifiers.
5. The computer-implemented method of claim 1 , wherein at least a portion of the content corpus comprises content uploaded from a first user account for access by a plurality of user accounts.
6. A system comprising one or more processors, and a non-transitory computer-readable medium including one or more sequences of instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving a search query, from a user account, for content submitted to a content corpus;
determining the content identified in the search query is unavailable;
generating a pseudo-identifier for the unavailable content identified in the search query;
inserting the pseudo-identifier into a sequence of content identifiers, the sequence associated with the user account;
generating an embedding for the pseudo-identifier;
identifying, via the embedding, a plurality of sequences of content identifiers, wherein a respective sequence corresponds to a different user account that previously sent a search query for the unavailable content identified by the pseudo-identifier;
for one or more of the respective sequences identified via the embedding:
(i) determining content interactions that occurred within a particular time range from an instance of the pseudo-identifier placed in the respective sequence, each of the determined content interactions associated with a proximate content identifier; and
(ii) identifying neighbor content from at least a portion of the proximate content identifiers;
generating search results responsive to the user account's search query based on the neighbor content.
7. The system of claim 6 , wherein each content identifier uniquely identifies a different portion of content accessed by the user account; and
wherein the sequence of content identifiers orders the content identifiers according to an access time by the user account of each respective content identifier.
8. The system of claim 6 , further comprising:
generating, via the embedding, search results responsive to the search query from the user account, the search results including at least one recommendation of similar content, the similar content comprising content available in the content corpus and similar to the unavailable content identified in the search query.
9. The system of claim 6 , wherein identifying a plurality of sequences of content identifiers further comprises:
identifying previous matching search queries from one or more of the different user accounts that match the search query from the user account within a threshold of similarity;
identifying respective different pseudo-identifiers that correspond to the previous matching search queries; and
identifying a plurality of sequence content identifiers, wherein a respective sequence includes an instance of at least one of the respective different pseudo-identifiers.
10. The system of claim 6 , wherein at least a portion of the content corpus comprises content uploaded from a first user account for access by a plurality of user accounts.
11. A computer program product comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions to:
receiving a search query, from a user account, for content submitted to a content corpus;
determining the content identified in the search query is unavailable;
generating a pseudo-identifier for the unavailable content identified in the search query;
inserting the pseudo-identifier into a sequence of content identifiers, the sequence associated with the user account;
generating an embedding for the pseudo-identifier;
identifying, via the embedding, a plurality of sequences of content identifiers, wherein a respective sequence corresponds to a different user account that previously sent a search query for the unavailable content identified by the pseudo-identifier;
for one or more of the respective sequences identified via the embedding:
(i) determining content interactions that occurred within a particular time range from an instance of the pseudo-identifier placed in the respective sequence, each of the determined content interactions associated with a proximate content identifier; and
(ii) identifying neighbor content from at least a portion of the proximate content identifiers;
generating search results responsive to the user account's search query based on the neighbor content.
12. The computer program product of claim 11 , wherein each content identifier uniquely identifies a different portion of content accessed by the user account; and
wherein the sequence of content identifiers orders the content identifiers according to an access time by the user account of each respective content identifier.
13. The computer program product of claim 11 , further comprising:
generating, via the embedding, search results responsive to the search query from the user account, the search results including at least one recommendation of similar content, the similar content comprising content available in the content corpus and similar to the unavailable content identified in the search query.
14. The computer program product of claim 11 , wherein identifying a plurality of sequences of content identifiers further comprises:
identifying previous matching search queries from one or more of the different user accounts that match the search query from the user account within a threshold of similarity;
identifying respective different pseudo-identifiers that correspond to the previous matching search queries; and
identifying a plurality of sequence content identifiers, wherein a respective sequence includes an instance of at least one of the respective different pseudo-identifiers.