Retrieving context from previous sessions
First Claim
1. A computer-implemented method comprising:
- receiving, by a search engine and from a speech-to-text engine, a search query that is based on an utterance of a user that was detected by a digital assistant device during a current search session;
determining, by the search engine, that the search query refers to a time indicator, the time indicator indicating a time earlier than the current search session;
determining, by the search engine, that the search query refers to one or more other query terms;
determining, by the search engine and from session data stored in a repository associated with the search engine, a first set of relevant previous search sessions from a second set of previous search sessions, wherein the second set of previous search sessions includes more previous search sessions than the first set of relevant previous search sessions, wherein each previous search session in the first set of relevant previous search sessions is associated with a respective time label corresponding to the time indicator;
identifying, by the search engine, a particular previous search session, from among the first set of relevant previous search sessions determined from the session data stored in the repository associated with the search engine, based on the one or more other query terms associated with the search query of the current search session without searching any previous search sessions of the second set of previous search sessions that are not in the first set of relevant previous search sessions;
identifying, by the search engine, one or more entities that are associated with one or more search queries or search results of the particular previous search session, based on the one or more other query terms of the search query of the current search session; and
providing (i) a response to the search query that includes a representation of one or more of the entities, from a text-to-speech engine, that is configured to be output on a speaker of the digital assistant device in response to the search query of the current search session and (ii) metadata, from the search engine, related to the one or more entities that is configured to be rendered on a graphical user interface of the digital assistant device during output of at least a portion of the response to the search query using the speaker of the digital assistant device.
2 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for retrieving and using contextual data from previous conversation sessions in conversational searches. In one aspect, a method includes receiving a first query for a first user session, determining that the first query refers to one or more tags in a first repository, the first repository associating respective identifiers to respective tags, each identifier representing a corresponding user session, determining one or more particular identifiers associated with the one or more tags in the first repository, retrieving particular contextual data associated with the determined particular identifiers in a second repository, the second repository associating respective identifiers to respective contextual data associated with corresponding user sessions represented by the respective identifiers, and performing an action responsive to the first query based on the retrieved particular contextual data.
31 Citations
28 Claims
-
1. A computer-implemented method comprising:
-
receiving, by a search engine and from a speech-to-text engine, a search query that is based on an utterance of a user that was detected by a digital assistant device during a current search session; determining, by the search engine, that the search query refers to a time indicator, the time indicator indicating a time earlier than the current search session; determining, by the search engine, that the search query refers to one or more other query terms; determining, by the search engine and from session data stored in a repository associated with the search engine, a first set of relevant previous search sessions from a second set of previous search sessions, wherein the second set of previous search sessions includes more previous search sessions than the first set of relevant previous search sessions, wherein each previous search session in the first set of relevant previous search sessions is associated with a respective time label corresponding to the time indicator; identifying, by the search engine, a particular previous search session, from among the first set of relevant previous search sessions determined from the session data stored in the repository associated with the search engine, based on the one or more other query terms associated with the search query of the current search session without searching any previous search sessions of the second set of previous search sessions that are not in the first set of relevant previous search sessions; identifying, by the search engine, one or more entities that are associated with one or more search queries or search results of the particular previous search session, based on the one or more other query terms of the search query of the current search session; and providing (i) a response to the search query that includes a representation of one or more of the entities, from a text-to-speech engine, that is configured to be output on a speaker of the digital assistant device in response to the search query of the current search session and (ii) metadata, from the search engine, related to the one or more entities that is configured to be rendered on a graphical user interface of the digital assistant device during output of at least a portion of the response to the search query using the speaker of the digital assistant device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system, comprising:
-
a data processing apparatus; and a non-transitory computer readable storage medium in data communication with the data processing apparatus and storing instructions executable by the data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising; receiving, by a search engine and from a speech-to-text engine, a search query that is based on an utterance of a user that was detected by a digital assistant device during a current search session; determining, by the search engine, that the search query refers to a time indicator, the time indicator indicating a time earlier than the current search session; determining, by the search engine, that the search query refers to one or more other query terms; determining, by the search engine and from session data stored in a repository associated with the search engine, a first set of relevant previous search sessions from a second set of previous search sessions, wherein the second set of previous search sessions includes more previous search sessions than the first set of relevant previous search sessions, wherein each previous search session in the first set of relevant previous search sessions is associated with a respective time label corresponding to the time indicator; identifying, by the search engine, a particular previous search session, from among the first set of relevant previous search sessions determined from the session data stored in the repository associated with the search engine, based on the one or more other query terms associated with the search query of the current search session without searching any previous search sessions of the second set of previous search sessions that are not in the first set of relevant previous search sessions; identifying, by the search engine, one or more entities that are associated with one or more search queries or search results of the particular previous search session, based on the one or more other query terms of the search query of the current search session; and providing (i) a response to the search query that includes a representation of one or more of the entities, from a text-to-speech engine, that is configured to be output on a speaker of the digital assistant device in response to the search query of the current search session and (ii) metadata, from the search engine, related to the one or more entities that is configured to be rendered on a graphical user interface of the digital assistant device during output of at least a portion of the response to the search query using the speaker of the digital assistant device. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and upon such execution cause the data processing apparatus to perform operations comprising:
-
receiving, by a search engine and from a speech-to-text engine, a search query that is based on an utterance of a user that was detected by a digital assistant device during a current search session; determining, by the search engine, that the search query refers to a time indicator, the time indicator indicating a time earlier than the current search session; determining, by the search engine, that the search query refers to one or more other query terms; determining, by the search engine and from session data stored in a repository associated with the search engine, a first set of relevant previous search sessions from a second set of previous search sessions, wherein the second set of previous search sessions includes more previous search sessions than the first set of relevant previous search sessions, wherein each previous search session in the first set of relevant previous search sessions is associated with a respective time label corresponding to the time indicator; identifying, by the search engine, a particular previous search session, from among the first set of relevant previous search sessions determined from the session data stored in the repository associated with the search engine, based on the one or more other query terms associated with the search query of the current search session without searching any previous search sessions of the second set of previous search sessions that are not in the first set of relevant previous search sessions; identifying, by the search engine, one or more entities that are associated with one or more search queries or search results of the particular previous search session, based on the one or more other query terms of the search query of the current search session; and providing (i)a response to the search query that includes a representation of one or more of the entities, from a text-to-speech engine, that is configured to be output on a speaker of the digital assistant device in response to the search query of the current search session and (ii) metadata, from the search engine, related to the one or more entities that is configured to be rendered on a graphical user interface of the digital assistant device during output of at least a portion of the response to the search query using the speaker of the digital assistant device. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27, 28)
-
Specification